It is important for food recognition to separate each ingredient within a food image at the pixel level. In this paper, we propose a new approach to segment ingredients by utilizing a CNN-based Single-Ingredient Classification Model. In detail, we firstly introduce a standardized biological-based hierarchical ingredient structure and construct a single-ingredient image dataset based on this structure. Then, we build a single-ingredient classification model based on a novel convolutional neural network (CNN) architecture that utilizes an attention mechanism. Afterwards, we propose a new framework for segmentation using the above single-ingredient classification model as the backbone. In this framework, two methods are involved in segmenting ingredients in the food images. We introduce five evaluation metrics (IoU, Dice, Purity, Entirety, Loss of GTs) to assess the performance of ingredient segmentation in terms of ingredient classification. Extensive experiments demonstrate the effectiveness of the proposed method, achieving an maximal mIoU of 0.65, mDice of 0.77, mPurity of 0.83, mEntirety of 0.80, and mLoGTs of 0.06 on the FoodSeg103 dataset. The results confirm that our CNN-based architecture achieves higher segmentation performance compared to ResNet18 and EfficientNet-B0 when used as the backbone for ingredient segmentation. We believe that our ingredient segmentation approach lays the foundation for subsequent ingredient recognition.

The internal wave recognition algorithm in an ocean data buoy system can be used to realize the real-time and flexible observation of internal waves, but there is no accurate automatic recognition method. To meet the need for automatic, real-time, and reliable internal wave recognition, an automatic internal wave recognition algorithm has been proposed for a tightly profiled intelligent buoy system. The sea profile temperature data collected by the Bailong buoy system in the Andaman Sea in 2018 were used to train and test the internal wave recognition neural network model, which consists of two parts: feature extraction and feature classification. The experiment compares the long short-term memory network (LSTM), convolutional neural network (CNN) with different layers, and deep neural network (DNN) without a feature extraction network and adjusts the number of convolutional nuclei and convolutional strides to improve the feature extraction efficiency. Experiments show that the best results can be obtained when a CNN layer is used as the feature extraction network, the convolutional step length is 4, the number of convolutional kernels is 5. The recall reaches 95.31% and the precision is 97.53%. The internal wave identification delay of the algorithm is 5.0862 minutes, the number of parameters is 1593, and the number of calculations is 3024. The algorithm can be directly deployed to the ocean data buoy system to realize the demand for automatic, real-time and reliable internal wave identification at the buoy end.

This paper proposes two max-pooling engines, named the RTB-MAXP engine and the CMB-MAXP engine, with a scalable window size parameter for FPGA-based convolutional neural network (CNN) implementation. The max-pooling operation for the CNN can be decomposed into two stages, i.e., a horizontal axis max-pooling operation and a vertical axis max-pooling operation. These two one-dimensional max-pooling operations are performed by tracking the rank of the values within the window in the RTB-MAXP engine and cascading the maximum operations of the values in CMB-MAXP engine. Both the RBM-MAXP engine and the CMB-MAXP engine were implemented using VHSIC Hardware Description Language (VHDL) and verified by simulations. They have been employed for and tested in our CNN accelerator targeting at the CNN model YOLOv4-CSP-S-Leaky for object detection.

Social networks have captured the attention of many people worldwide. However, these services have also attracted a considerable number of malicious users whose purpose is to compromise digital assets of other members by using messages as an attack vector to execute different variants of cyberattacks against them. Therefore, this work presents an approach based on Natural Language Processing tools and a Convolutional Neural Network architecture to detect and classify, on social network messages, four types of cyberattacks, such as malware, phishing, spam, and even one whose purpose is deceiving the user into spreading malicious messages to other users, which in this work is identified as bot attacks. One notable feature of this work is that it analyzes textual content without depending on any characteristics from a specific social network, making its analysis independent from particular data sources. Finally, this work was tested on real data, demonstrating its results in two stages. The first detects the existence of any of the four cyberattacks within the message, obtaining an accuracy value of 0.91. After detecting a message as a cyberattack, the next stage is to classify it into one of the four types of cyberattack, achieving an accuracy value of 0.82.

Accurately predicting electrical signals of three-phase Direct Torque Control (DTC) induction motors is crucial for optimal motor performance and effective condition monitoring. However, multiple DTC motors’ complexity and operating conditions’ variations pose challenges for traditional prediction methods. To overcome these challenges, we propose an innovative approach that combines Fast Fourier Transform (FFT) to transform electrical motor simulation data and a Bi-directional Long Short-Term Memory (Bi-LSTM) network to forecast processed motor data. By transforming the DTC induction motor signals from the time domain to the frequency domain, we enhance the capability of learning models to capture subtle differences and generate various input features. The Bi-LSTM model effectively captures both forward and backward dependencies in time series data, enabling accurate prediction of electrical signals. We evaluate the proposed approach using our simulated dataset and compare the proposed method to a state-of-the-art model, the Gated Recurrent Unit (GRU), demonstrating its effectiveness in improving the accuracy and reliability of induction motor signals forecasting. The finding provides valuable insights for advancing motor control and operation in industrial applications.

The primary goal of picture compression is to reduce the amount of unused image data while still storing or transmitting it in a format that is appropriate. The compression of raw binary data is quite different from the compression of a picture, and these differences may be rather substantial. In light of this, compression is often regarded as an essential technique for the purposes of both data storage an d transmission in order to mitigate the excessive amounts of data that are generated by these images. In order to transmit enormous datasets, particularly for the purposes of telemedicine and teleradiology, one needs a significant amount of storage capacity as well as an expansive network. As a result, compression is an important aspect of medical imaging. In addition to the importance of compression, the quality of the photos themselves is also an essential factor in the success of analysis. In addition to this, the amount of time necessary to compress the photographs before sending them should be reduced.

Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired in the visual cortex, are characterized by their hierarchical learning structure, which appears to gradually transform the representation space. Inspired by the direct connection between the LGN and V4, which allows V4 to handle low-level information closer to the trichromatic input in addition to processed information that comes from V2/V3, we propose the addition of a long skip connection (LSC) between the first and last blocks of the feature extraction stage to allow deeper parts of the network to receive information from shallower layers. This type of connection improves classification accuracy by combining simple-visual and complex-abstract features to create more color-selective ones. We have applied this strategy to classic CNN architectures and quantitatively and qualitatively analyzed the improvement in accuracy while focusing on color selectivity. The results show that, in general, skip connections improve accuracy, but LSC improves it even more and enhances the color selectivity of the original CNN architectures. As a side result, we propose a new color representation procedure for organizing and filtering feature maps, making their visualization more manageable.

: Innovative solutions are now being researched to manage the ever-increasing amount of data required to optimize the performance of internal combustion engines. Machine Learning ap-proaches have shown to be a valuable tool for signal prediction due to their real-time and cost-effective deployment. Among them, the architecture consisting of Long Short-Term Memory (LSTM) and one-dimensional Convolutional Neural Networks (1DCNN) has emerged as a highly promising and effective option for replacing the role of physical sensors. The architecture com-bines the capacity of LSTM to detect patterns and relationships in smaller segments of the signal with the ability of 1DCNN to detect patterns and relationships in larger segments of the signal. The purpose of this work is to assess the feasibility of substituting a physical device dedicated to calculating the torque supplied by a spark-ignition engine. The suggested architecture was trained and tested using signals from the field during a test campaign conducted under transient operating conditions. The results reveal that LSTM+1DCNN is particularly well suited for signal prediction with considerable variability. It constantly outperforms other architectures used for comparison, with average error percentages of less than 2%, proving the architecture's ability to replace physical sensors.

Abstract: The surge of diabetes poses a significant global health challenge, particularly in Oman and the Middle East. Early detection of diabetes is crucial for proactive intervention and improved patient outcomes. This research leverages the power of machine learning, specifically, Convolutional Neural Networks (CNNs), to develop an innovative 4D CNN model dedicated to early diabetes prediction. A region-specific dataset from Oman is utilized to enhance health outcomes for individuals at risk of developing diabetes. The proposed model showcases remarkable accuracy, achieving an average accuracy of 98.49% to 99.17% across various epochs. Additionally, it demonstrates excellent F1 score, recall, and sensitivity, highlighting its ability to identify true positive cases. The findings contribute to the ongoing effort to combat diabetes and pave the way for future research in using deep learning for early disease detection and proactive healthcare.

The utilization of Pig Emotion Recognition (PER) driven by Artificial Intelligence (AI) promises to mitigate labor costs and alleviate stress among domestic pigs, thereby minimizing the need for consistent human intervention. Nevertheless, this research acknowledges the inherent limitations within the raw PER datasets, which often include irrelevant porcine features, hence impeding genuine progress in real-world evaluations. A significant proportion of PER datasets derive from sequential pig imagery obtained from video recordings, and a common pitfall in these studies is the unregulated shuffling of data. This lack of control can result in the overlap of data samples between training and testing groups, thereby yielding skewed experimental evaluations. To address these challenges, this paper introduces a novel solution in the form of the Semi-Shuffle-Pig Detector (SSPD) for PER datasets, with the intent to facilitate a less biased experimental output. By applying the SSPD, we can ensure that all testing data samples remain distinct from the training datasets, and any superfluous information from raw images is systematically discarded. This optimized method enhances the true performance of classification, providing unbiased experimental evaluations. Notably, our approach has led to a remarkable improvement in the Isolation After Feeding (IAF) metric by 20.2\% and achieved higher accuracy in segregating IAF and Paired After Feeding (PAF) classifications exceeding 92\%. This methodology, thereby, ensures the preservation of pertinent data within the PER system and eliminates potential biases in experimental evaluations. Consequently, it elevates the accuracy and reliability of real-world PER applications, resulting in a tangible positive impact on both pig welfare management and food safety standards.

Nowadays people express their opinions on social media. Also provides product reviews on eCommerce websites and responds to various news as comments. It is necessary to know the polarity and aspect of various posts and comments for business, education and security. Aspect-based sentiment analysis (ABSA) predicts text category and polarity. In this paper, we proposed a deep learning framework Deep-ABSA for aspect-based sentiment analysis from Bangla texts. Our proposed framework is a multi-channel architecture. We implemented the word embedding, Bi-LSTM with the attention mechanism for one channel. And for another channel, we adopted the character-embedded convolutional neural network. Finally, we concatenated both channels for adjoining the features of each channel. We obtained an adequate performance from our proposed framework for aspect term analysis from Bangla sentences.

Hyperspectral image and LiDAR image fusion plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, like Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we proposed a invariant attribute-driven binary bi-branch classification (IABC) method which is a unified network that combines binary Convolutional Neural Network (CNN) and GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structured representation of HSI and LiDAR images in the spectral-spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision-making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrates the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques.

Ultrasonic-guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects experienced in metallic pipelines. Signal processing of the guided waves is often challenged due to the complexity of operational conditions and environments in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for signal process and data classification of complex systems, thus great potential for damage detection of critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model is utilized for decoding ultrasonic guided waves for damage detection of metallic pipelines, and twenty-nine features are extracted as input to classify different types of defects from metallic pipes. The prediction capacity of the CNN-LSTM model is assessed by comparing it to the CNN and LSTM. The results demonstrate that the CNN-LSTM hybrid model exhibits much higher accuracy, with 94.8%, as compared to those of CNN and LSTM. Interestingly, the results also reveal that predetermined features, including time-, frequency-, and time-frequency domains, could significantly improve the robustness of the deep learning approaches, even though the deep learning approaches are often believed they include automated feature extraction, without the hand-crafted steps as the shallow learning do. Furthermore, the CNN-LSTM model displays higher performance when the noise level is relatively low (e.g., SNR=9 or higher), as compared to the other two models, but its prediction drops gradually with the increase of the noise.

