The implementation of industrial robots across various sectors has ushered in unparalleled advancements in efficiency, productivity, and safety. This paper explores the domain of semantic trajectory... Show More

The implementation of industrial robots across various sectors has ushered in unparalleled advancements in efficiency, productivity, and safety. This paper explores the domain of semantic trajectory planning in the area of industrial robotics. By adeptly merging physical constraints and semantic knowledge of environments, the proposed methodology enables robots to navigate complex surroundings with utmost precision and efficiency. In a landscape marked by dynamic challenges, the research positions semantic trajectory planning as a linchpin in fostering adaptability. It ensures robots interact safely with their surroundings, providing vital object detection and recognition capabilities. The proposed ResNet model exhibits remarkable classification performance, bolstering overall productivity. The study underscores the significance of this approach in addressing real-world industrial applications while emphasizing accuracy, precision, and enhanced productivity.

In recent years, the internet and smart devices have developed rapidly. Many people no longer rely on newspapers, magazines, or television to receive news. They can see the latest news using... Show More

In recent years, the internet and smart devices have developed rapidly. Many people no longer rely on newspapers, magazines, or television to receive news. They can see the latest news using computers or mobile phones. According to a study by the Taiwan Internet Information Center, nearly 90% of Taiwanese people have used the internet. Many online streaming services have emerged, and people can easily watch movies and TV programs through computers or mobile phones. Hence, some websites use digital copyright management mechanisms to protect videos from being directly downloaded. However, 30% of websites use AES-128 encryption to protect their content. If the key access mechanism is not well protected, the encryption methodology may be useless. Therefore, this paper proposes a cross-platform digital copyright management mechanism for adaptive streaming. With this mechanism, users do not need to download additional applications, as the mechanism implements Web-Assembly language through the browser.

The industrial internet of things (IIoT) necessitates robust cross-domain authentication to secure sensitive on-site equipment data. This paper presents a refined reputation-based lightweight... Show More

The industrial internet of things (IIoT) necessitates robust cross-domain authentication to secure sensitive on-site equipment data. This paper presents a refined reputation-based lightweight consensus mechanism (LRBCM) tailored for IIoT's distributed network structures. Leveraging node reputation values, LRBCM streamlines ledger consensus, minimizing communication overhead and complexity. Comparative experiments show LRBCM outperforms competing mechanisms. It maintains higher throughput as the number of participating nodes increases and achieves a throughput approximately 10.78% higher than ReCon. Moreover, runtime analysis demonstrates LRBCM's scalability, surpassing ReCon by approximately 12.79% with equivalent nodes and transactions. In addition, as a combination of LRBCM, the proposed distributed lightweight authentication mechanism (ELAM) is rigorously evaluated against the security of various attacks, and its resilience is confirmed. Experiments show that ELAM has good efficiency while maintaining high security.

A network intrusion detection method for information systems using federated learning and improved transformer is proposed to address the problems of long detection time and low security and... Show More

A network intrusion detection method for information systems using federated learning and improved transformer is proposed to address the problems of long detection time and low security and accuracy when analyzing massive data in most existing intrusion detection methods. Firstly, a network intrusion detection system is constructed based on a federated learning framework, and the transformer model is used as its universal detection model. Then, the dataset is divided and an improved generative adversarial network is used for data augmentation to generate a new sample set to overcome the influence of minority class samples. At the same time, the new samples are input into the transformer local model for network attack type detection and analysis. Finally, the authors aggregate the detection results of each local model and input them into the Softmax classifier to obtain the final classification prediction results.

The NER task is largely developed based on well-annotated data. However, in many scenarios, the entities may not be fully annotated, leading to serious performance degradation. To address this... Show More

The NER task is largely developed based on well-annotated data. However, in many scenarios, the entities may not be fully annotated, leading to serious performance degradation. To address this issue, the authors propose a robust NER approach that combines a novel PU-learning algorithm and negative sampling. Unlike many existing studies, the proposed method adopts a two-step procedure for handling unlabeled entities, thereby enhancing its capability to mitigate the impact of such entities. Moreover, this algorithm demonstrates high versatility and can be integrated into any token-level NER model with ease. The effectiveness of the proposed method is verified on several classic NER models and datasets, demonstrating its strong ability to handle unlabeled entities. Finally, the authors achieve competitive performances on synthetic and real-world datasets.

