Search

Google Scholar has been a widely used platform for academic performance evaluation and citation analysis. The issue about the mis-configuration of author profiles may seriously damage the reliability of the data, and thus affect the accuracy of analysis. Therefore, it is important to detect the mis-configured author profiles. Dealing with this issue is challenging because the scale of the dataset is large and manual annotation is time-consuming and relatively subjective. In this paper, we first collect a dataset of Google Scholar's author profiles in the field of computer science and compare the mis-configured author profiles with the reliable ones. Then, we propose an integrated model that utilizes machine learning and node embedding to automatically detect mis-configured author profiles. Additionally, we conduct two application case studies based on the data of Google Scholar, i.e., outstanding scholar searching and university ranking, to demonstrate how the improved dataset after filtering out the mis-configured author profiles will change the results. The two case studies validate the importance and meaningfulness of the detection of mis-configured author profiles. [ABSTRACT FROM AUTHOR]

Neuronal models have remained an important area of research in computer science. The dendritic neuron model (DNM) is a novel neuronal model in recent years. Previous studies have focused on training DNM using more appropriate algorithms. This paper proposes an improvement to DNM based on the activity of excitation and proposes three new models. Each of the three improved models are designed to mimic the excitation and inhibition activity of neurons. The improved model proposed in this paper is shown to be effective in the experimental part. All three models and original DNM have their own strengths, so it can be considered that the new model proposed in this paper well enriches the diversity of neuronal models and contributes to future research on networks models. [ABSTRACT FROM AUTHOR]

Plant phenotyping studies the complex characteristics of plants, with the aim of evaluating and assessing their condition and finding better exemplars. Recently, a new branch emerged in the phenotyping field, namely, high-throughput phenotyping (HTP). Specifically, HTP exploits modern data sampling techniques to gather a high amount of data that can be used to improve the effectiveness of phenotyping. Hence, HTP combines the knowledge derived from the phenotyping domain with computer science, engineering, and data analysis techniques. In this scenario, machine learning (ML) and deep learning (DL) algorithms have been successfully integrated with noninvasive imaging techniques, playing a key role in automation, standardization, and quantitative data analysis. This study aims to systematically review two main areas of interest for HTP: hardware and software. For each of these areas, two influential factors were identified: for hardware, platforms and sensing equipment were analyzed; for software, the focus was on algorithms and new trends. The study was conducted following the PRISMA protocol, which allowed the refinement of the research on a wide selection of papers by extracting a meaningful dataset of 32 articles of interest. The analysis highlighted the diffusion of ground platforms, which were used in about 47% of reviewed methods, and RGB sensors, mainly due to their competitive costs, high compatibility, and versatility. Furthermore, DL-based algorithms accounted for the larger share (about 69%) of reviewed approaches, mainly due to their effectiveness and the focus posed by the scientific community over the last few years. Future research will focus on improving DL models to better handle hardware-generated data. The final aim is to create integrated, user-friendly, and scalable tools that can be directly deployed and used on the field to improve the overall crop yield. [ABSTRACT FROM AUTHOR]

Road crack detection is an important indicator of road detection. In real life, it is very meaningful work to detect road cracks. With the rapid development of science and technology, especially computer science and technology, quite a lot of methods have been applied to crack detection. Traditional detection methods rely on manual identification, which is inefficient and prone to errors. In addition, the commonly used image processing methods are affected by many factors, such as illumination, road stains, etc., so the results are unstable. In the research on pavement crack detection, many research studies mainly focus on the recognition and classification of cracks, lacking the analysis of the specific characteristics of cracks, and the feature values of cracks cannot be measured. Starting from the deep learning method in computer science and technology, this paper proposes a road crack detection technology based on deep learning. It relies on a new deep dictionary learning and encoding network DDLCN, establishes a new activation function MeLU, and adopts a new differentiable calculation method. The technology relies on the traditional Mask-RCNN algorithm and is implemented after improvement. In the comparison of evaluation indicators, the values of recall, precision, and F1-score reflect certain superiority. Experiments show that the proposed method has good implementability and performance in road crack detection and crack feature measurement. [ABSTRACT FROM AUTHOR]

