Emotion detection holds significant importance in facilitating human-computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers for profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field.

Facial Emotion Recognition (FER) is crucial across psychology, neuroscience, computer vision, and machine learning due to the diversified and subjective nature of emotions, varying considerably across individuals, cultures, and contexts. This paper investigates the impact of histogram equalization, data augmentation and model optimization strategies on three well-known FER datasets using pre-trained VGG models. Additionally, this paper showcases the effectiveness of different regularization techniques, callbacks, and learning schedulers in enhancing model performance by conducting extensive experiments. The model evaluation is discussed in terms of the following metrics: Accuracy, Area Under the Receiver Operating Characteristic Curve (AUC-ROC), Area Under the Precision-Recall Curve (AUC-PRC), and Weighted F1 score. Notably, the fine-tuned VGG models exhibit state-of-the-art performance compared to more complex conventional transfer learning models resulting in accuracies of 100%, 95.92%, and 69.65% on the CK+, KDEF, and FER2013 datasets, respectively.

Speech emotion recognition (SER) is a technology that can be applied in distance education to analyze speech patterns and evaluate speakers’ emotional states in real-time. It provides valuable insights and can be used to enhance the learning experience by enabling the assessment of instructors’ emotional stability, a factor that significantly impacts information delivery effectiveness. Students demonstrate different engagement levels during learning activities, and assessing this engagement is an important aspect of controlling the learning process and improving e-learning systems. An important aspect that may influence student engagement is the emotional states of their instructors. Accordingly, this research uses deep learning techniques to create an automated system for recognizing instructors’ emotions in their speech when delivering distance learning. This methodology entails integrating Transformer, convolutional neural network, and long short-term memory architectures into an ensemble to enhance SER. Feature extraction from audio data used Mel-frequency cepstral coefficients, chroma, Mel spectrogram, zero crossing rate, spectral contrast, centroid, bandwidth, roll-off, and root-mean square, with subsequent optimization processes adding noise to, conducting time stretching, and shifting the audio data. Notably, several Transformer blocks were incorporated, and a multi-head self-attention mechanism was employed to identify the relationships between the input sequence segments. The pre-processing and data augmentation methodologies significantly enhanced the precision of the results in that the model achieved accuracy rates of 96.3%, 99.86%, 96.5%, and 85.3% on the Ryerson Audio-Visual Database of Emotional Speech and Song, Berlin Database of Emotional Speech, Surrey Audio-Visual Expressed Emotion, and Interactive Emotional Dyadic Motion Capture datasets. Furthermore, it achieved 83% accuracy on another dataset created for this research—the Saudi Higher Education Instructor Emotions dataset. The results demonstrate this model’s considerable accuracy in detecting emotions in speech data across different languages and datasets.

This paper proposed emotion recognition methods for consecutive facial images, and implements the inference of neural network model on a field-programmable gate array (FPGA). The proposed emotion recognition methods are based on a neural network model architecture that combines convolution neural networks (CNNs), long short-term memory (LSTM), and fully connected neural networks (FCNNs), called CLDNN or ConvLSTM-FCN. This type of neural network mod-el can analyze the local feature sequences obtained through convolution of data, making it suita-ble for processing time-series data such as consecutive facial images. In this paper, sequences of facial images are sampled from videos corresponding to various emotional state of subjects. The sampled images are then pre-processed with the processes includes facial detection, greyscale conversion, resize, and data augmentation if necessary. The 2-D CNN in ConvLSTM-FCN is used for feature extraction for these pre-processed facial images. These sequences of facial im-age features are time sequences with dependent properties between the elements within them. The LSTM is then used to model these time sequences followed by fully connected neural net-works (FCNNs) for classification. The proposed consecutive facial emotion recognition method achieves an average recognition rate of 99.51% on RAVDESS dataset, 87.80% on BAUM-1s dataset and 96.82% on eNTERFACE’05 data set, using 10-fold cross-validation on the PC. Some com-parisons of recognition accuracies between the proposed method and the other existing related works are conducted in this paper. According to the comparisons, the proposed emotion recog-nition methods outperform the existing related researches. The proposed emotion recognition methods are then implemented on an FPGA chip using the neural network model inference algo-rithms in this paper, and the accuracies of the experiments conducted on the FPGA chip are iden-tical to those obtained on the PC. This verifies that the proposed neural network model imple-mented on the FPGA chip performs well.

Text-based CAPTCHA remains the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs) are the mainstream approach for text-CAPTCHA recognition, which are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment, they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive-CAPTCHA with a CRNN module and trainable and configurable filtering networks, which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexity show that compared with the baseline model Deep-CAPTCHA, the number of parameters of our proposed model is reduced by about 70% and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed.

Lysine plays a crucial role in promoting development, enhancing immune function, and improving the function of central nervous system tissues. The two configurational isomers of amino acids have significantly different effects. Currently, methods for chiral recognition of lysine all have drawbacks such as expensive equipment and complicated detection processes, whereas fluorescence analysis boasts high sensitivity, strong selectivity, and simple operation. In this study, we synthesized four novel Binaphthyl-Amine (BINAM)-based fluorescent probes capable of specifically identifying the L-configuration of lysine among the twenty amino acids constituting human proteins. The enantiomeric fluorescence enhancement ratio (ef or ΔIL/ΔID) reached up to 15.29, demonstrating high enantioselectivity. We also evaluated the probe's recognition ability under different pH, reaction times, and metal ion conditions, as well as the Limit of Detection of the probe. Our findings indicate that this probe is a highly stable tool for detecting chiral lysine.

This study explores the multifaceted influence of litter size, maternal care, exercise, and aging on rats' neurobehavioral plasticity and dentate gyrus microglia dynamics. Body weight evolution revealed a progressive increase until maturity, followed by a decline during aging, with larger litters exhibiting lower weights initially. Notably, exercised rats from smaller litters displayed higher body weights during mature and aged stages. Dentate gyrus volumes showed no significant differences among groups, except for aged sedentary rats from smaller litters, which exhibited a reduction. Maternal care varied significantly based on litter size, with large litter dams showing lower frequencies of caregiving behaviors. Behavioral assays highlighted the detrimental impact of a sedentary lifestyle and reduced maternal care/large litters on spatial memory, mitigated by exercise in aged rats from smaller litters. Microglial dynamics in the layers of dentate gyrus revealed age-related changes modulated by litter size and exercise. Exercise interventions mitigated microgliosis associated with aging, particularly in aged rats. These findings underscore the complex interplay between early-life experiences, exercise, microglial dynamics, and neurobehavioral outcomes during aging.

Exoskeletons designed to assist patients with activities of daily living are becoming increasingly popular, but still are subject to research. In order to gather requirements for the design of such systems, long-term gait observation of the patients over the course of multiple days in an environment of daily living are required. In this paper a wearable all-in-one data acquisition system for collecting and storing biomechanical data in everyday life is proposed. The system is designed to be cost efficient and easy to use, using off-the-shelf components and a cloud server system for centralized data storage. The measurement accuracy of the system was verified, by measuring the angle of the human knee joint at walking speeds between 3 and 12 km/h in reference to an optical motion analysis system. The acquired data was uploaded to a cloud database via a smartphone application. Verification results showed that the proposed toolchain works as desired. The system reached an RMSE from 2.9° to 8°, which is below most of the comparable system. The system provides a powerful, scalable platform for collecting and processing biomechanical data, which can help to automize the generation of an extensive database for human kinematics.

This enables the chip to regulate the voice recognition function of the gadget, leading to a more natural and human-like process. Integrating this technique into the English language voice recognition system can greatly improve its precision in identifying the speech of a particular person. This research seeks to investigate and create an automatic error detection technique for an embedded speech instruction recognition system for English using artificial intelligence. The study commences with a conventional introduction to artificial intelligence, thereafter delving into a comprehensive investigation of the speech recognition algorithm. The MATLAB programme is used to determine the accurate number of words recognised by the system and its accuracy rate. The embedded teaching recognition system for English is then tested in different contexts to assess its performance. Several tests are performed to compare and analyse the results, which indicate that the integrated English voice recognition system achieves an accuracy rate of over 90% and has a low error rate in a calm environment. In a bustling environment with numerous auditory stimuli, the accurate recognition rate typically exceeds 60%.

Antibodies are important tools for the study of membrane proteins in biological, biophysics and structural analyses. However, the production of purified membrane proteins is still a formidable challenge due to the amphipathic character and inherent instability of these proteins. In this work, we tested a strategy for producing antibodies against an ATP-Binding Cassette (ABC) transporter without the need to produce the full membrane complex. Instead, just the extra cytoplasmic regions of the ABC-type transporter Rv1819c from Mycobacterium tuberculosis were presented in the RAD-display, a scaffold system based on the engineered Pyrococcus furiosus RadA protein developed for exposition of peptides. The RadA scaffold protein is highly stable, can tolerate long insertions and easy to produce in Escherichia coli. Based on the three-dimensional structure of Rv1891c, we selected two versions of the main extracellular loops of the permease to use as test cases for this approach. Rv1819c-derived peptides displayed on RAD display system were used for immunization of mice and production of polyclonal antibodies. These antibodies were able to recognize the transporter in M. tuberculosis cell extracts, on intact cells by flow cytometry and as purified protein. The results showed the approach can be a useful tool for in vitro analyses, screening, and evaluation of different epitopes in membrane proteins.

Multivariate Time Series Classification (MTSC) is one of most important tasks in time series analysis, aiding in activities such as human motion recognition and medical diagnostics. Existing methods for MTSC do not explicitly model temporal differences and generalize the idea of temporal difference into a efficient temporal module. Additionally, existing methods are not yet able to capture cross-variable relationships well during network training. As a result, they are unable to achieve convincing feature representation, leading to suboptimal classification accuracy. In this paper, we propose a novel MTSC model called Temporal Difference and Cross-variate Fusion Network (TDCFN), which integrates a two-stream differential LSTM network and a cross-variate feature extraction network to enhance feature representation. TDCFN achieves superior classification accuracy by capturing dynamic temporal evolution and inter-variable relationships. The experimental results show that TDCFN can achieve competitive performance with state-of-the-art multivariate time series classification approaches.

The state-of-the-art smart city has been calling for an economic but efficient energy management over large-scale network, especially for the electric power system. It is a critical issue to monitor, analyze and control electric loads of all users in system. In this paper, we employ the popular computer vision techniques of AI to design a non-intrusive load monitoring method for smart electric energy management. First of all, we utilize both signal transforms (including wavelet transform and discrete Fourier transform) and Gramian Angular Field (GAF) methods to map one-dimensional current signals onto two-dimensional color feature images. Second, we propose to recognize all electric loads from color feature images using a deep neural network with multi-scale feature extraction and attention mechanism. Third, we design our method as a cloud-based, non-intrusive monitoring of all users, thereby saving energy cost during electric power system control. Experimental results on both public and our private datasets have demonstrated our method achieves superior performances than its peers, and thus supports efficient energy management over large-scale Internet of Things.

