Today, LLMs are not good at personalization providing recommendation. They advise physicians and financial advisors to ask professionals in respective fields for help, even having user information available. Answering questions of software professionals, LLM needs to deliver in-depth answers with codes or algorithms, whereas for professionals in other fields would need definitions and main concepts. The intent of this chapter is to make LLM answer tailored to the needs of users, taking into account available information about them. To do that, we need to generalize available information about a person like her health record, maintaining the privacy of this person. We rely on meta-learning techniques to design a LLM prompt to produce a personalization prompt to obtain a suitable relevant information. Such “meta-prompt” is produced by generalization operation applied to available documents for the user. These documents need to be de-identified so that they are sufficient for personalization on one hand and will maintain user privacy on the other hand. The second neuro-symbolic technique to support personalization is abductive reasoning, acting in parallel to LLM fine-tuning. Traditional recommendation and personalization techniques as well as modern, deep learning – based are presented, and the comparison is drawn to the proposed approach. We also share the evaluation and comparative analyses of these approaches. We consider an example for how to build personalization LLM systems coming from Langchain platform. We will explore how to construct chains to form a personalization profile for a user and apply it to user search and recommendation requests.

Floods, recognized for their erratic behavior and devastating effects, are a significant threat as a natural disaster. In Brunei Darussalam, the impact of climate change is becoming increasingly evident through higher temperatures and an expected increase in annual rainfall (5.0mm per year from 2021 to 2050), highlighting the critical need for updated flood risk management techniques. In line with the climate resilience and adaptation objectives of WAWASAN 2035, this paper introduces an innovative approach—a cutting-edge flood risk management framework that utilizes the capabilities of big data analytics, sophisticated machine learning algorithms, and smart Internet of Things (IoT) sensors. Traditional methods, which rely on numerical and physical data modeling, often do not provide precise short-term flood forecasts. Our suggested framework uses machine learning to analyze real-time flood forecasting, sensor data and enhance warning systems, addressing the shortcomings of traditional approaches. The key advantage of this approach is its potential to drastically decrease flood-related damages, protect lives, and boost infrastructure resilience. This proposal is not only in aligns with Brunei's vision for a safe and climate-adaptable future but also marks a significant step forward in adopting innovative and sustainable flood risk management solutions amidst an evolving climate.

This study investigates the pivotal areas where Artificial Intelligence (AI) integration in healthcare warrants further exploration, leveraging insights from Boston Specialists, a forefront healthcare provider in AI adoption. Employing a qualitative case study approach, enriched by in-depth interviews and comprehensive literature reviews, we identify three main domains for potential AI expansion: scheduling efficiency, clinical documentation, and AI-driven medical research. Our results underscore the substantial enhancements AI brings to operational workflows and patient care, notably through improved scheduling systems, accuracy in medical documentation, and the facilitation of data-driven research methodologies. These findings suggest a critical need for healthcare institutions to further invest in AI technologies, focusing on these key areas to harness AI's full potential in personalizing care, optimizing efficiency, and advancing medical knowledge. The study concludes with a call for continued investigation into AI's integration within healthcare settings, emphasizing the importance of a supportive organizational infrastructure, ethical considerations, and data security in realizing AI's transformative impact on healthcare delivery and patient outcomes.

In the dynamic landscape of modern education, characterized by an increasingly active involvement of IT technologies in learning, the imperative to transfer to students the skills necessary to integrate Artificial Intelligence (AI) into the process represents an important goal. This paper presents a novel framework for knowledge transfer, diverging from traditional programming language-centric approaches by integrating PSoC 6 microcontroller technology. This framework establishes a cyclical learning cycle encompassing theoretical fundamentals and practical experimentation, fostering AI literacy at the edge. Through a structured combination of theoretical instruction and hands-on experimentation, students develop proficiency in understanding and harnessing AI capabilities. Emphasizing critical thinking, problem-solving, and creativity, this approach equips students with the tools to navigate the complexities of real-world AI applications effectively. By leveraging PSoC 6 as an educational tool, a new generation of individuals is efficiently cultivated with essential AI skills. These individuals are adept at leveraging AI technologies to address societal challenges and drive innovation, thereby contributing to long-term sustainability initiatives. Specific strategies for experiential learning, curriculum recommendations, and results of knowledge application are presented, aimed at preparing students to excel in a future where AI will be omnipresent and indispensable.

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies’ environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% (1252 W for A100 with AMD EPYC 7V13 vs 613 W for Intel® Xeon® Gold 6538N) while providing production ready throughput & latency.

The value of artificial intelligence and machine learning applications for use in heritage research is increasingly appreciated [1]. In specific areas, notably remote sensing, data sets have increased in extent and resolution to the point that manual interpretation is problematic and availability of skilled interpreters to undertake such work is limited. Interpretation of geophysical data sets associated with prehistoric submerged landscapes is particularly challenging. Following the last glacial, sea levels rose 120 metres globally, and vast, habitable landscapes were lost to the sea. These landscapes were inaccessible until extensive remote sensing data sets were provided by the offshore energy sector. In this paper, we provide results of a research programme centred on AI applications using data from the southern North Sea. Here, an area of c.188,000 km2 of habitable terrestrial land was inundated between c. 20,000 BP and 7,0000 BP, along with the cultural heritage it contained [2]. As part of this project, machine learning tools were applied to detect and interpret features of archaeological significance from shallow seismic data. The output provides a proof-of-concept model demonstrating verifiable results and the potential for further, more complex leveraging of AI interpretation for the study of submarine palaeolandscapes. Image: Adobe Firefly Generative AI using keywords - marsh landscape deep underwater, auroch skull half-buried in peat

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2-2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

This research investigates the application of deep learning in sentiment analysis of Canadian maritime case law. It offers a framework for improving maritime law and legal analytics policy-making procedures. The automation of legal document extraction takes center stage, underscoring the vital role sentiment analysis plays at the document level. Therefore, this study introduces a novel strategy for sentiment analysis in Canadian maritime case law, combining sentiment case law approaches with state-of-the-art deep learning techniques. The overarching goal is to systematically unearth hidden biases within case law and investigate their impact on legal outcomes. Employing Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) based models, this research achieves a remarkable accuracy of 98.05% for categorizing instances. In contrast, Conventional Machine Learning techniques such as Support Vector Machines (SVM) yield an accuracy rate of 52.57%, Naive Bayes at 57.44 %, and Logistic Regression at 61.86%. The superior accuracy of the CNN and STM model combination underscores its usefulness in legal sentiment analysis, offering promising future applications in diverse fields like legal analytics and policy design. These findings mark a significant choice for AI-powered legal tools, presenting more sophisticated and sentiment-aware options for the legal profession.

When dealing with limited sample sizes or missing values in time series data, achieving high accuracy in forecasting becomes challenging. This challenge is particularly common in wind energy forecasting, where many wind farms lack complete data. In this paper, we employ the widely-used ARIMA (Autoregressive Integrated Moving Average) model for time series forecasting. To address the difficulties posed by limited sample sizes and missing values, we adopt a unique approach by utilizing multiple ARIMA models for different datasets. A key distinction from other multiple models methods for time series forecasting lies in each model within our approach using its own dataset, making the fusion process more intricate. To overcome this, we incorporate neural networks and two techniques for model fusion: direct fusion with a learning mechanism and compensation for missing data through training. For each ARIMA model, we introduce a noise estimation method to circumvent the white noise assumptions inherent in ARIMA models. Finally, we apply these methods to wind energy prediction, and our experimental results showcase a significant enhancement in forecasting accuracy.

Chinese texts often feature a substantial volume of normative content, and their analysis has increasingly become a focal point in recent semantic analysis endeavors. Enhancing the effectiveness of text classification and clustering is pivotal in unveiling the intricate semantics within extensive textual data. Empirical research within the realm of computational social science has underscored the need for improved explanatory power when it comes to general text clustering methods applied to normative texts. This study introduces an innovative hierarchical clustering method that incorporates part-of-speech (POS) features and pioneers a novel semantic network model. It achieves this by amalgamating a POS-based feature weight calculation method with hierarchical clustering techniques. To assess its efficacy, the method is rigorously evaluated across three diverse text datasets, encompassing normative reports, news articles, and social media content. The experimental results unequivocally demonstrate the superior performance of the POS-HC method, surpassing the traditional TF and TF-IDF feature extraction methods in terms of clustering accuracy, and surpassing some existing clustering methods. Furthermore, its classification effectiveness exhibits notable advantages, particularly in the semantic classification of normative texts.

Heavy rains have created significant threats to human health and life. Floods and other natural disasters, which have a global impact annually, can be attributed to extended durations of intense precipitation. Accurate rainfall predictions are crucial in nations such as Bangladesh, where agriculture is the predominant occupation. The efficiency of machine learning (ML) methods is enhanced by the non-linearity of rainfall, surpassing the effectiveness of other alternative ways. Machine learning techniques show that individual classifiers exhibit worse accuracy than ensemble learning (EL) methodologies. Ensemble Learning techniques are utilized for rainfall prediction and estimating rainfall quantity and daily average temperature to enhance comprehension of the diverse Machine Learning algorithms. This research implements the machine learning techniques and ensemble-based classifier to predict the rainfall occurrence, along with the machine learning regressor models and ensemble-based regressor for the rainfall amount prediction and daily average temperature prediction, using Bangladesh Weather Dataset. The results of the machine learning and ensemble-based models are compared using the Accuracy and F1 score for rainfall occurrence prediction. In contrast, MAE and RMSE evaluation metrics are used for ensemble regressor and regression algorithms for the rainfall amount and daily average temperature prediction. With an accuracy of 83.41% and a recall of 78.17%, the Ensemble Classifier is the best at predicting when it will rain, but its precision of 51.16% stands in for the lowest. The Ensemble Regression model outperforms Linear Regression, Random Forest, and SVR in rainfall amount prediction, with the lowest MAE of 0.36 and RMSE of 0.90. The Ensemble Regression provides the most precise results for daily average temperature prediction with the lowest MAE 0.42 and RMSE 0.54 highlighting its superiority over the other regression models in forecasting temperature with less error. Ensemble approaches consistently lead task performance metrics.

In the dynamic field of mental health care, the nuanced application of Artificial Intelligence (AI) through Natural Language Processing (NLP) and Automatic Speech Recognition (ASR) is a pivotal innovation in patient empowerment and service optimization. This study introduces a distinctive online therapy platform that capitalizes on the synergy of NLP and ASR to offer unprecedented levels of interactive and personalized therapeutic interventions. The architecture of our system is meticulously detailed, featuring an ASR component with an impressive Word Error Rate (WER) of 14% when trained on the diverse French subsets of the Mozilla Common Voice dataset, complemented by a high-precision NLP framework skilled in processing and responding to user inputs. The evaluation of our system highlights its efficacy in enhancing therapy sessions and user satisfaction, with an emphasis on the qualitative aspects of user feedback. The paper addresses challenges such as dataset representativeness and language model refinement and articulates the strategic solutions employed to overcome them. The paper concludes with forward-looking perspectives on AI's role in mental health services, advocating for the creation of sophisticated, language-specific datasets and models to satisfy the increasing demands of online therapy, reflecting a growing commitment of patients in the management of their therapy. This research underscores the transformative impact of AI in advancing mental health care into the digital age, representing a significant evolution over existing methodologies.