Recently, the spread of fake images on social media platforms has become a significant concern for individuals, organizations, and governments. These images are often created using sophisticated techniques to spread misinformation, influence public opinion, and threaten national security. This paper begins by defining fake images and their potential impact on society, including the spread of misinformation and the erosion of trust in digital media. This paper also examines the different types of fake images and their challenges for detection. We then review the recent approaches proposed for detecting fake images, including digital forensics, machine learning, and deep learning. These approaches are evaluated in terms of their strengths and limitations, highlighting the need for further research. This paper also highlights the need for multimodal approaches that combine multiple sources of information, such as text, images, and videos. Furthermore, we present an overview of existing datasets, evaluation metrics, and benchmarking tools for fake image detection. This paper concludes by discussing future directions for fake image detection research, such as developing more robust and explainable methods, cross-modal fake detection, and the integration of social context. It also emphasizes the need for interdisciplinary research that combines computer science, digital forensics, and cognitive psychology experts to tackle the complex problem of fake images. This survey paper will be a valuable resource for researchers and practitioners working on fake image detection on social media platforms. [ABSTRACT FROM AUTHOR]

Emotion analysis is the key technology in human–computer emotional interaction and has gradually become a research hotspot in the field of artificial intelligence. The key problems of emotion analysis based on EEG are feature extraction and classifier design. The existing methods of emotion analysis mainly use machine learning and rely on manually extracted features. As an end-to-end method, deep learning can automatically extract EEG features and classify them. However, most of the deep learning models of emotion recognition based on EEG still need manual screening and data pre-processing, and the accuracy and convenience are not high enough. Therefore, this paper proposes a CNN-Bi-LSTM-Attention model to automatically extract the features and classify emotions based on EEG signals. The original EEG data are used as input, a CNN and a Bi-LSTM network are used for feature extraction and fusion, and then the electrode channel weights are balanced through the attention mechanism layer. Finally, the EEG signals are classified to different kinds of emotions. An emotion classification experiment based on EEG is conducted on the SEED dataset to evaluate the performance of the proposed model. The experimental results show that the method proposed in this paper can effectively classify EEG emotions. The method was assessed on two distinctive classification tasks, one with three and one with four target classes. The average ten-fold cross-validation classification accuracy of this method is 99.55% and 99.79%, respectively, corresponding to three and four classification tasks, which is significantly better than the other methods. It can be concluded that our method is superior to the existing methods in emotion recognition, which can be widely used in many fields, including modern neuroscience, psychology, neural engineering, and computer science as well. [ABSTRACT FROM AUTHOR]

In this paper, a network consisting of an object localization module and a discriminative feature extraction module is designed for fine-grained image retrieval (FGIR). In order to reduce the interference of complex backgrounds, the object localization module is introduced into the network before feature extraction. By selecting the convolutional feature descriptors, the main object is separated from the background, and thus, most of the interference is filtered out. Further, in order to improve the overall performance of the network, a discriminative filter bank is introduced into the network as the local feature detector. Hence, the local discriminative features can be extracted directly from the original feature map. The experimental results based on the CUB-200-2011 and Cars-196 datasets demonstrate that the proposed method can improve the performance of FGIR. [ABSTRACT FROM AUTHOR]

The optimal path problem is an important topic in the current geographic information system (GIS) and computer science fields. The Dijkstra algorithm is a commonly used method to find the shortest path, which is usually used to find the least cost path from a single source. Based on the analysis and research of the traditional Dijkstra algorithm, this paper points out the problems of the Dijkstra algorithm and optimizes it to improve its storage capacity and operation efficiency. Then, combined with the traffic elements, a new network-based optimal path planning method is established. However, the existing network is far from actual operation in terms of the expansion of the transportation network, the uncertainty of the transportation environment, and the differences in the transportation area. Therefore, this paper proposes an optimal transshipment path planning method based on deep learning, which is oriented to multimodal transportation scenarios. This paper mainly introduces the intelligent transportation system and intelligent navigation system, and then conducts in-depth research on optimal path planning. This paper also uses the deep neural network algorithm to optimize the calculation, and finally analyzes its use and application. Simulation experiments were also performed to analyze the relationship between energy consumption, emissions, speed, load cost, and other factors under the optimal path. The final experimental results show that within the range of the emission limit of [100,200], the emission is 50%, the emission is less than 100%, but the emission is higher than 75%. In [100,200], 75% of the loading rate emits no less than 100%. In [200,300], the 50% and 100% emissions are the same. This also means that the emissions are the same but the paths are not necessarily the same. [ABSTRACT FROM AUTHOR]

Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine capable of responding in a manner similar to human intelligence. Research in this area includes robotics, language recognition, image identification, natural language processing, and expert systems. In recent years, the availability of large datasets, the development of effective algorithms, and access to powerful computers have led to unprecedented success in artificial intelligence. This powerful tool has been used in numerous scientific and engineering fields including mineral identification. This paper summarizes the methods and techniques of artificial intelligence applied to intelligent mineral identification based on research, classifying the methods and techniques as artificial neural networks, machine learning, and deep learning. On this basis, visualization analysis is conducted for mineral identification of artificial intelligence from field development paths, research hot spots, and keywords detection, respectively. In the end, based on trend analysis and keyword analysis, we propose possible future research directions for intelligent mineral identification. [ABSTRACT FROM AUTHOR]

Hence, in this Special Issue of I Symmetry i , we invited original research investigating 5G/B5G/6G, deep learning, mobile networks, cross-layer design, wireless sensor networks, cloud computing, edge computing, Internet of Things, software-defined networks, or network security and privacy, which are relevant to Prof. Chao's research fields. Han-Chieh Chao received his MS and PhD degrees in Electrical Engineering from Purdue University, West Lafayette, Indiana, in 1989 and 1993, respectively. Prof. Chao first proposed and established a novel network framework based on the cross-layer design technology for the Taiwan Academic Network (TANet). [Extracted from the article]

Recently, systems have become more flexible and smarter in their implementation and functions. Post-processing involves automatic post editing and the application of various strategies during decoding in the translation process. Park et al. propose a software that can be applied to natural language processing (NLP) by way of pre-processing and post-processing. The purpose of these papers is to share research ideas surrounding algorithm development and data processing and analysis for smart systems. [Extracted from the article]

The explosive growth of the social media community has increased many kinds of misinformation and is attracting tremendous attention from the research community. One of the most prevalent ways of misleading news is cheapfakes. Cheapfakes utilize non-AI techniques such as unaltered images with false context news to create false news, which makes it easy and "cheap" to create and leads to an abundant amount in the social media community. Moreover, the development of deep learning also opens and invents many domains relevant to news such as fake news detection, rumour detection, fact-checking, and verification of claimed images. Nevertheless, despite the impact on and harmfulness of cheapfakes for the social community and the real world, there is little research on detecting cheapfakes in the computer science domain. It is challenging to detect misused/false/out-of-context pairs of images and captions, even with human effort, because of the complex correlation between the attached image and the veracity of the caption content. Existing research focuses mostly on training and evaluating on given dataset, which makes the proposal limited in terms of categories, semantics and situations based on the characteristics of the dataset. In this paper, to address these issues, we aimed to leverage textual semantics understanding from the large corpus and integrated with different combinations of text-image matching and image captioning methods via ANN/Transformer boosting schema to classify a triple of (image, caption1, caption2) into OOC (out-of-context) and NOOC (no out-of-context) labels. We customized these combinations according to various exceptional cases that we observed during data analysis. We evaluate our approach using the dataset and evaluation metrics provided by the COSMOS baseline. Compared to other methods, including the baseline, our method achieves the highest Accuracy, Recall, and F1 scores. [ABSTRACT FROM AUTHOR]

Medical data is frequently quite sensitive in terms of data privacy and security. Federated learning has been used to increase the privacy and security of medical data, which is a sort of machine learning technique. The training data is disseminated across numerous machines in federated learning, and the learning process is collaborative. There are numerous privacy attacks on deep learning (DL) models that attackers can use to obtain sensitive information. As a result, the DL model should be safeguarded from adversarial attacks, particularly in medical data applications. Homomorphic encryption-based model security from the adversarial collaborator is one of the answers to this challenge. Using homomorphic encryption, this research presents a privacy-preserving federated learning system for medical data. The proposed technique employs a secure multi-party computation protocol to safeguard the deep learning model from adversaries. The proposed approach is tested in terms of model performance using a real-world medical dataset in this paper. [ABSTRACT FROM AUTHOR]