Human Activity Recognition (HAR) technology enables continuous behavior monitoring, particularly valuable in healthcare. This study investigates the viability of using an ear-worn motion sensor for classifying daily activities, including lying, sitting/standing, walking, ascending stairs, descending stairs, and running. Fifty healthy participants (between 20 and 47 years old) engaged in these activities while under monitoring. Various machine learning algorithms, ranging from interpretable shallow models to state-of-the-art deep learning approaches designed for HAR, were employed for classification. Results demonstrate the ear sensor's efficacy, with deep learning models achieving 98% accuracy rate of classification. The obtained classification models are agnostic regarding which ear the sensor is worn and robust against moderate variations in sensor orientation (e.g., due to differences in auricle anatomy), meaning no initial calibration of the sensor orientation is required. The study underscores the ear's efficacy as a suitable site for monitoring human daily activity and suggests its potential for combining HAR with in-ear vital signs monitoring. This approach offers a practical method for comprehensive health monitoring by integrating sensors in a single anatomical location. This integration facilitates individualized health assessments, with potential applications in tele-monitoring, personalized health insights, and optimizing athletic training regimes.

Oncolytic virotherapy is a promising immunotherapy approach for cancer treatment, utilizing viruses to preferentially infect and eliminate cancer cells while stimulating immune responses. In this review we synthesize current literature on the molecular circuits of immune sensing and response to oncolytic virotherapy; focusing on viral DNA or RNA sensing by infected cells, cytokine and danger-associated signal sensing by neighboring cells, and subsequent downstream activation of immune pathways. The sequential sense-and-response mechanisms involve the triggering of molecular sensors by viruses or infected cells to activate transcription factors and related genes for a breadth of immune responses. We describe how molecular signals induced in the tumor upon virotherapy can trigger diverse immune signaling pathways, activating both antigen-presenting cell-based innate and T cell-based adaptive immune responses. Insights into these complex mechanisms provide valuable knowledge for enhancing oncolytic virotherapy strategies.

In the context of artificial intelligence's pervasive integration across sectors, the rigorous examination of methodologies used in constructing mathematical models is imperative. This study delves into facial recognition models, particularly in their ability to extract features such as age. We address the prevalent practice of training models with unbalanced datasets and its implications for model performance and bias introduction. Utilizing 27,305 facial images, we investigate the influence of dataset imbalance on age prediction based on ethnicity. Employing preprocessing and oversampling techniques, we equalize sample sizes across ethnicities. A Convolutional Neural Network trained on the balanced dataset serves as our baseline, while three additional models undergo training with a 50% sample size reduction for each group to assess accuracy degradation. Our findings reveal a notable decline in accuracy for ethnic groups with reduced representation. The Asian group experiences a 67.94% accuracy deterioration, followed by a 51.60% drop for the Black group, and a 38.46% decline for the White group. These results underscore the sensitivity of certain ethnic groups to underrepresentation, highlighting the nuanced impact on age prediction accuracy. While a 50% reduction in representation does not uniformly result in a 50% accuracy decline, it unquestionably influences predictive accuracy for affected groups.

Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.

(1) Background: The proportion of fully mechanized harvesting systems in Austria is constantly increasing especially because of the technological development of the machines, which allows them to drive on increasingly steep terrain. This leads to additional challenges and potential hazards for the operators, which may also cause higher stress levels. The purpose of this study is to develop and debate a new set of methodologies for determining time and space resolved psychophysiology data to analyze stressful and non-stressful work situations for harvester and forwarder operators; (2) Methods: we suggest a study protocol to analyze a) tasks performed by the driver, b) environmental factors, like slope gradient, c) the psychophysiological response of experts during these tasks, and d) evaluate the worker´s subjective stress and fatigue before and after a harvest operation. (3) Results: Within this manuscript we present a study protocol based on quantitative and qualitative methods, like time and space resolved psychophysiology, questionnaires, qualitative interviews, as well as video and sensor-based analysis of environmental and machine data. The first results from real measurements of a forwarder driver are presented; (4) Conclusions: This multimodal research protocol serves to explore the relationship between stress, fatigue, and performed tasks. Through our quantitative and qualitative methodology, researchers can improve the health and safety of forest workers at work, improve their productivity and reduce damage to remaining trees.

In this comprehensive review, we delve into the realm of intention recognition within the context of digital forensics and cybercrime. The rise of cybercrime has become a major concern for individuals, organizations, and governments worldwide. Digital forensics is a field that deals with the investigation and analysis of digital evidence in order to identify, preserve, and analyze information that can be used as evidence in a court of law. Whereas, Intention recognition is a subfield of artificial intelligence that deals with the identification of agents’ intentions based on their actions and change of states. In the context of cybercrime, intention recognition can be used to identify the intentions of cybercriminals and even to predict their future actions. Employing a meticulous six-step systematic review approach, we curated research articles from reputable journals and categorized them into three distinct modeling approaches: logic-based, classical machine learning-based, and deep learning-based. Notably, intention recognition has transcended its historical confinement to network security, now addressing critical challenges across various subdomains, including social engineering attacks, AI black box vulnerabilities, and physical security. While deep learning emerges as the dominant paradigm, its inherent lack of transparency poses unique challenges in the digital forensics landscape. We advocate for hybrid solutions that blend deep learning’s power with interpretability. Furthermore, we propose the creation of a comprehensive taxonomy to precisely define intention recognition, paving the way for future advancements in this pivotal field.

Abstract: Rationale. Object tracking has significance in many applications ranging from control of unmanned vehicles to autonomous monitoring of specific situations and events, especially when providing safety for patients with certain adverse conditions such as epileptic seizures. Conventional tracking methods face many challenges, such as the need for dedicated attached devices or tags, influence by high image noise, complex object movements, and intensive com-putational requirements. We have developed earlier computationally efficient algorithms for global optical flow reconstruction of group velocities that provide means for convulsive seizure detection and have potential applications in fall and apnea detection. Here, we address the chal-lenge of using the same calculated group velocities for object tracking in parallel. Methods. We propose a novel optical flow-based method for object tracking. It utilizes real-time image se-quences from the camera and directly reconstructs global motion-group parameters of the con-tent. These parameters can steer a rectangular region of interest surrounding the moving object to follow the target. The method successfully applies to multi-spectral data, further improving its effectiveness. Results. Experimental results on simulated tests and complex real-world data demonstrate the method's capabilities. The proposed optical flow reconstruction can provide accurate, robust, and faster results compared to current state-of-the-art approaches.

This study introduces a specialized Automatic Speech Recognition (ASR) system, leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in French language. Our methodology focused on adapting the model to accurately transcribe medical terminology and diverse accents within the French language context, achieving a notable Word Error Rate (WER) of 17.121%. The research involved extensive data collection and preprocessing, utilizing a wide range of French medical audio content. The results demonstrate the system's effectiveness in transcribing complex radiological data, underscoring its potential to enhance medical documentation efficiency in French-speaking clinical settings. The discussion extends to the broader implications of this technology in healthcare, including its potential integration with Electronic Health Records (EHRs) and its utility in medical education. The study also explores future research directions, such as tailoring ASR systems to specific medical specialties and languages. Overall, this research contributes significantly to the field of medical ASR systems, presenting a robust tool for radiological transcription in the French language and paving the way for advanced technology-enhanced healthcare solutions.

Taekwondo has evolved from a traditional martial art into an official Olympic sport. This study introduces a novel action recognition model tailored for Taekwondo unit actions, utilizing joint motion data acquired via wearable inertial measurement unit (IMU) sensors. The utilization of IMU sensor-measured motion data facilitates the capture of the intricate and rapid movements characteristic of Taekwondo techniques. The model, underpinned by a conventional convolutional neural network (CNN)-based image classification framework, synthesizes action images to represent individual Taekwondo unit actions. These action images are generated by mapping joint motion profiles onto the RGB color space, thus encapsulating the motion dynamics of a single unit action within a solitary image. To further refine the representation of rapid movements within these images, a time-warping technique was applied, adjusting motion profiles in relation to the velocity of the action. The effectiveness of the proposed model was assessed using a dataset compiled from 40 Taekwondo experts, yielding remarkable outcomes: an accuracy of 0.998, precision of 0.983, recall of 0.982, and an F1-score of 0.982. These results underscore the time-warping technique's contribution to enhancing feature representation, as well as the proposed method's scalability and effectiveness in recognizing Taekwondo unit actions.

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

Pedestrian Dead Reckoning (PDR) is a promising algorithm for indoor positioning. However, the accuracy of PDR degrades due to the accumulated error, especially in multi-floor buildings. This paper introduces a three-dimensional (3D) positioning method based on terrain feature matching to reduce the influence of accumulated error in multi-floor scene. The proposed method involves two steps: motion pattern recognition and position matching calibration. The motion pattern recognition aims to detect different motion states, i.e., taking the stairs or horizontal walking, from the streaming data. Then, stair entrances and corridor corners are matched with transition points of motion states and pedestrian turning points, respectively. After matching, calibration is performed to eliminate the accumulated errors. By carrying out experiments on a two-floor closed-loop path with a walking distance about 145 m, it is shown that this method can effectively reduce the accumulated error of PDR , achieving accurate 3D positioning . The average error is reduced from 6.60 m to 1.83 m.

Human action recognition (HAR) based on skeleton data is a challenging yet important technique because of its wide range of applications in many fields, including patient monitoring, security surveillance, and observing human-machine interactions. Many algorithms that attempt to distinguish between many types of activities have been proposed. However, most practical applications require highly accurate detection of specific types of activities. In this study, a novel and highly accurate spatiotemporal graph autoencoder network for HAR based on skeleton data is proposed. Furthermore, an extensive study was conducted using different modalities. For this purpose, a spatiotemporal graph autoencoder that automatically learns spatial as well as temporal patterns from human skeleton datasets was built. The powerful graph convolutional network named GA-GCN, developed in this study, notably outperforms most of the existing state-of-the-art methods based on two common datasets, namely NTU RGB+D and NTU RGB+D 120 . On the first dataset, we achieved an accuracy of 92.3% and 96.7% based on the cross-subject and cross-view evaluations, respectively. On the other more challenging dataset (i.e. NTU RGB+D 120), GA-GCN achieved 88.8% and 90.4% based on the cross-subject and cross-set evaluation, respectively.

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

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

Recognition, decoding and tracking of vortex patterns is of increasing importance in many fields reaching from astronomical observation of distant galaxies to turbulence phenomena in liquids or gases. Currently, coherent light beams with orbital angular momentum (OAM) are of particular interest for optical communication, metrology, micro-machining or particle manipulation. One common task is to identify characteristic spiral patterns in pixelated intensity maps at real-world signal-to-noise ratios. Recently, Fast Fourier Transform (FFT) was applied to the quantitative analysis of spiral interference patterns of OAM beams. Our study considers this approach in more detail. It is demonstrated that specific information can be extracted by combining conformal mapping by polar transform with determining one- or two-dimensional angular frequency spectra either in spatially fixed or scanning mode. Results of proof-of-principle experiments are presented.