To secure computers and information systems from attackers taking advantage of vulnerabilities in the system to commit cybercrime, several methods have been proposed for real-time detection of vulnerabilities to improve security around information systems. Of all the proposed methods, machine learning had been the most effective method in securing a system with capabilities ranging from early detection of software vulnerabilities to real-time detection of ongoing compromise in a system. As there are different types of cyberattacks, each of the existing state-of-the-art machine learning models depends on different algorithms for training which also impact their suitability for detection of a particular type of cyberattack. In this research, we analyzed each of the current state-of-theart machine learning models for different types of cyberattack detection from the past 10 years with a major emphasis on the most recent works for comparative study to identify the knowledge gap where work is still needed to be done with regard to detection of each category of cyberattack

The ever-evolving ways attacker continues to im prove their phishing techniques to bypass existing state-of-the-art phishing detection methods pose a mountain of challenges to researchers in both industry and academia research due to the inability of current approaches to detect complex phishing attack. Thus, current anti-phishing methods remain vulnerable to complex phishing because of the increasingly sophistication tactics adopted by attacker coupled with the rate at which new tactics are being developed to evade detection. In this research, we proposed an adaptable framework that combines Deep learning and Randon Forest to read images, synthesize speech from deep-fake videos, and natural language processing at various predictions layered to significantly increase the performance of machine learning models for phishing attack detection.

This paper analyses the application of deep learning techniques for predicting wave overtopping events in port environments using sea state and weather forecasts as inputs. The study was conducted in the outer port of Punta Langosteira, A Coruña, Spain. A video recording infrastructure was installed to monitor overtopping events from 2015 to 2022, identifying 3709 overtopping events. The data collected was merged with actual and predicted data for the sea state and weather conditions during the overtopping events, creating three datasets. We used these datasets to create several machine learning models to predict whether an overtopping event would occur based on sea state and weather conditions. The final models achieved a high accuracy level during the training and testing stages: 0.81, 0.73, and 0.84 average accuracy during training and 0.67, 0.48, and 0.86 average accuracy during testing, respectively. The results of this study have significant implications for port safety and efficiency, as wave overtopping events can cause disruptions and potential damage. Using deep learning techniques for overtopping prediction can help port managers take preventative measures and optimize operations, ultimately improving safety and helping to minimize the economic impact that overtopping events have on the port's activities.

This paper addresses the critical issue of trust in Artificial Intelligence systems, especially when users might find it challenging to comprehend the internal decision-making processes of such systems. A relevant topic of research in this respect is Theory of Mind, which involves attempting to understand these systems as if they possessed beliefs, desires, and intentions. We focus on the latter: intentions, and we examine how producing explanations based on them can improve \emph{understandability} while allowing for a better interpretation of how they align with human values. We also review some existing methods for identifying intentions in AI systems and we conclude with a discussion on possible future directions in this line of research.

Epilepsy is a common neurological condition, typically diagnosed using Electroencephalogram (EEG). Large scale EEG datasets have recently been made publicly available, allowing the use of advanced Machine Learning (ML) algorithms to analyze EEG patterns associated with epilepsy. While most existing studies focus on identifying seizures in the EEG, few have tried to identify preictal EEG segments. Identifying preictal EEG segments are not only useful in developing early warning systems but also helps inform the course of treatment for the patient. In this study, we propose to represent EEG segments as images, instead of time-series data, and identify preictal EEG segments using a preexisting ML algorithm (YOLOv8) designed for image processing. Multiplexed images (containing the original EEG signal represented on a 2D grid, kurtosis, and spectral entropy) achieve the best accuracy of 95.75% on the dataset while images just containing the EEG signal result in an accuracy of 91.25%. Using only spectrograms, generated from the original EEG signal, results in an accuracy of 90.15%.

The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes ArabianGPT, a series of transformer-based models within the ArabianLLM suite designed explicitly for Arabic. These models, including ArabianGPT-0.1B and ArabianGPT-0.3B, vary in size and complexity, aligning with the nuanced linguistic characteristics of Arabic. The AraNizer tokenizer, integral to these models, addresses the unique morphological aspects of Arabic script, ensuring more accurate text processing. Empirical results from fine-tuning the models on tasks like sentiment analysis and summarization demonstrate significant improvements. For sentiment analysis, the fine-tuned ArabianGPT-0.1B model achieved a remarkable accuracy of 95%, a substantial increase from the base model's 56%. Similarly, in summarization tasks, fine-tuned models showed enhanced F1 scores, indicating improved precision and recall in generating concise summaries. Comparative analysis of fine-tuned ArabianGPT models against their base versions across various benchmarks reveals nuanced differences in performance, with fine-tuning positively impacting specific tasks like question answering and summarization. These findings underscore the efficacy of fine-tuning in aligning ArabianGPT models more closely with specific NLP tasks, highlighting the potential of tailored transformer architectures in advancing Arabic NLP.

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

The rapid advancements and the merging of hybrid quantum-classical computing, artificial intelligence (AI), machine learning (ML), and deep learning (DL) pose a potentially unseen and significant threat to encryption that may impact Post-Quantum Cryptography (PQC) transition timelines. There is a direct hybrid quantum-classical computing threat on cryptography, and there is also a direct threat AI/ML on cryptography. However, the synergistic combination of these technologies presents known and unknown threats that need attention, focus action, and research. This paper reviews Grover's Adaptive Search (GAS), which combines Grover's Algorithm with adaptive techniques to optimize search further, potentially making it even more efficient for attacking encryption. This work also examines the quantum-accelerated Harrow-Hassidim-Lloyd (HHL) Algorithm, designed to solve systems of linear equations exponentially faster than classical algorithms in certain conditions. The HHL algorithm can solve some lattice-based problems, which have implications for lattice-based encryption. This technological confluence and its potential impact on cryptography and encryption necessitate a proactive and coordinated approach to developing and implementing quantum-resistant AI/ML cryptographic solutions. This paper reviews the technological confluence and its potential implications for classical cryptography and PQC transition timelines and calls for further research.

The use of credit cards and online banking is expanding exponentially. As more individuals use debit cards, credit cards, and internet banking, the likelihood of falling victim to various forms of fraud also rises. Due to ignorance, credit card company customers have provided their card details, personal information, and one-time password to an unknown bogus caller on several occasions in the recent past. One of the biggest issues facing financial institutions and customers alike is credit card theft. It may result in large financial losses and harm to the financial institution's image. While there are several ways to identify credit card fraud, one of the best is machine learning.By using past data, machine learning algorithms may be trained to recognize trends and abnormalities that point to fraud. The state-of-the-art in machine learning for credit card fraud detection is reviewed in this study. Numerous research on the same subject have been conducted in the past with a variety of well-known machine-learning techniques. However, with a grasp of the notion of hybrid machine learning, we will now examine how well hybrid machine learning performs on the same problem statement.

Radial basis function (RBF) networks are often viewed as instable when used in multi-layered architectures and therefore are mostly used in a single-layered manner. Universal approximation theorems for single-layered RBF networks further render deeper architectures useless. However, deep neural networks have proven their effectiveness on many different tasks. We show that deeper RBF architectures with multiple radial basis function layers are achievable and able to learn. We introduce an initialization scheme for deep RBF networks based on k-means clustering and covariance estimation. We further show how to make use of convolutions to speed up the calculation of a Mahalanobis distance in a partially-connected fashion, similar to convolutional neural networks (CNNs). Finally, we evaluate our approach on image classification as well as speech emotion recognition tasks. Our results show that deep RBF networks perform similar to simple CNNs.

Deep learning (DL) algorithms used for DOTATATE PET lesion detection typically require large, well-annotated training datasets. These are difficult to obtain due to low incidence of gastroenteopancreatic neuroendocrine tumors (GEP-NETs), and the high cost of manual annotation. Furthermore, networks trained and tested with data acquired from site specific PET/CT instrumentation, acquisition and processing protocols have reduced performance when tested with offsite data. This lack of generalizability requires even larger, more diverse training datasets. The objective of this study is to investigate the feasibility of improving DL algorithm performance by better matching the background noise in training datasets to higher noise, out-of-domain testing datasets. 68Ga-DOTATATE PET/CT datasets were obtained from two scanners: Scanner1, a state-of-the-art digital PET/CT (GE DMI PET/CT; n=83 subjects), and Scanner2, an older-generation analog PET/CT (GE STE; n=123 subjects). Set1, the data set from Scanner1 was reconstructed with standard clinical parameters (5 minutes; Q.Clear) and list-mode reconstructions (VPFXS 2, 3, 4, and 5-minutes). Set2, data from Scanner2, representing out-of-domain clinical scans, used standard iterative reconstruction (5 minutes; OSEM). Reconstructed datasets were divided into training, validation, and testing datasets in a 60%, 20%, 20% proportion, and a deep neural network was trained with each: Network1 for Scanner1 and Network2 for Scanner2. DL performance (Network1) was tested with out-of-domain test data (Set2). To evaluate the effect of training sample size, we tested DL model performance using a fraction (25%, 50%, and 75%) of Set1 for training. Scanner1, list-mode 2-minute reconstructed data demonstrated the most similar noise level compared that of Set2, resulting in the best performance (F1=0.713). This was not significantly different compared to the highest performance, upper-bound limit using in-domain training for Network2 (F1=0.755; p-value=0.103). Regarding sample size, the F1 score significantly increased from 25% training data (F1=0.478) to 100% training data (F1=0.713; p<0.001). List-mode data from modern PET scanners can be reconstructed to better match the noise properties of older scanners. Using existing data and their associated annotations dramatically reduces the cost and effort in generating these datasets, and significantly improves the performance of existing DL algorithms. List-mode reconstructions can provide an efficient, low-cost method to improve DL algorithm generalizability.

In recent years the field of computer science has experienced great changes, due to the incredible advances in the field of artificial intelligence. Deep Learning models are responsible for most of them since the biggest milestones occurred in 2012 when AlexNet won the image classification challenge called ImageNet. These models have demonstrated great performances in different types of complex tasks like image restoration, medical diagnosis or object recognition. Their disadvantages are related to their high data dependency, which forces experts in the field to follow a precise methodology to obtain accurate models. In this paper, we describe a complete workflow that begins with the management of the raw data until the in-depth interpretation of the performance of the models. This should be taken as a high-level consultation document describing good practices that should be applied. Apart from the step-by-step methodology, we present different use cases that correspond to the two main problems of the field: classification and regression.

In a densely populated country like Bangladesh, universities grapple with the challenge of efficiently addressing myriad queries from a large student body, leading to a heightened workload for university stakeholders. To tackle these challenges, we introduce PixieGPT, a tailor-made Generative Pre-Trained Transformer for Bangladeshi universities. PixieGPT significantly mitigates workload by adeptly handling common university-related queries, thereby enhancing user experience. The hierarchical structure plays a crucial role in managing diverse queries from thousands of students about the university system. The solution introduces a modular hierarchical knowledge base (KB) with simpler complexities, addressing the intricacies of efficiently managing large volumes of queries. PixieGPT is designed in a modular way so that the solution is also adaptable for the implementation of other universities worldwide based on the requirements of a particular administrative system. The modular nature facilitates easy adaptation with minor changes based on specific university requirements, ensuring a seamless integration process. This paper delves into the intricacies of PixieGPT's design, emphasizing its pivotal role in mitigating workload challenges for university stakeholders in Bangladesh. The incorporation of BERT for Natural Language Understanding(NLU) and GPT models for Natural Language Generation(NLG) enhances PixieGPT's capabilities, contributing to the scalability and efficiency of the system. The presented use case underscores the practical benefits of PixieGPT, positioning it as a promising solution for universities globally with similar operational frameworks.

The main purpose of this article is to identify brain diseases such as Alzheimer's and Parkinson's in an intelligent way using Python software and processing the function of neurons in the neural network areas of the brain, which are classified into different components, and the data is based on the information obtained from FMRI images using algorithms artificial intelligence can intelligently diagnose the type of disease. Therefore, by using spatial clustering based on the deep learning method with noise algorithm (DBSCAN), fMRI brain image and fMRI brain surface complexity are classified, and then image preprocessing will be applied to fMRI images by using artificial intelligence neural networks (ANN) algorithm. became. Then, by using the ANN algorithm and Deep CNN topology of the brain neural network, the type of disease in the brain can be diagnosed by simulating the performance of an artificial neural network (ANN) in Python software. Deep machine learning-based methods, especially algorithms based on neural networks, have shown great success in medical image analysis for various tasks including brain tumor detection, segmentation, and classification, and Alzheimer's and epilepsy. In this research, we propose an integrated model based on a convolutional neural network for simultaneous recognition and classification of brain diseases for intelligent diagnosis of tumors and epilepsy. The average accuracy obtained from our proposed model is 97.89 percent accuracy and 91.66 percent specificity.