Nowadays, Data Science (DS) is gaining a relevant impact on the community. The most recent developments in Computer Science, such as advances in Machine and Deep Learning, Big Data, Knowledge Discovery, and Data Analytics, have triggered the development of several innovative solutions (e.g., approaches, methods, models, or paradigms). It is a trending topic with many application possibilities and motivates the researcher to conduct experiments in these most diverse areas. This issue created an opportunity to expose some of the most relevant achievements in the Knowledge Discovery and Data Science field and contribute to such subjects as Health, Smart Homes, Social Humanities, Government, among others. The relevance of this field can be easily observed by its current achieved numbers: thirteen research articles, one technical note, and forty-six authors from fifteen nationalities. [ABSTRACT FROM AUTHOR]

Medicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19. These datasets were introduced to the combination network that contained deep learning techniques, which were based on a convolutional neural network (CNN) or autoencoder, to extract features and combine them with the next step of the meta-heuristic algorithm in order to select optimal features using the particle swarm optimization (PSO) algorithm. This combination sought to reduce the dimensionality of the datasets while maintaining the original performance of the data. This is considered an innovative method and ensures highly accurate classification results across various medical datasets. Several classifiers were employed to predict the diseases. The COVID-19 dataset found that the highest accuracy was 99.76% using the combination of CNN-PSO-SVM. In comparison, the brain tumor dataset obtained 99.51% accuracy, the highest accuracy derived using the combination method of autoencoder-PSO-KNN. [ABSTRACT FROM AUTHOR]

On the other hand, this study, with supervised machine learning techniques, provided possible features for analysis, some of them different from those used in the statistical study. The introduced gesture recognition method was tested by simulation and real-time gesture recognition experiment. Cognitive science is an interdisciplinary field of investigation of the mind and intelligence. The statistical study concluded that no significant differences were found between participants in solving the crossword puzzle task; significant differences were only detected in the parameters saccade amplitude minimum and saccade velocity minimum. [Extracted from the article]

This article explores the impact of automation on environmental sensing, focusing on advanced technologies that revolutionize data collection analysis and monitoring. The International Union of Pure and Applied Chemistry (IUPAC) defines automation as integrating hardware and software components into modern analytical systems. Advancements in electronics, computer science, and robotics drive the evolution of automated sensing systems, overcoming traditional limitations in manual data collection. Environmental sensor networks (ESNs) address challenges in weather constraints and cost considerations, providing high-quality time-series data, although issues in interoperability, calibration, communication, and longevity persist. Unmanned Aerial Systems (UASs), particularly unmanned aerial vehicles (UAVs), play an important role in environmental monitoring due to their versatility and cost-effectiveness. Despite challenges in regulatory compliance and technical limitations, UAVs offer detailed spatial and temporal information. Pollution monitoring faces challenges related to high costs and maintenance requirements, prompting the exploration of cost-efficient alternatives. Smart agriculture encounters hurdle in data integration, interoperability, device durability in adverse weather conditions, and cybersecurity threats, necessitating privacy-preserving techniques and federated learning approaches. Financial barriers, including hardware costs and ongoing maintenance, impede the widespread adoption of smart technology in agriculture. Integrating robotics, notably underwater vehicles, proves indispensable in various environmental monitoring applications, providing accurate data in challenging conditions. This review details the significant role of transfer learning and edge computing, which are integral components of robotics and wireless monitoring frameworks. These advancements aid in overcoming challenges in environmental sensing, underscoring the ongoing necessity for research and innovation to enhance monitoring solutions. Some state-of-the-art frameworks and datasets are analyzed to provide a comprehensive review on the basic steps involved in the automation of environmental sensing applications. [ABSTRACT FROM AUTHOR]