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

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

Videogames have been the focus of research since their widespread popularity, with particular emphasis on their effects on cognitive and affective abilities, especially in children and adolescents. Despite numerous correlational studies, robust evidence on the causal relationship between videogames and cognition remains scarce, hindered by the absence of a comprehensive assessment tool for gaming skills across various genres. This study aimed to develop and validate the Gaming Skill Questionnaire (GSQ) and to assess the impact of gaming skills in six different genres (Sport, First-Person Shooters, Role-Playing Games, Action-Adventure, Strategy, and Puzzle Games) on adolescents’ cognitive and affective abilities. The GSQ exhibited strong reliability and validity, highlighting its potential as a valuable tool. Gaming skills positively affected executive function, memory, overall cognition, cognitive flexibility, and emotion recognition, except for empathy. Various game genres had different effects on cognitive and affective abilities, with verbal fluency influenced mainly by sports, executive functions by action, strategy, and puzzle, and emotion recognition positively impacted by action and puzzle but negatively by sports and strategy games. Both age and gaming skills influenced cognitive flexibility, with gaming having a greater effect. These intriguing genre-specific effects on cognitive and affective functioning postulate further research with GSQ's contribution.

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

New ideas on the framework of Neutrosophic SuperHyperGraph for different styles of Neutrosophic SuperHyper-Wheel and Neutrosophic SuperHyper-Star are introduced. More instances and more clarifications alongside sufficient references are featured with a specific type of independency of SuperHyperVertices.

Caring for dolphins is a delicate process that requires experienced caretakers to pay close attention to their behavioral characteristics. However, caretakers may sometimes lack experience or not be able to give their full attention, which can lead to misjudgment or oversight. To address these issues, a dolphin behavior analysis system has been designed to assist caretakers in making accurate assessments. The study utilized image preprocessing techniques to reduce sunlight reflection in the pool and enhance the outline of dolphins, making it easier to analyze their movements. The dolphins were divided into 11 keypoints using an open-source tool called DeepLabCut, which helped accurately mark various body parts for skeletal detection. The AquaAI Dolphin Decoder (ADD) was then used to analyze six dolphin behaviors. To improve behavior recognition accuracy, the Long Short-Term Memory (LSTM) neural network was introduced. The ADD and LSTM models were integrated to form the ADD-LSTM system. Several classification models, including unidirectional and bidirectional LSTM, GRU, and SVM, were compared. The results showed that the ADD module combined with a double-layer bidirectional LSTM method achieved high accuracy in dolphin behavior analysis. The accuracy rates for each behavior were over 90%.

In order to improve real-time performance of gesture recognition by micro-Doppler map of mmWave Radar, the point cloud based gesture recognition for mmWave Radar is proposed in this paper.Two steps are carried out for mmWave Radar based gesture recognition. The first step is to estimate the point cloud of the gestures by 3D-FFT and the peak grouping. The second step is to train the TRANS-CNN model by combining the multi-head self-attention and the 1D-convolutional network, so as to extract the features in the point cloud data at a deeper level to categorize the gestures. In the experiments, TI mmWave Radar sensor IWR1642 is used as benchmark to evaluate the feasibility of the proposed approach. The results show that the accuracy of the gesture recognition reaches 98.5%. In order to prove the effectiveness of our approach, a simply 2Tx2Rx Radar sensor is developed in our lab and the accuracy of recognition reaches 97.1%. The results show that our proposed gesture recognition approach achieves the best performance in real-time with limited training data, in comparison with the existing methods.

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

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

The integration of Artificial Intelligence (AI) in dairy farm management through biometric facial recognition for cows is a significant stride in livestock management. This review critically evaluates the evolution, applications, and challenges of AI-driven biometric facial recognition in dairy farming. It emphasizes the role of this technology in enhancing individual monitoring of dairy cows, providing accurate health, behavior, and productivity tracking. Originally derived from human facial recognition systems, this approach utilizes distinctive bovine facial features for essential, non-invasive, real-time monitoring in large-scale operations. The progression of AI from elementary pattern recognition to advanced Convolutional Neural Networks (CNNs) and deep learning models marks a shift toward data-driven farming. This study addresses key challenges such as environmental variability, data collection hurdles, ethical concerns, and technological limitations. It also contrasts various AI models, spotlighting their unique strengths and practical utility in dairy farming scenarios. Despite these challenges, facial recognition technology holds promise for improving farm efficiency, animal welfare, and sustainable practices, highlighting the need for continuous research and development. The review concludes by advocating for future research focused on environmental adaptability, ethical AI application, cross-breed compatibility, and integration with other farming technologies. Ultimately, it underscores AI's transformative potential in modernizing dairy farming towards a more data-oriented, responsible agricultural future.

One of the needs of the teaching and learning processes is the lack of information during the process, such as the emotions of students. Emotions influence learning, the ability to process information and accurately understand what we are dealing with. They profoundly affect students’ academic engagement and performance. One new way of getting such information is monitoring students' emotions. This research aims to expose 6 groups of secondary school students to video recordings for further analysis and categorization of their emotions. A model of emotional recognition (ER) during classroom learning was designed, with a custom-made code, from recorded videos to images to identify faces, action units (AUs) and consequently the emotions of each of the students shown on the screen. In addition, the ER model was optimized, from detecting few students to many students during a class. Emotions were then analysed according to the academic year, subject, and comparing the emotions at the beginning and at the end of the class. The results indicate the presence of a variety of emotions in the classroom and we found significant differences in the presence of some emotions depending on the time of class, subject and academic year, although there are no clear patterns. We discussed how emotions influence students' academic performance, and we suggest future research focus on teachers utilizing tools like this to improve student well-being and performance.

Scientific research in the study of Human-Robot Interactions (HRI) has advanced significantly in recent years. Social humanoid robots have undergone severe testing and have been implemented in a variety of settings, including educational institutions, healthcare facilities and senior care centers. Humanoid robots have also been evaluated across diverse population groups. However, the research on different children-groups is still scarce, especially deaf children. This feasibility study includes both hearing children and deaf children, and aim to assess the interaction between children and a humanoid robot without the use of sounds and voices. In addition, an experiment was conducted where the children were asked to watch a video and then assess whether the NAO humanoid robot responded to the emotions shown in the video in a congruent or incongruent way. The findings indicated that there was no difference between the children who were present-ed with congruent emotions in the NAO as opposed to the children who were presented with in-congruent emotions in the robot. Only the ability to predict emotion in videos and gender were significant predictors of guessing the correct emotion in robot. Although no significantly differ-ence was found between hearing and deaf children, this feasibility study is intended to lay the groundwork for future research in this unexplored field of study.

Currently, Pythagorean fuzzy sets (PFSs) have been widely applied in various fields due to their substantial advantages in expressing and dealing with uncertainty. However, measuring the similarity and difference between PFSs effectively remains an unresolved issue. Inspired by Tanimoto similarity, we propose a novel set of similarity and distance measures for PFSs. We delve into the theoretical properties of the proposed measures and compare it with existing PFSs measures. Numerous numerical examples validate their rationality and effectiveness. Furthermore, our experimental findings suggest that in contrast to existing measures, the introduced measures successfully circumvent various counter-intuitive issues encountered by current measures, and yield more pronounced outcomes in the discrimination of different fuzzy sets. This enhances the uniqueness and superiority of our measures. Finally, we developed two decision models based on the proposed measures and validated their applicability in three applications.

Gesture recognition technology has been quickly developed in the field of human-computer interaction. The multiple-input multiple-output (MIMO) radar has been widely adopted in gesture recognition because of its notable spatial resolution. In this work, a highly accurate MIMO radar-based hand gesture recognition algorithm with very low complexity is proposed. To make the proposed system applicable in the industry and work well even when the size of the training data is limited, we applied several low-complexity adaptive signal processing methods to extract features and reduce the noise effect. First, spectrum analysis is applied to range-Doppler maps (RDMs) and a cell-averaging constant false alarm rate (CA-CFAR) with mirror filters is applied to improve the robustness to noise. Afterward, the features related to the distance, speed, direction, and the elevation angle of the moving object are determined by the proposed adaptive signal analysis techniques and the random forest is applied for classification. The proposed system has the capability to precisely distinguish and identify eight motions, including waving, moving to the left or right, patting, pushing, pulling, and rotating clockwise or anticlockwise, with an accuracy of 95%. Experiments demonstrate the capability of the proposed hand gesture recognition system to classify different movements precisely.

Entamoeba histolytica, the causative agent of amebiasis, is the third leading cause of death among parasitic diseases globally. Its life cycle includes encystation, which has been mostly studied in Entamoeba invadens, responsible of reptilian amebiasis. However, the molecular mechanisms underlying this process are not fully understood. Therefore, we focused on the identification and characterization of Myb proteins, that regulate the expression of encystation-related genes in various protozoan parasites. Through bioinformatic analysis, we identified 47 genes in E. invadens encoding MYB-domain-containing proteins. These were classified into single-repeat 1R (19), 2R-MYB proteins (27), and one 4R-MYB protein. The in silico analysis suggests that these proteins are multifunctional, participating in transcriptional regulation, chromatin remodeling, telomere maintenance, and splicing. Transcriptomic data analysis revealed expression signatures of eimyb genes, suggesting a potential orchestration in the regulation of early and late encystation-excystation genes. Furthermore, we identified 3135 probable target genes associated with reproduction, meiotic cell cycle, ubiquitin-dependent protein catabolism, and endosomal transport. In conclusion, our findings suggest that E. invadens Myb proteins regulate stage-specific proteins and a wide array of cellular processes. This study provides a foundation for further exploration of the molecular mechanisms governing encystation and unveils potential targets for therapeutic intervention in amebiasis.

This research delves into the realm of predictive modeling within artificial intelligence (AI) and introduces an innovative ensemble approach designed to enhance prognostic precision. The proposed methodology, characterized by its ebullient nature, leverages the collective wisdom of diverse predictive models, synthesizing a comprehensive and robust framework. The pursuit of parsimony are paramount, underscoring the need for efficient model architectures that balance predictive acuracy and computational efficiency. Our study meticulously explores the amalgamation of diverse algorithms, encapsulating the intrinsic complexity of real-world phenomena. We navigate the intricate landscape of feature selection, algorithmic diversity, and model combination, fostering a holistic understanding of the prognostic process. The ebullient ensemble emerges as a dynamic solution, harnessing the synergy of constituent models while mitigating the risk of overfitting. To validate the efficacy of our approach, extensive experiments are conducted on diverse datasets, spanning domains such as healthcare, finance, and natural language processing. Comparative analyses demonstrate the superior predictive performance of our ensemble model in comparison to individual algorithms and traditional ensemble methods. Additionally, we delve into interpretability aspects, elucidating the underlying mechanisms that contribute to the model's prognostic prowess. Our research advances the frontier of predictive modeling in AI, offering a nuanced and sophisticated paradigm for prognostication. The ebullient ensemble approach stands as a testament to the synergy achievable through the amalgamation of diverse predictive models, providing a pragmatic and parsimonious avenue for enhanced prognostic acuracy in artificial intelligence applications.