Under the premise of ensuring data privacy, traditional network intrusion detection (NID) methods cannot achieve high accuracy for different types of intrusions. A NID method combining transformer... Show More

Under the premise of ensuring data privacy, traditional network intrusion detection (NID) methods cannot achieve high accuracy for different types of intrusions. A NID method combining transformer and federated learning (FedL) is proposed for this purpose. First, a multi-party collaborative learning framework was built based on FedL, which achieved data exchange and sharing. Then, by introducing the self-attention mechanism (AttM) to improve the traditional transformer, it could quickly converge. Finally, an NID model integrating transformer and FedL was constructed by combining DNN, GRU, and an encoder module composed of improved transformer, achieving accurate detection of network intrusion. The proposed NID method was compared with the other three methods. The results show that the proposed method has the highest NID accuracy and F1 score on the NSL-KDD and UNSW-NB15 dataset, with the highest accuracy reaching 99.65% and 89.25%, while the F1 score has the highest accuracy, reaching 99.45% and 88.13%, outperforming the other three comparative algorithms in terms of performance.

Land desertification is the key contradiction restricting the sustainable development of Chinese society. Farmers and herders' behavior in desert management is particularly important for the smooth... Show More

Land desertification is the key contradiction restricting the sustainable development of Chinese society. Farmers and herders' behavior in desert management is particularly important for the smooth development of the desertification control project. Although farmers and herders express willingness, they do not engage in desert management behavior. The research through random sampling survey analyzes survey data from 572 farmers and herders in the Kubuqi Desert region of Inner Mongolia using structural equation modeling and mediation analysis, based on the TPB. The aim is to understand the paradoxical willingness and behavior of farmers and herders to participate in desert management. The study found that farmers and herders' willingness to participate is a crucial factor that influences their behavior. The authors suggest cultivating a sense of ecological responsibility and strengthening ecological education to guide the behavior of farmers and herders towards more sustainable practices.

The traditional multi-modal sentiment analysis (MSA) method usually considers the multi-modal characteristics to be equally important and ignores the contribution of different modes to the final MSA... Show More

The traditional multi-modal sentiment analysis (MSA) method usually considers the multi-modal characteristics to be equally important and ignores the contribution of different modes to the final MSA result. Therefore, an MSA method based on hierarchical adaptive feature fusion network is proposed. Firstly, RoBERTa, ResViT, and LibROSA are used to extract different modal features and construct a layered adaptive multi-modal fusion network. Then, the multi-modal feature extraction module and cross-modal feature interaction module are combined to realize the interactive fusion of information between modes. Finally, an adaptive gating mechanism is introduced to design a global multi-modal feature interaction module to learn the unique features of different modes. The experimental results on three public data sets show that the proposed method can make full use of multi-modal information, outperform other advanced comparison methods, improve the accuracy and robustness of sentiment analysis, and is expected to achieve better results in the field of sentiment analysis.

This study aims to quantify the perception of value and acceptance by citizens of the use of cyber-physical systems (CPS) in transportation systems and smart cities using neurotechnologies. The work... Show More

This study aims to quantify the perception of value and acceptance by citizens of the use of cyber-physical systems (CPS) in transportation systems and smart cities using neurotechnologies. The work has been developed in the main cities of the following Latin American countries: Spain, Ecuador, Colombia, and Argentina. Targeting urban, public transport-using graduates, it assesses CPS in smart cities and user experiences. Triangulating qualitative research and neurotechnology, the study extends the taxonomy of emotional domains. The results indicate that users do not always assign equivalent importance to what they truly feel, and it is noteworthy that the most important factor, both quantitatively and emotionally, is the application of CPS to improve efficiency in public transportation. The implications of these analyses are discussed in the final part of the article with the aim of providing recommendations to policymakers on the key aspects to be considered in the design and development of CPS for use in smart cities.