Emotions play a vital role in understanding human behavior and interpersonal relationships. The ability to recognize emotions through Electroencephalogram (EEG) signals offers an alternative to traditional methods, such as questionnaires, enabling the identification of emotional states in a non-intrusive manner. Automatic emotion recognition holds great potential, eliminating the need for clinical examinations or physical visits, thereby contributing significantly to the advancement of Brain-Computer Interface (BCI) technology. However, one of the key challenges lies in effectively selecting and extracting relevant features from the EEG signal to establish meaningful distinctions between different emotional states. The process of feature selection is often time-consuming and demanding. In this research, we propose a groundbreaking approach for automatically identifying three emotional states (positive, negative, and neutral) by leveraging auditory stimulation of EEG signals. Our novel method directly applies the raw EEG signal to a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) architecture, bypassing the conventional feature extraction and selection steps. This unconventional approach offers a significant departure from existing literature. Our proposed network architecture comprises ten convolutional layers, followed by three LSTM layers and two fully connected layers. Through extensive simulations and evaluations on 12 active channels, our algorithm demonstrates exceptional performance, achieving an accuracy of 97.42\% and 95.23\% for the binary classification of negative and positive emotions, as well as a Cohen's Kappa coefficient of 0.96 and 0.93 for the three-class classification (negative, neutral, and positive), respectively. These promising results highlight the efficacy of our novel methodology and its potential implications in advancing emotion recognition using EEG signals.

Structural magnetic resonance imaging (sMRI) is widely used in the clinical diagnosis of diseases due to its advantages: high definition and noninvasive. Therefore, computer-aided diagnosis based on sMRI images is broadly applied in classifying Alzheimer’s disease (AD). Due to the excellent performance of Transformer in computer vision, Vision Transformer (ViT) has been employed for AD classification in recent years. ViT relies on access to large datasets, while the sample size of brain imaging datasets is relatively insufficient. Moreover, the pre-processing procedures of brain sMRI images are complex and labor-intensive. To overcome the limitations mentioned above, we propose Resizer Swin Transformer (RST), a deep learning model that can extract information from brain sMRI images that are only briefly processed to achieve multi-scale and cross-channel features. In addition, we pre-trained our RST on a natural image dataset and obtained better performance. The experimental results of ADNI and AIBL datasets prove that RST can achieve better classification performance in AD prediction compared with CNN-based and Transformer models.

SQL injection attacks are one of the most common types of attacks on web applications. These attacks exploit vulnerabilities in the application’s database access mechanisms, allowing attackers to execute unauthorized SQL queries. In this study, we propose an architecture for detecting SQL injection attacks using a recurrent neural network (RNN) autoencoder. The proposed architecture was trained on a publicly available dataset of SQL injection attacks. Then compared with several other machine learning models, including ANN, CNN, Decision Tree, Naïve Bayes, SVM, Random Forest, and Logistic Regression. The experimental result showed that the proposed approach achieved an accuracy of 94% and an F1 score of 92%, which demonstrate its effectiveness in detecting QL injection attacks with high accuracy in comparison with other models covered in the study.

Microarray gene expression-based detection and classification of medical conditions have been prominent in research studies over the past few decades. However, extracting relevant data from the high-volume microarray gene expression with inherent nonlinearity and inseparable noise components raises significant challenges during data classification and disease detection. So, this paper proposes a two-level strategy involving feature extraction and selection methods before the classification step. The feature extraction step utilizes Short Term Fourier Transform (STFT), and the feature selection step employs Particle Swarm Optimization (PSO) and Harmonic Search (HS) metaheuristic methods. The classifiers employed are Non-Linear Regression, Gaussian Mixture Model, Softmax Discriminant, Naive Bayes, SVM (Linear), SVM (Polynomial), and SVM (RBF). The two-level extracted relevant features are compared with raw data classification results, including Convolutional Neural Network (CNN) Methodology. Among the methods, STFT with PSO feature selection and SVM (RBF) classifier produced the highest accuracy of 94.47%.

The CAN protocol is widely adopted for in-vehicle networks due to its cost efficiency and reliable transmission. However, despite its popularity, the protocol lacks built-in security mechanisms, making it vulnerable to various attacks such as flooding, fuzzing, and DoS. These attacks can exploit vulnerabilities and disrupt the normal behavior of the in-vehicle network. One of the main reasons for these security concerns is that the protocol relies on broadcast frames for communication between ECUs within the network. To tackle this issue, this paper presents an intrusion detection system that leverages multiple LSTM-Autoencoders. The proposed system utilizes diverse features, including transmission interval and payload value changes, to capture various characteristics of normal network behavior. By analyzing different types of features separately using the LSTM-Autoencoder model, the system effectively detects anomalies. In our evaluation, we conducted experiments using real vehicle network traffic, and the results demonstrated the system's high precision with a 99% detection rate in identifying anomalies.

Deep learning is improving by leaps and bounds in remote sensing images (RSIs) analysis, pre-trained convolutional neural networks (CNNs) have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, pre-trained CNNs require massive annotated data as samples for data training. When labeled samples are not sufficient, the most common solution is to the pre-trained CNNs using a great deal of natural image dataset (e.g. ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical-quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical-quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proved that the proposed algorithm improves the classification accuracy while greatly decreasing sum of model parameters and sum of training data.

GNSS time series prediction plays a significant role in monitoring crustal plate motion, landslide detection, and maintenance of the global coordinate framework. Long Short-Term Memory (LSTM), a deep learning model has been widely applied in the field of high-precision time series prediction especially when combined with Variational Mode Decomposition (VMD) to form the VMD-LSTM hybrid model. To further improve the prediction accuracy of the VMD-LSTM model, this paper proposes a dual variational modal decomposition long short-term memory (DVMD-LSTM) model to effectively handle the noise in GNSS time series prediction. This model extracts fluctuation features from the residual terms obtained after VMD decomposition to reduce the prediction errors associated with residual terms in the VMD-LSTM model. Daily E, N, and U coordinate data recorded at multiple GNSS stations between 2000 and 2022 are used to validate the performance of the proposed DVMD-LSTM model. The experimental results demonstrate that compared to the VMD-LSTM model, the DVMD-LSTM model achieves significant improvements in prediction performance across all measurement stations. The average RMSE is reduced by 9.86%, and the average MAE is reduced by 9.44%. Furthermore, the average accuracy of the optimal noise model for the predicted results is improved by 36.50%, and the average speed accuracy of the predicted results is enhanced by 33.02%. These findings collectively attest to the superior predictive capabilities of the DVMD-LSTM model, thereby enhancing the reliability of the predicted results.

Bone Scan Index (BSI) is an image biomarker for quantification on bone metastasis of cancers. To compute BSI, not only the hotspots (metastasis) but also the bones have to be segmented. Most related researches focus on binary classification on bone scintigraphy: having metastasis or none. Rare studies focus on pixelwise segmentation. In this study we compare three advanced convolutional neural network (CNN) based models to explore the bone segmentation on dataset in house. The best model is Mask R-CNN, which reaches the precision, sensitivity and F1-score: 0.93, 0.87, 0.90 for prostate cancer patients and 0.92, 0.86, 0.88 for breast cancer patients, respectively. The results are the average of 10-fold cross-validation, which reveals the reliability for clinical use on bone segmentation.

Time series (TS)-based predictions are made by examining the behaviour of historical data to forecast future values. Multiple industries; such as stock market trading, power load forecasting, medical monitoring, and intrusion detection; frequently use it. Several variables; such as the performance of other markets as well as the economic situation of a country which affect its market performance; significantly affect the prediction of stock market prices. Therefore, this present study uses numerous variables; such as the opening, lowest, highest, and closing prices; to predict the indices of the stock market of the Kingdom of Saudi Arabia (KSA). Successfully accomplishing an investment goal largely depends on choosing the right stocks to buy, sell, or maintain. The project's output is the projected closing prices (regression) over the next seven days, which helps investors make the best decisions. This present study used exponential smoothing (ES) to remove noise from the input data obtained from the Saudi Stock Exchange, or Tadawul, before using a multivariate long short-term memory (LSTM) deep learning (DL) algorithm to forecast stock market prices. The proposed multivariate LSTMDL model had satisfactory prediction rates of 97.49% and 92.19% for the univariate model. Therefore, it can be used to effectively predict stock market prices. The results also indicate that DL as well as multiple sources of information can be used to accurately predict stock markets.

Epilepsy is a chronic neurological disorder characterized by abnormal electrical activity in the brain, often leading to recurrent seizures. With approximately 50 million people worldwide affected by epilepsy, there is a pressing need for efficient and accurate methods to detect and diagnose seizures. Electroencephalogram (EEG) signals, which record the brain’s electrical activity, have emerged as a valuable tool in detecting epilepsy and other neurological disorders. Traditionally, the process of analyzing EEG signals for seizure detection has relied on manual inspection by experts, which is time-consuming, labor-intensive, and susceptible to human error. To address these limitations, researchers have turned to machine learning and deep learning techniques to automate the seizure detection process. In this work, we propose a novel method for epileptic seizure detection, leveraging the power of 1-D Convolutional layers in combination with Bidirectional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) and Average pooling Layer as a unit. The performance of the proposed model is verified on the Bonn dataset. Our proposed model offers significant advancements over existing approaches for the detection of epileptic seizures, particularly for 2, 3, 4, and 5-class classification tasks. To assess the robustness and generalizability of our proposed architecture, we employ 5-fold cross-validation. By dividing the dataset into five subsets and iteratively training and testing the model on different combinations of these subsets, we obtain robust performance measures, including accuracy, sensitivity, and specificity. We demonstrate the effectiveness of the proposed architecture in accurately detecting epileptic seizures from EEG signals by using EEG signals of varying lengths. The results indicate its potential as a reliable and efficient tool for automated seizure detection, paving the way for improved diagnosis and management of epilepsy.

The continuous advancements in healthcare technology have empowered the discovery, diagnosis, and prediction of diseases, revolutionizing the field. Artificial intelligence (AI) is expected to play a pivotal role in achieving the goals of precision medicine, particularly in disease prevention, detection, and personalized treatment. This study aims to determine the optimal combination of the mother wavelet and AI model for the analysis of pediatric electroretinogram (ERG) signals. The dataset, consisting of signals and corresponding diagnoses, undergoes Continuous Wavelet Transform (CWT) using commonly used wavelets to obtain a time-frequency representation. Wavelet images were used for the training of five widely used deep learning models: VGG-11, ResNet-50, DensNet-121, ResNext-50, and Vision Transformer, to evaluate their accuracy in classifying healthy and unhealthy patients. The findings demonstrate that the combination of Ricker Wavelet and Vision Transformer consistently yields the highest median accuracy values for ERG analysis, as evidenced by the upper and lower quartile values. The median balanced accuracy of the obtained combination of the three considered types of ERG signals in the article are 0.83, 0.85, and 0.88. However, other wavelet types also achieved high accuracy levels, indicating the importance of carefully selecting the mother wavelet for accurate classification. The study provides valuable insights into the effectiveness of different combinations of wavelets and models in classifying ERG wavelet scalograms.

Over the past decade, Deep Learning (DL) had been applied in a large number of optical sensors’ applications. DL algorithms can improve the accuracy and reduce the noise level in optical sensors. Optical sensors are considered as promise technology for the modern intelligent sensing platforms. These sensors are widely used to process monitoring, quality prediction, pollution, defense, security and many other applications. However, they suffer major challenges such as the large generated data and low processing speed for that data and moreover the much cost of these sensor. These challenges can be mitigated by integrating deep learning system with the optical sensor technologies. This paper presents recent studies that integrate DL algorithms with optical sensors applications. This paper also highlights several of DL algorithms directions that promise a considerable impact on use for optical sensor applications. Moreover, this study provides new directions for the future related research development.