The field of nephrology has recently directed a considerable amount of attention towards the stimulator of interferon genes (STING) molecule since it appears to be a potent driver of chronic kidney disease (CKD). STING and its activator, the cyclic GMP-AMP synthase (cGAS) are among the most relevant inducers that promote the expression of type I interferons (IFN-Is). These cytokines have been long recognized as part of the mechanism used by the innate immune system to battle viral infections; however, their involvement in sterile inflammation remains unclear. Mounting evidence pointing to the involvement of the IFN-I pathway in sterile kidney inflammation provides potential insights into the complex interplay between the innate immune system and damage to the most sensitive segment of the nephron, the glomerulus. The STING pathway is often cited as the cause of renal disease originating from non-infection related caused by the induction of IFN-I expression. However, other receptors have been implicated in this process, mainly by recognizing host-derived nucleic acids. This review explores the main endogenous inducers of IFN-I in glomerular cells, discusses what exposure to the main autocrine and paracrine cytokines has on these cells, and identifies the pathways that are implicated in the development of glomerular damage.

Fermatean fuzzy sets (FFSs) are a versatile tool for handling uncertain problems and have shown great effectiveness in practical applications. However, many existing Fermatean fuzzy similarity measures exhibit counter-intuitive situations, making it challenging to accurately measure the similarity or difference between FFSs. To address this issue, several similarity and distance measures for FFSs are proposed, inspired by the Tanimoto similarity measure. The properties of the proposed measures are also explored, along with several comparative examples with existing measures for FFSs, which illustrate their superior performance in processing fuzzy information from FFSs. The proposed measures have effectively overcome the counter-intuitive challenges posed by many existing measures and significantly outperforms existing measures in differentiating different FFSs. Furthermore, we demonstrate the practical applicability of the proposed measures in solving pattern recognition, medical diagnosis and multiple-attribute decision-making problems.

The automated transcription of handwritten characters into a legible output is a multi-faceted process with diverse applications. In this paper, a novel approach to optical character recognition (OCR) for handwritten digits is proposed that, in certain components, exceeds current architectures in terms of accuracy, effectiveness, adjustability, temporal efficiency, and/or computational simplicity. This model succeeds in the adoption and enhancement of deprecated or obsolete algorithms across eight steps of image pre-processing—normalization, grayscaling, thresholding/binarization, noise removal, skew-correction, skeletonization/thinning, line separation, and character segmentation. The aforementioned model is evaluated with the use of a Convolutional Neural Network (CNN) leveraging the Balanced eMNIST dataset for training and testing. By suggesting contour-based feature extraction methods as alternatives to pixel-by-pixel iteration, the proposed paradigm demonstrates its capacity to serve as a suitable alternative to current, commonly used algorithms and computational techniques for textual image classification.

RFID based technology innovated a new field of wireless sensing, which has been applied in posture recognition, object localization and the other sensing fields, the existing sensing methods often require tags to be attached to dynamic targets (because RFID signals are more sensitive to moving target), significantly limiting their applications. It is a challenging task to sensing a static target without tag attached in NLOS (Non-Line-of-Sight). We utilized RFID technologies to sense the static foreign objects in agricultural products, and taken metal, rock, rubber and clod as sensing targets that are common in agricultural. By deploying a tag matrices to create a sensing region, we observed the signal variations before and after the appearance of the targets in this sensing region, determined the targets’ positions and their types. Here, we buried the targets in the media of seedless cotton and wheat, and detected static targets with a non-contact method in the NLOS. Researches illustrated that by deploying appropriate tag matrices and adjusting the angle of a single RFID antenna, the matrices signals can be sensitive to the static targets’ positions and their properties,i.e. matrices signals vary with different targets and their positions. Specifically, we achieved a 100% success rate in locating metallic targets, while the success rate for clods was the lowest at 86%. We achieved a 100% recognition rate for the types of all the four objects.

Stroke is a global leading cause of death and disability. Knowledge of related guidelines is crucial for Emergency Department (ED) staff, influencing early diagnosis and timely treatment. We investigated Greek-Cypriot ED healthcare professionals' (nurses and physicians) knowledge in recognizing and managing stroke. A descriptive cross-sectional study spanned November 2019 to April 2020, encompassing four private and seven public EDs in the Republic of Cyprus. The data were collected through a self-reported questionnaire developed by the research team, consisting of 37 questions. Eight questions focused on sociodemographic and employment characteristics, 28 assessed knowledge in stroke recognition and management (each item was equally weighted without deliberate prioritization), and one question addressed self-assessment of knowledge in stroke care. 255 nurses [Response Rate (RR): 74.1%] and 26 physicians (RR: 47.3%) completed the questionnaire. The average correct response rate was 12.9 out of 28 statements (SD: 4.2), with nurses and physicians scoring 12.6 (SD: 4.1) and 15.7 (SD: 4), respectively. Work experience significantly influenced stroke knowledge, with all groups demonstrating superiority over those with less than one year of experience. Participants with previous training scored an average of 1.45 additional correct answers while educational attainment did not significantly influence stroke knowledge. Investigating stroke knowledge among Emergency Department nurses and physicians in the Republic of Cyprus revealed significant deficits. The study stresses targeted interventions, including, education, yearly examinations, workshops with hands-on training, and repeated training, to address these gaps and enhance the overall stroke care capabilities of the healthcare professionals.

Purpose: Understanding how older adults perceive and interpret emotional cues in speech prosody contributes to our knowledge of cognitive aging. This study provides a systematic review with meta-analysis to investigate the extent of the decline in affective prosody recognition (APR) among older adults in terms of overall and emotion-specific performance and explore potential moderators that may cause between-study heterogeneity. Method: Incorporated into the literature search were six electronic databases, with a specific emphasis on studies comparing the APR performance of older adults with that of younger adults. This comparison was focused on basic emotions. Meta-regression analyses were executed to pinpoint potential moderators related to demographic and methodological characteristics. Results: A total of 19 studies were included in the meta-analysis, involving 560 older adults with a mean age of 69.15 years. The findings indicated a substantial negative effect size (g = －1.21). Furthermore, the magnitude of aggregated effect sizes showed a distinct valence-related recognition pattern with positive prosody exhibiting smaller effect sizes. Years of education were found to moderate the overall performance effect estimate while age and gender significantly influenced the effect estimate of happiness. Conclusions: The results confirmed a significant decline in APR ability among older adults, but this decline was unbalanced across basic emotions. Educational level emerged as a significant factor influencing APR ability. Moreover, participants with a higher mean age exhibited notably poorer performance in recognizing happy prosody. These findings underscore the need to further investigate the neurobiological mechanisms for APR decline associated with aging.

The content of this paper is a very significant contribution to the heritage regional reconstruction and conservation interventions. The results about the iconographic analysis of the Early-Renaissance frescoes of St. Leocadia Church, in Chaves, in the north-east of Portugal, were presented for the first time. This paper aims to study facial similarity analysis applied to identification of the personages represented in the 1511-1513 mural paintings of the apse of St. Leocadia Church, in Chaves Municipality (North of Portugal) and those ones in the oil paintings by the Proto-Renaissance Portuguese painter Nuno Gonçalves. In this work, it was explored the feasibility of face recognition technologies in answering many ambiguities concerning Manueline stylistic identity and iconography. A proposal was made to identify the characters, fundamental to the meaning of the frescoes. It has been experimentally proved on 7 characters of St. Leocadia Church’s paintings, in comparison with the referred old master portraits. It was used an in-house trained deep face recognition model to extract facial features from images of 15th and 16th century portraits to compare their degree of similarity. It was undertaken facial similarity analysis of the faces in the formidable portrait gallery of the 15th century Portuguese society represented in the Panels of St. Vicent, which has been subject of national and international research for 130 years. On the other, in the oil painting of St. Peter and St. Paul and Infanta St. Joana, of the same old master. The iconographic interpretation of the mural paintings of St. Leocadia, based in the deep facial features of the images, is plausible: a catechetical purpose; the ritual practices of royal ancestor worship in royal portrait apses of the churches; the Portuguese maritime expansion and the macro-imperial ideology of D. Manuel I.

Machine learning is a fundamental aspect of artificial intelligence that involves the development of algorithms and models that allow computers to learn and make predictions or decisions without explicit programming. With the development of neural networks, back-propagation algorithms and deep learning, machine learning has made breakthroughs in the fields of image recognition, natural language processing and handwriting recognition using machine learning techniques. The advent of deep learning has revolutionized the field of handwriting recognition, using convolutional neural networks, recurrent neural networks, and sequence-to-sequence models to provide solutions that go beyond machine learning methods and significantly improve the accuracy and robustness of handwriting recognition systems. But challenges remain, including the need for large labelled datasets, computational resources and addressing potential biases. As research in deep learning techniques continues to drive handwriting recognition closer towards realisability, machine learning approaches remain at the forefront.

The surface electromyogram (sEMG)--based gesture recognition to the development of intelligent prostheses has emerged as a promising avenue for upper limb amputees. However, the temporal variations in sEMG have rendered recognition models less efficient than anticipated. Cross-session calibration and training data indicate the capacity to reduce this variation. The impact of varying calibration and training data amounts on gesture recognition performance for amputees is still unknown. To assess these effects, we present four datasets for the evaluation of calibration data and examine the impact of training data volume on benchmark performance. Two amputees who had undergone amputations years prior were recruited and seven sessions of data were collected for analysis from each of them. The experimental results show that the calibration data improved the average accuracy per subject by 3.03% and 6.16%, respectively, compared to the baseline results. Moreover, it was found that to collect training data for modeling, boosting the number of training sessions proves more efficient than increasing the number of trials within a single session. Two potentially effective strategies are proposed in light of this research to enhance the cross-session models further. We consider these findings to be of the utmost importance for the commercialization of intelligent prostheses, as they demonstrate the criticality of gathering calibration and cross-session training data, as well as offer effective strategies for maximizing the utilization of the entire dataset.

In this paper, an intelligent blind guide system based on 2D LiDAR and RGB-D camera sensing is proposed, and the system is mounted on the smart cane. The intelligent guide system relies on 2D LiDAR, RGB-D camera, IMU, GPS, Jetson nano B01, STM32 and other hardware. The main advantage of the intelligent guide system proposed by us is that the distance between the smart cane and obstacles can be measured by 2D LiDAR based on Cartographer algorithm, thus achieving Simultaneous localization and mapping (SLAM). At the same time, through the improved yolov5 algorithm, pedestrians, vehicles, pedestrian crosswalks, traffic lights, warning posts, stone piers, tactile paving and other objects in front of the visually impaired can be quickly and effectively identified. Laser SLAM and improved yolov5 obstacle identification tests were carried out inside a teaching building on the campus of Hainan Normal University and on a pedestrian crossing on Longkun South Road in Haikou City, Hainan Province. The results show that the intelligent guide system developed by us can drive the wheels and omnidirectional wheels at the bottom of the smart cane, and give the smart cane a self-leading blind guide function like a "guide dog", which can effectively guide the visually impaired to avoid obstacles and reach the predetermined destination, and can quickly and effectively identify the obstacles on the way out. The laser SLAM speed of this system is 25~31FPS, which can realize the short-distance obstacle avoidance and navigation function both in indoor and outdoor envionments. The improved yolov5 helps to identify 86 types of objects, the recognition rate for pedestrian crosswalks and for vehicles are 84.6% and 71.8%, respectively; the overall recognition rate for 86 types of objects is 61.2%, and the obstacle recognition rate of the intelligent guide system is 25-26FPS.