Recent advances in artificial intelligence combined with behavioral sciences have led to the development of cutting-edge tools for recognizing human emotions based on text, video, audio, and physiological data. However, these data sources are expensive, intrusive, and regulated, unlike plants which have been shown to be sensitive to human steps and sounds. A methodology is proposed to use plants as human emotion detectors. Electrical signals from plants are tracked and labeled based on video data. Labeled data are then used for classification. MLP, biLSTM, MFCC-CNN, MFCC-ResNet, and additionally, Random Forests, 1-Dimensional CNN, and biLSTM without windowing models are set using a grid search algorithm with cross-validation. Finally, best-parameterized models are trained and used with the test set for classification. The performance of this methodology is measured with a case study with 54 participants, who were watching an emotionally charged video, as ground truth their facial emotions were simultaneously measured using face emotion analysis. The Random Forest model shows the best performance, particularly in recognizing high-arousal emotions, achieving an overall weighted accuracy of 55.2% and demonstrating high weighted recall in emotions such as fear 61.0% and happiness 60.4%. The MFCC-ResNet model offers decently balanced results, with Accuracy(MFCC-ResNet)=0.318 and Recall (MFCC-ResNet)=0.324. With the MFCC-ResNet model fear and anger are recognized with 75% and 50% recall respectively. Thus, using plants as an emotion recognition tool seems worth investigating, addressing both cost and privacy concerns.

Aiming at the problem of UAV cluster configuration reconstruction, in order to obtain the cluster reconstruction method, the theory and simulation of cluster reconstruction control strategy is studied by simplifying the model，deducing the theoretical formula and analyzing the example. Taking 10 UAVs cluster as an example, the distribution of UAVs in different configurations was analyzed. According to the change of cluster configuration, the principle of formation reconstruction and the execution ability of configuration, the cluster capability was analyzed. The group behavior is modeled by group behavior rules, reconfiguration topology analysis and reconfiguration cost measurement. Based on the cluster parameters and configuration characteristics, simulation experiments were carried out to obtain the change curve of the reconstruction cost and time and the trajectory movement diagram of the UAV in different configurations.

Educational institutions must identify students who are academically struggling to provide them with necessary support to improve their performance. In this context, recommendation systems powered by deep learning techniques are vital for detecting and categorizing such students. These systems help students plan their future by uncovering patterns in their historical academic data. This study introduces a new deep learning model designed to classify academically underperforming students in educational settings. The model incorporates a Gated Recurrent Neural Network (GRU) and includes specific neural network features like a dense layer, max-pooling layer, and the ADAM optimization algorithm. The model's training and evaluation were conducted using a dataset comprising 15,165 student assessment records from various academic institutions. The performance of the developed GRU model was benchmarked against other educational recommendation systems, including Recurrent Neural Network models, AdaBoost, and the Artificial Immune Recognition System v2. The proposed GRU model demonstrated remarkable accuracy, achieving an overall rate of 99.70%.

This study focuses on the reasoning of symptoms of TCM internal diseases. Taking cough as an example, the BERT-BiLSTM-CRF model is used for entity recognition. Experiments show that the model has the best entity recognition effect on three types of texts, including teaching cases, clinical cases and literature data, and the F1 value is up to 0.967. It can effectively identify symptoms, course of disease, tongue condition and pulse condition in TCM diagnosis and treatment texts, which lays a solid foundation for intelligent assisted syndrome differentiation and treatment of TCM. By constructing four types of entity corpora and using three mainstream entity recognition models for experiments, it is found that the BERT-BiLSTM-CRF model has a good entity recognition effect in three types of data: teaching cases, clinical cases and literature data. Experimental results show that the F1 values of the BERT-bilSTM-CRF model in teaching cases, clinical cases and literature data are 0.967, 0.82 and 0.91, respectively, which provides an effective method for information extraction in the field of TCM syndrome differentiation diagnosis and treatment, and lays a foundation for further research on knowledge reasoning.

The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumor from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making processes, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging state-of-the-art DL frameworks with transfer learning, we conduct a comprehensive evaluation encompassing both classification accuracy and interpretability. Using state-of-the-art DL frameworks with transfer learning, we conduct a thorough evaluation covering both classification accuracy and interpretability. We employ adaptive path-based techniques to understand the underlying decision-making mechanisms of these models. Grad-CAM and Grad-CAM++ highlight critical image regions where the tumors are located.

In a dynamic production processes, mechanical degradation poses a significant challenge, impacting product quality and process efficiency. This paper explores a novel approach for monitoring degradation in the context of viscose fiber production, a highly dynamic manufacturing process. Using causal discovery techniques, our method allows domain experts to incorporate background knowledge into the creation of causal graphs. Further, it enhances the interpretability and increases the ability to identify potential problems via changes in causal relations over time. The case study employs a comprehensive analysis of the viscose fiber production process within a prominent textile industry, emphasizing the advantages of causal discovery for monitoring degradation. The results are compared with state-of-the-art methods, which are not considered to be interpretable, specifically LSTM-based autoencoders, showcasing the alignment and validation of our approach. This paper provides valuable information on degradation monitoring strategies, demonstrating the efficacy of causal discovery in dynamic manufacturing environments. The findings contribute to the evolving landscape of process optimization and quality control.

Nollywood, based on the idea of Bollywood from India, is a series of outstanding movies that originate from Nigeria. Unfortunately, while the movies are in English, they are hard to understand for many native speakers due to the dialect of English that is spoken. In this article, we accomplish two goals: (1) create a phonetic sub-title model that is able to translate Nigerian English speech to American English and (2) use the most advanced toxicity detectors to discover how toxic the speech is. Our aim is to highlight the text in these videos which is often times ignored for lack of dialectal understanding due the fact that many people in Nigeria speak a native language like Hausa at home.

Groundwater represents a pivotal asset in conserving natural water reservoirs for potable consumption, irrigation, and diverse industrial uses. Nevertheless, human activities intertwined with industry and agriculture contribute significantly to groundwater contamination, highlighting the critical necessity to appraise water quality for safe drinking and effective irrigation. This research primarily focused on employing the Water Quality Index (WQI) to gauge water's appropriateness for these purposes. However, the generation of an accurate WQI can prove time-intensive owing to potential errors in sub-index calculations. In response to this challenge, an artificial intelligence (AI) forecasting model was devised, aiming to streamline the process while mitigating errors. The study collected 422 data samples from Mirpurkash, a city nestled in the province of Sindh, for a comprehensive exploration of the region's WQI attributes. Furthermore, the study probed into unraveling the interdependencies amidst variables in the physiochemical analysis of water. Diverse machine learning classifiers were employed for WQI prediction, with findings revealing that random forest and gradient boosting eclipsed other algorithms, achieving an accuracy rate of 99%. In close pursuit were SVM and XGBoost, registering accuracy scores of approximately 95% and 93%, respectively, while KNN and Decision Trees garnered accuracy rates of 88% and 87%, respectively. In addition to WQI prediction, the study conducted an uncertainty analysis of the models using the R-factor, providing insights into the reliability and consistency of predictions. This dual approach, combining accurate WQI prediction with uncertainty assessment, contributes to a more comprehensive understanding of water quality in Mirpurkash and enhances the reliability of decision-making processes related to groundwater utilization

Speech recognition, or automatic speech recognition (ASR), is a technology designed to convert spoken language into text using software. However, conventional ASR methods involve several distinct components, including language, acoustic, and pronunciation models with dictionaries. This modular approach can be time-consuming and may influence performance. In this study, we propose a method that streamlines the speech recognition process by incorporating a unified recurrent neural network (RNN) architecture. Our architecture integrates a convolutional neural network (CNN) with an RNN and employs a connectionist temporal classification (CTC) loss function. Key experiments were carried out using a dataset comprising 576,656 valid sentences, using erosion techniques. Evaluation of the model performance, measured by the word error rate (WER) metric, demonstrated remarkable results, achieving a WER of 2%. This approach has significant implications for the realm of speech recognition, as it alleviates the need for labor-intensive dictionary creation, enhancing the efficiency and accuracy of ASR systems, and making them more applicable to real-world scenarios. For future enhancements, we recommend the inclusion of dialectal and spontaneous data in the dataset to broaden the model's adaptability. Additionally, fine-tuning the model for specific tasks can optimize its performance for targeted objectives or domains, further enhancing its effectiveness in those areas.

Ridesharing effectively tackles urban mobility challenges by providing a service comparable to private vehicles while minimising resource usage. Our research primarily concentrates on dynamic ridesharing, which conventionally involves connecting drivers with passengers in need of transportation. The process of one-to-one matching presents a complex challenge, particularly when addressing it on a large scale, as the substantial number of potential matches make the attainment of a global optimum a challenging endeavour. This paper aims to address the absence of an optimal approach for dynamic ridesharing by refraining from conventional heuristic-based methods, commonly used to achieve timely solutions in large-scale ride-matching. We propose a novel approach that provides snapshot optimal solutions for various forms of one-to-one matching, ensuring they are generated within an acceptable timeframe for service providers. Additionally, we introduce and solve a new variant where the system itself provides the vehicles. The efficacy of our methodology is substantiated through experiments carried out with real-world data extracted from the openly available New York City taxicab dataset.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

Speech recognition, also known as automatic speech recognition (ASR), is a technology that enables software to transcribe spoken language into text. However, existing Amharic ASR methods require multiple separate blocks, such as language, acoustic, and pronunciation models with dictionaries, which can be time-consuming and influence performance. This study proposes an approach that replaces much of the speech pipeline with a single recurrent neural network (RNN) architecture. Our proposed architecture is based on a hybrid approach that combines a convolutional neural network (CNN) with a recurrent neural network (RNN) and a connectionist temporal classification (CTC) loss function. We conducted several experiments with noisy audio data that contain 20,000 valid sentences. The model was evaluated using the word error rate (WER) metric, achieving impressive results of 7% WER on noisy data. This approach has significant implications for the field of speech recognition, as it reduces the human effort required to create dictionaries and improves the efficiency and accuracy of ASR systems, making them more practical for real-world applications.

Large Language Models (LLMs) have proved significant proficiency when comes to code generation especially in Structured Query Language (SQL) for databases and recent successful Text-to-SQL method involves fine-tuning pre-trained LLMs for SQL generation tasks. Transforming natural language text into SQL queries, has been attempted to solve with various learning techniques including Few-shot learning[1], fine tuning. In this paper we propose Supervised fine-tuning (SFT) as a better alternative for learning technique for text-to-SQL generation task using Code-Llama that pushes state of art accuracy on spider test suite to 89.6% on dev set which represent first instance of surpassing the earlier best-in-class with 5.5% higher score and 86.8% of exact match accuracy on dev set. Furthermore, we demonstrate that properly prompted LLM along with SFT provides far fewer hallucinations and much more robust LLM that can be used as a general tool for any text-to-SQL generation use case.

Developing effective trend estimators is a main method to solve the online portfolio selection problem. Although the existing portfolio strategies have demonstrated good performance through the development of various trend estimators, it is still challenging to determine in advance which estimator will yield the maximum final cumulative wealth in online portfolio selection tasks. This paper studies an online ensemble approach for online portfolio selection by leveraging the strengths of multiple trend estimators. Specifically, a return-based loss function and a cross-entropy-based loss function are first designed to evaluate the adaptiveness of different trend estimators in a financial environment. On this basis, a passive aggressive ensemble model is proposed to weigh these trend estimators within a unit simplex according to their adaptiveness. Extensive experiments are conducted on benchmark datasets from various real-world stock markets to evaluate the performance. The results show that the proposed strategy achieves the state-of-the-art performance including efficiency and cumulative return.