Traditional deep learning models for text sentiment analysis fail to fully harness the contextual semantic information of aspect nodes or use prior sentiment resources. This paper proposes a dual... Show More

Traditional deep learning models for text sentiment analysis fail to fully harness the contextual semantic information of aspect nodes or use prior sentiment resources. This paper proposes a dual channel sentiment analysis model named M2BERT-BLSTM AA that is based on an enhanced Bidirectional Encoder Representations from Transformers(BERT)and Bidirectional Long short-term memory(BLSTM) model and incorporates a Dual Attention Mechanism. Firstly, an emotional resource database is constructed using existing emotional resources. Secondly, vectors are concatenated following mean and max pooling along the dimension of sentence length. These semantic features mitigate evaluation imbalance.Then the text and sentiment information are encoded separately, using distinct Attention Mechanism(Att-M) to extract contextual relationships and emotional features. The model's Aspect-Based multi-class sentiment prediction accuracies on the three Chinese datasets of Meituan ordering, restaurants, and laptops are 75.2%, 87.5%, and 75%, respectively, showing improved performance on sentiment classification.

Selective attention, essential in discerning visual stimuli, enables the identification of threats such as snakes—a prime evolutionary influence on the human visual system. This phenomenon is... Show More

Selective attention, essential in discerning visual stimuli, enables the identification of threats such as snakes—a prime evolutionary influence on the human visual system. This phenomenon is encapsulated in snake detection theory (SDT), which posits that our ancestors' need to recognize these predators led to specialized perceptual abilities. This investigation utilizes steady-state visual evoked potentials (SSVEP) alongside the random image structure evolution technique, which systematically increases visual clarity through the interpolation of random noise, to probe the neural mechanisms underpinning selective attention, with a focus on serpentine forms. These findings underscore snakes' unique perceptual impact due to their curved forms and scaled textures, crucial for quick recognition—advancing image semantic segmentation and recognition tech.. This is particularly relevant for security and wildlife management, showcasing the evolutionary progression and cognitive prowess of the human visual apparatus.

In recent years, knowledge graph completion (KGC) has garnered significant attention. However, noise in the graph poses numerous challenges to the completion of tasks, including error propagation... Show More

In recent years, knowledge graph completion (KGC) has garnered significant attention. However, noise in the graph poses numerous challenges to the completion of tasks, including error propagation, missing information, and misleading relations. Many existing KGC methods utilize the multi-head self-attention mechanism (MHA) in transformers, which yields favorable results in low-dimensional space. Nevertheless, employing MHA introduces the risk of overfitting due to a large number of additional parameters, and the choice of model loss function is not comprehensive enough to capture the semantic discriminatory nature between entities and relationships and the treatment of RDF indicates that the dataset contains only positive (training) examples, and the error facts are not encoded, which tends to cause overgeneralization.

With the intention of addressing the concern that existing point of interest recommendation methods fail to fully utilize the auxiliary information of the point of interest, from which it is... Show More

With the intention of addressing the concern that existing point of interest recommendation methods fail to fully utilize the auxiliary information of the point of interest, from which it is challenging to extricate a substantial quantity of deeper feature information, a personalized point of interest (POI) recommendation model using Context-Aware Gated Recurrent Unit (CAGRU) and implicit semantic feature extraction was proposed. First, the check-in data is divided into five tags, and the continuous geographical location check-in data and time data are discretized. Then, the CAGRU was used to obtain the POI check-in features. Finally, the time sequence location information, user information and target location information are transformed through the nonlinear activation function to obtain the score of each location in the data set as the next POI location, and the Top-N recommendation is generated through the score. Experiments indicated that the results of the suggested method were better than the comparative methods.

The existing EEG emotion classification methods have some problems, such as insufficient emotion representation and lack of targeted channel enhancement module due to feature redundancy. To this... Show More

The existing EEG emotion classification methods have some problems, such as insufficient emotion representation and lack of targeted channel enhancement module due to feature redundancy. To this end, a novel EEG emotion recognition method (SCLE-2D-CNN) combining scaled convolutional layer (SCLs), enhanced channel module and two-dimensional convolutional neural network (2D-CNN) is proposed. Firstly, the time-frequency features of multi-channel EEG emotional signals were extracted by stacking scl layer by layer. Secondly, channel enhancement module is used to reassign different importance to all EEG physical channels. Finally, 2D-CNN was used to obtain deep local spatiotemporal features and complete emotion classification. The experimental results show that the accuracy of SEED data set and F1 are 98.09% and 97.00%, respectively, and the binary classification accuracy of DEAP data set is 98.06% and 96.83%, respectively, which are superior to other comparison methods. The proposed method has a certain application prospect in the recognition of human mental state.