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Auto-mated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with mean intersection over union (IoU) of 0.93, and mean dice coefficient of 0.96, on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.

The Centers for Disease Control and Prevention (CDC) indicates that individuals with prediabetes are significantly less likely to develop type 2 diabetes if they participate in a lifestyle change program that results in at least 5% weight loss and 150 minutes of physical activity per week. The CDC recognizes distance learning as an effective delivery mode for lifestyle change programs to prevent type 2 diabetes. The purpose of this study was to assess enrollment, engagement, and effectiveness of a type 2 diabetes prevention program (DPP) using synchronous distance technology. Eat Smart, Move More, Prevent Diabetes (ESMMPD) is an intensive 12-month DPP delivered using synchronous distance technology. Throughout 26 lessons, participants focused on healthy eating, physical activity, and mindfulness behaviors. Study findings showed a significant decrease in A1C (-0.24 p<.0001). Weight loss averaged 5.66% for those who completed the program. Based on the Wilcoxon signed-rank test, participants demonstrated statistically significant changes in self-reported confidence in their ability to perform all 18 health-promoting behaviors assessed (p<.0001). Participation in the program also resulted in the adoption of health promoting behaviors. A DPP using synchronous distance technology is an effective delivery mode to help participants adopt healthy behaviors, increase physical activity, and achieve the weight loss necessary to prevent or delay the onset of type 2 diabetes.

Chinese calligraphy, revered globally for its therapeutic and mindfulness benefits, encompasses styles such as Regular (Kai Shu), Running (Xing Shu), Official (Li Shu), and Cursive (Cao Shu) scripts. Beginners often start with Regular script, advancing to more intricate styles like Cursive. Each style, marked by unique historical calligraphers' contributions, requires learners to discern distinct nuances. The integration of AI in calligraphy analysis, collection, recognition, and classification are pivotal. This study introduces an innovative Convolutional Neural Network (CNN) architecture, pioneering the application of CNN in the classification of Chinese calligraphy. Focusing on the four principal calligraphers' styles from the Tang dynasty (690-907 A.D), this research spotlights the era when the traditional regular script font (Kai Shu) was refined. A comprehensive dataset of 8282 samples from these calligraphers, representing the zenith of regular style, was compiled for CNN training and testing. The model distinguishes personal styles for classification, showing superior performance over existing networks. Achieving 89.5-96.2% accuracy in calligraphy classification, our approach underscores the significance of CNN in both font and artistic style categorization. This research paves the way for advanced studies in Chinese calligraphy and its cultural implications.

Nowadays, the combination of fingerprinting methodology with friendly environmental and economical analytical instrumentation are becoming increasingly relevant in the food sector. In this study, a highly versatile portable analyser based on Spatially Offset Raman Spectroscopy (SORS) to obtain the edible vegetable oils (sunflower and olive oils) fingerprints was used to evaluate the capability of such fingerprints, obtained quickly, reliable and without any sample treatment, to discriminate/classify the analysed samples. After data treatment, not only HCA and PCA as unsupervised pattern recognition techniques but also SVM, kNN and SIMCA as supervised pattern recognition techniques, showed that the main effect over the discrimination/classification was associated to those regions of RAMAN fingerprint related to the free fatty acids content, especially oleic and linoleic acid. These facts allowed the discrimination attending to the original raw material used in the oil's elaboration. In all the model established, reliable qualimetric parameters were obtained.

Augmented reality (AR) provides an opportunity for mobile fitness applications to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user’s current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of activities of daily living. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning methods commonly used in HAR. On our data set, all CNN architectures significantly outperformed traditional machine learning methods, reaching up to 97.14±1.36% classification accuracy on the test set for ResNet. Whereas a reduced input data size invariably led to a performance loss, removing specific sensors improved the performance of all CNN architectures, with our Scaling-FCN reaching the highest accuracy of 99.86±0.11%. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively.

Human-to-human communication via the computer is mainly done using a keyboard or microphone. In the field of Virtual Reality (VR), where the most immersive experience possible is desired, the use of a keyboard contradicts this goal, while the use of a microphone is not always desirable (e.g. silent commands during task force training) or simply not possible (e.g. if the user has a hearing loss). Data gloves help to increase immersion within the VR as they correspond to our natural interaction. At the same time, they offer the possibility to accurately capture hand shapes, such as those used in non-verbal communication (e.g. thumbs up, okay gesture, ...) and in sign language. In this paper, we present a hand shape recognition system using Manus Prime X data gloves, including data acquisition, data preprocessing, and data classification to enable nonverbal communication within VR. We investigate the impact on accuracy and classification time of using an Outlier Detection and a Feature Selection approach in our data preprocessing. To obtain a more generalized approach, we also studied the impact of artificial Data Augmentation, i.e., we create new artificial data from the recorded and filtered data to augment the training dataset. With our approach, 56 different hand shapes could be distinguished with an accuracy of up to 93.28%. With a reduced number of 27 hand shapes, an accuracy of up to 95.55% could be achieved. Voting Meta-Classifier (VL2) has proven to be the most accurate, albeit slowest, classifier. A good alternative is Random Forest (RF), which was even able to achieve better accuracy values in a few cases and was generally somewhat faster. Outlier Detection has proven to be a effective approach, especially in improving classification time. Overall, we have shown that our hand shape recognition system using data gloves is suitable for communication within VR.

The importance of radar-based human activity recognition increased significantly over the last two decades in safety and smart surveillance applications due to its superiority towards vision-based sensing in the presence of poor environmental conditions, like illumination, increased radiative heat, occlusion, and fog. An increased public sensitivity for privacy protection, and the progress of cost-effective manufacturing, led to a higher acceptance and distribution. Deep learning approaches proved that the manual feature extraction that relies heavily upon process knowledge can be avoided by its hierarchical, non-descriptive nature. On the other hand, ML techniques based on manual feature extraction provide a robust, yet empirical based approach where the computational effort is comparatively low. This review outlines the basics of classical ML- and DL-based human activity recognition and its advances while taking recent progress of both categories into regard. For every category, state-of-the-art methods are introduced, briefly explained and discussed in terms of their pros, cons and gaps. A comparative study is performed to evaluate the performance and computational effort based on a benchmarking data set to provide a common basis for the assessment of the techniques’ degree of suitability.

Against the backdrop of the current carbon peaking and carbon neutrality policies, higher requirements have been put forward for the upgrading and construction of smart grids. Non-intrusive load monitoring (NILM) technology is a key technology for advanced measurement systems at the end of the power grid. It obtains detailed power information of the load, without the need for traditional hardware deployment. The key step to solve this problem is load decomposition and identification. This paper first utilized Long Short Term Memory-Denoising Autoencoder(LSTM-DAE) to decompose the mixed current signal on the household busbar and obtain the current signals of multiple independent loads that constituted the mixed current. Then, the obtained independent current signals were combined with voltage signals to generate multi-cycle colored Voltage-Current(VI) trajectories, which were color-coded according to the background. These colored VI trajectories with background colors formed a feature library. When the CNN network was used for load recognition, considering the influence of hyperparameters on recognition results, the BOA algorithm was used for optimization, and the optimized CNN network was employed for VI trajectory recognition. Finally, the proposed method was validated using the PLAID dataset. Experimental results showed that the proposed method exhibited better performance in load decomposition and identification.

Due to the recent trend of unmanned economy, retail stores have gradually reduced their service and cashier manpower. The retail product recognition becomes one of key issues for unmanned shopping. Although the success of deep neural networks has made object recognition feasible in a variety of applications, it still struggles to perform well on a large number of classes of retail products. In this paper, we propose an improved ensemble learning-based approach for retail product recognition. In the proposed approach, the object classification network is first improved through feature extraction and block attention. An ensemble model is then built by integrating multiple network models and using loss selection as model weights. In the experiments, the feasibility of our ensemble learning-based approach has been evaluated through many production items. The results demonstrate the effectiveness of the proposed approach compared with previous retail product recognition methods.

Autonomous target recognition (ATR) plays a crucial role in maintaining situational awareness during environmental monitoring. Unmanned aerial vehicles (UAVs) equipped with autonomous target recognition technology can gather and analyze real-time information about targets, including their locations, sizes, and types. However, UAV-captured images in complex real-world environments often display significant variations in perspective and scale due to changes in UAV altitude and distance. Existing methods for autonomous target recognition on UAVs struggle to capture targets from large field-of-view and multi-scale images, resulting in low recognition accuracy and high false-positive rates. This paper introduces two novel Slimmable neural network models, namely SE-YOLOv5s and ST-YOLOv5s, which are based on the YOLOv5s architecture. These models incorporate the Squeeze and Excitation and Swin-Transformer mechanisms to enhance the ability to extract features from large field-of-view and multi-scale images. To evaluate their performance, experiments were conducted on the Visdrone19 aerial dataset. Compared to the state-of-the-art YOLOv5s algorithm, the utilization of SE-YOLOv5s and ST-YOLOv5s for autonomous target recognition on low-altitude drones resulted in improvements in both accuracy and false-positive rates. These proposed methods combine Slimmable neural network design with feature enhancement mechanisms, addressing the challenges posed by complex real-world environments in UAV missions. The advancements in autonomous target recognition on low-altitude drones will significantly contribute to enhancing situational awareness in future environmental monitoring.

Machine learning (ML) systems that use sensors obtain observations from sensors and use them to recognize and interpret the current situation. These systems are susceptible to sensor-based adversarial example attacks (AEs); if some sensors are vulnerable and can be compromised by an attacker, the attacker can change the output of the system by changing the values of the sensors. The detection of compromised sensors is important to defend the system against sensor-based AEs, because we can check the sensors and replace them by detecting the sensors used by the attacker. In this paper, we propose a method to detect the sensors used in sensor-based AEs by utilizing the features of the attack that cannot be avoided. In this method, we introduced a model called the feature-removable model (FRM), which allows us to select the features used as inputs into the model. Our method detects the sensors used in sensor-based AEs by finding the inconsistencies between the outputs of the FRM obtained by changing the selected features. We evaluated our method using a human activity recognition model with sensors attached to the user’s chest, wrist, and ankle. We demonstrate that our method can accurately detect sensors used by the attacker and achieves an average Recall of Detection of 0.92, and the average Precision of Detection is 0.72.

Human violence recognition is an area of great interest in the scientific community, given its broad spectrum of applications, especially in video surveillance systems, since detecting violence in real-time could prevent criminal acts and save lives. Despite the number of existing proposals and research, most focus on the precision of results, leaving aside efficiency and its practical implementation. Thus, this work proposes a model that is effective and efficient in recognizing human violence in real-time. The proposed model consists of three modules: a first module called Spatial Motion Extractor (SME), in charge of extracting regions of interest from a frame; a second module called Short Temporal Extractor (STC), whose function is to extract temporal characteristics of rapid movements, finally the Global Temporal Extractor (GET) module, responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated regarding efficiency, effectiveness, and ability to operate in real-time. The results obtained on Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to other alternatives. A VioPeru dataset was created to validate real-time applicability with violent and non-violent videos captured by real video surveillance cameras in Peru. The effectiveness results in this dataset outperformed the best existing proposal. Therefore, our proposal has contributions in efficiency, effectiveness, and real-time.