In this study on volume determination in waste sorting facilities, we evaluate the effectiveness of ultrasonic sensors and address waste-material-specific challenges. Although ultrasonic sensors offer a cost-effective automation solution, their accuracy is affected by irregular waste shapes, varied compositions, and environmental factors. Notable inconsistencies in volume measurements between storage bunkers and conveyor belts underscore the need for a comprehensive approach to standardize bale production. With prediction reliability being constrained by limited data sets, undocumented modifications to machine-settings and sensor failures, this task renders a challenging application area for Machine Learning. We explore related research and present dataset analyses from three distinct waste sorting facilities in Europe, addressing issues as sensor usability, data quality and material specifics. Our analysis suggests promising strategies and future directions for enhancing waste volume measurement accuracy, ultimately aiming to advance sustainable waste management.

Remote Photoplethysmography (rPPG) has emerged as a non-intrusive and promising physiological sensing capability in HCI research, gradually extending its applications in health-monitoring and clinical care contexts. With advanced machine learning models, recent datasets collected in real-world conditions have gradually enhanced the performance of rPPG methods in recovering heart-rate and heart-rate variability metrics. However, the signal quality of reference ground-truth PPG data in existing datasets is by and large neglected, while poor quality references negatively influence models. Here, this work introduces a new imaging blood volume pulse (iBVP) dataset of synchronized RGB and thermal infrared videos with PPG ground-truth signals from the ear and its high resolution signal quality labels, for the first time. Participants perform rhythmic breathing, head-movement, and stress-inducing tasks, which help reflect real-world variations in psycho-physiological states. This work conducts dense (per sample) signal quality assessment to discard noisy segments of ground-truth and corresponding video frames. We further present a novel end-to-end machine learning framework, iBVPNet that features an efficient and effective spatio-temporal feature aggregation for reliable estimation of BVP signals. Finally, this work examines the feasibility of extracting BVP signals from thermal video frames, which is underexplored. The iBVP dataset and source codes are publicly available for research use.

Domain generalization has led to remarkable achievements in Hyperspectral Image (HSI) classification. Inspired by contrastive language-image pre-training (CLIP), the language-aware domain generalization method has been explored to learn cross-domain-invariant representation. However, existing methods face some challenges: 1) The weak capacity to extract long-range contextual information and inter-class correlation. 2) Due to the inadequacies of the large-scale pre-training for HSI data, the spatial-spectral features of HSI and linguistic features can not be straightforwardly alignment. To address the above problems, a novel network has been proposed with a CLIP framework, which consists of an image encoder, based on an encoder-only transformer to obtain the global contextual information and inter-class correlation, a frozen text encoder, and a cross-attention mechanism, named Linguistic-Interact-with-Visual Engager (LIVE), enhances the interaction between two modalities. Extensive experiments demonstrating superior performance over state-of-the-art methods in HSI Domain Generalization with a CLIP framework.

In this paper we develop and explore a methodical pipeline for swimmer localisation in outdoor environments. The developed framework is intended to be used for enhancing swimmer safety. A main issue we deal with by the proposed approach is the lack of real world training data in such outdoor environments. Natural lighting changes, dynamic water textures and possibly barely visible swimming persons are key elements to approach. We account for these difficulties by adopting an effective background removal technique with available training data. This allows us to edit swimmers into natural environment backgrounds for the use in subsequent image augmentation. We created 17 training datasets with real images, synthetic images and a mixture of both to investigate different aspects and characteristics of the proposed approach. The datasets are used to train a YOLO architecture for the possible future application in real-time detection. The trained framework is then tested and evaluated on outdoor environment imagery acquired by a safety drone to investigate and confirm the usefulness for outdoor swimmer localisation.

Natural language Processing (NLP) has significantly transformed in the last decade, especially in the field of Language Modeling. Large Language Models (LLMs) have achieved SOTA performances on Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks by learning language representation in self-supervised ways. This paper provides a comprehensive survey to capture the progression of advances in Language Models. In this paper, we examine the different aspects of Language Models, which started with a few million parameters but have reached the size of a trillion in a very short time. We also look at how these LLMs transitioned from task-specific to task-independent to task-and-language-independent architectures. This paper extensively discusses different pre-training objectives, benchmarks, and transfer learning methods used in LLMs. It also examines different fine-tuning and In-Context learning techniques used in downstream tasks. It also explores how LLMs can perform well across many domains and datasets if sufficiently trained on a large and diverse dataset. Next, it discusses how, over time, the availability of cheap computational power and large datasets have improved LLM’s capabilities and raised new challenges. As part of our study, we also inspect LLMs from the lens of scalability to see how their performance is affected by the model’s depth, width, and data size. Lastly, we provide an empirical comparison of existing trends and techniques and a comprehensive analysis of where the field of LLM currently stand.

Transformer models have emerged as frontrunners in the field of natural language processing, primarily due to their adept use of self-attention mechanisms to grasp the semantic linkages between words in sequences. Despite their strengths, these models often face challenges in single-task learning scenarios, particularly when it comes to delivering top-notch performance and crafting strong latent feature representations. This challenge is more pronounced in the context of smaller datasets and is particularly acute for under-resourced languages such as Arabic. In light of these challenges, this study introduces a novel methodology for text classification of Arabic texts. This method harnesses the newly developed Reverse Positional Encoding (RPE) technique. It adopts inductive-transfer learning (ITL) framework combined with a switching self-attention shared encoder, thereby increasing the model's adaptability and improving its sentence representation accuracy. The integration of Mixture of Experts (MoE) and Reverse Positional Encoding (RPE) techniques empowers the model to process longer sequences more effectively. This enhancement is notably beneficial for Arabic text classification, adeptly supporting both the intricate five-point and the simpler ternary classification tasks. The empirical evidence points to its outstanding performance, achieving accuracy rates of 87.20% for the HARD dataset, 72.17% for the BRAD dataset, and 86.89% for the LABR dataset, as evidenced by the assessments conducted on these datasets.

"Deep fake" technologies are often associated with face-swapping algorithms based on images or videos. Although much research is focused on developing these techniques, there is still room for improvement, especially in human and visual assessment. In this study, we present an innovative approach to the problem of face replacement based on one model while preserving background features. Our model uses the Adaptive Attentional Denormalization method from FaceShifter while integrating identity features from the ArcFace and BiSeNet models to support the attribute extraction process. We used Fast GAN as a generative model to optimize and accelerate the training process on smaller data sets. Our research proves the effectiveness of the proposed approach by combining innovative methods and architectures in one coherent solution.

The exceptional performance advantages of the fiber optic gyroscope (FOG) position it as a dominant player in middle and high-end inertial navigation systems. To prevent the loss of sensor precision caused by algorithm design and simplify the complex modeling strategy in traditional methods. We gradually demonstrate the significant role of Convolutional Neural Network (CNN) in the navigation system based on FOG, and utilize the particle swarm optimization algorithm (PSO) to expedite the convergence of the network. The experimental results demonstrate that the initial alignment method based on deep learning is more accurate than the traditional method. The attitude angle error is reduced by 81.25%, 92.54% and 36.53% respectively. The research provides support for the future application of deep learning in optical navigation systems.

Selection of the most suitable material is one of the key decisions to be taken at the design stage of a manufacturing process. Traditional approaches as Ashby maps based on material properties are widely used in the industry. However, in the production of multimaterial components, the criteria for the selection can include antagonistic approaches. The aim of this work is the implementation of a methodology based on the results of process simulations for several materials and classify them by applying an advanced data analytics method based on Machine Learning (ML), in this case the Support Vector Regression (SVR) and Multi-Criteria Decision Making (MCDM) methodolo-gies, in this case Multi-criteria Optimization and Compromise Solution (VIKOR) combined with Entropy weighting methods. In order to do this, a Finite Element Model (FEM) has been built to evaluate the extrusion force and the die wear in a multi-material co-extrusion process of bimetallic Ti6Al4V-AZ31B billets. After applying SVR and VIKOR combined with Entropy weighting methodologies, a comparison has been established based on the material selection and complexity of the methodology used, resulting that material chosen in both methodologies is very similar and MCDM method is easier to implement because there is no need of evaluate the error of the pre-diction model and the time for data preprocessing is less than the time needed in SVR.

AbstractThe escalating impact of artificial intelligence (AI) has birthed the fascinating technology of deepfakes, capable of meticulously crafting hyper-realistic audio-visual manipulations. Within the realm of healthcare, this technology presents a double-edged sword, brimming with potential for revolutionizing various facets of care delivery while simultaneously harboring significant ethical and practical challenges. This research delves into the complex narrative surrounding AI deepfakes in healthcare, meticulously analyzing both the exciting opportunities they offer, and the inherent risks associated with their implementation.Background:Traditional healthcare practices face limitations in patient engagement, accessibility, and training efficacy. Deepfakes, with their ability to simulate real-world scenarios and interactions, emerge as a potential solution, offering personalized patient education, immersive mental health interventions, remote consultations with virtual avatars, and realistic training simulations for medical professionals.Objective:This research aims to comprehensively understand the multifaceted impact of AI deepfakes in healthcare systems. It seeks to: Identify and analyze the potential benefits of deepfakes in specific healthcare applications. Assess the ethical and practical challenges associated with deepfake implementation in healthcare settings. Propose recommendations for safe, responsible, and ethical integration of deepfakes within the healthcare system.Results/Conclusion:The research findings illuminate a landscape replete with opportunities and challenges. Deepfakes offer the potential to enhance patient education, personalize mental health interventions, facilitate remote consultations, and revolutionize medical training. However, concerns regarding misinformation, ethical breaches, data privacy, and technical limitations pose significant challenges.The conclusion emphasizes the need for a balanced approach that capitalizes on the innovative potential of deepfakes while mitigating potential harm. Collaborative efforts involving healthcare professionals, technologists, and policymakers are crucial for establishing ethical frameworks, ensuring responsible development, and harnessing the positive power of deepfakes to build a future where healthcare benefits from cutting-edge technology while prioritizing patient well-being and ethical principles.

With end-to-end encryption for video streaming services becoming more popular, network administrators face new challenges in preserving network performance and user experience. Video ads may cause traffic congestion and poor Quality of Experience. Because of the natural variation in user interests and network situations, traditional algorithms for increasing QoE may face limitations. To solve this problem, we suggest a novel method that uses user facial emotion recognition to deduce QoE and study the effect of ads. We use open-access Face Emotion Recognition (FER) datasets and extract facial emotion information from actual observers to train machine learning models. Participants were requested to watch ad videos and provide feedback, which will be used for comparison, training, testing, and validation of our suggested technique. Our tests show that our approach beats the ITU-T P.1203 standard in terms of accuracy by 37.1%. Our method provides a hopeful answer to the problem of increasing user engagement and experience in video streaming services.

In this paper, we use a machine learning method, known as Nonnegative Matrix Factorization, to extract from a given image some new information obtained from a number of color space representations. Such kind of information, termed ``metacolor'', can be considered as a particular color space representation of the image, which can be used to obtain a binary segmentation of the investigated image by distinguishing foreground and background pixels. Some numerical experiments prove that the proposed method shows improved results when compared with common simpler thresholding algorithms.

Evolutionary algorithms find applicability in reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using evolutionary algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. In Part1 and Part2, the author previously reported experimental evaluations on Genetic Algorithm and Evolution Strategy for reinforcement learning of neural networks, utilizing the Acrobot control task. This article constitutes Part3 of the series of comparative research. In this study, Differential Evolution is adopted as the third instance of major evolutionary algorithms. The experimental results show a statistically significant superiority of DE over both GA and ES (p < .01). In addition, DE exhibits its robustness to variations in hyperparameter configurations (the number of offsprings and generations). In the previous experiments, both ES and GA showed significant performance differences depending on the configurations, whereas in the experiment reported in this article, such differences are not detected for DE.