Reducing the costs of repairing concrete structures damaged due to the appearance of cracks and reducing the number of people involved in the process of their repair is the subject of a multitude of experimental studies. Special emphasis should be placed on research involving industrial by-products, the disposal of which has a negative environmental impact, as is the case in the research presented in this paper. The basic idea was to prepare a mortar with added granulated blast furnace slag from Smederevo Steel Mill and then treat artificialy produced cracks with a Sporosarcina pasteurii DSM 33 suspension under the conditions of sterile demineralized and water from Danube river in order to simulate natural conditions. The results show a bio-stimulated healing efficiency of 32.02% in sterile demineralized water and 42.74% in Danube water already after 14 days. The SEM images clearly show calcium carbonate crystals as the main compound that has started to fill the crack, and the crystals are much more developed under the Danube water conditions. As a special type of research, microscopic images of cracks were classified into those with and without the presence of bacterial culture. By applying convolutional neural networks (ResNet 50), the classification success rate was 91.55%.

Hand gestures are an essential part of human-to-human communication and interaction, and therefore for technical applications, the aim is increasingly to achieve interaction between humans and computers that is as natural as possible, for example by means of natural language or hand gestures. In the context of human-machine interaction research, these methods are consequently being explored more and more. However, the realization of natural communication between humans and computers is a major challenge. In the field of hand gesture recognition, research approaches are being pursued that use additional hardware such as special gloves to classify gestures with high accuracy. Recently, deep learning techniques using artificial neural networks have been increasingly proposed for the problem of gesture recognition without using such tools. In this context, in our approach convolutional neural network (CNN) will be explored in detail for the task of hand gesture recognition. CNN is a deep neural network that can be used in the field of visual object processing and classification. The goal of this work is to recognize ten types of static hand gestures in front of complex backgrounds and different hand sizes based on raw images without the use of extra hardware. We achieved good results with a CNN network architecture consisting of seven layers. Through data augmentation and skin segmentation, a significant increase of the model accuracy was achieved. On public benchmarks the ten gestures have been classified almost perfectly with a testing accuracy of 96.5%

Accurately estimating a person's age is crucial for identity verification at all critical checkpoints, including airports, land borders, and seaports. Human gait may be used as a biometric identifier and indicator of age, among other things. This study aims to develop methods for estimating a person's age by observing their walk. In this paper, a novel technique for preprocessing the proposed gait dataset has been used by utilizing a combination of the gait energy image (GEI), the accumulated frame difference energy image (AFDEI), and the invariant moment of the image. The proposed technique outperformed state-of-the-art methods in terms of accuracy. The proposed method was tested and evaluated using a convolutional neural network (CNN), and it achieved an average accuracy of 90.35% across 14 different view angles within 5 K-Fold, the proposed method resulted in 94.68% and 94.54% in 30º and 75º view degree respectively. concluding that the approach is effective and promising for estimating age using human gait.

Industrial process control systems commonly exhibit features of time-varying, strong coupling, and strong nonlinearity. Obtaining accurate mathematical models of these nonlinear systems and achieving satisfactory control performance is still a challenging task. In this paper, data-driven modeling techniques and deep learning methods are used to accurately capture a category of smooth nonlinear system’s spatiotemporal features. The operating point of these systems may change over time, and their nonlinear characteristics can be locally linearized. We established the LSTM-CNN-ARX model by utilizing a fusion of long short-term memory (LSTM) network and convolutional neural network (CNN) to fit the coefficients of the state-dependent exogenous variable autoregressive (SD-ARX) model. Compared to other models, the hybrid LSTM-CNN-ARX model is more effective in capturing the nonlinear system’s spatiotemporal characteristics due to its incorporating the strengths of LSTM for learning temporal characteristics and CNN for capturing spatial characteristics. The model-based predictive control (MPC) strategy, namely LSTM-CNN-ARX-MPC, is developed by utilizing the model's local linear and global nonlinear features. The control comparison experiments conducted on a water tank system (WTS) show the effectiveness of the developed models and MPC methods.

The prompt and accurate diagnosis of breast lesions, including the distinction between cancer, non-cancer, and suspicious cancer, plays a crucial role in the prognosis of breast cancer. In this paper, we introduce a novel method based on feature extraction and reduction for detection of breast cancer in mammography images. First, we extract features from multiple pre-trained convolutional neural network (CNN) models, and then concatenate them. The most informative features are selected based on their mutual information with the target variable. Subsequently, the selected features can be classified using a machine learning algorithm. We evaluate our approach using four different machine learning algorithms, and our results demonstrate that the neural network-based classifier yields an accuracy as high as 92% for the RSNA dataset which is a new dataset that provides two views and additional features such as age. We compare our proposed algorithm with state-of-the-art methods and demonstrate its superiority, particularly in terms of accuracy and sensitivity. For the MIAS dataset, we achieve an accuracy as high as 94.5%, and for the DDSM dataset, an accuracy of 96% is attained. These results highlight the effectiveness of our method in accurately diagnosing breast lesions and surpassing existing approaches.

Grain yield prediction affects policy making in various aspects such as agricultural production planning, food security assurance, and adjustment of foreign trade. Accurately predicting grain yield is of great significance in ensuring global food security. This paper is based on the MODIS remote sensing image data products from 2010 to 2020, and adds band information such as vegetation index and temperature to form composite remote sensing data as a data set. Aiming at the lack of models for large-scale forecasting and the need for human intervention in traditional models, this paper proposes a grain production estimation model based on deep learning. First, image cropping and yield mapping techniques are used to process the data to generate training samples. Then the channel and spatial attention mechanism (Convolutional Block Attention Module, CBAM) is added for extracting spatial information in different remote sensing bands to improve the efficiency of the model. Long Short-Term Memory (LSTM) neural networks is also added to obtain feature information in the time dimension. Finally, a national-scale grain yield prediction model is constructed. The proposed model was tested on data from 2018 to 2020 showing an average R2 of 0.940 and an average RMSE of 80,020 tons, indicating that it can predict Chinese grain yield better. The model proposed in this paper extracts grain yield information directly from the composite remote sensing data, and solves the problem of small-scale research and imprecise yield prediction in an end-to-end manner.

A full connected world is expected to gain in the 6th generation mobile network (6G). As a typi-cal fully connected scenario, the internet of vehicle (IoV) enables intelligent vehicle operations via artificial intelligence (AI) and edge computing technologies. In the future of vehicular net-works, wide variety of services need powerful computing resources and higher quality of ser-vice (QoS). Existing resources are insufficient to match these requirements. Aim to this problem, An intelligent service offloading framework is provided. Based on the framework, an Algorithm of Improved Gradient Descent (AIGD) is created to accelerate the speed of iteration. So, the con-vergence of convolutional neural network (CNN) based on AIGD is able to be accelerated too. Then, an Algorithm of convolutional long short-term memory (CN_LSTM) Based Traffic Predic-tion (ACLBTP) is designed to gain the predicted number of vehicles belonged to the edge node. At last, an Algorithm of Service Offloading Based on CN_LSTM (ASOBCL) is conducted to of-fload these services to the vehicles belonged to the edge node. In ASOBCL, sorting technique is adopted to speed up the offloading work. Simulation results demonstrate the fact that the pre-diction strategy designed in this paper has high accuracy. The low offloading time and main-taining stable load balance is gained via running ASOBCL. Low offloading time means short response time. And, the QoS is guaranteed. So, these strategies designed in this paper are effec-tive and valuable.

The intrinsic non-linearity and complexity of suspended sediment dynamics, which are impacted by the geographical variability of basin parameters and temporal climatic patterns, make it difficult to estimate suspended sediment concentration (SSC) accurately in hydrological processes. Deep neural networks (DNNs), a cutting-edge modeling method that can capture the innate non-linearity in hydrological systems, have emerged as a solution to this problem. Using primary data on discharge, SSC, and turbidity, the long short-term memory method of DNNs was employed in this study to simulate the discharge-suspended sediment connection for the Esopus Creek, NY, USA as the first objective. To develop effective modeling strategies, multiple scenarios of feature selection, including combinations of discharge, turbidity and SSC for preceding days, were considered. Secondly, the variations in SSC and discharge between the three USGS gages along Esopus Creek that were upper stream, lower stream, and downstream, adjacent to the pourpoint were analyzed. Statistical metrics and scenarios of feature importance were used to evaluate the effectiveness of the DNN-based models. The study shows that among 24 DNN approaches feature selection is crucial in simulating the daily SSC, and discharge and presenting novel research directions for utilizing machine learning algorithms in water quality.

The deployment of a Static Synchronous Compensator within a microgrid can facilitate voltage and reactive power regulation, leading to enhanced stability and reliability. Within a microgrid setting, a STATCOM can effectively balance power supply and demand, and mitigate voltage fluctuations caused by the intermittent nature of renewable energy sources. To ensure the successful integration of a STATCOM within a microgrid, coordinating the control system with other Distributed Energy Resources, especially when multiple control strategies are employed, can be a challenging task. Therefore, a meticulously designed control system is indispensable to guarantee the microgrid’s efficient and effective operation. The use of GA in LSTM tuning can accelerate the process of finding optimal hyperparameters for a specific task, obviating the necessity for time-consuming and computationally expensive grid search or manual tuning. This method can be particularly advantageous when handling large data sets and complex models. In this paper, an attempt has been made to model the STATCOM to communicate with the microgrid tuned using LSTM-GA for effective calculation of real and reactive power support during grid disturbances.

In this paper, we propose an imagined speech-based brain wave pattern recognition using deep learning. Multiple features were extracted concurrently from eight-channel Electroencephalography (EEG) signals. To obtain classifiable EEG data with fewer number of sensors, we placed the EEG sensors on carefully selected spots on the scalp. To decrease the dimensions and complexity of the EEG dataset and to avoid overfitting during the deep learning algorithm, we utilized the wavelet scattering transformation. A low-cost 8-channel EEG headset was used with MATLAB 2023a to acquire the EEG data. The Long-Short Term Memory Recurrent Neural Network (LSTM-RNN) was used to decode the identified EEG signals into four audio commands: Up, Down, Left, and Right. Wavelet scattering transformation was applied to extract the most stable features by passing the EEG dataset through a series of filtration processes. Filtration has been implemented for each individual command in the EEG datasets. The proposed imagined speech-based brain wave pattern recognition approach achieved a 92.50% overall classification accuracy. This accuracy is promising for designing a trustworthy imagined speech-based Brain-Computer Interface (BCI) future real-time systems. For better evaluation of the classification performance, other metrics were considered, and we obtained 92.74%, 92.50% and 92.62% for precision, recall, and F1-score, respectively.

Nowadays, power sector is an area that gather great scientific interest, due to events such as the increase in electricity prices in the wholesale energy market and new investments due to technological development in various sectors. These new challenges have in turn created new needs, such as the accurate prediction of the electrical load of the end users. On the occasion of the new challenges, Artificial Neural Networks approaches have become increasingly popular due to their ability to adopt efficiently to time-series predictions. In this paper, it is presented the development of a model which, through an automated process, will provide an accurate prediction of electrical load for the island of Thira in Greece. Through an automated application, deep learning load forecasting models have been created, such as Multilayer Perceptron, Long Short-Term Memory (LSTM), Convolutional Neural Network One Dimensional (CNN-1D), CNN-LSTM, Temporal Convolutional Network (TCN) and a proposed hybrid model called Convolutional LSTM Encoder-Decoder. The results in terms of prediction accuracy show satisfactory performances for all models, with the proposed hybrid model achieving the best accuracy.