Table tennis is a popular sport around the world. A key technology in table tennis education and analysis system is reconstructing the trajectory of the fast-moving ball from videos. Typically the... Show More

Table tennis is a popular sport around the world. A key technology in table tennis education and analysis system is reconstructing the trajectory of the fast-moving ball from videos. Typically the table tennis ball is too small and barely visible in the video, making it difficult to be recognized directly by detection models like YOLO. However, table tennis balls usually has obvious motion features, which are usually not found in similar false targets. It inspired the authors to first find all candidate targets and then use the motion features of table tennis ball to select them out. In this article, the authors propose a tree-based algorithm named T-FORT to track the ball and reconstruct its trajectory. Specifically, they consider all the possible objects in a tree-framework, and identify the real target by integrating visual features and moving patterns. The authors conduct a set of experiments on three datasets to evaluate the effectiveness and performance of the proposed algorithm. The experimental results show that the proposed method is more precise than existing algorithms, and is robust in various scenarios.

Aspect-based sentiment analysis is the key to natural language processing, and it focuses on the polarity of emotions associated with specific text aspects. Traditional models that combine text and... Show More

Aspect-based sentiment analysis is the key to natural language processing, and it focuses on the polarity of emotions associated with specific text aspects. Traditional models that combine text and visual data tend to ignore the deeper interconnections between patterns. To solve this problem, the authors propose a multimodal sentiment-oriented analysis (BiCCM-ABSA) model based on bidirectional complementary correlation. The model utilizes text-image synergy through a novel cross-modal attention mechanism to align text with image features. With the transformer architecture, it is not only a simple fusion, but also ensures the complex alignment of multi-modal features and gating mechanisms. Experiments were conducted on the Twitter-15 and Twitter-17 datasets, achieving 69.28 accuracy and 67.54% F1 score, respectively. The experimental results demonstrate the advantages of BiCCM-ABSA, the bidirectional approach of the model and the effective cross-modal correlation set a new benchmark in the field of multimodal emotion recognition, providing insights beyond traditional single-modal analysis.

Gamification in mobile apps has a research gap, given the potential for gamification to enhance user repurchase intention in a mobile commerce context. This research investigates the concept of... Show More

Gamification in mobile apps has a research gap, given the potential for gamification to enhance user repurchase intention in a mobile commerce context. This research investigates the concept of gamified m-commerce platform application through the lenses of customer experience and repurchase intention. The study proposes an empirical model to examine the relationship between hedonic value, utilitarian value, customer experience, and repurchase intention in the context of mobile commerce platform application. It is underscoring the importance of exploring the application of gamified m-commerce platforms and their impact on customer experience and repurchase intention. The findings contribute to the existing body of literature on online retail by offering new insights into the implications of gamified m-commerce platform applications. A quantitative research approach was employed, and an online questionnaire was used to gather data. The collected data from a sample of 270 mobile commerce shoppers was analyzed. The results supported all direct hypothesized associations among variables.

Machine learning is playing an increasingly important role in education. This article examines its potential to bring about transformative change in this field. By using machine learning algorithms... Show More

Machine learning is playing an increasingly important role in education. This article examines its potential to bring about transformative change in this field. By using machine learning algorithms, physical education teachers can gather and analyze data on student performance and behavior. This enables them to create personalized learning experiences that cater to the unique needs of each student. Machine learning can also track and assess student progress, providing educators with valuable insights into the effectiveness of their teaching strategies. Furthermore, it can optimize the design of physical education curricula and assessments, making them more efficient and effective. Additionally, machine learning offers a more objective and accurate approach to evaluating and grading students. This paper discusses the challenges and opportunities associated with integrating machine learning into physical education, including ethical considerations and potential limitations.