AbstractThe emergence of AI-powered deepfakes, manipulatively realistic synthetic media, raises unprecedented challenges for human information processing and decision-making. This paper explores the cognitive and emotional consequences of exposure to deepfakes, delving into how these digitally fabricated experiences can reshape perception, trust, and social interactions. By reviewing existing research and outlining potential methodological approaches, this paper aims to establish a framework for investigating the multifaceted impact of deepfakes on the human brain.BackgroundThe digital age has ushered in an era of unprecedented information abundance and accessibility. Yet, this abundance breeds vulnerability, particularly with the emergence of AI-powered deepfakes. These hyper-realistic synthetic media creations present a potent threat to the fundamental trust and integrity of information sources. Deepfakes have infiltrated various domains, from entertainment and social media to politics and journalism, blurring the lines between truth and fabrication. Consequently, understanding the cognitive and emotional consequences of encountering deepfakes becomes crucial for navigating this increasingly deceptive landscape.ObjectivesThis research aims to: Investigate how exposure to deepfakes impacts various cognitive functions, including perception, attention, memory, and decision-making. Elucidate the emotional responses elicited by deepfakes and their underlying neural mechanisms. Evaluate the role of individual differences, such as susceptibility to deception and emotional sensitivity, in mediating the impact of deepfakes. Develop a comprehensive framework for understanding the multifaceted influence of deepfakes on the human brain. Results (anticipated)This research is expected to yield insights into: The specific cognitive and emotional processes altered by deepfakes, providing evidence for potential mechanisms of deception and manipulation. The neural circuitry involved in detecting and responding to deepfakes, leading to the development of more effective detection methods. The influence of individual differences (e.g., age, cognitive style) on susceptibility to deepfakes, informing targeted interventions and educational efforts.ConclusionBy deciphering the impact of deepfakes on the human brain, this research will offer valuable tools for mitigating the harmful consequences of misinformation and promoting responsible use of this powerful technology. Ultimately, understanding how deepfakes manipulate our cognitive and emotional landscape is not merely a scientific pursuit, but a critical step towards ensuring a future where truth prevails in the digital world.

Background: This research examines how market knowledge and artificial intelligence (AI) interact in different market designs such as business-to-business (B2B) settings while taking emerging technologies and the changing digitalization landscape into account. Objective: The main goal is to understand how AI affects market knowledge in different market designs such as business-to-business (B2B) contexts, taking into account language barriers, practical difficulties, and the revolutionary effects on decision-making and customer interactions. Result: They underscore the transformative potential of artificial intelligence (AI) by highlighting how it shapes market knowledge, encourages customized approaches, and improves marketing efficacy in the business-to-business (B2B) space. Conclusion: In order to create a path for responsible AI integration in B2B marketing, the study concludes with recommendations for standardized terminology related to AI, practical insights into implementation challenges, and ethical issues.

Due to the major impact of climate change on the world's environment, political and economic systems, climate change mitigation has become a pressing priority for the international community and requires rapid action from the whole society. With the continuous advancement of artificial intelligence research, the integration of AI and other technologies makes it more and more used in the whole society. It has become a promising and innovative avenue in the field of climate change mitigation. This paper comprehensively considers the key role of AI technology in the field of climate change mitigation, such as climate modeling, the optimization of renewable energy systems, the development of intelligent solutions for sustainable practices and CSS technology, and affirms its future prospects. It also describes the challenges of AI in the field of climate change mitigation. As researchers, policymakers, and industries collaborate to refine AI methodologies and integrate them into practical applications, a concerted effort is required to establish ethical guidelines, transparency standards, and inclusive governance frameworks.

Machine learning models are increasingly being used in critical domains, but their complexity, lack of transparency, and poor interpretability remain problematic. Decision trees (DTs) and rule-based approaches are well-known examples of interpretable models, and numerous studies have investigated techniques for approximating tree ensembles using DTs or rule sets; however, tree ensemble approximators do not consider interpretability. These methods are known to generate three main types of rule sets: DT-based, unordered-based, and decision list-based. However, no known metric has been devised to distinguish and compare these rule sets. Therefore, the present study proposes an interpretability metric to allow comparisons of interpretability between different rule sets, such as decision list- and DT-based rule sets, and investigates the interpretability of the rules generated by the tree ensemble approximators. To provide new insights into the reasons why decision list-based and inspired classifiers do not work well for categorical datasets consisting of mainly nominal attributes, we compare objective metrics and rule sets generated by the tree ensemble approximators and the \textit{Recursive-Rule eXtraction algorithm (Re-RX) with J48graft}. The results indicated that \textit{Re-RX with J48graft} can handle categorical and numerical attributes separately, has simple rules, and achieves high interpretability, even when the number of rules is large.

Abstract:The digital landscape is rapidly reshaping under the influence of AI-powered cloud-based e-commerce platforms (PCEPs). These platforms leverage the transformative power of AI to personalize customer experiences, optimize pricing strategies, enhance security, and streamline operations, offering businesses a significant competitive edge. However, challenges surrounding data privacy, algorithmic bias, and potential job displacement raise crucial ethical questions regarding widespread AI adoption in e-commerce.This study delves into the untapped potential and ethical considerations of PCEPs, distinguishing itself by proposing practical strategies for responsible development and ethical implementation.Objectives: Investigate the transformative potential of PCEPs: Personalized product recommendations:Analyze effectiveness and potential bias. Dynamic pricing strategies:Explore impact on consumer fairness and market stability. Enhanced fraud detection:Evaluate accuracy and privacy implications. Optimized supply chain management:Assess efficiency gains and job displacement risks. Critically analyze the ethical considerations of AI in e-commerce: Data privacy:Assess current practices and develop mitigation strategies. Algorithmic bias:Identify potential sources and propose solutions for fairer decision-making. Job displacement:Evaluate impacts and propose reskilling initiatives. Propose comprehensive and practical strategies for responsible PCEP development and implementation: Transparency:Enhance user awareness and control over data usage. Fairness:Design AI systems to mitigate bias and uphold consumer rights. Accountability:Establish clear guidelines and oversight mechanisms for ethical AI development.Conclusion: While PCEPs offer a plethora of transformative benefits, their ethical implementation is paramount. By adhering to principles of transparency, fairness, and accountability, businesses can unlock the full potential of PCEPs while minimizing potential risks and shaping the future of online commerce in a sustainable and equitable manner

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diag-nosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obsta-cles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate clas-sification. As such, skilled clinicians often struggle to differentiate benign moles from early ma-lignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to confront difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification which combines snake models of Active Contour (AC) Segmentation, ResNet50 for feature ex-traction and a Capsule Network with a fusion of lightweight attention mechanisms, to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimi-nation, and improve accuracy. We employed the Stochastic Gradient Descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated derma-tological diagnosis and provide a helpful tool for medical practitioners.

Accurate and robust deep learning models for facial expression recognition are challenging to achieve, given the diversity of human faces and variations in images, including different facial poses and lighting conditions. In this work, we proposed a clock-driven convolutional Spiking Neural Network (SNN) and STDP fine-tune architecture, meticulously calibrated its hyperpa-rameters, and experimented with various optimization methods. The best model resulted was trained and evaluated on the Fer2013 and FER+ database, obtaining an accuracy of 61.87% and 79.97% without requiring auxiliary training data or face registration. To our best knowledge, the proposed SNN achieved comparable accuracy to CNNs of similar depth and possessed advantages of low energy consumption and high computational efficiency. The computational efficiency of the proposed SNN is approximately three times that of CNNs. Along with this, we introduced the very recent cumulative spike guided encoder visualization technique and revealed the strong encoding capability of the proposed SNN.

The proliferation of deep learning in natural language processing (NLP) has led to the development and release of innovative technologies capable of understanding and generating human language with remarkable proficiency. Atinuke, a Transformer-based neural network, optimises performance across various language tasks by utilising a unique configuration. The architecture interweaves layers for processing sequential data with attention mechanisms to draw meaningful affinities between inputs and outputs. Due to the configuration of its topology and hyperparameter tuning, it can emulate human-like language by extracting features and learning complex mappings. Atinuke is modular, extensible, and integrates seamlessly with existing machine learning pipelines. Advanced matrix operations like softmax, embeddings, and multi-head attention enable nuanced handling of textual, acoustic, and visual signals. By unifying modern deep learning techniques with software design principles and mathematical theory, the system achieves state-of-the-art results on natural language tasks whilst remaining interpretable and robust.

La reflexión sobre la formación que necesitan los docentes panameños tiene poca tradición investigativa, aunque recientemente se han desarrollado programas de formación de docentes para enseñar matemáticas de acuerdo con las tendencias actuales en la enseñanza de esta materia. Este artículo explica uno de estos programas de formación de posgrado. Específicamente, se discuten los lineamientos para su diseño y algunos resultados de su segunda implementación. Entre los resultados más importantes para este artículo tenemos a) la creación de la plataforma así como el conjunto de tareas diseñadas, las cuales han sido utilizadas para la formación de posteriores promociones de docentes; b) Destaca el cambio en los criterios que orientan la práctica docente al final del programa, en relación con los criterios utilizados antes de la formación, destacando particularmente la relevancia que adquieren los aspectos emocionales y los relacionados con la interacción en este proceso.

Stress has emerged as a major concern in modern society, significantly impacting human health and well-being. Statistical evidence underscores the extensive social influence of stress, especially in terms of work-related stress and associated healthcare costs. This work addresses the critical need for accurate stress detection, emphasising its far-reaching effects on health and social dynamics. Focusing on remote stress monitoring, this work proposes an efficient deep learning framework to discern stress from facial videos. In contrast to research on wearable devices, this paper investigates the application of *dl for stress detection based on *rppg. The methodology involves selecting suitable *dl models (*lstm, *gru, *1dcnn), optimising hyperparameters, and investigating augmentation techniques. 1D-CNNv1 model achieved the best performance compared to other approaches, particularly with augmentation techniques such as linear interpolation and white noise, achieving a stress classification accuracy of 95.83% while maintaining excellent computational efficiency. The experimental results demonstrate the use of *dl for stress detection based on *rppg, with the potential to make significant contributions to the international standard in the field.

Background: The research is conducted against the backdrop of the rising incidence of diabetes and the demand for novel approaches to improve patient outcomes. With the goal of revolutionizing conventional methods and addressing the changing healthcare landscape, the study concentrated on the application of AI technology in diabetes treatment. Objective: Examining the various ways AI can be used in diabetes care and assessing how it can enhance automated screenings, tailored treatment recommendations, predictive modeling, and patient self-management were the main goals of the study. Result: The findings demonstrated how well AI works to anticipate a patient's unique reaction to a therapy, assist medical personnel in making decisions, and give patients more control over their own care. Artificial intelligence (AI)-powered solutions showed promise in improving real-time monitoring and encouraging patient adherence, supporting a comprehensive strategy for managing diabetes. Conclusion: The research indicates that artificial intelligence (AI) has great potential to change the way diabetes is treated. However, it also highlights the need for more research, ethical issues, and validation of AI. The results advocate for joint efforts to ensure responsible and patient-centered technology innovation in diabetes care and encourage the integration of AI with new technologies.