Facial expression recognition is crucial for understanding human emotions and nonverbal communication. With the growing prevalence of facial recognition technology and its various applications, accurate and efficient facial expression recognition has become a significant research area. However, most previous methods have focused on designing unique deep-learning architectures while overlooking the loss function. This study presents a new loss function that allows simultaneous consideration of inter- and intra-class variations to be applied to CNN architecture for facial expression recognition. More concretely, this loss function reduces the intra-class variations by minimizing the distances between the deep features and their corresponding class centers. It also increases the inter-class variations by maximizing the distances between deep features and their non-corresponding class centers, and the distances between different class centers. Numerical results from several benchmark facial expression databases, such as Cohn-Kanade Plus, Oulu-Casia, MMI, and FER2013, are provided to prove the capability of the proposed loss function compared with existing ones.

This article provides a general overview of the bio-inspired computing method called DNA-Based Computing (DBC), including its theory and applications. The main theme of DBC is the central dogma of molecular biology (once information of DNA/RNA has got into a protein, it can’t get out again), i.e., DNA to RNA (sequences of four types of nucleotides) and DNA/RNA to protein (sequence of twenty types of amino acids) are allowed, not the reverse ones. Thus, DBC transfers few-element information (DNA/RAN-like) to many-element information (protein-like), solving a given cognitive problem. DBC can take many forms; this article elucidates two main forms, denoted as DBC-1 and DBC-2. Using arbitrary numerical examples, it is shown that DBC-1 can solve the following cognitive problems: “similarity indexing between seemingly different but inherently identical objects” and “recognizing regions of an image separated by a complex boundary.” DBC-2 can solve the following cognitive problem: “pattern recognition when the relevant information is insufficient.” Smart manufacturing-based systems (digital twins and big data analytics) must solve the abovementioned problems to make the manufacturing enablers (machine tools and monitoring systems) more self-reliant and autonomous. Consequently, DBC can improve the cognitive problem-solving ability of smart manufacturing-relevant systems and, thereby, can enhance its biologicalization.

Accurate prediction of the degree of airport delays under the influence of convective weather is crucial for collaborative traffic management implementation and improving the efficiency of airport operations. However, existing studies usually only consider numerical-type quantitative features of weather-affected traffic in their models, and lack the introduction of spatial information to comprehensively portray the traffic operation scenarios under the influence of weather. In order to overcome this problem, this paper firstly designs a new image representation of weather-affected air traffic, and constructs a multi-channel traffic and weather scene image (MTWSI) by populating the airspace two-dimensional grid with traffic and meteorological information to represent the overall traffic operation situation in the terminal area under the influence of convective weather; then, a deep convolutional neural network-based airport delay prediction model ( ADLCNN), which takes MTWSI images as input and uses a specific CNN model to extract the deep features that affect traffic operation in it to input into the subsequent classification algorithm to predict the flight delay level; finally, a series of comparative experiments are carried out on the operational data of Guangzhou Baiyun Airport, and the experimental validation shows that, compared with the traditional machine learning methods, the proposed CNN-based airport delay prediction The experimental validation shows that the proposed CNN-based airport delay prediction model has satisfactory prediction performance compared with the traditional machine learning methods, which also proves that the proposed MTWSI method can more comprehensively respond to the real traffic conditions.

An algorithm is proposed for discriminating the fatigue state of air traffic controllers based on ap-plying multispeech feature fusion using an FSVM to voice data, and for extracting eye-fatigue-state discrimination features based on PERCLOS eye data. For the speech algorithm and an eye-fatigue index, a new controller fatigue-state evaluation index based on the entropy weight method is proposed based on decision-level fusion of fatigue discrimination results for speech and the eyes. Experimental results show that the fatigue-state recognition accuracy rate was 84.81% for the fatigue state evaluation index, which was 3.36% and 1.86% higher than those for speech and eye assessments, respectively. The comprehensive fatigue evaluation index provides important reference values for controller scheduling and mental-state evaluations.

The water resources carrying capacity (WRCC) system comprises multiple complex and nonlinear interactions related to society, economy, water resources and the water environment. A full understanding of its internal mechanism is conducive to the further improvement of the regional WRCC. This article focuses on the temporal and spatial variability of WRCC to explore a method of dynamic successive assessment. Firstly, the Pressure-State-Response (PSR)framework is used to develop a systematic and causal indicator system. Then, The Variable Fuzzy Pattern Recognition (VFPR) model and an analytic hierarchy process-entropy (AHP-E) model are combined to successively and dynamically assess WRCC. The proposed method is applied to the dynamic successive assessment of WRCC in Hebei Province, and it is obtained that the poor water resources carrying capacity in Hebei Province is mainly due to the basic attribute of the decision of the water resources shortage, but Hebei Province actively adopts a variety of measures to save water and pressurize mining, which makes the province's water resources carrying capacity have a tendency to become better gradually. At the same time, the system dynamics model (SD) of water resources carrying capacity based on the analysis of the model structure was established. Moreover, three scenarios were designed, including existing continuation, high-efficiency water-saving, cross-regional water transfer and coordinated development, each scenario divided into high and low-speed economic development and population growth schemes, then total 6 schemes between 2023 and 2030 were simulated and predicted respectively. The results indicate that if the current development model is adopted, the water resource carrying capacity will continue to maintain low levels. It was concluded that the high-speed development of economy and population, the efficient water conservation and inter-basin transfer scenario (scenario 2 with high-speed) is the best choice for sustainable development of water resources and social economy in Hebei.

Human activity recognition (HAR) using wearable sensors is gaining popularity in the healthcare domain, enabling continuous monitoring and timely interventions. The conventional HAR systems are centralised and need data sharing with a server for processing and model training. However, this data sharing leads to various challenges, such as privacy concerns, increased communication and storage costs, inefficient computational algorithms, data scarcity due to unwillingness to share, and difficulty achieving high accuracy and personalised models simultaneously. To overcome these challenges, this paper introduces a privacy and energy-aware federated learning (FL) framework for model training without data sharing. The proposed scheme incorporates spiking neural networks (SNNs), which are particularly suited for resource-constrained devices due to their event-driven information processing. The key idea is to synergise the strengths of SNNs and long short-term memory (LSTM) to create a hybrid model for robust HAR. The proposed hybrid spiking LSTM (S-LSTM) model uses the LSTM as an input layer to capture temporal dependencies efficiently, followed by spiking layers that replace the typical activation using leaky integrate-and-fire neurons. We employ the combination of surrogate gradient learning and backpropagation through time (BPTT) to update the weights of SNN layers in a supervised manner. The performance of the proposed model is evaluated using two publicly available datasets for both indoor and outdoor scenarios. The results show that the proposed S-LSTM performs much better than spike convolutional neural networks (S-CNN) and simple CNN, achieving the accuracy of 97% and 87% for indoor and outdoor datasets, respectively. Personalisation, also known as fine-tuning the global model using local data, is crucial in HAR. It allows the model to adapt to individual behaviour and preferences, making predictions more accurate. The results also show that personalisation improves the performance of participants up to 9% on average. Additionally, analysis with 50% random client participation reduces communication costs by 50% with minimal impact on accuracy.

Detecting and understanding emotions is critical for our daily activities. As emotion recognition (ER) systems develop, we start looking at more difficult cases than just acted adult audio-visual speech. In this work, we investigate automatic classification of audio-visual emotional speech of children. Our interest is, specifically, in the improvement of the utilization of the cross-modal relationships between the selected modalities: video and audio. To underscore the importance of developing ER systems for the real-world environment, we present a corpus of children’s emotional audio-visual speech that we collected. We select a state-of-the-art model as a baseline for the purposes of comparison and present several modifications focused on a deeper learning of the cross-modal relationships. By conducting experiments with our proposed approach and the selected baseline model, we observe a relative improvement in performance by 2%. Finally, we conclude that focusing more on the cross-modal relationships may be beneficial for building ER systems for child-machine communications and the environments where qualified professionals work with children.

The precise molecular basis of anti-tumor immunity is not yet fully understood, although commensal Bifidobacterium (c-BIF) is expected to be one of the key players in cancer control via antigenic mimicry. We investigated the sequence similarity between c-BIF and cytotoxic T lymphocyte (CTL) epitope peptides against human tumor-associated antigens to better understand the molecular basis of antigenic mimicry. We used two different similarity analyses for this purpose, a linear sequence analysis and a similarity analysis of T cell receptor (TCR)-mediated recognition of CTL epitope peptides on antigen-presenting cells. The linear sequence analysis revealed 3,900 positive numbers of similarity sites between them with 126 mean per peptide and 107 median per peptide, while the TCR-mediated recognition analysis revealed 5,018 positive numbers with a mean of 162 and median of 132 per peptide. These results demonstrated the existence of durable and abundant sequence similarities between c-BIF and CTL epitope peptides, suggesting that the former play a pivotal in inducing cellular and humoral immunity against the latter in the absence of cancer cells via antigenic mimicry.

A major challenge of augmented and mixed reality applications is identifying the context and semantics of the real environment. Studies on object and action recognition were developed based on the improvement of machine learning techniques, allowing them to be annotated and recognized. This study aims to characterize current knowledge on the use of machine learning for recognizing objects and actions in augmented and mixed reality environments, increasing context awareness. Therefore, a systematic literature review of works related to these topics was made, using the Scopus and Web of Science knowledge bases. We searched articles and conference reviews or papers published between 2018 and 2022 and selected fifteen studies to be reviewed. The results indicate that there is a great demand for using machine learning to immersive technologies in factories, engineering, entertainment, education, health, among other application domains. However, these real-time interactive systems still have challenges and limitations to be solved, involving network communication, prediction time and the creation of a model that recognize objects and actions in broad contexts. Furthermore, additional research is needed to investigate how object and action recognition can increase context awareness in augmented reality applications.

Voice search technology has gained popularity in recent years, transforming the way individuals interact with digital devices. This study aims to explore the sustainable use intention of voice search, focusing on the psychological factors that influence new technology adoption. Using the Technology Acceptance Model (TAM) and anthropomorphism theory, it provides insights for developers, marketers, and policymakers interested in voice search technology. Through an online survey targeting experienced voice search users in the U.S., the study examines the impact of TAM factors (perceived usefulness, ease of use, quality satisfaction) and anthropomorphism traits (narcissism, Machiavellianism) on sustainable use intention of voice search. Results from hierarchical regression analysis show that perceived usefulness, ease of use, and quality satisfaction positively affect sustainable intention of voice search. Additionally, narcissism and Machiavellianism predict sustainable intention of voice search. By merging TAM and anthropomorphism theory, this study enhances our understanding of voice search behavior and technology adoption.