In computer network security, the escalating use of computer networks and the corresponding increase in cyberattacks have propelled Intrusion Detection Systems (IDSs) to the forefront of research in computer science. IDSs are a crucial security technology that diligently monitor network traffic and host activities to identify unauthorized or malicious behavior. This study develops highly accurate models for detecting a diverse range of cyberattacks using the fewest possible features, achieved via a meticulous selection of features. We chose 5, 9, and 10 features, respectively, using the Artificial Bee Colony (ABC), Flower Pollination Algorithm (FPA), and Ant Colony Optimization (ACO) feature-selection techniques. We successfully constructed different models with a remarkable detection accuracy of over 98.8% (approximately 99.0%) with Ant Colony Optimization (ACO), an accuracy of 98.7% with the Flower Pollination Algorithm (FPA), and an accuracy of 98.6% with the Artificial Bee Colony (ABC). Another achievement of this study is the minimum model building time achieved in intrusion detection, which was equal to 1 s using the Flower Pollination Algorithm (FPA), 2 s using the Artificial Bee Colony (ABC), and 3 s using Ant Colony Optimization (ACO). Our research leverages the comprehensive and up-to-date CSE-CIC-IDS2018 dataset and uses the preprocessing Discretize technique to discretize data. Furthermore, our research provides valuable recommendations to network administrators, aiding them in selecting appropriate machine learning algorithms tailored to specific requirements. [ABSTRACT FROM AUTHOR]

Automated Machine Learning (AutoML) tools are revolutionizing the field of machine learning by significantly reducing the need for deep computer science expertise. Designed to make ML more accessible, they enable users to build high-performing models without extensive technical knowledge. This study delves into these tools in the context of time series analysis, which is essential for forecasting future trends from historical data. We evaluate three prominent AutoML tools—AutoGluon, Auto-Sklearn, and PyCaret—across various metrics, employing diverse datasets that include Bitcoin and COVID-19 data. The results reveal that the performance of each tool is highly dependent on the specific dataset and its ability to manage the complexities of time series data. This thorough investigation not only demonstrates the strengths and limitations of each AutoML tool but also highlights the criticality of dataset-specific considerations in time series analysis. Offering valuable insights for both practitioners and researchers, this study emphasizes the ongoing need for research and development in this specialized area. It aims to serve as a reference for organizations dealing with time series datasets and a guiding framework for future academic research in enhancing the application of AutoML tools for time series forecasting and analysis. [ABSTRACT FROM AUTHOR]

The weld defects inspection from radiography films is critical for assuring the serviceability and safety of weld joints. The various limitations of human interpretation made the development of innovative computer-aided techniques for automatic detection from radiography images an interest point of recent studies. The studies of automatic defect inspection are synthetically concluded from three aspects: pre-processing, defect segmentation and defect classification. The achievement and limitations of traditional defect classification method based on the feature extraction, selection and classifier are summarized. Then the applications of novel models based on learning(especially deep learning) were introduced. Finally, the achievement of automation methods were discussed and the challenges of current technology are presented for future research for both weld quality management and computer science researchers. [ABSTRACT FROM AUTHOR]

Automatic speech recognition, especially large vocabulary continuous speech recognition, is an important issue in the field of machine learning. For a long time, the hidden Markov model (HMM)-Gaussian mixed model (GMM) has been the mainstream speech recognition framework. But recently, HMM-deep neural network (DNN) model and the end-to-end model using deep learning has achieved performance beyond HMM-GMM. Both using deep learning techniques, these two models have comparable performances. However, the HMM-DNN model itself is limited by various unfavorable factors such as data forced segmentation alignment, independent hypothesis, and multi-module individual training inherited from HMM, while the end-to-end model has a simplified model, joint training, direct output, no need to force data alignment and other advantages. Therefore, the end-to-end model is an important research direction of speech recognition. In this paper we review the development of end-to-end model. This paper first introduces the basic ideas, advantages and disadvantages of HMM-based model and end-to-end models, and points out that end-to-end model is the development direction of speech recognition. Then the article focuses on the principles, progress and research hotspots of three different end-to-end models, which are connectionist temporal classification (CTC)-based, recurrent neural network (RNN)-transducer and attention-based, and makes theoretically and experimentally detailed comparisons. Their respective advantages and disadvantages and the possible future development of the end-to-end model are finally pointed out. Automatic speech recognition is a pattern recognition task in the field of computer science, which is a subject area of Symmetry. [ABSTRACT FROM AUTHOR]