Diabetic retinopathy (DR), a major complication of prolonged diabetes, poses a significant risk of vision loss. Early detection is critical for effective treatment, yet traditional diagnostic methods by ophthalmologists are time-consuming, costly, and subject to variability. This study introduces a novel approach employing a hybrid Convolutional Neural Network-Radial Basis Function (CNN-RBF) classifier integrated with Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP) features for enhanced DR detection. We implemented advanced image preprocessing techniques, including noise reduction, morphological operations, and Otsu’s thresholding, to optimize blood vessel segmentation from retinal images. Our method demonstrates exceptional performance in screening DR, achieving an average of 96.10% precision, 95.35% sensitivity, 97.06% specificity, and 96.10% accuracy. These results significantly outperform traditional methods and offer a promising tool for remote and efficient screening of DR. Applied to publicly available datasets, this research contributes to the development of accessible, accurate diagnostic methods in ophthalmology, potentially reducing the global burden of diabetic vision loss.

Humans have a unique cognitive ability known as relational abstraction, which allows us to identify logical rules and patterns beyond basic perceptual characteristics. This ability represents a key difference between how humans and other animals learn and interact with the world. With current large language models rivaling human intelligence in many regards, we investigated whether relational abstraction was an emergent chat completion capacity in various models. We find that despite their impressive language processing skills, all tested language models failed the relational match-to-sample (RMTS) test, a benchmark for assessing relational abstraction. These results challenge the assumption that advanced language skills inherently confer the capacity for complex relational reasoning. The paper highlights the need for a broader evaluation of AI cognitive abilities, emphasizing that language proficiency alone may not be indicative of certain higher-order cognitive processes thought to be supported by language.

Current methods for assessing individual well-being in team collaboration at the workplace rely often on manually collected surveys. This limits continuous real-world data collection and proactive measures to improve team member workplace satisfaction. We propose a method to automatically derive social signals related to individual well-being in team collaboration from raw audio and video data collected in teamwork contexts. The goal is to develop computational methods and measurements to facilitate the mirroring of individuals’ well-being to themselves. We are focusing on how speech behavior is perceived by team members to improve their well-being. Our main contribution is the assembly of an integrated toolchain to perform multi-modal extraction of robust speech features in noisy field settings and to find which features are predictors of self-reported satisfaction scores. We apply the toolchain to a case study where we collected videos of 22 teams with 56 participants collaborating over a four-day period in a team project. Our audiovisual speaker diarization extracts individual speech features in a noisy environment. As the dependent variable team members filled out a daily PERMA (positive emotion, engagement, relationships, meaning, and accomplishment) survey. These well-being scores have been predicted with speech features extracted from the videos using machine learning. The results suggest that the proposed toolchain is able to automatically predict individual well-being in teams, leading to better teamwork and happier team members.

The use of hyperthermia is one of the effective methods of treating cancer. In this case, the problem arises of constructing and predicting the distribution of the thermal field inside tissues depending on their type. This paper discusses the use of linear and polynomial regression methods, as well as regression algorithms based on decision tree, random forest and K nearest neighbors methods to recover missing temperature values. The influence of the size of the training sample when performing regression on the quality of the reconstructed values is investigated. Experimental recommendations on sample size are given for the selected decision tree and random forest methods. The possibility of a significant (10 times or more) reduction in the initial sample size, without leading to a decrease in the R² metric by more than 0.05 for various tissues, has been shown.

The moisture content of maize seed is an important indicator for evaluating seed quality and a fundamental item in grain testing. The experiment used direct drying method to measure the moisture content of 80 different varieties of maize samples, and captured their images using a hyperspectral imaging (HSI) system in the spectral range of 1100~2498nm. By comparing seven spectral preprocessing methods, the PLSR model established after Normalize pretreatment had the best effect. The characteristic wavelengths were selected by Successive Projections Algorithm (SPA), Competitive Adaptive Reweighted Sampling (CARS) and Uninformative Variable Elimination (UVE). Twelve prediction models were established for full band spectra and characteristic wavelengths based on PLSR, PCR and SVM. By comparing the performance of the prediction models, it was found the Normalize-SPA-PLSR algorithm was optimized. The values of RC2 and RP2 in the model were higher, which were 0.9936 and 0.9933, respectively, while the values of RMSEP and RMSECV were lower, which were 0.0357 and 0.0380, respectively. The Normalize-SPA-PLSR model was used as a visual prediction model for moisture content of maize seed, the 20 maize varieties in the prediction set were visualized to obtain visualized color images of moisture content. The color differences between different moisture content images were significant. The result indicated that hyperspectral imaging could accurately, rapidly, and non-destructive predict moisture content of maize seed, which provided technical support for moisture content detection in the process of maize harvest, storage and processing.

This research delves into the intricate challenges confronting the agricultural sector, with a specialized focus on mitigating infections in tomato crops, particularly powdery mildew induced by the Leveillula Taurica pathogen. Tomatoes, renowned for their nutritional richness, are vital to global food security. However, conventional methodologies for disease detection exhibit both laborious processes and limited accuracy. In response to these challenges, this study advocates for an innovative fusion of hyperspectral imaging and deep learning methodologies to detect crop disease and its severity. The systematic workflow commenced with the curation of a dataset, involving the acquisition of live images through OpenCV, followed by conversion to RGB format and subsequent feature extraction utilizing a pre-trained visual geometry group (VGG-16) model for enhanced analysis. Sequentially, RGB images were transformed into simulated hyperspectral images (SHSI) leveraging a Neural Network generator model, offering a distinctive viewpoint on spectral information. This novel approach transcends conventional constraints by delivering a three-dimensional perspective, seamlessly integrating spatial and spectral dimensions for holistic data acquisition. The SHSI is further transmuted into a 3D visualization cube comprehensive grasp of spatial and spectral aspects encompassing spectral, spatial, and Haralick features. The research concludes with severity detection, categorized as low, moderate, or high, employing a Gaussian Mixture Model (GMM) and K-means for visualization.

Buildings are rapidly becoming more digitized, to a large extent due to developments in IoT. This will provide many opportunities but also a number of challenges. One of the central challenges in the process of digitizing buildings is the ability to monitor the building’s status effectively. This monitoring is essential for various services that rely on information about the presence and activities of individuals within different areas of the building. Occupancy information, including people counting, occupancy detection, location tracking, and activity detection, plays a vital role in the management of smart buildings. In this article, our primary focus is on the use of Passive Infrared (PIR) sensors for gathering occupancy information. PIR sensors are among the most widely used sensors for this purpose due to their consideration of privacy concerns, cost-effectiveness, and low processing complexity compared to many others. Despite numerous literature review articles in the field of occupancy information, there currently isn’t a specialized literature review dedicated to occupancy information derived specifically from PIR sensors.Therefore, this study analyzes articles that specifically explore the application of PIR sensors for occupancy information. This article provides a comprehensive literature review of PIR sensor technology from 2015 to 2023, with a focus on applications in people counting, activity detection, and localization (traking and location). It consolidates findings from a number of articles that have explored and enhanced the capabilities of PIR sensors in these interconnected domains. This review thoroughly examines the application of various techniques, machine learning algorithms, and configurations for PIR sensors in indoor building environments, emphasizing not only the data processing aspects but also their advantages, limitations, and efficacy in producing accurate occupancy information.These developments are crucial for improving building management systems in terms of energy efficiency, security, and user comfort, among other operational aspects.These developments are crucial for improving building management systems in terms of energy efficiency, security, and user comfort, among other operational aspects. The paper seeks to offer a thorough analysis of the present state and potential future advancements of PIR sensor technology in efficiently monitoring and understanding occupancy information by classifying and analyzing improvements in these domains.

The integration of Artificial Intelligence (AI) with the Internet of Things (IoT) has propelled technological innovation across various industries. This systematic literature review explores the current state and future trajectories of AI in IoT, with a particular focus on emerging trends in intelligent data analysis and privacy protection. The proliferation of IoT devices, marked by voluminous data generation, has reshaped data processing methods, providing actionable insights for informed decision-making. While previous reviews have offered valuable insights, they often fall short of comprehensively addressing the multifaceted dimensions within the AI-driven IoT landscape. This review aims to bridge this gap by systematically examining existing literature and acknowledging the limitations of past studies. To achieve this aim, the study uses a meticulous approach guided by established methodologies. The chosen methodology ensures the rigor and validity of the review, aligning with PRISMA guidelines for systematic reviews. This systematic literature review serves as a comprehensive guide for researchers, practitioners, and policymakers, offering insights into the current landscape and paving the way for future research directions. The identified trends and challenges provide a valuable resource for navigating the evolving domain of AI in IoT, fostering a balanced, secure, and sustainable advancement in this dynamic field.

As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.

In this review paper, we discuss the use of BERT, one of the most well-liked deep learning-based language models. The model's operation mechanism, key areas of applicability to text analytics tasks, comparisons with related models for each activity, and a description of certain proprietary models are all covered in this work. The data from several dozen original scientific studies that have been published in the last few years and have garnered the greatest interest from the scientific community were systematized in order to prepare this review. All researchers and students who wish to learn about the most recent developments in the field of natural language text analysis may find this survey helpful. Bidirectional Encoder Representations from Transformers, or BERT for short, is the subject of a thorough investigation that we present. The area of natural language processing holds significant importance in the creation of intelligent systems. To do a variety of activities, one must comprehend the sentence's correct meaning in order to produce the desired result. Computers have a hard time understanding languages because of how context constantly changes. The main challenge in natural language processing tasks is getting computers to understand text context, and BERT is seen as a revolution in this regard. It picks up the language and its meaning in a manner that is quite similar to how the human brain processes meaning from sentences. Its capacity to identify a word from both the left and right contexts of a sentence makes it special. A new era in the perception and comprehension of natural languages has been ushered in with the development of BERT, which could help computers understand natural languages more fully. This study aims to provide readers with a deeper knowledge of the BERT language model and how it is applied to different NLP tasks.

Heart failure is a leading cause of death among people worldwide. The cost of treatment can be prohibitive, and early prediction of heart failure would reduce treatment costs to patients and hospitals. Improved prediction of readmission would also be of great help hospital, allowing them to better manage their treatment programs and budgets. This systematic review aims to summarize recent studies of predictive analytics models that have been constructed to predict heart failure and readmission. Some of these models use a statistical approach and others a machine learning approach. Electronic patient health records, including demography, physical and clinical values, and laboratory findings are used to design and build predictive models. Predictive analytics with good performance have become essential for clinicians and specialists. Choosing a suitable machine learning algorithm and data preprocessing technique will improve predictive model performance, including data imputation and class imbalance.

Since the outbreak of the COVID-19 pandemic, patients infected with COVID-19 may experience abnormal heart rates, posing potential health risks. This study proposes a non-contact method for measuring heart rate (HR) and heart rate variability (HRV) to effectively reduce the risk of infection and assist healthcare professionals in more accurate diagnosis and treatment. In this study, except for the different image acquisition method, other research processes and methods are similar to the research methods in [15]. The image acquisition method is changed from forehead image to palm image. The new non-contact measurement performance of the proposed method can effectively not only avoid infection concerns but also obtain heart rate and HRV quickly and conveniently, providing higher accuracy for physiological parameters, root mean square error (RMSE), and mean absolute percentage error (MAPE) compared to those in recently published papers.

Pedestrian object detection plays a significant role in intelligent systems such as intelligent traffic and monitoring. Traditional machine learning methods on pedestrian detection have shown various drawbacks, \eg{} low accuracy, slow speed, \etc The Convolutional Neural Network (CNN) based object detection algorithms have demonstrated remarkable advantages in the field of pedestrian detection. However, the mainstream CNNs still face the problems of slow speed and low detection accuracy, especially on small and occluded targets from aerial perspective. In this paper, we propose Multi-Scale Attention YOLO (MSA-YOLO) detection algorithm to address the above issues. MSA-YOLO includes a Squeeze, Excitation and Cross Stage Partial (SECSP) channel attention module for CNNs to extract richer pedestrian features with a small number of extra parameters. It also contains a multi-scale prediction module to capture the information among different pedestrian scales, which can recognize the small objects with higher accuracy and significantly reduce the missed detection. To sufficiently evaluate our proposed model, we manually collect and annotate a new benchmark dataset, Luoyang Pedestrian Dataset \footnote{The dataset can be downloaded through this anonymous link: \url{https://drive.google.com/drive/folders/13po1FX7Qk5RDgb60-dzOi74cq_kqDJtM?usp=sharing} }, which has much more sample annotations, features, scenes and image view angles than the existing benchmark datasets. In addition, the images in our dataset have higher resolution than most of benchmark pedestrian detection datasets, which can provide more detailed features of pedestrians and thus improve the model performance. When tested on Luoyang Pedestrian Dataset, our proposed MSA-YOLO algorithm significantly outperform the most commonly used baseline models with almost the same model size. This shows the efficiency of our proposed model. (The code and new dataset will be released to the public later.)