A multitude of factors influence our well-being and health in everyday life. Some of which we are totally aware like a delayed train, car exhausts, or continuous work stress. Other factors influence us on a subconscious level, making them, however, not less important to address. One of these factors is the built environment surrounding us almost every second of our lives. The idea of biophilic design states the importance of natural elements implemented in architectural structures to improve the occupants’ health and well-being. Adding to this field of research, this article targets the impact of biophilic design on positive emotions and productivity by using novel approaches like Facial Emotion Recognition (FER) with Residual Masking Networks, and sentiment detection using Large Language Models. Two separate but related studies were conducted and their results reported here. The first study measured emotions of people when confronted with images of different kinds of architecture, via FER (Facial Emotion Recognition) and also via a user survey. We distinguish between self-stated emotions entered through a survey by study participants, and emotions detected from studying the participants’ faces through AI from our FER (Facial Emotion Recognition) system. We found clear trends for most detected emotions, and significant evidence for self-stated emotions, that architecture implementing biophilic design evokes more positive emotions than one that does not. The second study measures the influence of natural elements on productivity and team-engagement. We found that natural elements do influence productivity and sentiment positively; however, only the change in sentiment was shown to be significant. As our sample size, especially for the second study, was relatively small, future research will apply these ideas in a larger setup to acquire further evidence for the importance of biophilic design for human well-being and health.

Our image recognition system mainly judges whether the left upper limb in the image is the left upper limb or the right upper limb through our deep learning model in the image. The doctor then could give the correct surgical position. From the experimental results, it could be found that the precision rate and recall rate of the intelligent image recognition system proposed in this paper for preventing the upper limb dislocation surgery could reach 98% and 93%, respectively. It proved that our artificial intelligent image recognition system, AIIRS, could indeed assist orthopedic surgeons to prevent the occurrence of left and right dislocation in upper limb surgery. At the same time, this paper also completes the IRB application approval through the prototype experimental results and will conduct the second phase of human trials in the future. It showed that the research results of this paper will be of great benefit and research value to upper limb orthopedic surgery.

Human Action Recognition is widely used in multiple fields to recognize activities and extract spatial and temporal information. This paper focuses on analyzing various methods as well as provides extensive knowledge of the foundational concepts of the HAR. A dataset is also very crucial for any research study so we discussed the popular dataset and its features in this paper.

This study leverages transformer-based models and focuses on data representation strategies in the named entity recognition task, including "single" (one sentence per vector), "merged" (multiple sentences per vector), and "context" (sentences joined with attention to context). Performance analysis reveals that models trained with a single strategy may not perform well on different data representations. A combined training procedure is proposed to address this limitation, using all three strategies to enhance the stability and adaptability of the model. The results of this approach are presented and discussed for various datasets for four languages (English, Polish, Czech, and German), demonstrating the effectiveness of the combined strategy.

It is a challenging problem that air-written Arabic letters has received a lot of attention in the past decades when compared to commonly spoken languages like English languages. To fill this gap, we propose a strong model that brings together machine learning (ML) and optical character recognition (OCR) methods. The model applied several ML methods, (i.e., Neural Networks (NN), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), with deep convolutional neural networks (CNNs) such as VGG16, VGG19, and SqueezeNet for effective feature extraction. Our study utilizes the AHAWP dataset, which consists of varied writing styles and variations in hand signs, to train and evaluate the model. Preprocessing systems are applied to improve data quality by reduction bias. Besides, OCR methods are combined into our model to sequestrate individual letters from continuous air-written gestures and refine recognition results. Results of this study show that the proposed model has achieved the extreme accuracy of 88.8% using NN with VGG16. This study presents an inclusive approach that combines ML, deep CNNs, and OCR methods to address the issue of Arabic in air writing recognition research.

Purpose: School-age children with autism spectrum conditions (ASC) often experience difficulties in speech-in-noise (SiN) perception, leading to increased listening effort that impacts their well-being and academic performance. This study aimed to investigate the SiN processing challenges faced by Mandarin-speaking children with ASC and its impact on their listening effort. Methods: Participants completed sentence recognition tests in both quiet and noisy conditions, with a steady-state noise masker presented at 0 dB signal-to-noise ratio in the noisy condition. We compared recognition accuracy and task-evoked pupil responses from 23 Mandarin-speaking children with ASC to 19 age-matched neurotypical (NT) counterparts to gauge their behavioral performance and listening effort during these auditory tasks. Results: The ASC group demonstrated notably decreased accuracy in noise compared to their NT peers, suggesting poorer SiN perception. Pupillometric data further revealed significantly larger peak dilations in the ASC group than in the NT group under comparable conditions. Importantly, the ASC group's peak dilation in quiet mirrored the NT group's in noise. However, the ASC group exhibited shorter peak latencies and reduced mean dilations than the NT group in similar conditions. Such patterns indicate the ASC group might initially experience a heightened cognitive load but utilize fewer cognitive resources as the task continued, indicating an atypical allocation of cognitive resources and a potential tendency towards relatively superficial and automated auditory processing. Conclusion: Our findings highlight the unique SiN processing challenges children with ASC face, underscoring the importance of a nuanced, individual-centric approach for interventions and support.

Sea cucumber detection represents a significate step in underwater environmental perception, which is an indispensable part of the intelligent subsea fishing system. However, various complex factors such as water turbidity declines the clarity of underwater images, presenting a challenge to vision-based underwater target detection. Therefore, accurate, real-time and lightweight detection models are required. First of all, the development of subsea target detection is summarized in this presented work. Besides, since target detection methods based on deep learning such as YOLOv5 and DETR, which are respectively examples of one-stage and anchor-free deep leaning methods, have been increasingly applied in underwater detection scenarios. Based on the analysis of state-of-the-art underwater sea cucumber detection approaches and aiming to provide a reference for practical subsea identification, the sea cucumber detection based on the YOLOv5 and DETR are investigated and compared in detail. For each approach, the detection experiment is carried out on the derived dataset which contains a wide variety of sea cucumber sample images. The compared experiments demonstrate that the overall outperformance of YOLOv5 in terms of low computing consumption and high precision, particularly in detection of small and dense features. Nevertheless, the DETR exhibits rapid development and holds promising prospects in underwater object detection applications, owing to its relatively simple architecture and ingenious attention mechanism.

Previous studies to recognize negative emotions (e.g. disgust, fear, sadness) for mental health care have used heavy equipment directly attaching electroencephalogram (EEG) electrodes to the head, making it difficult to use in daily life, and they have proposed binary classification methods to determine whether negative emotion or not. To tackle this problem, we propose a negative emotion recognition system to collect multimodal biosignal data such as five EEG signals in an EEG headset and heart rate, galvanic skin response, and skin temperature in a smart band for classifying multiple negative emotions. It consists of android Internet of Things (IoT) application, an oneM2M-compliant IoT server, and a machine learning server. The android IoT application upload the biosignal data to the IoT server. By using the biosignal data stored in the IoT server, the machine learning server recognizes the negative emotions of disgust, fear, and sadness using a multi-class support vector machine (SVM) model with a radial basis function kernel (RBF). The experimental results showed that the multi-class SVM model achieved 93% accuracy when considering all the multimodal biosignal data. Moreover, when considering only data in the smart band, it could achieve 98% accuracy by optimizing the hyper-parameter of the RBF kernel.

Abstract:The objects of fine-grained image categories(e.g., bird species) are various subclass under different categories. Because the differences between subclass are very subtle and most of them are concentrated in multiple local areas, the task of fine-grained image recognition is very challenging. At the same time, some fine-grained networks tend to focus on a certain region when judging the target category, resulting in the lack of other auxiliary regional features. To this end, Inception V3 is used as the backbone network, and an enhanced and complementary fine-grained image classification network is designed. While adopting the method of reinforcement learning to obtain more detailed fine grain image features, the complementary network can obtain the complementary discriminant area of the target through the method of attention erasure to increase the network's perception of the overall target. Finally, experiments are conducted on CUB-200-2011, FGVC Aircraft and Stanford dogs three open datasets. The experimental results show that the proposed model has better performance.

Sign language recognition is essential in hearing-impaired people’s communication. Sign language recognition is an important concern in computer vision and has been developed with rapid progress in image recognition technology. However, sign language recognition using a general monocular camera has problems with occlusion and recognition accuracy in sign language recognition. In this research, we aim to improve accuracy by using a 2-axis bending sensor as an aid in addition to image recognition. We aim to achieve higher recognition accuracy by acquiring hand keypoint information of sign language actions captured by a monocular RGB camera and adding sensor assist. To improve sign language recognition, we need to propose new AI models. In addition, the amount of dataset is small because it uses the original data set of our laboratory. To learn using sensor data and image data, we used MediaPipe, CNN, and BiLSTM to perform sign language recognition. MediaPipe is a method for estimating the skeleton of the hand and face provided by Google. In addition, CNN is a method that can learn spatial information, and BiLSTM can learn time series data. Combining the CNN and BiLSTM methods yields higher recognition accuracy. We will use these techniques to learn hand skeletal information and sensor data. Additionally, the 2-axis Bending sensor glove data support training AI model. Using these methods, we aim to improve the recognition accuracy of sign language recognition by combining sensor data and hand skeleton data. Our method performed better than using skeletal information, achieving 96.5% accuracy in Top-1.

Speech Emotion Recognition (SER) is an interesting and difficult problem to handle. In this paper, we deal with it through the implementation of deep learning networks. We have designed and implemented six different deep learning networks, a Deep Belief Network (DBN), a simple deep neural network (SDNN), a LSTM network (LSTM), a LSTM network with the addition of an attention mechanism (LSTM-ATN), a Convolutional neural network (CNN), and a Convolutional neural network with the addition of an attention mechanism (CNN-ATN), having in mind, apart from solving the SER problem, to test the impact of attention mechanism to the results. Dropout and Batch Normalization techniques are also used to improve the generalization ability (prevention of overfitting) of the models as well as to speed up the training process. The Surrey Audio-Visual Expressed Emotion database (SAVEE), and the Ryerson Audio-Visual Database (RAVDESS) database were used for training and evaluation of our models. The results showed that networks with the addition of the attention mechanism did better than the others. Furthermore, they showed that CNN-ATN was the best among tested networks, achieving an accuracy of 74% for the SAVEE and 77% for the RAVDESS dataset, and exceeded existing state-of-the-art systems for the same datasets.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

This paper proposes a position recognition method for the receiver coil by the secondary coil current. Based on the practical value of the current of the receiver coil, the position recognition of the receiver coil in the WPT system is realized. This paper proposes a 3×3 array multi-transmitter coil grouping and control logic. The mathematical model of mutual inductance between the receiver and transmitter coil at different positions on the X-Y plane is established. A method for identifying the position of the receiver coil according to the current of the receiver coil is proposed. Compared with the traditional position recognition method of the receiver coil, this method does not need to add a detection coil and position sensor and can realize the position recognition of the receiver coil on the 2D plane.