Intestinal parasitic infections pose a grave threat to human health, particularly in tropical and subtropical regions. The traditional manual microscopy system of intestinal parasites detection remains the golden standard procedure for the diagnosis of parasites cyst or eggs, but this approach is costly time-consuming (30min/sample), highly tedious, and also required specialist. However, computer vision based on deep learning has made great stride in recent time. Despite the significant advances in deep convolutional neural network-based architectures, little research has been conducted to explore the potential of these techniques in the field of parasitology, specifically for intestinal parasites. Therefore, the goal of this research is to evaluate the performance of proposed state-of-the-art transfer learning architecture for detecting and classifying intestinal parasite eggs from images. We would ensure that patients receive prompt treatment while also relieving experts of extra work if we used such an architecture. Here, in stage first, we applied image pre-processing and augmentation to the dataset, and in stage second, we utilized the YOLOv5 algorithms for detection and classification and then compared their performance based on different parameters. Our algorithms achieved a mean average precision of 97% approximatiely and 8.5 ms detection time per sample for 5,393 intestinal parasite images. Thus, this approach may form a solid theoretical basis for real-time detection and classification in routine clinical examinations while accelerating the process to satisfy increasing demand.

Panoramic and periapical radiograph tools help dentists diagnose the most common dental diseases. Generally, dentists identify dental caries manually by inspecting X-ray images. However, due to their heavy workload, or poor image quality, dentists may sometimes overlook some unnoticeable dental caries, which may ultimately hinder the patient treatment. The purpose of this study was to develop an algorithm that classifies the teeth X-Ray images into three categories of “Normal”, “Caries”, and “Filled”. Our study used a dataset of 116 patients and 3712 single teeth images for training, validation and testing. Images were pre-processed using a sharpening filter and an intensity color map. We used a pre-trained transfer learning model, the NASNetMobile, which served as the feature extractor and the Convolutional Neural Network (CNN) model served as the classifier. The training dataset had a “Recall” of 0.92, 0.90 and 0.91 for “Normal”, “Caries” and “Filled” respectively and the test dataset had a “Recall” of 0.86, 0.81 and 0.85 for “Normal”, “Caries” and “Filled” respectively. The classification of the teeth X-Rays was successful and can be valuable for dentist as the artificial intelligence algorithm can serve as a decision support tool to aid dentists when they need to diagnose dental treatment.

Activated sludge process is a well known method to treat municipal and industrial waste water. In this complex process, the oxygen concentration in the reactors plays a critical role in the plant efficiency. This paper proposes the use of a Long Short-Term Memory (LSTM) network to identify an input-output model suitable for the design of an oxygen concentration controller. The model is identified from easy-accessible measures collected from a real plant. This dataset covers almost a month. The performances achieved with the proposed LSTM model are compared with the ones obtained with a standard AutoRegressive model with eXogenous input (ARX). Both models catch the oscillation and the overall behaviour (ARX ρ=0.833 , LSTM ρ=0.921), but, while the ARX model fails in reaching the correct amplitude (FIT=41.20%), the LSTM presents satisfactory performance (FIT=60.56%).

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process sensitive information such as personal communications and confidential documents. In this study, we propose a method for training NLP models on encrypted text data to mitigate data privacy concerns while maintaining similar performance to models trained on non-encrypted data. We demonstrate our method using two different architectures, namely Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups dataset. Our results indicate that both encrypted and non-encrypted models achieve comparable performance, suggesting that our encryption method is effective in preserving data privacy without sacrificing model accuracy. In order to replicate our experiments, we have provided a Colab notebook at the following address: https://t.ly/lR-TP

In recent years, with the popularity of smart mobile devices, the interaction between devices and users, especially in the form of voice interaction, has become increasingly important. If smart devices can understand more users' emotional states through voice data, more customized services can be provided for users. This paper proposes a novel machine learning model for speech emotion recognition, which combines convolutional neural networks (CNN), long short-term memory neural networks (LSTM), and deep neural networks (DNN), called CLDNN. To make the designed system can recognize the audio signal closer to the human auditory system does, this article uses the Mel frequency cepstral coefficients (MFCCs) of audio data as the input of the machine learning model. First, the MFCCs of the voice signal is extracted as the input of the model, and the feature values of the data are calculated using several local feature learning blocks (LFLB) composed of one-dimensional CNN. Because the audio signals are time-series data, the feature values obtained from LFLBs then input into LSTM layer to enhance the learning on time-series level. Finally, fully connected layers are used for classification and prediction. Three databases RAVDESS, EMO-DB and IEMOCAP are used for the experiments in this paper. The experimental results show that the proposed method can improve the accuracy compared to other related researches in speech emotion recognition.

Photovoltaic(PV) power generation is highly nonlinear and stochastic. Accurate prediction of PV power generation plays a crucial role in grid connection as well as the operation and scheduling of power plants. To predict the PV power combination model, this paper suggests a method based on Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Nonlinear Auto-Regressive Neural Networks with Exogenous Input (NARXNN), Long Short Term Memory (LSTM) Neural Network, and Light Gradient Boosting Machine (LightGBM) algorithms. To attempt to reduce the non-smoothness of PV power, the weather variable features with the greatest effect on PV power are first identified by correlation analysis. Following this, the PV power modal decomposition is split and reorganized into a new feature matrix. Finally， a NARX is used to obtain preliminary PV power components and residual vector features， and the PV power is predicted by combining three models of LightGBM， LSTM, and NARX and then the final prediction results are obtained by combining the PV power prediction results using error inverse method weighted optimization. The prediction results demonstrate that the model put forth in this paper outperforms those of other models and validate the model's validity by utilizing real measurement data from Andre Agassi College in the United States.

Unmanned Aerial Vehicles (UAV) are increasingly being used in a variety of domains and precision agriculture is no exception. Precision agriculture is the future of agriculture and will play a key role in long-term sustainability of agricultural practices. This paper presents a survey of how image data collected using UAVs has been used in conjunction with ma-chine learning techniques to support precision agriculture. Numerous agricultural applications including classification of crop types and trees, crops detection, weed detection, cropland cover, and segmentation of farming fields are discussed. A variety of supervised, semi-supervised and unsupervised machine learning techniques for image-based preci-sion agriculture are compared. The survey showed that for traditional machine learning approaches, Random Forests performed better than Support Vector Machines (SVM) and K-Nearest Neighbor Algorithm (KNN) for crop/weed classification. And, while Convolutional Neural Networks (CNN) have been used extensively, the U-Net-based models out-performed conventional CNN models for classification and segmentation tasks. Among the Single Stage Detectors (SSD), YOLO series performed relatively well. Two-Stage Detectors like R-CNN, FPN, and Mask R-CNN generally tended to outperform SSDs. Vision Trans-formers (ViT) showed promising results amongst transformer-based models which did not generally perform better than CNNs. Finally, Generative Adversarial Networks (GANs) have been used to address the problem of smaller datasets and unbalanced data

The purpose of this work was to achieve non-destructive detection of the internal defects of in-shell walnuts using X-ray radiography technology based on improved Faster R-CNN network model. First, the FPN structure was added to the feature extraction layer to extract richer image information. Then ROI Align was used to instead of ROI Pooling for eliminating the localization bias problem caused by quantization operation. Finally, the Softer-NMS module was introduced to the final regression layer with the predicted bounding box for improving the localization accuracy of the candidate boxes. The results indicated that the internal defects in intact walnuts with shells could be identified effectively using the proposed improved network model in this study. Specifically, the discrimination accuracy of the in-shell sound, shriveled and empty-shell walnuts were 96.14%, 91.72% and 94.80% respectively, and the highest overall accuracy can reach 94.22 %. Contrasted with original Faster R-CNN network model, the mAP and F1-value of the improved Faster R-CNN model increased by 5.86% and 5.65%, respectively. Consequently, the proposed method can be applied for the in-shell walnuts with shriveled and empty-shell defects.

This study proposes a machine-learning-based framework for detecting mechanical damage in pipelines, utilizing physics-informed datasets collected from simulations for mechanical damage. The framework provides an effective workflow from dataset generation to damage detection and identification for three types of pipeline events: welds, clamps, and corrosion defects. While the study initially focused on optimizing the CNN structure using various advanced optimizers, it also investigated the impact of sensing systems on data classification and the effect of noise on classification performance. The study's analysis highlights the importance of selecting the appropriate sensing system for the specific application. The authors also found that the proposed framework is robust to experimentally relevant levels of noise, suggesting its applicability in real-world scenarios where noise is present. Overall, this study contributes to the development of a more reliable and effective method for detecting mechanical damage in pipelines. The proposed framework provides an effective workflow for damage detection and identification, and the findings on the impact of sensing systems and noise on classification performance add to its robustness and reliability.

The integration of deep learning methods, especially Convolutional Neural Networks (CNN), and Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has been widely deployed in the field of radar signal processing. Nevertheless, these methods are frequently regarded as black-box models due to the limited visual interpretation of their internal feature representation and parameter organization. In this paper, we propose an innovative approach named C-RISE, which builds upon the RISE algorithm to provide a post-hoc interpretation technique for black-box models used in SAR Images Target Recognition. C-RISE generates saliency maps that effectively visualize the significance of each pixel. Our algorithm outperforms RISE by clustering masks that capture similar fusion features into distinct groups, enabling more appropriate weight distribution and increased focus on the target area. Furthermore, we employ Gaussian blur to process the masked area, preserving the original image structure with optimal consistency and integrity. C-RISE has been extensively evaluated through experiments, and the results demonstrate superior performance over other interpretation methods based on perturbation when applied to neural networks for SAR image target recognition. Furthermore, our approach is highly robust and transferable compared to other interpretable algorithms, including white-box methods.

The problem of health status prediction of insulated-gate bipolar transistors (IGBTs) gains a lot of attention in the field of health management of power electronic equipment. The performance degradation of IGBT gate oxide layer is one of the important failure modes. In view of failure mechanism analysis and easy implementation of monitoring circuit, this paper selects the gate leakage current of IGBT as the precursor parameter of gate oxide degradation, and uses time domain characteristic analysis, gray correlation degree, Mahalanobis distance, Kalman filter and other methods to carry out feature selection and fusion, and finally obtains a health indicator characterizing the degradation of IGBT gate oxide. Based on the Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) network, this paper constructs an IGBT gate oxide degradation prediction model, and performs experimental analysis on the dataset released by NASA-Ames Laboratory, and the average absolute error of performance degradation prediction is as low as 0.0216. Compared with Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Support Vector Regression (SVR) and CNN-LSTM models, CNN-LSTM network has the highest prediction accuracy. These results show the feasibility of gate leakage current as a precursor parameter of IGBT gate oxide layer failure, as well as the accuracy and reliability of the CNN-LSTM prediction model.

Accurate demand forecasting plays a critical role in most furniture businesses’ operational, tactical, and strategic decisions, as the demand in the furniture business is considered seasonal and becomes more complex in crises. In this work, a neural network model using the Long Short-Term Memory (LSTM) method was developed to forecast the demand for specific product groups. LSTM is a leading deep learning model for time series prediction, particularly seasonal, multi-item, and non-linear situations. The developed model was used to predict the demand based on old data before the Covid-19 pandemic and recent data of the first months of the pandemic as a fast response to the crisis. In addition, a comparison study was conducted between the developed model and the traditional planning inventory used by furniture businesses that provided us with the data. The results showed that the Covid-19 pandemic significantly impacted demand forecasting. Also, the fast response to Covid-19 pandemic has slightly increased the model performance. Finally, the comparison study demonstrated that our model is robust and better than the traditional demand forecasting method. Therefore, the developed model may help the business improve inventory and production planning to create a more flexible supply chain.