The term artificial intelligence refers to the field of computer science that deals with the design and implementation of computer systems that mimic elements of human behavior that imply basic intelligence: learning, adaptability, inference, contextual understanding, and problem solving among others. Artificial intelligence is a point of intersection between multiple sciences such as computer science, psychology, philosophy, neurology, linguistics and engineering science, with the aim of synthesizing intelligent behavior, with elements of reasoning, learning and adaptation to the environment, while it is usually applied to specially made machines or computers.

Human Pose Estimation (HPE) is a technique in computer vision and AI for detecting and tracking human body parts and poses from images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods using monocular cameras are highly versatile due to their applicability in standard video and CCTV footage. These methods have evolved from 2D to 3D pose estimation. However, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges such as limited training data, depth perception ambiguity, left/right switching, and issues with occlusions when applied in real-world environments. This study compares two representative 3D HPE methods by assessing their strengths and weaknesses with real-world videos. Then, we propose data processing techniques to eliminate and correct anomalies like left/right inversion and false detections of joint positions in daily life motions. Finally, we obtain joint angle trajectories using an optimization method based on a 3D humanoid simulator, taking as input the joint coordinate data corrected by applying the proposed human joint data processing technique. The efficacy of the proposed 3D HPE method is verified by applying it to three-dimensional freehand gymnastics exercises and comparing the joint angle trajectories during the motion.

Recent technological advancements such as IoT and Big Data have granted industries extensive access to data, opening up new opportunities for integrating Artificial Intelligence (AI) across various applications to enhance production processes. We can cite two critical areas where AI can play a key role in industry such as product quality control and predictive maintenance. This paper presents a survey of AI applications in the domain of Industry 4.0, with a specific focus on product quality control and predictive maintenance. Experiments were conducted using two datasets, incorporating different machine learning and deep learning models from the literature. Furthermore, this paper provides an overview of the AI solution development approach for product quality control and predictive maintenance. This approach includes several key steps, such as data collection, data analysis, model development, model explanation, and model deployment.

Document image binarization is a challenging task, especially when it comes to text segmentation in degraded document images. The binarization, as a pre-processing step of optical character recognition (OCR), is one of the most fundamental and commonly used segmentation methods. It separates the foreground text from the background of the document image to facilitate subsequent image processing. In view of the different degradation degree of document image, researchers have proposed a variety of solutions. This paper reviews the main binarization techniques, including both traditional algorithms and deep learning-based algorithms. We also summarize some difficulties and challenges in the field of document image binarization. Here, we evaluate various image binarization techniques to identify shortcomings in current methods and provide some help for future research.

Generative models have recently gained popularity in Remote Sensing, offering substantial benefits for interpreting and utilizing satellite imagery across diverse applications such as climate monitoring, urban planning, and wildfire detection. These models are particularly adept at addressing the challenges posed by satellite images, which often exhibit domain variability due to seasonal changes, sensor characteristics, and especially variations in spectral bands. Such variability can significantly impact model performance across various tasks. In response to these challenges, our work introduces a novel approach that harnesses the capabilities of Generative Adversarial Networks (GANs), augmented with Contrastive Learning, to generate target domain images that account for multi-spectral band variations effectively. By maximizing mutual information between corresponding patches and leveraging the power of GANs, our model aims to generate realistic-looking images across different multi-spectral domains. We present a comparative analysis of our model against other well-established generative models, demonstrating its efficacy in generating high-quality satellite images while effectively managing domain variations inherent to multi-spectral diversity.

The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well-informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we introduce an application of an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs, through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first application of policy graphs in the context of explaining agent behaviour in collaborative multi-agent scenarios and presents experimental results that sets this kind of scenario apart from previous application in single-agent scenarios: when requiring collaborative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.

Amidst the burgeoning global concerns surrounding skin cancer, the quest for precise and efficient diagnostic methodologies has intensified. Conventional diagnostic approaches relying on subjective visual inspection by dermatologists often grapple with subjectivity and resource constraints. This predicament underscores the critical role of Artificial Intelligence (AI) in revolutionizing diagnostic paradigms by significantly enhancing accuracy and accessibility. This study embarks on an extensive exploration of skin cancer classification, specifically targeting the intricate task of 8-class skin cancer classification. Employing cutting-edge deep learning models on the ISIC2019 dataset, a comprehensive analysis was conducted utilizing a diverse array of pre-trained ImageNet architectures and Vision Transformer models. To counteract the inherent class imbalance in skin cancer datasets, a pioneering "Naturalize" augmentation technique was introduced, leading to the creation of indispensable tools—the Naturalized 2.4K ISIC2019 and groundbreaking Naturalized 7.2K ISIC2019 datasets—catalyzing advancements in classification accuracy. The pivotal role of AI in mitigating the risks of misdiagnosis and under-diagnosis in skin cancer becomes evident through this research. AI’s proficiency in analyzing vast datasets and discerning subtle patterns augments the diagnostic prowess of dermatologists significantly. Integration of AI-powered systems in skin cancer diagnosis holds immense promise in facilitating early detection and substantially improving patient outcomes. The meticulous evaluation employed quantitative measures such as confusion matrices, classification reports, and visual analyses using Score-CAM across diverse dataset variations. Astonishingly, the culmination of these endeavors culminated in an unprecedented achievement—100% average accuracy, precision, recall, and F1-Score—within the groundbreaking Naturalized 7.2K ISIC2019 dataset. This remarkable feat underscores the transformative potential of AI-driven methodologies, exemplifying their prowess in redefining the landscape of skin cancer diagnosis and management. In summary, this research represents a pivotal stride towards redefining dermatological diagnosis, showcasing the remarkable impact of AI-powered solutions in surmounting the challenges inherent in skin cancer diagnosis. The attainment of 100% across crucial metrics within the Naturalized 7.2K ISIC2019 dataset serves as a testament to the transformative capabilities of AI-driven approaches in reshaping the trajectory of skin cancer diagnosis and patient care.

Researchers are always looking to find ways to use energy more efficiently while keeping people comfortable at home. They've tried different methods like fuzzy logic and genetic algorithms to do this. In this paper, we introduce a novel model that combines different techniques like data smoothing, optimization, machine learning, and control algorithms to reach this goal in smart homes. The proposed model is made up of three main parts: smoothing, optimization, and control. The smoothing part uses the Kalman filter to get rid of any unnecessary noise and make sure the data used to predict energy use is clean and smooth. The optimization part uses both genetic with firefly algorithms and artificial neural networks to minimize the gap between the actual environmental conditions and the conditions users find comfortable. It adjusts the comfort settings in real-time using machine learning. The control part uses Mamdani fuzzy logic to make sure energy is delivered in the best way possible to the systems that control temperature, lighting, etc., making the home comfortable and saving energy at the same time. Comparative analyses demonstrate the superiority of the proposed model over existing algorithms, including the Particle Swarm Optimization (PSO) algorithm. Additionally, the paper discusses the importance of adaptive controllers in addressing issues associated with incorrect PID controller selection and highlights the benefits of using the FA-GA in energy optimization and comfort improvement. Overall, the proposed model offers an effective solution for efficient energy consumption optimization and enhanced user comfort in diverse settings through the integration of advanced algorithms and optimization modules.

With the recent advances in Machine Learning (ML), several models have been successfully applied to financial and accounting data to predict the likelihood of companies’ bankruptcy. However, time series have received little attention in literature with a lack of studies on the application of Deep Learning sequence models as Recurrent Neural Networks (RNN) and the recent Attention-based models in general. In this research work, we investigated the application of Long Short Term Memory (LSTM) networks to exploit time series of accounting data for bankruptcy prediction. The main contributions of our work are the following: a) we have proposed a Multi-head LSTM that models each financial variable in a time window independently and compared it with a single-input LSTM and other traditional ML models. The Multi-head LSTM outperforms all the other models; b) We identify the optimal time series length for bankruptcy prediction to be equal to 4 years of accounting data; c) We made public the dataset we used for the experiments that include data from 8262 different public companies in the American stock market generated in the period between 1999-2018. Furthermore, we prove the efficacy of the Multi-head LSTM models in terms of lower false positives and better division of the two classes.

Continuous Distributed Constraint Optimization Problem (C-DCOPs) are a powerful framework to model problems with continuous variables in multi-agent systems. Previous works about C-DCOP algorithms mainly use pseudo-trees to guarantee the anytime property or are without anytime property guarantees. However, there is a risk of privacy leakage in the pseudo-tree due to utility passing between agents. Therefore, based on the basic constraint graph instead of the pseudo-tree, we (i) extend the Maximum Gain Message (MGM) algorithm by combining the local search strategy to solve C-DCOPs, named Continuous MGM (C-MGM), and it’s able to guarantee the monotonicity of the solution quality; (ii) propose a Parallel C-MGM (C-PMGM) algorithm to improve the solution quality through parallel random search; and (iii) introduce the differential search into C-PMGM to design a Parallel Differential Search C-MGM (C-PDSM) algorithm, which constructs a heuristic method to speed up convergence and improve solution quality. Compared to other anytime C-DCOP algorithms using pseudo-trees, the proposed three algorithms can exhibit better performance in avoiding privacy violations. We theoretically prove that the proposed algorithms are the anytime algorithms and empirically demonstrate that our algorithms outperform the state-of-the-art C-DCOP algorithms.

Language bias stands as a noteworthy concern in Visual Question Answering (VQA), wherein models tend to rely on spurious correlations between questions and answers for prediction. This prevents the models from effectively generalizing, leading to a decrease in performance. To address this bias, we propose a novel modality fusion collaborative de-biasing algorithm (CoD). In our approach, bias is considered as the model’s neglect of information from a particular modality during prediction. We employ a collaborative training approach to facilitate mutual modeling between different modalities, achieving efficient feature fusion and enabling the model to fully leverage multi-modal knowledge for prediction. Our experiments on various datasets, including VQA-CP v2, VQA v2, and VQA-VS, using different validation strategies, demonstrate the effectiveness of our approach. Notably, employing a basic baseline model resulted in an accuracy of 60.14% on VQA-CP v2.

In recent years, e-commerce platforms have replaced conventional marketplaces. People are rapidly adopting internet shopping due to the convenience of making purchases from the comfort of their homes. Online review sites allow customers to share their thoughts on products and services. Customers and businesses are increasingly relying on online reviews to assess and improve the quality of products. Existing literature uses Natural language processing (NLP) to analyze customer reviews for different applications. Due to the growing importance of NLP for online customer reviews, this study attempts to provide a taxonomy of NLP applications based on existing literature. This study also examined emerging methods, data sources, and research challenges by reviewing 154 publications from 2013 to 2023 that explore state-of-the-art approaches for diverse applications. Based on existing research, the taxonomy of applications divides literature into five categories: sentiment analysis, review analysis, customer feedback and satisfaction, user profiling, and marketing and reputation management. It is interesting to note that the majority of existing research relies on Amazon user reviews. Additionally, recent research has encouraged the use of advanced techniques like Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory (LSTM), and ensemble classifiers. The rising number of articles published each year indicates increasing interest of researchers and continued growth. This survey additionally addresses open issues, providing future directions in online customer review analysis.