The use of contrastive learning (CL) in recommendation has advanced significantly. Recently, some works use perturbations in the embedding space to obtain enhanced views of nodes. This makes the... Show More

The use of contrastive learning (CL) in recommendation has advanced significantly. Recently, some works use perturbations in the embedding space to obtain enhanced views of nodes. This makes the representation distribution of nodes more even and then improve recommendation effectiveness. In this article, the authors provide an explanation on the role of added noises in the embedding space from the perspective of invariant learning and feature selection. Guided by this thinking, the authors devise a more reasonable method for generating random noises and put forward web semantic based robust graph contrastive learning for recommendation via invariant learning, a novel graph CL-based recommendation model, named RobustGCL. RobustGCL, randomly zeros the values of certain dimensions in the noise vectors at a fixed ratio. In this way, RobustGCL can identify invariant and variant features and then learn invariant and variant representations. Tests on publicly available datasets show that our proposed approach can learn invariant representations and achieve better performance.

Restoring the trajectory of a bat from a table tennis match video is critical in analyzing a table tennis technique and conducting statistical analysis. However, directly bat location detection in... Show More

Restoring the trajectory of a bat from a table tennis match video is critical in analyzing a table tennis technique and conducting statistical analysis. However, directly bat location detection in each frame is challenging due to changing shapes caused by varying movement directions and speeds, leading to ambiguity. This paper develops a novel two-stage method. The first stage utilizes YOLO for bat detection in each frame, followed by filtering out erroneous candidate boxes. In the second stage, the authors use a temporal prediction model that integrating human keypoint information and interpolation to reconstruct a complete bat trajectory with minimal errors. The method's effectiveness and performance are evaluated on our video datasets. The evaluation results demonstrate that the proposed method outperforms traditional methods on precision performance metrics. The error screening algorithm improves precision score to nearly 1. In addition, the method has the recall score 22.3% higher than YOLO 's and also 1.4% higher than that of YOLO with cubic spline interpolation.

Enhanced processors empower edge devices like smartphones for human detection, yet their application is constrained by algorithmic efficiency and precision. This paper introduces YOLO-DCNet, a... Show More

Enhanced processors empower edge devices like smartphones for human detection, yet their application is constrained by algorithmic efficiency and precision. This paper introduces YOLO-DCNet, a lightweight neural network detector built upon YOLOv7-tiny. Incorporating a dynamic multi-head structural re-parameterization (DMSR) module within its backbone network enables effective processing of the features utilized in the model. To improve multi-scale feature aggregation, the model integrates a channel information compression and linear mapping (CLM) module into its feature pyramid architecture. Moreover, the optimization of training and inference performance is achieved by employing RepVGG blocks between the main computational modules of the model. Experimental data reveal that the enhanced YOLOv7-tiny model achieves a 31.7% faster inference speed and marginal gains of 0.7% in mAP@0.5 and 0.5% in mAP@0.5:0.95 over the original. This underscores the model's improved performance and applicability for real-time human detection on edge devices across diverse applications.

Consortium contracting is a contracting model that China encourages and advocates. Due to the interest drive, members within the consortium are very prone to negative cooperation and midway... Show More

Consortium contracting is a contracting model that China encourages and advocates. Due to the interest drive, members within the consortium are very prone to negative cooperation and midway withdrawal, which hinders the healthy development of the consortium. Therefore, this paper constructs a game model of EPC consortium cooperation evolution, analyzes the influence of different reward and punishment mechanisms on the cooperation of consortium members, and applies system dynamics to simulation. The results show that under the static reward and punishment and dynamic reward mechanism, the consortium cooperation is not stable; while under the dynamic punishment mechanism and the dynamic reward and punishment mechanism in which the maximum punishment is greater than the maximum reward, the evolution of consortium cooperation is gradually stable and the behavioral strategies are gradually unified. It also puts forward suggestions for measures conducive to stabilizing cooperation, which provide certain reference value for the internal management of consortium members' cooperation.

The large language models based on transformers have shown strong text generation ability. However, due to the need for significant computing resources, little work has been done to generate... Show More

The large language models based on transformers have shown strong text generation ability. However, due to the need for significant computing resources, little work has been done to generate emotional text using language models such as GPT-2. To address this issue, the authors proposed an affective prompt-tuning-based language model (APT-LM) equipped with an affective decoding (AD) method, aiming to enhance emotional text generation with limited computing resources. In detail, the proposed model incorporates the emotional attributes into the soft prompt by using the NRC emotion intensity lexicon and updates the additional parameters while freezing the language model. Then, it steers the generation toward a given emotion by calculating the cosine distance between the affective soft prompt and the candidate tokens generated by the language model. Experimental results show that the proposed APT-LM model significantly improves emotional text generation and achieves competitive performance on sentence fluency compared to baseline models across automatic evaluation and human evaluation.