Macrolide antibiotics, effective antimicrobial agents, are intensively used in human and veterinary medicine as well as in agriculture and therefore are found all over the world as environmental pollutants, harming sensitive eco-community organisms and provoking the selection of resistant forms. A novel azithromycin derivative was synthesized and as a rationally designed hapten conjugate ensured group immunorecognition of 6 major macrolide representatives (105-41%), erythromycin, erythromycin ethylsuccinate, clarithromycin, roxithromycin, azithromycin and dirithromycin in competitive immunoassay based on anti-clarithromycin antibodies. The heterologous hapten-based ELISA format simultaneously contributed to a 5-fold increase in sensitivity (ERY IC50 = 0.04 ng/mL). However, for the detection of trace macrolides in environmental samples, an underexploited in immunoassay field strategy was proposed in the present study to significantly improve the detectability of analytes. Unlike most approaches, it does not require special enhancers/amplifiers or additional concentration/extraction procedures, but only involves a larger volume of test samples. Gradual volume increase of samples (from 0.025 to 10 mL) analyzed in direct competitive ELISA, immunobeads, and immunofiltration assay formats based on the same reagents resulted in a significant improvement (more than 50-fold) in assay sensitivity and detection limit up to 5 and 1 pg/mL, respectively. The suitability of the test for detecting macrolide contamination of natural water was confirmed by recovery of macrolides from spiked blank samples (71.7-141.3%). A series of natural water samples from Lake Onega and its influents near Petrozavodsk were analyzed during a 2022-2023 using both the developed immunoassay and HPLC-MS/MS and revealed no macrolide antibiotic contamination.

Convolution, recurrent and attention-based deep learning techniques have produced the most recent state-of-the-art results in multiple sensor-based human activity recognition (HAR) datasets. However, these techniques have high computing costs, restricting their use in low-powered devices. Different methods have been employed to increase the efficiency of these techniques; however, this often results in worse performance. Recently, pure MLP architectures have demonstrated competitive performance in vision-based tasks with lower computation costs than other deep-learning techniques. The MLP-Mixer is a pioneering pure MLP architecture that produces competitive results with state-of-the-art models in computer vision tasks. This paper shows the viability of the MLP-Mixer in sensor-based HAR. Furthermore, experiments are performed to gain insight into the Mixer modules essential for HAR, and a visual analysis of the Mixer’s weights is provided, validating the Mixer’s learning capabilities. As a result, the Mixer achieves an F1 score of 97%, 84.2%, 91.2% and 90% on the PAMAP2, Daphnet Gait, Opportunity Gestures and Opportunity Locomotion datasets, respectively, outperforming state-of-the-art models in all datasets except Opportunity Gestures.

This research aims to thoroughly understand the delicate interplay between stakeholders' perspectives, biometric data protection policies, and the deployment of face recognition technologies in Indonesia's dynamic digital world. Adopting a qualitative methodology, the study conducts Focus Group Discussions (FGDs) with various stakeholders, including government agencies, technology developers, regulatory agencies, civil society groups, and data subjects as end-users. Face-to-face group discussions facilitate an in-depth exploration of participants' perspectives, yielding rich qualitative data that reveals nuanced insights into the delicate balance between technological innovation, ethical considerations, and socioeconomic repercussions associated with implementing face recognition technology. The research comprehensively explains the difficulties and opportunities associated with responsible technological progress and biometric data security. The findings from the FGDs influence the development of strategies that effectively balance technical advancement with individual rights, privacy, and social well-being within the growing digital landscape of Indonesia. The regulatory function of the government seeks to bridge the gap between public expectations and technological advancements. Collaboration between academic institutions, government agencies, the private sector, and data subjects as end-users emerges as a crucial element, fostering an all-encompassing strategy integrating research, law, technology deployment, and user empowerment. This holistic approach is necessary to ensure that biometric data and facial recognition technology are utilized responsibly, thereby laying the way for Indonesia's technologically sophisticated and ethically aware digital future.

Recently, deep learning models have been widely applied to modulation recognition, which have become a hot topic due to their excellent end-to-end learning capabilities. However, current methods are mostly based on uni-modal inputs, which suffer from incomplete information and local optimization. To complement the advantages of different modalities, we focus on the multi-modal fusion method. Therefore, we introduce an iterative dual-scale attentional fusion (iDAF) method to integrate multimodal data. Firstly, two feature maps with different receptive field sizes are constructed using local and global embedding layers. Secondly, the feature inputs are iterated into the Iterative Dual Scale Attention Module (iDCAM), where the two branches capture the details of high-level features and the global weights of each modal channel, respectively. The iDAF not only extracts the recognition characteristics of each specific domains, but also complements the strengths of different modalities to obtain a fruitful view. Our iDAF achieves a recognition accuracy of 93.5\% at 10dB and 0.6232 at full SNR. The comparative experiments and ablation studies effectively demonstrate the effectiveness and superiority of the iDAF.

Our image recognition system mainly judges whether the left upper limb in the image is the left upper limb or the right upper limb through our deep learning model in the image. The doctor then could give the correct surgical position. From the experimental results, it could be found that the precision rate and recall rate of the intelligent image recognition system proposed in this paper for preventing the upper limb dislocation surgery could reach 98% and 93%, respectively. It proved that our intelligent image recognition system could indeed assist orthopedic surgeons to prevent the occurrence of left and right dislocation in upper limb surgery. At the same time, this paper also completes the IRB application approval through the prototype experimental results and will conduct the second phase of human trials in the future. It showed that the research results of this paper will be of great benefit and research value to upper limb orthopedic surgery.

Emotion recognition and social inference impairments are well-documented post-traumatic brain injury (TBI) yet the mechanisms underpinning these are not fully understood. We examined dynamic emotion recognition, social inference abilities, and eye fixation patterns between adults with and without TBI. Eighteen individuals with TBI and 18 matched non-TBI participants were recruited and underwent all three components of The Assessment of Social Inference Test (TASIT). The TBI group were less accurate in identifying emotions compared to the non-TBI group. Individuals with TBI also scored lower when distinguishing sincere and sarcastic conversations but scored similarly to those without TBI during lie vignettes. Finally, those with TBI also had difficulty understanding the actor’s intentions, feelings, and beliefs compared to participants without TBI. No group differences were found for eye fixation patterns and there were no associations between fixations and behavioural accuracy scores. This conflicts with previous studies and might be related to an important distinction between static and dynamic stimuli. Visual strategies appeared goal- and stimulus-driven, with attention being distributed to the most diagnostic area of the face for each emotion. These findings suggest that low-level visual deficits may not be modulating emotion recognition and social inference disturbances post-TBI.

Recognizing highly occluded objects is believed to arises from the interaction between the brain's vision and cognition controlling areas, although supporting neuroimaging data is currently limited. To explore the neural mechanism during this activity, we conducted an occlusion object recognition experiment using functional magnetic resonance imaging (fMRI). During magnet resonance examinations, 66 subjects engaged in object recognition tasks with three different occlusion degrees. Generalized linear model (GLM) analysis showed that the activation degree of occipital lobe (inferior occipital gyrus, middle occipital gyrus, and occipital fusiform gyrus) and dorsal anterior cingulate cortex (dACC) was related to the occlusion degree of the objects. Multivariate pattern analysis (MVPA) further unearthed a considerable surge in classification precision when dACC activation was incorporated as a feature. This suggested the combined role of dACC and occipital lobe in occluded object recognition tasks. Moreover, psychophysiological interaction (PPI) analysis disclosed that functional connectivity (FC) between the dACC and the occipital lobe was enhanced with increased occlusion, highlighting the necessity of FC between these two brain regions in effectively identifying exceedingly occluded objects. In conclusion, these findings contribute to understanding the neural mechanisms of highly occluded objects recognition, augmenting our appreciation of how the brain manages incomplete visual data.

New ideas on the framework of Neutrosophic SuperHyperGraph for different styles of Neutrosophic SuperHyper-Bipartite and Neutrosophic SuperHyper-Path are introduced. More instances and more clarifications alongside sufficient references.

This study focuses on the impact of weak partial discharges (PDs) on defect recognition accuracy in epoxy resin through phase-resolved partial discharge (PRPD) analysis. Two measurement conditions are compared until PRPD pattern saturation: one-minute and one-hour durations. The PD data specifically target three void types located at different positions within the epoxy material. The aim is to evaluate how the presence of weak PDs at the PD extinction voltage (PDEV) influences defect recognition accuracy. This research sheds light on the potential implications of neglecting the significance of weak PD signals in defect detection. A convolutional neural network (CNN) model is trained using PRPD data recorded at the PD inception voltage (PDIV) and tested using the new PRPD data from both conditions recorded from a lower PDIV to a PDEV. The trained CNN model achieves a defect recognition accuracy of 100% for a one-hour duration, highlighting the importance of not neglecting weak PD signals. This emphasizes the significance of extended measurement duration and pattern saturation in capturing and analyzing weak PD signals for improved defect recognition. This study contributes to the advancement of practical applications by understanding the behavior of the epoxy material and enhancing defect detection techniques.

It is crucial to select the right machine learning classifier for image classification and face recog-nition. This study examines the effectiveness of four different face recognition classifiers - Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Neural Networks. An analysis of the Large Faces in the Wild (LFW) dataset was carried out using Principal Component Analysis (PCA). Classifiers are rigorously trained and evaluated based on the extracted features. Comparison of classifier performance is an insightful way to figure out their strengths and weaknesses. Having a visual representation of the classifier's performance gives a complete understanding of its capabilities. Through the selection of the most appropriate classifier, study results contribute to advancements in image classification, recognition, and biometric identification. The comparison study demonstrated that the Neural Network classifier was exceptionally accurate and proficient in recognizing faces from the LFW dataset when used in conjunction with PCA for feature extraction. According to the comparative analysis, the Neural Network classifier proved exceptionally accurate and proficient at identifying faces from the LFW dataset when combined with PCA for feature extraction.

Issues of fairness and consistency in Taekwondo poomsae evaluation have emerged owing to the lack of an objective evaluation method. This study proposes a three-dimensional (3D) convolutional neural network (CNN)-based action recognition model for the objective evaluation of Taekwondo poomsae. The model exhibits robust recognition performance regardless of variation in perspective by reducing the discrepancies between training and test images. The model uses 3D skeletons of the poomsae unit action collected using a full-body motion-capture suit to generate synthesized two-dimensional (2D) skeletons from the desired perspective. This approach aids in obtaining 2D skeletons from diverse perspectives as part of the training dataset and ensures consistent recognition performance regardless of the viewpoint. The model was trained using 2D skeletons projected from diverse viewpoints, and its performance was evaluated using various test datasets, including projected 2D skeletons and RGB images captured from various viewpoints. Comparison of the performance of the proposed model with that of previously reported action recognition models demonstrated the superiority of the model, underscoring its effectiveness in recognizing and classifying Taekwondo poomsae actions.

Identification of plants is a challenging task which aims to identify the family, genus, and species level according to morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users to narrow down the possibilities. However, numerous morphological similarities between and within species make the classification difficult. In this paper, we tested a custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88K and 16K images for classifying plants at genus and species levels respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. The ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. ViT models also perform better for classifying plants at the species level compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success.