Election outcomes have been predicted in the past with the help of various state-of-the-art language models. Sentiment analysis helps in establishing the opinions of the public about a particular subject, a popular experiment known as opinion mining. Twitter has grown in popularity and proven to be a key tool in mining people’s sentiments concerning election and other trending subjects of interest. The outcome of the just concluded Presidential election in Nigeria shifts the focus on Lagos State governorship election. In this study, we propose a Bidirectional Encoder Representations from Transformers (BERT) model for the sentiment analysis of governorship election in Lagos State Nigeria using Twitter data. A total of 800,000 personal and public tweets were scraped from twitter concerning the three prominent contesting candidates using carefully selected search queries. The tweets were preprocessed to avoid noise and inconsistencies. The preprocessed tweets were passed into the pretrained and finetuned BERT model. The result was analyzed to establish the sentiments of the public about the candidates. The social networks of the candidates were also analyzed. The parameter-tuning yield different results with different learning rates (LR). Results showed that the learning rate at 1e-7 gave the best performance and that the smaller the learning rate, the higher the accuracy but the larger the epoch size, the higher the accuracy.

Chatbots are extensively needed in customer services to handle customer inquiries, such as tracking orders or providing information about products and services. One of the most reliable implementations of chatbots is using the common architectures of LSTM networks named Seq2Seq networks. The networks are using an encoder and a decoder. Seq2Seq chatbot is a type of chat system that is professional enough to pass the Turing test. The Turing test is a way of deciding the accuracy of the machine by examining its response, it should appear like a human response. In this research, we will introduce a novel architecture that can pass the Turing test. The seq2seq Accuracy is improved by making incremental training to the chatbot. The new proposal provides higher accuracy and high similarity to human chat responses.

Deepfakes are manipulated or altered images, or video, that are created using deep learning models with high levels of photorealism. The two popular methods of producing a deepfake are based on either convolutional neural networks (CNN), or autoencoders. Deepfakes created using CNN comparatively show higher qualities of realism, yet oftentimes leave artifacts and distortions in the generated media that can be detected using machine learning and deep learning algorithms. In recent years, there has been an influx of periocular image and video data because of the increase usage of face masks. By wearing masks, much of what is used for facial recognition is hidden, leaving only the periocular region visible to an observer. This loss of vital information leads to easier misidentification of media, allowing deepfakes to less likely be identified as fake. In this work, feature extraction methods, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and CNN, are used to train an ensemble deep learning model to detect deepfakes in videos on a frame-by-frame level based on the periocular region. Our proposed model is able to distinguish original and manipulated images with accuracies around 98.9 percent, which is an improvement to previous works by combining SIFT and HOG for deepfake detection in convolutional neural networks.

United Nations Framework Convention on Climate Change (UNFCCC) has recently established the Reducing Emissions from Deforestation and forest Degradation (REDD+) program that requires countries to report their carbon emissions and sink estimates through national greenhouse gas inventories (NGHGI). Thus, developing automatic systems capable of estimating the carbon absorbed by forests without in-situ observation becomes essential. To support this important need, in this work we introduce ReUse, a simple but effective deep-learning approach to estimate the carbon absorbed by forest areas based on remote sensing. The novelty of the proposed method is in the use of the public above-ground biomass (AGB) data from the European Space Agency's Climate Change Initiative Biomass project as ground truth to estimate the carbon sequestration capacity of any portion of land on Earth using Sentinel-2 images and a pixel-wise Regressive UNet. The approach has been compared to two literature proposals, using a private dataset and human-engineered features. The results show a greater generalization ability of the proposed approach, with a decrease in Mean Absolute Error and Root Mean Squared Error, respectively, of 16.9 and 14.3 in the area of Vietnam and 4.7 and 5.1 in the area of Myanmar over the runner-up. Finally, as a case study, we reported an analysis made for the Astroni area, a nature reserve located near the metropolitan area of Naples in southern Italy, struck by a large fire, producing predictions consistent with values found by experts in the field. These results further support the use of such an approach for the early detection of AGB variations, both in urban and rural areas.

The continuously developing project aims to build an informatics system enabling analysis of spatial and temporal parameters of movement activities occurring in the sport of speed climbing. The monitoring system (climbing information speed system – CISS) is to be used for conducting comprehensive scientific research in the field of speed climbing. The system enables the evaluation of the training process of climbers at various levels of competition. The study analysis was based on video. The video recording with a camera positioned at a short distance (10 m) from the wall. The marker was positioned closest to the centre of mass (gravity) BMC. Results: development of a system for data collection and analysis of the climbing run based on video recording (application of the Kanade-Lucas-Tomasi (KLT) algorithm). Our results showed that used devices can measure a wide range of specific internal and external variables during speed climbing. Some of the analyzed parameters were significantly correlated with speed climbing time. These results could be a theoretical basis for future research and for training program’s preparation.

Background: MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences. Methods: Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes, T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20101 MRI images) was used for training, while C2 (197, 11333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics models' performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I). Results: Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95%-Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. 620 images were misclassified; Manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased on average the PFS model C-I by 14.6% compared to a model trained without MR-Class. Conclusions: We provide a DCNN-based method for sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.

Measuring pulmonary nodules accurately can help with early diagnosis of lung cancer, which can improve a patient’s chances of survival. Many methods for segmenting nodules have been developed, but they all rely on input from radiologists in the form of a 3D volume of interest (VOI) or use a constant region of interest (ROI) and only consider the presence of nodule within the given VOI. These approaches limit the networks’ ability to detect nodules outside the given VOI and can also include unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation by using 2D region of interest (ROI) inputted from radiologist or computer-aided detection (CADe) system. Particularly, we design a dual-encoder-based hard attention network (DEHA-Net) which incorporates the full slice of thoracic computed tomography scan along with the ROI mask to produce an accurate segmentation mask of lung nodule in the given slice. The proposed architecture exploits the adaptive region of interest (A-ROI) algorithm to automatically investigates the penetration of lung nodule into surrounding slices while eliminating the need to drawing separate ROIs in each slice. Further, the framework performs the multi-view analysis, i.e., in sagittal and coronal views, to improve the segmentation performance. The proposed scheme has been rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset and an extensive analysis of results have been performed. The quantitative analysis shows that the proposed method not only improves the existing state-of-the-art in term of dice score but also, significantly robust against the different types, shape and dimensions of lung nodules.

The Median American Sign Language Interpretation Software (ASL) Interpretation Software is a web application that is capable of interpreting American Sign Language in real-time, utilizing an internet connection and a primary web camera, complete with basic phrases and letters. Extensive use of Deep Learning and Neural Networks, specifically Convoluted Neural Networks, enables Median to interpret video inputs and generate accurate results directly displayed to the user in text format. The ultimate goal for Median is to have it act as a bridge between hearing people and members of the deaf community, allowing deaf people to communicate with non-signing people using American Sign Language. Furthermore, Median has been designed to benefit people who lack access to a human ASL Translator, as its format as a website allows it to be accessible anywhere at any time, giving increased availability over human interpreters. Median is designed to be a very versatile program with great potential for growth and expansion.

The alteration of natural land cover to impervious surfaces during development increases stormwater runoff. Stormwater Control Measures (SCMs) are used to manage water quantity and enhance water quality by restoring the hydrologic cycle altered by development. Often, SCMs have an outflow pipe to handle overflows or to manage the release of water detained when infiltration is not possible. Traditionally, these are static controls (e.g. a small orifice is used to restrict the volume of outflow), however, these systems can be improved by instituting real-time controls (RTC). RTC improve the functionality of SCMs by dynamically controlling outflows to adjust to environmental conditions. A major impediment to the widespread implementation of RTC is the high cost of installation and operation. This study utilized machine learning methods to develop a forecasting approach for the implementation of low-cost RTC that were implemented on a programmable gate of the outlet structure of a multi-stage basin in southeastern Pennsylvania. The goals were to decrease the peak flow exiting the basin during rain events, increase the volume of water detained, decrease the number of overtopping events, maintain healthy vegetation in the basin, and protect the downstream vegetation from erosion. Multiple popular data science algorithms were evaluated including multiple linear regression and long short-term memory. These algorithms were used with a dataset, which consisted of four years of historical sensor data, collected in 5-minute intervals, to train models to predict water levels to optimize operations. The accuracy of 30 models with three different methods of handling missing values were compared. A long short-term memory model configured with a 30-minute lead time produced the best results. Having an approximate same lag time of 30 minutes for the contributing drainage area of the SCM provided a sufficient RTC functioning period to improve the performance of the outlet structure.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

Soil moisture is an important factor affecting the plant growth. For a long time, the convenience, timeliness and accuracy of soil moisture monitoring have been limited due to the backward of observation methods and equipment. Therefore, the quantitative prediction of soil moisture has become a difficult problem. Aiming at the problems of high erection cost, easily damaged sensors and low measurement accuracy of the existing fixed sensor soil moisture monitoring system, a soil moisture prediction model based on the long short term memory neural network (LSTM) integrating the particle swarm optimization (PSO) (PSO-LSTM) is designed and implemented. The hyperparameters of the LSTM network can be obtained based on the excellent global search ability of the PSO algorithm. According to the meteorological data and soil moisture data of Haidian Park in 2019, the long short term memory(LSTM) neural network based prediction model is constructed with input vectors of surface temperature, average temperature, evaporation, sunshine hours, precipitation and average wind speed, and the output vector of soil relative humidity. The results show that compared with the back propagation(BP) neural network, the Elman neural network and the LSTM neural network, the proposed PSO-LSTM model has higher prediction performance.

Introduction: Social media platforms such as Facebook, LinkedIn, Twitter, among others have been used as a tool for staging protests, opinion polls, campaign strategy, medium of agitation and a place of interest expression especially during elections. Past studies have established people’s opinion elections using social media posts. The advent of state-of-the-art algorithms for unstructured text processing implies tremendous progress in natural language processing and understanding. Aim: In this work, a Natural Language framework is designed to understand Nigeria 2023 presidential election based on public opinion using Twitter dataset. Methods: Raw datasets concerning discourse around Nigeria 2023 elections from Twitter of 2,059,113 18 dimensions were collected. Sentiment analysis was performed on the preprocessed dataset using three different machine learning models namely: Long Short-Term Memory (LSTM) Recurrent Neural Network, Bidirectional Encoder Representations from Transformers (BERT) and Linear Support Vector Classifier (LSVC) models. Personal tweet analysis of the three candidates provided insight on their campaign strategies and personalities while public tweet analysis established the public’s opinion about them. The performance of the models was also compared using accuracy, recall, false positive rate, precision and F-measure. Results: LSTM model gave an accuracy, precision, recall, AUC and f-measure of 88%, 82.7%, 87.2% , 87.6% and 82.9% respectively; the BERT model gave an accuracy, precision, recall, AUC and f-measure of 94%, 88.5%, 92.5%, 94.7% and 91.7% respectively while the LSVC model gave an accuracy, precision, recall, AUC and f-measure of 73%, 81.4%, 76.4%, 81.2% and 79.2% respectively. Conclusion: The experimental results show that sentiment analysis and other Natural Language Processing tasks can aid in the understanding of the social media space. Results also revealed the leverage of each aspirant towards winning the election. We conclude that sentiment analysis can form a general basis for generating insights for election and modeling election outcomes.