Prediction of visual attention is a new and challenging subject, and to the best of our knowledge, there are not many pieces of research devoted to the anticipation of students' cognition when solving tests. The aim of this paper is to propose, implement, and evaluate a machine learning method that is capable of predicting saliency maps of students who participate in a learning task in the form of quizzes based on quiz questionnaire images. Our proposal utilizes several deep encoder–decoder symmetric schemas which are trained on a large set of saliency maps generated with eye tracking technology. Eye tracking data were acquired from students, who solved various tasks in the sciences and natural sciences (computer science, mathematics, physics, and biology). The proposed deep convolutional encoder–decoder network is capable of producing accurate predictions of students' visual attention when solving quizzes. Our evaluation showed that predictions are moderately positively correlated with actual data with a coefficient of 0.547 ± 0.109. It achieved better results in terms of correlation with real saliency maps than state-of-the-art methods. Visual analyses of the saliency maps obtained also correspond with our experience and expectations in this field. Both source codes and data from our research can be downloaded in order to reproduce our results. [ABSTRACT FROM AUTHOR]

In clinical practice, image-based postoperative evaluation is still performed without state-of-the-art computer methods, as these are not sufficiently automated. In this study we propose a fully automatic 3D postoperative outcome quantification method for the relevant steps of orthopaedic interventions on the example of Periacetabular Osteotomy of Ganz (PAO). A typical orthopaedic intervention involves cutting bone, anatomy manipulation and repositioning as well as implant placement. Our method includes a segmentation based deep learning approach for detection and quantification of the cuts. Furthermore, anatomy repositioning was quantified through a multi-step registration method, which entailed a coarse alignment of the pre- and postoperative CT images followed by a fine fragment alignment of the repositioned anatomy. Implant (i.e., screw) position was identified by 3D Hough transform for line detection combined with fast voxel traversal based on ray tracing. The feasibility of our approach was investigated on 27 interventions and compared against manually performed 3D outcome evaluations. The results show that our method can accurately assess the quality and accuracy of the surgery. Our evaluation of the fragment repositioning showed a cumulative error for the coarse and fine alignment of 2.1 mm. Our evaluation of screw placement accuracy resulted in a distance error of 1.32 mm for screw head location and an angular deviation of 1.1° for screw axis. As a next step we will explore generalisation capabilities by applying the method to different interventions. [ABSTRACT FROM AUTHOR]

Definition: Nature is composed of elements at various spatial scales, ranging from the atomic to the astronomical level. In general, human sensory experience is limited to the mid-range of these spatial scales, in that the scales which represent the world of the very small or very large are generally apart from our sensory experiences. Furthermore, the complexities of Nature and its underlying elements are not tractable nor easily recognized by the traditional forms of human reasoning. Instead, the natural and mathematical sciences have emerged to model the complexities of Nature, leading to knowledge of the physical world. This level of predictiveness far exceeds any mere visual representations as naively formed in the Mind. In particular, geometry has served an outsized role in the mathematical representations of Nature, such as in the explanation of the movement of planets across the night sky. Geometry not only provides a framework for knowledge of the myriad of natural processes, but also as a mechanism for the theoretical understanding of those natural processes not yet observed, leading to visualization, abstraction, and models with insight and explanatory power. Without these tools, human experience would be limited to sensory feedback, which reflects a very small fraction of the properties of objects that exist in the natural world. As a consequence, as taught during the times of antiquity, geometry is essential for forming knowledge and differentiating opinion from true belief. It not only provides a framework for understanding astronomy, classical mechanics, and relativistic physics, but also the morphological evolution of living organisms, along with the complexities of the cognitive systems. Geometry also has a role in the information sciences, where it has explanatory power in visualizing the flow, structure, and organization of information in a system. This role further impacts the explanations of the internals of deep learning systems as developed in the fields of computer science and engineering. [ABSTRACT FROM AUTHOR]