In the rapidly advancing field of Artificial Intelligence (AI), this study presents a critical evaluation of the resilience and cybersecurity efficacy of leading AI models, including ChatGPT-4, Bard, Claude, and Microsoft Copilot. Central to this research is the use of innovative adversarial prompts designed to rigorously test the content moderation capabilities of these AI systems. The study introduces new types of adversarial tests and the Response Quality Score (RQS), a metric specifically developed to assess the nuances of AI responses. Additionally, the research spotlights FreedomGPT, an AI tool engineered to optimize the alignment between user intent and AI interpretation. The empirical results from this investigation are pivotal for assessing the current robustness and security of AI models. They highlight the necessity for ongoing development and meticulous testing to bolster AI defenses against an array of adversarial challenges. Importantly, the study also delves into the ethical and societal implications associated with employing advanced 'jailbreak' techniques in AI testing. The findings are significant for understanding AI vulnerabilities and formulating strategies to enhance the reliability and ethical soundness of AI technologies, paving the way for safer and more secure AI applications.

The integration of artificial intelligence (AI) into the European Foundation for Quality Management (EFQM) business excellence model is a promising approach to improve the efficiency and effectiveness of excellence in organizations. This research paper’s integrated framework follows the ISO/IEC 23053 standard in addressing some of the concerns related to time and cost associated with the EFQM model, achieving higher EFQM scores, hence operational excellence. A case study involving a UAE government organization serves as a sample to train the AI framework. Historical EFQM results from different years are used as training data. The AI framework utilizes the unsupervised machine learning technique known as k-means clustering (with k=2). This technique follows the ISO/IEC 23053 standard to predict EFQM output total scores based on criteria and sub-criteria inputs. The research paper's main output is a novel AI framework that can predict EFQM scores for organizations at an early stage. If the predicted EFQM score is not high enough, then the AI framework provides feedback to decision makers regarding the criteria that need reconsideration. Continuous use of this integrated framework helps organizations attain operational excellence. This framework is considered valuable for decision makers as it provides early predictions of EFQM total scores and identifies areas that require improvement before officially applying for the EFQM excellence award. This approach can be considered as an innovative contribution and enhancement to knowledge body and organizational practices.

The weighted K-nearest neighbors (WKNN) algorithm has been widely used in indoor fingerprint localization, which utilizes fingerprint distance (FD) of pairwise positions to discriminate the physical distance (PD) between them. However, due to the varied states of different wireless access points (APs), their contribution to FD discrimination capability varies. In our study, we analyzed several critical causes that affect APs’ contribution, including AP’s health state, the distance, and the direction between APs and position pairs. Inspired by these insights, a threshold was set for all sample RSS to eliminate the impact of abnormal APs on FD, and a correction quantity for each RSS was provided by the distance between APs and sample positions to reduce the strong signal influence on FD. Furthermore, a priority weight was designed by RSS differences (RSSD) to further optimize FD’s capability to discriminate PD. Integrating the above policies, a new indoor fingerprint localization technique is redefined, referred to FD’s discrimination capability improvement WKNN (FDDC-WKNN), which is suitable for indoor scenes with a large number of APs that are not uniformly managed. Our simulation results show that the correlation and consistency between FD and PD are well improved, with strong correlation increasing from 0 to 76% and high consistency increasing from 26% to 99%, which confirms that the proposed policies can greatly enhance FD’s discrimination capabilities to PD, and we also found that abnormal APs can cause significant impact on FDs’ discrimination Capability. Further, by implementing the FDDC-WKNN algorithm in experiments, we obtained the optimal K value in both the simulation scene and real library scene, under which the average localization errors have been reduced from 2.2732m to 1.2183m and from 3.4295m to 2.2068m, respectively. In addition, compared to not using the FDDC-WKNN, the cumulative distribution function (CDF) of the localization errors curve converged faster and the errors fluctuation is smaller, which demonstrate FDDC-WKNN having stronger robustness and more stable localization performance to the state of APs in indoor environments.

This study develops a 7-layer Long Short-Term Memory (LSTM) model to enhance early diabetes detection in Oman, aligning with the theme of 'Artificial Intelligence in Healthcare'. The model focuses on addressing the increasing prevalence of Type 2 diabetes, projected to impact 23.8% of Oman's population by 2050. It employs LSTM neural networks to manage factors contributing to this rise, including obesity and genetic predispositions, and aims to bridge the gap in public health awareness and prevention. The model's performance is evaluated through various metrics. It achieves an accuracy of 99.40%, specificity and sensitivity of 100% for positive cases, a recall of 99.34% for negative cases, an F1 score of 96.24%, and an AUC score of 94.51%. These metrics indicate the model's capability in diabetes detection. The implementation of this LSTM model in Oman's healthcare system is proposed to enhance early detection and prevention of diabetes. This approach reflects an application of AI in addressing a significant health concern, with potential implications for similar healthcare challenges globally.st diagnostic capabilities, representing a significant leap forward in healthcare technology in Oman.

In the industrial field, the 3D target detection algorithm PointPillars has gained popularity. Improving target detection accuracy while maintaining high efficiency has been a significant challenge. To address the issue of low target detection accuracy in the PointPillars 3D target detection algorithm, this paper proposes an algorithm based on feature enhancement to improve the backbone network. The algorithm enhances preliminary feature information of the Backbone network by modifying it based on PointPillars with the aid of channel attention and spatial attention mechanisms. To address the inefficiency caused by the excessive number of subsampled parameters in PointPillars, FasterNet (a lightweight and efficient feature extraction network) is utilized for downsampling and forming different scale feature maps. To prevent the loss and blurring of extracted features resulting from the use of inverse convolution, we utilize the lightweight and efficient up-sampling modules Carafe and Dysample for adjusting resolution. Experimental results indicate improved accuracy under all difficulties of the KITTI dataset, demonstrating the superiority of the algorithm over PointPillars.

The utilization of smart IoT devices, commonly referred to as digital twins, is aimed at the digitalization of human knowledge within aquaculture processes. This involves the incorporation of cutting-edge technologies, including information-based management with big data and modeling, to automate machinery and gain comprehensive insights into the aquaculture environment and fish farm conditions. The ultimate objective is to empower farmers to make informed decisions, furnishing them with objective data to enhance their capacity in monitoring and controlling the various factors impacting fish production. As a result, farming decisions can be fine-tuned to enhance fish health and optimize farm output. In the context of large and modern aquaculture farms, technological innovation becomes imperative to automate processes, minimize labor requirements, and streamline fish feeding operations. Remarkably, the literature currently offers limited discussions on the digital transformation of aquaculture through the application of digital twin methodologies. A prior study underscores the critical influence of factors such as market prices and fish survival rates on the profitability of offshore caging culture. In this study, we embark on an analysis of the prerequisites for establishing a digital twin infrastructure tailored to intelligent fish feeding management. This infrastructure is designed to facilitate the integration of technology and data-driven decision-making, ultimately enhancing the efficiency of fish feeding processes. The proposed architecture for the fish feeding digital twin encompasses various digital twin components, encompassing water quality forecasting, fish population assessment, fish metrics estimation, fish feed prediction, and evaluation of fish feeding intensity. Furthermore, we optimize the daily fish feeding process through reinforcement learning algorithms. Finally, we implement a cloud-based AIoT system that provides the runtime environment for executing digital twins and controlling our intelligent fish feeding machinery. Experimental findings underscore the efficacy of the proposed digital twin system in significantly improving traditional fish feeding processes, notably in terms of reducing food costs and labor requirements.

Solar energy adoption worldwide has expanded exponentially due to a surge in international interest in producing clean energy and the declining cost of solar power plants and their technology. It is anticipated that by 2050, solar will have surpassed fossil fuels to become the primary source of energy. However, one of the main challenges associated with solar energy production is the instability of photovoltaic (PV) power generation because of weather changes. Short-term forecasting of the power output of photovoltaic systems is essential for efficient management of the power grid and energy markets. This paper aims to evaluate the ability of deep learning (DL) models to provide accurate forecasting of hourly global horizontal irradiance (GHI) using different sets of features, including weather and aerosol variables along with solar radiation components. The results show that the best forecast skills are achieved by the long short-term memory autoencoder (LSTM-AE) model.

The core motivation for this study emanates from Voronin S.'s seminal work on the universality of the zeta function. This universality positions the zeta function as a pivotal element in the conceptual framework of global artificial intelligence, suggesting its potential as a foundational component. A critical barrier to harnessing this promising universality has been the absence of efficient algorithms capable of actualizing this concept.

Electrolysis stands as a pivotal method for environmentally sustainable hydrogen production. However, the formation of gas bubbles during the electrolysis process poses significant challenges by impeding the electrochemical reactions, diminishing cell efficiency, and dramatically increasing energy consumption. Furthermore, the inherent difficulty in detecting these bubbles arises from the non-transparency of the wall of electrolysis cells. Additionally, these gas bubbles induce alterations in the conductivity of the electrolyte, leading to corresponding fluctuations in the magnetic flux density outside of the electrolysis cell, which can be measured by externally placed magnetic sensors. By solving the inverse problem of the Biot-Savart Law, we can estimate the conductivity distribution as well as the void fraction within the cell. In this work, we study different approaches to solve the inverse problem including Invertible Neural Networks (INNs) and Tikhonov regularization. Our experiments demonstrate that INNs are much more robust to solving the inverse problem than Tikhonov regularization when the level of noise in the magnetic flux density measurements is not known or changes over space and time.

FV (finger vein) identification is a biometric identification technology that extracts the features of FV images for identity authentication. To address the limitations of CNN-based FV identification, particularly the challenge of small receptive fields and difficulty in capturing long-range dependencies, an FV identification method Let-Net(Large kernel and attention mechanism Network) was introduced, which combines local and global information. Firstly, Let-Net employs large kernels to broaden the receptive field and incorporates depthwise convolution with residual connections to reduce parameter count. Secondly, Let-Net integrates an attention mechanism to enhance the information flows in channels and spaces for more comprehensive and distinctive FV feature extraction. The experimental results on nine public datasets show that Let-Net has excellent identification performance, and the EER and accuracy rate on the FV_USM dataset can reach 0.04% and 99.77%. The parameter number and FLOPs of Let-Net are only 0.89M and 0.25G, which means that the time cost of training and reasoning of the model is low, and it is easier to deploy and integrate into various applications.

This paper presents a customized adaptive cascaded deep learning (ACDL) model for the design and performance prediction of metasurface absorbers. A multi-resonant metasurface absorber structure is introduced, with 10 target-driven design parameters. The proposed deep learning model takes advantage of cascading several sub-deep neural network (DNN) layers with forward noise mitigation capability. The inherent appearance of sparse data is completely dealt with in this work by proposing a trained adaptive selection technique. On the basis of the findings, the prediction response is quite fast and accurate enough to retrieve the design parameters of the studied metasurface absorber and with two sized patches of 4000 and 7000 datasets. The training loss taken form the second DNN of our proposed model shows logarithmic mean squared errors of 0.039 and 0.033 when using Keras and the adaptive method, respectively, with a dataset split of 4000. On the contrary, for a dataset split of 7000, the errors are 0.049 with Keras and 0.045 with the adaptive method. On the other hand, the validation loss is evaluated using the mean square error method, which results in a loss with 4000 datasets split with the Keras method of 0.044, while it is 0.020 with the adaptive method. When extending the dataset to 7000, the validation loss with the keras splitting method is 0.0073, while it is improved, reaching 0.006 with the proposed adaptive method, and achieving a prediction accuracy of 94%. This proposed deep learning model can be deployed in the design process and synthesis of multi-resonant metasurface absorber structures. The proposed model shows its advantages of making the design process more efficient in sparse dataset handling, efficient approach in multi-resonance metasurface data pre-processing, less time consuming, and computationally valuable.