Objective: The aim of this study was to provide a new machine learning method to determine temporal events and inner-cycle parameters (e.g., cycle, poles and skis contact and swing time) in cross-country roller ski skating on the field, using a single deported inertial measurement unit (IMU). Methods: The developed method is based on long short-term memory neural networks to detect poles and skis initial and final contact with the ground during the cyclic movements. Eleven athletes skied four laps of 2.5 km at low and high intensity using skis with two different rolling coefficients. They were equipped with IMUs attached to the upper back, lower back and to the sternum. Data from force insoles and force poles were used as reference system. Results: The IMU placed on the upper back provided the best results, as the LSTM network was able to determine the temporal events with an accuracy ranging from 49 to 55 ms and the corresponding inner-cycles parameters were calculated with a precision of 63 to 68 ms. The method detected 95% of the events for the poles and 87% of the events for the skis. Conclusion: The proposed LSTM method provides a promising tool for assessing temporal events and inner-cycle phases in roller ski skating showing the potential of using a deported IMU to estimate different spatio-temporal parameters of human locomotion.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

River flow prediction is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the climatic variables e.g., precipitation has a significant impact on the temporal distribution of the river discharge in recent days making the discharge forecasting even more complicated for diversified water-related issues e.g., flood prediction and irrigation planning. To predict the discharge, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-driven predictions, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, Long Short-term Memory (LSTM) neural network regression model is trained using over 80 years of daily data to forecast the discharge time series up to 3 days ahead of time. The performance of the model is found satisfactory through the comparison of the predicted data with the observed data, visualization of the distribution of the errors and Root Mean Squared Error (RMSE) value of 0.09. Higher performance is achieved through the increase in the number of epochs and hyper parameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time river discharge prediction.

Research has been growing on object detection using semi-supervised methods in past few years. We examine the intersection of these two areas for floor-plan objects to promote the research objective of detecting more accurate objects with less labelled data. The floor-plan objects include different furniture items with multiple types of the same class, and this high inter-class similarity impacts the performance of prior methods. In this paper, we present Mask R-CNN based semi-supervised approach that provides pixel-to-pixel alignment to generate individual annotation masks for each class to mine the inter-class similarity. The semi-supervised approach has a student-teacher network that pulls information from the teacher network and feeds it to the student network. The teacher network uses unlabeled data to form pseudo-boxes, and the student network uses both unlabeled data with the pseudo boxes and labelled data as ground truth for training. It learns representations of furniture items by combining labelled and unlabeled data. On the Mask R-CNN detector with ResNet-101 backbone network, the proposed approach achieves mAP of 98.8%, 99.7%, and 99.8% with only 1%, 5% and 10% labelled data, respectively. Our experiment affirms the efficiency of the proposed approach as it outperforms the fully supervised counterpart using only 10% of the labels.

The sustainability of the planet and its inhabitants is in dire danger and is among the highest priorities on global agendas such as the Sustainable Development Goals (SDGs) of the United Nations (UN). Solar energy -- among other clean, renewable, and sustainable energies -- is seen as essential for environmental, social, and economic sustainability. Predicting solar energy accurately is critical to increasing reliability and stability, and reducing the risks and costs of the energy systems and markets. Researchers have come a long way in developing cutting-edge solar energy forecasting methods. However, these methods are far from optimal in terms of their accuracies, generalizability, benchmarking, and other requirements. Particularly, no single method performs well across all climates and weathers due to the large variations in meteorological data. This paper proposes SENERGY (an acronym for Sustainable Energy), a novel deep learning-based auto-selective approach and tool that, instead of generalising a specific model for all climates, predicts the best performing deep learning model for GHI forecasting in terms of forecasting error. The approach is based on carefully devised deep learning methods and feature sets through an extensive analysis of deep learning forecasting and classification methods using ten meteorological datasets from three continents. We analyse the tool in great detail through a range of metrics and methods for performance analysis, visualization, and comparison of solar forecasting methods. SENERGY outperforms existing methods in all performance metrics including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Forecast Skills (FS), Relative Forecasting Error, and the normalised versions of these metrics. The proposed auto-selective approach can be extended to other research problems such as wind energy forecasting and predict forecasting models based on different criteria (in addition to the minimum forecasting error used in this paper) such as the energy required or speed of model execution, different input features, different optimisations of the same models, or other user preferences.

To improve the monitoring of the electrical power grid it is necessary to evaluate the influence of contamination in relation to leakage current and its progression to a disruptive discharge. In this paper, insulators were tested in a saline chamber to simulate the increase of salt contamination on their surface, and to evaluate the supportability of these components. From the time series forecasting of the leakage current, it is possible to evaluate the development of the fault before a flashover occurs. Choosing which method to use is always a difficult task since some models may have higher computational effort. In this paper, for a complete evaluation, the long short-term memory (LSTM), group method of data handling (GMDH), adaptive neuro-fuzzy inference system (ANFIS), bootstrap aggregation (bagging), sequential learning (boosting), random subspace, and stacked generalization (stacking) ensemble learning models are analyzed. A review and comparison of these well-established methods for time series forecasting is performed. From the results of the best structure of the model, the hyperparameters are evaluated and the Wavelet transform is used to obtain an enhanced model.

Along with the popularity of the Internet, people are exposed to more and more ways of micro-videos, and a huge amount of micro-video data has emerged. micro-videos have gradually become the Internet content preferred by the public, and a large number of micro-video apps have also emerged, such as Tiktok and Kwai. Intelligent classification and mining of micro-videos can greatly enhance user experience, improve business operation efficiency and enhance user experience. Through deep intelligent analysis and mining of micro-videos, important information in micro-videos can be extracted to provide an important basis for beautifying videos, content appreciation, video recommendation, content search, etc. In the past, content understanding for short videos often used human work annotation, but in recent years, with the great success of deep convolutional neural networks in image recognition, short video content understanding based on this method has gradually developed. Nowadays, most recognition algorithms extract the feature representation of each frame independently and then fuse them. However, while extracting the feature representation, some low-level semantic features are lost, which makes the algorithm unable to accurately distinguish the category of the video. At present, the algorithm of micro-video recognition based on deep learning has surpassed the iDT algorithm, making these traditional methods fade out of people’s view. In this paper according to the micro-video classification task, a new network model is proposed to concatenate features of each modality into the overall features of various modalities through the network, and then fuse the various modal features with the attention mechanism to obtain the whole micro-video features, which will be used for classification. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

Extensive growth in the volume of irregular brain cells is known as brain tumor. Human brain is surrounded by stiff skull. There are various issues that occur due to the growth of any tumor inside this restricted space. The malignant and benign are two main categories of the brain tumor. The skull is pressurized to enlarge from inside in case of growth of any benign or malignant tumor. This tumor leads to harm in brain and it may be dangerous to life also. The brain tumor is divided into two kinds - primary or secondary. The brain tumor detection techniques have various phases. In this paper, comparative study of CNN with GLCM approach and superpixel based spectral clustering is done tumor. This work takes into account metrics like accuracy, sensitivity and specificity for drawing the comparison between both the techniques.

Nowadays, technological advancement has transformed traditional vehicles into Au-tonomous Vehicles (A.V.s). In addition, in our daily lives, A.V.s play an important role since they are considered an essential component of smart cities. A.V. is an intelligent vehicle capable of main-taining safe driving by avoiding crashes caused by drivers. Unlike traditional vehicles, which are fully controlled and operated by humans, A.V.s collect information about the outside environment using sensors to ensure safe navigation. Furthermore, A.V.s reduce environmental impact because they usually use electricity to operate instead of fossil fuel, thus decreasing the greenhouse gasses. However, A.V.s could be threatened by cyberattacks, posing risks to human life. For example, re-searchers reported that Wi-Fi technology could be vulnerable to cyberattacks through Tesla and BMW AVs. Therefore, more research is needed to detect cyberattacks targeting the components of A.V.s to mitigate their negative consequences. This research will contribute to the security of A.V.s by detecting cyberattacks at the early stages. First, we inject False Data Injection (FDI) attacks into an A.V. simulation-based system developed by MathWorks. Inc. Second, we collect the dataset generated from the simulation model after integrating the cyberattack. Third, we implement an intelligent symmetrical anomaly detection method to identify FDI attacks targeting the control system of the A.V. through a compromised sensor. We use long short-term memory (LSTM) deep networks to detect FDI attacks in the early stage to ensure the stability of the operation of A.V.s. Our method classifies the collected dataset into two classifications: normal and anomaly data. The ex-perimental result shows that our proposed model's accuracy is 99.95%. To this end, the proposed model outperforms other state-of-the-art models in the same study area.

This paper introduces a multi-class hand gesture recognition model developed to identify a set of defined hand gesture sequences in two-dimensional RGB video recordings. The work presents an action detection classifier that looks at both appearance and spatiotemporal parameters of consecutive frames. The classifier utilizes a convolutional-based network combined with a long-short-term memory unit. To leverage the need for a large-scale dataset, the model uses an available dataset to then adopt a technique known as transfer learning to fine-tune the model on the hand gestures of relevance. Validation curves performed over a batch size of 64 indicate an accuracy of 93.95% (± 0.37) with a mean Jaccard index of 0.812 (± 0.105) for 22 participants. The presented model illustrates the possibility of training a model with a small set of data (113,410 fully labelled frames). The proposed pipeline embraces a small-sized architecture that could facilitate its adoption.

The choice of holiday destinations is highly depended on climate considerations. Nowadays, since the effects of climate crisis are being increasingly felt, the need of accurate weather and climate services for hotels is crucial. Such a service could be beneficial for both the future planning of tourists’ activities and destinations and for hotel managers as it could help in decision making about the planning and expansion of the touristic season, due to a prediction of higher temperatures for a longer time span, thus causing increased revenue for companies in the local touristic sector. The aim of this work is to calculate predictions on climatic variables using statistical techniques as well as Artificial Intelligence (AI) for a specific area of interest utilising data from in situ meteorological station, and produce valuable and reliable localised predictions with the most cost-effective method possible. This investigation will answer the question of the most suitable prediction method for time series data from a single meteorological station that is deployed in a specific location. As a result, an accurate representation of the microclimate in a specific are is achieved. To achieve this high accuracy in situ measurements and prediction techniques are used. As prediction techniques, Seasonal Auto Regressive Integrated Moving Average (SARIMA), AI techniques like the Long-Short-Term-Memory (LSTM) Neural Network and hybrid combinations of the two are used. Variables of interest are divided in the easier to predict temperature and humidity that are more periodic and less chaotic, and the wind speed as an example of a more stochastic variable with no known seasonality and patterns. Our results show that the examined Hybrid methodology performs the best at temperature and wind speed forecasts, closely followed by the SARIMA whereas LSTM perform better overall at the humidity forecast, even after the correction of the Hybrid to the SARIMA model.

Currently, face recognition technologies are the most widely used methods for verifying 1an individual’s identity. Nevertheless, it has increased in popularity, raising concerns about face spoofing attacks, in which a photo or video of an authorized person’s face is used to get access to services. Based on a combination of Background Subtraction (BS) and Convolutional Neural Networks (CNN), as well as an ensemble of classifiers, we propose an efficient and more robust face spoof detection algorithm. This algorithm includes a Fully Connected (FC) classifier with a Majority Vote (MV) algorithm, which uses different face spoof attacks (e.g., printed photo and replayed video). By including a majority vote to determine whether the input video is genuine or not, the proposed method significantly enhances the performance of the Face Anti-Spoofing (FAS) system. For evaluation, we considered the MSU MFSD, REPLAY-ATTACK, and CASIA-FASD databases. The obtained results by our proposed approach are better than those obtained by state of the art methods. On the REPLAY-ATTACK database, we were able to attain a Half Total Error Rate (HTER) of 0.62% and an Equal Error Rate (EER) of 0.58%. It was possible to attain an EER of 0% on both the CASIA-FASD and the MSU FAS databases.