The recognition of human activities (HAR) using wearable device data, such as smartwatches, has gained significant attention in the field of computer science due to its potential to provide insights into individuals' daily activities. This article aims to conduct a comparative study of deep learning techniques for recognizing activities of daily living (ADL). A mapping of HAR techniques was performed, and three techniques were selected for evaluation, along with a dataset. Experiments were conducted using the selected techniques to assess their performance in ADL recognition, employing standardized evaluation metrics, such as accuracy, precision, recall, and F1-score. Among the evaluated techniques, the DeepConvLSTM architecture, consisting of recurrent convolutional layers and a single LSTM layer, achieved the most promising results. These findings suggest that software applications utilizing this architecture can assist smartwatch users in understanding their movement routines more quickly and accurately. [ABSTRACT FROM AUTHOR]

Existing zero-shot learning (ZSL) methods typically focus on mapping from the feature space (e.g., visual space) to class-level attributes, often leading to a non-injective projection. Such a mapping may cause a significant loss of instance-level information. While an ideal projection to instance-level attributes would be desirable, it can also be prohibitively expensive and thus impractical in many scenarios. In this work, we propose a variational disentangle zero-shot learning (VDZSL) framework that addresses this problem by constructing variational instance-specific attributes from a class-specific semantic latent distribution. Specifically, our approach disentangles each instance into class-specific attributes and the corresponding variant features. Unlike transductive ZSL, which assumes that unseen classes' attributions are known beforehand, our VDZSL method does not rely on this strong assumption, making it more applicable in real-world scenarios. Extensive experiments conducted on three popular ZSL benchmark datasets (i.e., AwA2, CUB, and FLO) validate the effectiveness of our approach. In the conventional ZSL setting, our method demonstrates an improvement of 12∼15% relative to the advanced approaches and achieves a classification accuracy of 70% on the AwA2 dataset. Furthermore, under the more challenging generalized ZSL setting, our approach can gain an improvement of 5∼15% compared with the advanced methods. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence has become increasingly popular and is more often used by scientists and entrepreneurs. The rapid development of electronics and computer science is conducive to developing this field of science. Man needs intelligent machines to create and discover new relationships in the world, so AI is beginning to reach various areas of science, such as medicine, economics, management, and the power industry. Artificial intelligence is one of the most exciting directions in the development of computer science, which absorbs a considerable amount of human enthusiasm and the latest achievements in computer technology. This article was dedicated to the practical use of artificial neural networks. The article discusses the development of neural networks in the years 1940–2022, presenting the most important publications from these years and discussing the latest achievements in the use of artificial intelligence. One of the chapters focuses on the use of artificial intelligence in energy processes and systems. The article also discusses the possible directions for the future development of neural networks. [ABSTRACT FROM AUTHOR]

RoboCupJunior is a project-oriented competition for primary and secondary school students that promotes robotics, computer science and programing. Through real life scenarios, students are encouraged to engage in robotics in order to help people. One of the popular categories is Rescue Line, in which an autonomous robot has to find and rescue victims. The victim is in the shape of a silver ball that reflects light and is electrically conductive. The robot should find the victim and place it in the evacuation zone. Teams mostly detect victims (balls) using random walk or distant sensors. In this preliminary study, we explored the possibility of using a camera, Hough transform (HT) and deep learning methods for finding and locating balls with the educational mobile robot Fischertechnik with Raspberry Pi (RPi). We trained, tested and validated the performance of different algorithms (convolutional neural networks for object detection and U-NET architecture for sematic segmentation) on a handmade dataset made of images of balls in different light conditions and surroundings. RESNET50 was the most accurate, and MOBILENET_V3_LARGE_320 was the fastest object detection method, while EFFICIENTNET-B0 proved to be the most accurate, and MOBILENET_V2 was the fastest semantic segmentation method on the RPi. HT was by far the fastest method, but produced significantly worse results. These methods were then implemented on a robot and tested in a simplified environment (one silver ball with white surroundings and different light conditions) where HT had the best ratio of speed and accuracy (4.71 s, DICE 0.7989, IoU 0.6651). The results show that microcomputers without GPUs are still too weak for complicated deep learning algorithms in real-time situations, although these algorithms show much higher accuracy in complicated environment situations. [ABSTRACT FROM AUTHOR]