A model for predicting physical health of college students based on semantic web and deep learning under cloud edge collaborative architecture is proposed to address the issue of most physical... Show More

A model for predicting physical health of college students based on semantic web and deep learning under cloud edge collaborative architecture is proposed to address the issue of most physical health prediction models being unable to fully describe the characteristics of sports performance changes and having large prediction errors. Firstly, the authors design a measurement data analysis system based on cloud edge collaboration architecture to improve data analysis efficiency. Then, they preprocess the data on the edge side, such as missing samples, and extract data features using an equal dimensional dynamic GOM model. Finally, they deploy the RBFNN-SSA model in the cloud center, input the characteristics of each indicator into the model for predictive analysis, and obtain the physical health status of college students. Based on the physical health test data of Hohai University from 2018 to 2021, an experimental analysis was conducted. The results showed that all three intervention measures had significant effects on maintaining and improving the physical health level of college students.

Artificial intelligence (AI) integration, notably in healthcare, has been significant, yet effective implementation in critical areas requires expertise. KoopaML, a previously developed visual... Show More

Artificial intelligence (AI) integration, notably in healthcare, has been significant, yet effective implementation in critical areas requires expertise. KoopaML, a previously developed visual platform, aims at bridging this gap, enabling users with limited AI knowledge to build ML pipelines. Its core is a heuristic-based ML task recommender, offering guidance and contextual explanations. The authors compared the use of KoopaML with two non-expert groups: one with the recommender system enabled and the other without. Results showed KoopaML's intuitiveness benefits all but emphasized that textual guidance doesn't substitute for fundamental ML understanding. This underscores the need for educational components in such tools, especially in critical fields like healthcare. The paper suggests future KoopaML enhancements include educational modules, making ML accessible, and ensuring users develop a solid AI foundation. This is crucial for quality outcomes in sectors like healthcare, leveraging AI's potential through enhanced non-expert user capability.

In response to the critical need for advanced solutions in medical imaging segmentation, particularly for real-time applications in diagnostics and treatment planning, this study introduces SM-UNet.... Show More

In response to the critical need for advanced solutions in medical imaging segmentation, particularly for real-time applications in diagnostics and treatment planning, this study introduces SM-UNet. This novel deep learning architecture efficiently addresses the challenge of real-time, accurate medical image segmentation by integrating convolutional neural network (CNN) with multilayer perceptron (MLP). The architecture uniquely combines an initial convolutional encoder for detailed feature extraction, MLP module for capturing long-range dependencies, and a decoder that merges global features with high-resolution CNN map. Further optimization is achieved through a tokenization approach, significantly reducing computational demands. Its superior performance is confirmed by evaluations on standard datasets, showing interaction times drastically lower than comparable networks—between 1/6 to 1/10, and 1/25 compared to SOTA models. These advancements underscore SM-UNet's potential as a groundbreaking tool for facilitating real-time, precise medical diagnostics and treatment strategies.

The emergency response process consists of methodical and coordinated series of actions and protocols executed by individuals and organizations to proficiently address crises. When planning for... Show More

The emergency response process consists of methodical and coordinated series of actions and protocols executed by individuals and organizations to proficiently address crises. When planning for medical emergencies, it is vital to work with responsive medical organizations to ensure good communication and coordination. Unlike e-government processes, emergency response processes are focused on knowledge and may frequently change as the emergency situation develops. It is important to change the emergency response plan for dynamic situations and the proposed method helps to create a flexible plan for emergency responses. The proposed approach uses a system for organizing knowledge to figure out the needs and the resources essential for an emergency. It helps to identify the organizations to be involved based on their rules for mutual aid and jurisdiction. Experimental analysis shows that the proposed method outperforms Smart-c and DCERP in suggesting a greater number of hospitals during medical emergency and achieves 0.8, 0.9 and 0.9 precision, recall, and f-measure approximately.