The accurate prediction of heat load profiles with a daily resolution is required for a broad range of applications such as potential studies, design, or predictive operation of heating systems. If the heat demand of a consumer is mainly caused by (production) processes independent of the ambient temperature, existing load profile prediction methods fail. To close this gap, this study develops two ex post machine learning models for the prediction of the heat demand with a daily resolution. The selected input features are commonly available to each consumer connected to public natural gas and electricity grids or operating an energy monitoring system: Ambient temperature, weekday, electricity consumption, and heat consumption of the last seven days directly before the predicted day. The study’s database covers electricity and natural gas consumption load profiles from 82 German consumers over a period of two years. Electricity and heat consumption correlate strongly with individual patterns for many consumers. Both, shallow and deep learning algorithms are evaluated. The highest accuracy is achieved by a Long Short Term Memory (LSTM) model with a median of R² of 0.94. The ex post model architecture makes the model suitable for automated anomaly detection in energy monitoring systems.

COVID-19 has a severe risk of spreading rapidly, the quick identification of which is essential. In this regard, chest radiology images have proven to be a practical screening approach for COVID-19 affected patients. This study proposes a deep learning-based approach using Densenet-121 to detect COVID-19 patients effectively. We have trained and tested our model on the COVIDx dataset and performed both 2-class and 3-class classification, achieving 96.49% and 93.71% accuracy, respectively. By successfully utilizing transfer learning, we achieve comparable performance to the state-of-the-art method while using 15x fewer model parameters. Moreover, we performed an interpretability analysis using Grad-CAM to highlight the most significant image regions at test time. Finally, we developed a website that takes chest radiology images as input and detects the presence of COVID-19 or pneumonia and a heatmap highlighting the infected regions. Source code for reproducing results and model weights are available.

Commercial buildings are a significant consumer of energy worldwide. Logistics facilities, and specifically warehouses, are a common building type yet under-researched in the demand-side energy forecasting literature. Warehouses have an idiosyncratic profile when compared to other commercial and industrial buildings with a significant reliance on a small number of energy systems. As such, warehouse owners and operators are increasingly entering in to energy performance contracts with energy service companies (ESCOs) to minimise environmental impact, reduce costs, and improve competitiveness. ESCOs and warehouse owners and operators require accurate forecasts of their energy consumption so that precautionary and mitigation measures can be taken. This paper explores the performance of three machine learning models (Support Vector Regression (SVR), Random Forest, and Extreme Gradient Boosting (XGBoost)), three deep learning models (Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)), and a classical time series model, Autoregressive Integrated Moving Average (ARIMA) for predicting daily energy consumption. The dataset comprises 8,040 records generated over an 11-month period from January to November 2020 from a non-refrigerated logistics facility located in Ireland. The grid search method was used to identify the best configurations for each model. The proposed XGBoost models outperform other models for both very short load forecasting (VSTLF) and short term load forecasting (STLF); the ARIMA model performed the worst.

The multi-modal data fusion method based on IA-net and CHMM technical proposed is designed to solve the problem that the incompleteness of target behavior information in complex family environment leads to the low accuracy of human behavior recognition.The two improved neural networks(STA-ResNet50、STA-GoogleNet)are combined with LSTM to form two IA-Nets respectively to extract RGB and skeleton modal behavior features in video. The two modal feature sequences are input CHMM to construct the probability fusion model of multi-modal behavior recognition.The experimental results show that the human behavior recognition model proposed in this paper has higher accuracy than the previous fusion methods on HMDB51 and UCF101 datasets. New contributions: attention mechanism is introduced to improve the efficiency of video target feature extraction and utilization. A skeleton based feature extraction framework is proposed, which can be used for human behavior recognition in complex environment. In the field of human behavior recognition, probability theory and neural network are cleverly combined and applied, which provides a new method for multi-modal information fusion.

The article considers an approach to the problem of assessing the quality of speech during speech rehabilitation as a classification problem. For this, a classifier is built on the basis of an LSTM neural network for dividing speech signals into two classes: before the operation and immediately after. At the same time, speech before the operation is the standard to which it is necessary to approach in the process of rehabilitation. The metric of belonging of the evaluated signal to the reference class acts as an assessment of speech. An experimental assessment of rehabilitation sessions and a comparison of the resulting assessments with expert assessments of phrasal intelligibility were carried out.

Free-space communication is a leading component in global communications. Its advantages relate to a broader signal spread, no wiring, and ease of engagement. Satellite communication services became recently attractive to mega-companies that foresee an excellent opportunity to connect disconnected remote regions, serve emerging machine-to-machine communication, Internet-of-things connectivity, and more. Satellite communication links suffer from arbitrary weather phenomena such as clouds, rain, snow, fog, and dust. In addition, when signals approach the ground station, it has to overcome buildings blocking the direct access to the ground station. Therefore, satellites commonly use redundant signal strength to ensure constant and continuous signal transmission, resulting in excess energy consumption, challenging the limited power capacity generated by solar energy or the fixed amount of fuel. This research proposes LTSM, an artificial recurrent neural network technology that provides a time-dependent prediction of the expected attenuation level due to rain and fog and the signal strength that remained after crossing physical obstacles surrounding the ground station. The satellite transmitter is calibrated accordingly. The satellite outgoing signal strength is based on the predicted signal strength to ensure it will remain strong enough for the ground station to process it. The instant calibration eliminates the excess use of energy resulting in energy savings.

Three-dimensional convolutional neural networks (3D CNN) as a type of artificial intelligence (AI) are powerful in image processing and recognition using deep learning to perform generative and descriptive tasks. The advantage of CNN compared to its predecessors is that it automatically detects the important features without any human supervision. 3D CNN are used to extract features in three dimensions where input is a 3D volume or a sequence of 2D pictures e.g., slices in a cone-beam computer tomography scan (CBCT). The main aim of this article was to bridge interdisciplinary cooperation between forensic medical experts and deep learning engineers. With emphasis activating clinical forensic experts in the field with possibly basic knowledge of advanced artificial intelligence techniques with interest in its implementation in their efforts to advance the forensic research further. This paper introduces a novel workflow of 3D CNN analysis of full-head CBCT scans. Authors explore and present 3D CNN method for forensic research design concept in five perspectives: (1) sex determination, (2) biological age estimation, (3) 3D cephalometric landmark annotation, (4) growth vectors prediction, (5) facial soft-tissue estimation from the skull and vice versa. In conclusion, 3D CNN application can be a watershed moment in forensic medicine, leading to unprecedented improvement of forensic analysis workflows based on 3D neural networks.

During planetary exploration mission operations, one of the key responsibilities of the instrument teams to determine data viability for subsequent analysis. During the 2019 CanMoon Lunar Sample Return Analogue Mission, the Lead Raman Specialist manually examined each spectra to provide quality assurance/validation. This non-trivial process requires years of experience to complete accurately. With the proven efficacy of Convolutional Neural Networks (CNNs) in classification tasks, and the increased use of automation and control loops on planetary space platforms for navigation and science targeting, an opportunity presents itself to approach this validation problem utilising CNNs. We present the Generalised Raman Validation Network (GRaVN), an neural network focused specifically on extracting the generalised structure of Raman spectra for quality assurance/validation. This work demonstrates the viability of utilising a CNN network in validation activities for Raman spectroscopy. Utilising only two hidden layers, a configuration was developed that provided good levels of accuracy on a manually curated dataset. This indicates that such a system could be useful as part of an autonomous control loop during planetary exploration activities.

Background: Processing whole-slide images (WSI) to train neural networks can be intricate and laborious. We developed an open-source library covering recurrent tasks in processing of WSI and in evaluating the performance of the trained networks for classification tasks. Methods: Two histopathology use-cases were selected. First we aimed to train a CNN to distinguish H&E-stained slides obtained from neuropathologically classified low-grade epilepsy-associated dysembryoplastic neuroepithelial tumor (DNET) and ganglioglioma (GG). The second project we trained a convolutional neural network (CNN) to predict the hormone expression of pituitary adenoms only from hematoxylin and eosin (H&E) stained slides. In the same approach, we addressed the issue to also predict clinically silent corticotroph adenoma. We included four clinico-pathological disease conditions in a multilabel approach. Results: Our best performing CNN achieved an area under the curve (AUC) of 0.97 for the receiver operating characteristic (ROC) for corticotroph adenoma, 0.86 for silent corticotroph adenoma and 0.98 for gonadotroph adenoma. Our DNET-GG classifier achieved an AUC of 1.00 for the ROC curve. All scores were calculated with the help of our library on predictions on a case basis. Conclusions: Our comprehensive library is most helpful to standardize the work-flow and minimize the work-burden in training CNN. It is also compatible with fastai. Indeed, our new CNNs reliably extracted neuropathologically relevant information from the H&E staining only. This approach will supplement the clinico-pathological diagnosis of brain tumors, which is currently based on cost-intense microscopic examination and variable panels of immunohistochemical stainings.

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is a challenging problem. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Identifying objects in floor plan images is also challenging due to the variety of floor plans and different objects. We faced a problem in training our network because of the lack of publicly available datasets. Currently, available public datasets do not have enough images to train deep neural networks efficiently. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10000 images to address this issue. Our proposed method conveniently surpasses the previous state-of-the-art results on the SESYD dataset and sets impressive baseline results on the proposed SFPI dataset. The dataset can be downloaded from SFPI Dataset Link. We believe that the novel dataset enables the researcher to enhance the research in this domain further.

Table detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparatively lightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions. We evaluate the proposed approach on five different publicly available table detection datasets. Our CasTabDetectoRS outperforms the previous state-of-the-art results on four datasets (ICDAR-19, TableBank, UNLV, and Marmot) and accomplishes comparable results on ICDAR-17 POD. Upon comparing with previous state-of-the-art results, we obtain a significant relative error reduction of 56.36%, 20%, 4.5%, and 3.5% on the datasets of ICDAR-19, TableBank, UNLV, and Marmot, respectively. Furthermore, this paper sets a new benchmark by performing exhaustive cross-datasets evaluations to exhibit the generalization capabilities of the proposed method.

Computer systems that operate in remote locations such as satellites, remote weather stations and autonomous robots are highly limited in the availability of energy for their operation. This work aims to employ artificial intelligence algorithms in energy management in order to obtain the maximum energy yield and the prediction of energy availability to the system. The work presents the main types of algorithms used in artificial intelligence and presents the creation of a prototype that will operate as a low power system powered by batteries and a small solar plate, the prototype will perform inferences on the LSTM neural network algorithm in order to predict the future availability of energy, consequently the management system will carry out the energy distribution in order to obtain the maximum operation of the prototype without total discharge of the batteries. So that the artificial intelligence system could be embedded in the prototype, the TensorFlow Lite framework was used, which allows the inference to be carried out in devices with low consumption and limited processing power.

In the last few decades, glaucoma became the second biggest leading cause of irreversible vision loss. Because of its asymptotic growth, it is not properly diagnosed until the relatively late stage. To stop the severe damage by glaucoma it is needed to detect glaucoma in its early stages. Surprisingly diabetes also be the greatest cause of glaucoma. In the modern era, artificial intelligence makes great progress in the medical image processing field. Image analysis based on machine learning gives a huge success in diagnosis glaucoma without any misdiagnosis. The aim of this proposed paper is to create an automated process that can detect glaucoma and diabetic retinopathy. Here various Machine Learning models are used and results of these methods are presented.

Optical motion capture is a mature contemporary technique for the acquisition of motion data, alas it is non-error-free. Due to technical limitations and occlusions of markers, gaps might occur in such recordings. The article reviews various neural network architectures applied for gap filling problem in motion capture sequences within FBM framework providing the representation for body kinematic structure. The results are compared with interpolation and matrix completion methods. We found out, that for longer sequences simple linear feedforward neural networks can outperform the other, sophisticated architectures. We were also able to identify, that acceleration and monotonicity of input sequence are the parameters that have a notable impact on the obtained results.