How to design efficient scheduling strategy for different environments is a hot topic in cloud computing. In the private cloud of computer science labs in universities, there are several kinds of tasks with different resource requirements, constraints, and lifecycles such as IT infrastructure tasks, course design tasks submitted by undergraduate students, deep learning tasks and and so forth. Taking the actual needs of our laboratory as an instance, these tasks are analyzed, and scheduled respectively by different scheduling strategies. The Batch Scheduler is designed to process tasks in rush time to improve system throughput. Dynamic scheduling algorithm is proposed to tackle long-term lifecycle tasks such as deep learning tasks which are hungry for GPU resources and have dynamically changing priorities. Experiments show that the scheduling strategies proposed in this paper improve resource utilization and efficiency. [ABSTRACT FROM AUTHOR]

As the Coronavirus Disease 2019 (COVID-19) continues to impact many aspects of life and the global healthcare systems, the adoption of rapid and effective screening methods to prevent the further spread of the virus and lessen the burden on healthcare providers is a necessity. As a cheap and widely accessible medical image modality, point-of-care ultrasound (POCUS) imaging allows radiologists to identify symptoms and assess severity through visual inspection of the chest ultrasound images. Combined with the recent advancements in computer science, applications of deep learning techniques in medical image analysis have shown promising results, demonstrating that artificial intelligence-based solutions can accelerate the diagnosis of COVID-19 and lower the burden on healthcare professionals. However, the lack of large, well annotated datasets poses a challenge in developing effective deep neural networks, especially in the case of rare diseases and new pandemics. To address this issue, we present COVID-Net USPro, an explainable few-shot deep prototypical network that is designed to detect COVID-19 cases from very few ultrasound images. Through intensive quantitative and qualitative assessments, the network not only demonstrates high performance in identifying COVID-19 positive cases, using an explainability component, but it is also shown that the network makes decisions based on the actual representative patterns of the disease. Specifically, COVID-Net USPro achieves 99.55% overall accuracy, 99.93% recall, and 99.83% precision for COVID-19-positive cases when trained with only five shots. In addition to the quantitative performance assessment, our contributing clinician with extensive experience in POCUS interpretation verified the analytic pipeline and results, ensuring that the network's decisions are based on clinically relevant image patterns integral to COVID-19 diagnosis. We believe that network explainability and clinical validation are integral components for the successful adoption of deep learning in the medical field. As part of the COVID-Net initiative, and to promote reproducibility and foster further innovation, the network is open-sourced and available to the public. [ABSTRACT FROM AUTHOR]

The purpose of our bibliometric research was to capture and analyze the trends of two types of well-known classical artificial intelligence (AI) algorithms: neural networks (NNs) and genetic algorithms (GAs). Symmetry is a very popular international and interdisciplinary scientific journal that cover six major research subjects of mathematics, computer science, engineering science, physics, biology, and chemistry which are all related to our research on classical AI algorithms; therefore, we referred to the most innovative research articles of classical AI algorithms that have been published in Symmetry, which have also introduced new advanced applications for NNs and Gas. Furthermore, we used the keywords of "neural network algorithm" or "artificial neural network" to search the SSCI database from 2002 to 2021 and obtained 951 NN publications. For comparison purposes, we also analyzed GA trends by using the keywords "genetic algorithm" to search the SSCI database over the same period and we obtained 878 GA publications. All of the NN and GA publication results were categorized into eight groups for deep analyses so as to investigate their current trends and forecasts. Furthermore, we applied the Kolmogorov–Smirnov test (K–S test) to check whether our bibliometric research complied with Lotka's law. In summary, we found that the number of applications for both NNs and GAs are continuing to grow but the use of NNs is increasing more sharply than the use of GAs due to the boom in deep learning development. We hope that our research can serve as a roadmap for other NN and GA researchers to help them to save time and stay at the cutting edge of AI research trends. [ABSTRACT FROM AUTHOR]