Neural decoding from spiking activity is an essential tool for understanding the information encoded in population neurons, especially in applications like brain-computer interface (BCI). Various quantitative methods have been proposed and have shown superiorities under different scenarios respectively. From the machine learning perspective, the decoding task is to map the high-dimensional spatial & temporal neuronal activity to the low-dimensional physical quantities (e.g., velocity, position). Because of the complex interactions and the abundant dynamics among neural circuits, good decoding algorithms usually have the capability of capturing flexible spatiotemporal structures embedded in the input feature space. Recently, the Transformer-based models are widely used in processing natural languages and images due to its superior performances in handling long-range and global dependencies. Hence, in this work we examine the potential applications of Transformers in neural decoding and introduce two Transformer-based models. Besides adapting the Transformer to neuronal data, we also propose a data augmentation method for overcoming the data shortage issue. We test our models on three experimental datasets and their performances are comparable to the previous state-of-the-art (SOTA) RNN-based methods. In addition, Transformer-based models show increased decoding performances when the input sequences are longer, while LSTM-based models deteriorate quickly. Our research suggests that Transformer-based models are important additions to the existing neural decoding solutions, especially for large datasets with long temporal dependencies.

Edge AI accelerators have been emerging as a solution for near customers’ applications in areas such as unmanned aerial vehicles (UAVs), image recognition sensors, wearable devices, robotics, and remote sensing satellites. These applications not only require meeting performance targets but also meeting strict reliability and resilience constraints due to operations in harsh and hostile environments. Numerous research articles have been proposed, but not all of these include full specifications. Most of these tend to compare their architecture with other existing CPUs, GPUs, or other reference research. This implies that the performance results of the articles are not comprehensive. Thus, this work lists the three key features in the specifications such as computation ability, power consumption, and the area size of prior art edge AI accelerators and the CGRA accelerators during the past few years to define and evaluate the low power ultra-small edge AI accelerators. We introduce the actual evaluation results showing the trend in edge AI accelerator design about key performance metrics to guide designers on the actual performance of existing edge AI accelerators’ capability and provide future design directions and trends for other applications with challenging constraints.

Cervical cancer is a worldwide public health problem with a high rate of illness and mortality among women. In this study, we proposed a novel framework based on Faster RCNN-FPN ar-chitecture for the detection of abnormal cervical cells in cytology images from cancer screening test. We extended the Faster RCNN-FPN model by infusing deformable convolution layers into the feature pyramid network (FPN) to improve scalability. Furthermore, we introduced a global contextual aware module alongside the Region Proposal Network (RPN) to enhance the spatial correlation between the background and the foreground. Extensive experimentations with the proposed deformable and global context aware (DGCA) RCNN were carried out using the cer-vical image dataset of “Digital Human Body" Vision Challenge from the Alibaba Cloud TianChi Company. Performance evaluation based on the mean average precision (mAP) and receiver operating characteristic (ROC) curve has demonstrated considerable advantages of the proposed framework. Particularly, when combined with tagging of the negative image samples using tra-ditional computer-vision techniques, 6-9% increase in mAP has been achieved. The proposed DGCA-RCNN model has potential to become a clinically useful AI tool for automated detection of cervical cancer cells in whole slide images of Pap smear.

This paper presents a novel architecture for detecting mathematical formulas in document images, which is an important step for reliable information extraction in several domains. Recently, Cascade Mask R-CNN networks have been introduced to solve object detection in computer vision. In this paper, we suggest a couple of modifications to the existing Cascade Mask R-CNN architecture: First, the proposed network uses deformable convolutions instead of conventional convolutions in the backbone network to spot areas of interest better. Second, it uses a dual backbone of ResNeXt-101, having composite connections at the parallel stages. Finally, our proposed network is end-to-end trainable. We evaluate the proposed approach on the ICDAR-2017 POD and Marmot datasets. The proposed approach demonstrates state-of-the-art performance on ICDAR-2017 POD at a higher IoU threshold with an f1-score of 0.917, reducing the relative error by 7.8%. Moreover, we accomplished correct detection accuracy of 81.3% on embedded formulas on the Marmot dataset, which results in a relative error reduction of 30%.

High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using convolutional neural networks (CNN). Damage in concrete subjected to compression is modeled at the mesoscale using the discrete element method. Ultrasonic wave propagation simulation on the damaged concrete specimens are performed using the rotated staggered finite-difference grid method. The simulated ultrasonic signals are used to train a CNN based classifier capable of classifying three different damage stages (microcrack initiation, microcrack growth and microcrack coalescence leading to macrocracks). The performance of the classifier is improved by refining the dataset via an analysis of the averaged envelope of the signal. The classifier using the refined dataset has an overall accuracy of 90%.

In this paper, we propose a new methodology for crack monitoring in concrete structures. This approach is based on a n this paper, we propose a new methodology for monitoring cracks in concrete structures. This approach is based on a multi-resolution analysis of a sample or a specimen of the studied material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processing by a dedicated wavelet will be analyzed according to several scales in order to detect internal cracks and crack initiation. The ultimate goal of this work is to propose an automatic crack type identification scheme based on convolutional neural networks (CNN). In this context, crack propagation can be monitored without access to the concrete surface and the goal is to detect cracks before they are visible on the concrete surface. The key idea allowing such a performance is the combination of two major data analysis tools which are wavelets and Deep Learning. This original procedure allows to reach a high accuracy close to 0.90. In this work, we have also implemented another approach for automatic detection of external cracks by deep learning from publicly available datasets.

Advancements in deep learning and availability of medical imaging data have led to use of CNN based architectures in disease diagnostic assisted systems. In spite of the abundant use of reverse transcription-polymerase chain reaction (RT-PCR) based tests in COVID-19 diagnosis, CT images offer an applicable supplement with its high sensitivity rates. Here, we study classification of COVID-19 pneumonia (CP) and non-COVID-19 pneumonia (NCP) in chest CT scans using efficient deep learning methods to be readily implemented by any hospital. We report our deep network framework design that encompasses Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory (biLSTM) architectures. Our study achieved high specificity (CP: 98.3%, NCP: 96.2% Healthy: 89.3%) and high sensitivity (CP: 84.0%, NCP: 93.9% Healthy: 94.9%) in classifying COVID-19 pneumonia, non-COVID-19 pneumonia and healthy patients. Next, we provide visual explanations for the CNN predictions with gradient-weighted class activation mapping (Grad-CAM). The results provided a model explainability by showing that Ground Glass Opacities (GGO), indicators of COVID-19 pneumonia disease, were captured by our CNN network. Finally, we have implemented our approach in three hospitals proving its compatibility and efficiency.

Emotion recognition defined as identifying human emotion and is directly related to different fields such as human-computer interfaces, human emotional processing, irrational analysis, medical diagnostics, data-driven animation, human-robot communi- cation and many more. The purpose of this study is to propose a new facial emotional recognition model using convolutional neural network. Our proposed model, “ConvNet”, detects seven specific emotions from image data including anger, disgust, fear, happiness, neutrality, sadness, and surprise. This research focuses on the model’s training accuracy in a short number of epoch which the authors can develop a real-time schema that can easily fit the model and sense emotions. Furthermore, this work focuses on the mental or emotional stuff of a man or woman using the behavioral aspects. To complete the training of the CNN network model, we use the FER2013 databases, and we test the system’s success by identifying facial expressions in the real-time. ConvNet consists of four layers of convolution together with two fully connected layers. The experimental results show that the ConvNet is able to achieve 96% training accuracy which is much better than current existing models. ConvNet also achieved validation accuracy of 65% to 70% (considering different datasets used for experiments), resulting in a higher classification accuracy compared to other existing models. We also made all the materials publicly accessible for the research community at: https://github.com/Tanoy004/Emotion-recognition-through-CNN.

There is a crucial need for advancement in the online educational system due to the unexpected, forced migration of classroom activities to a fully remote format, due to the coronavirus pandemic. Not only this, but online education is the future, and its infrastructure needs to be improved for an effective teaching-learning process. One of the major concerns with the current video call-based online classroom system is student engagement analysis. Teachers are often concerned about whether the students can perceive the teachings in a novel format. Such analysis was involuntarily done in the offline mode, however, is difficult in an online environment. This research presents an autonomous system for analyzing the students' engagement in the class by detecting the emotions exhibited by the students. This is done by capturing the video feed of the students and passing the detected faces to an emotion detection mode. The emotion detection model in the proposed architecture was designed by finetuning VGG16 pre-trained image classifier model. Lastly, the average student engagement index is calculated. We received considerable performance setting reliability of the use of the proposed system in real-time giving a future scope to this research.

This paper provides a review of an emerging field in the food processing sector, referring to efficient and safe food supply chains, ’from farm to fork’, as enabled by Artificial Intelligence (AI). Recent advances in machine and deep learning are used for effective food production, energy management and food labeling. Appropriate deep neural architectures are adopted and used for this purpose, including Fully Convolutional Networks, Long Short-Term Memories and Recurrent Neural Networks, Auto-Encoders and Attention mechanisms, Latent Variable extraction and clustering, as well as Domain Adaptation. Three experimental studies are presented, illustrating the ability of these AI methodologies to produce state-of-the-art performance in the whole food supply chain. In particular, these concern: (i) predicting plant growth and tomato yield in greenhouses, thus matching food production to market needs and reducing food waste or food unavailability; (ii) optimizing energy consumption across large networks of food retail refrigeration systems, through optimal selection of systems that can get shut-down and through prediction of the respective food de-freezing times, during peaks of power demand load; (iii) optical recognition and verification of food consumption expiry date in automatic inspection of retail packaged food, thus ensuring safety of food and people’s health.

Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.

The aim of this paper is to use deep learning tools to innovate pre-trained object detection models to improve the accuracy of non-destructive testing (NDT) of civil aviation maintenance. First, this thesis classifies object defects for NDT, such as cracks, undercut, etc. Nowadays, thesis surveys innovation deep-learning methods technology is used to improve the defect detection performance inferencing capability, increase the accuracy and efficiency of automatic identification which in enhanced the safety and reliability of aircraft fuselage in future, mark hidden cracks and solve the challenges that cannot be identified by manual inspection. Second, recent mainstream techniques the YOLOv4 neural network to the graphics card GPU core operator to speed up the recognition of defect images is being applied to the non-destructive inspection process of aircraft maintenance on A, C and D-Level, fully validating the deep learning model's powerful defect detection target capability. The attention-based YOLOv4 algorithm is improved by applying a one-stage attention mechanism to the YOLOv4, thereby improving the accuracy of the innovation model. Finally, thesis improved YOLOv4 based on an attention mechanism is proposed for object detection NDT via the deep learning method to effectively improve and shorten the inspection anomaly detection method for automatic detection sensor systems.

Many studies in the current literature annotate patterns in stock prices and use computer vision models to learn and recognize these patterns from stock price-action chart images. Additionally, current literature also use Long Short-Term Memory Networks to predict prices from continuous dollar amount data. In this study, we combine the two techniques. We annotate the consolidation breakouts for a given stock price data, and we use continuous stock price data to predict consolidation breakouts. Unlike computer vision models that look at the image of a stock price action, we explore using the convolution operation on raw dollar values to predict consolidation breakouts under a supervised learning problem setting. Unlike LSTMs that predict stock prices given continuous stock data, we use the continuous stock data to classify a given price window as breakout or not. Finally, we do a regularization study to see the effect of L₁, L₂, and Elastic Net regularization. We hope that combining regression and classification shed more light on stock market prediction studies.