Many studies on community detection are mainly based on the similarity in friendship between users. Recent studies have started to explore node contents to identify semantically meaningful... Show More

Many studies on community detection are mainly based on the similarity in friendship between users. Recent studies have started to explore node contents to identify semantically meaningful communities. However, the sentimental interaction information which plays an important role in community detection is often ignored. By analyzing and utilizing the abundant sentimental interaction information, one can not only more precisely identify the communities, but also discover the interesting interactions and conflicts between these communities. Based on this concept, the authors propose a new Community Sentiment Diffusion Detection Model (CSDD), which utilizes sentimental information embedded in forward posts. Furthermore, the authors present an efficient variational algorithm for model inference. The community detection results have been verified on two large Twitter datasets. It is experimentally demonstrated that we can provide a fine-grained view of sentimental interaction between communities and discover the mechanism of sentiment diffusion between communities.

In edge computing scenarios, due to the wide distribution of devices, complex application environments, and limited computing and storage capabilities, their authentication and access control... Show More

In edge computing scenarios, due to the wide distribution of devices, complex application environments, and limited computing and storage capabilities, their authentication and access control efficiency is low. To address the above issues, a secure trusted authentication scheme based on semantic Long Short-Term Memory (LSTM) and blockchain is proposed for IoT applications. The attribute-based access control model is optimized, combining blockchain technology with access control models, effectively improving the robustness and credibility of access control systems. Semantic LSTM is used to predict environmental attributes that can further restrict user access and dynamically meet the minimum permission granting requirements. Experiments show that when the number of certificates is 60, the computational overhead of the proposed method is only 203s, which is lower than other state-of-the-art methods. Therefore, the performance of the proposed schema in information security protection in IoT environments shows promise as a scalable authentication solution for IoT applications.

Fast and accurate segmentation is important for robot judgement, e.g. robot detection, segmentation, and control. Most researchers have focused on deploying lightweight semantic segmentation models... Show More

Fast and accurate segmentation is important for robot judgement, e.g. robot detection, segmentation, and control. Most researchers have focused on deploying lightweight semantic segmentation models into robot services. The problem is that the critical interaction between semantic segmentation and boundaries is ignored. In this chapter, the authors propose a lightweight parallel execution model (EPSSNet) based on semantic flow branch (SFB), edge flow branch (EFB) and self-adapting weighting fusion (SAWF) for mobile robot service projects. The semantic flow branching module is used to obtain accurate object shape features. The boundary constraint module uses multiple convolution and upsampling to distinguish boundary features from semantic features. In order to adaptively fuse boundary features with semantic segmentation features, the SAWF is proposed. It adaptively fuses semantic and boundary features by learning boundary and semantic feature fusion weights. Detailed experimental results on Cityscapes, Pascal VOC 2012 and ADE20k datasets demonstrate the superior performance of our approach.

Depression, a significant psychiatric disorder, affects individuals' physical well-being and daily functioning. This focused analysis provides a comprehensive exploration of contemporary research... Show More

Depression, a significant psychiatric disorder, affects individuals' physical well-being and daily functioning. This focused analysis provides a comprehensive exploration of contemporary research conducted between 2012 and 2023 that delves into the utilization of sophisticated machine learning methodologies aimed at identifying correlates of depression within social media content. Our study meticulously dissects various data sources and performs a comprehensive examination of different machine learning algorithms cited in the researched articles and literature, aiming to pinpoint an approach that can enhance detection accuracy. Furthermore, we have scrutinized the use of varied data from social media platforms and pinpointed emerging trends, notably spotlighting novel applications of artificial neural networks for image processing and classification, along with advanced gait image models. Our results offer essential direction for future research focused on enhancing detection precision, acting as a valuable reference for academic and industry scholars in this field.

In recent years, smart contracts have risen rapidly in the blockchain field, but security issues have also become increasingly prominent. Due to the lack of unified evaluation standards, the... Show More

In recent years, smart contracts have risen rapidly in the blockchain field, but security issues have also become increasingly prominent. Due to the lack of unified evaluation standards, the security analysis of smart contracts mainly relies on complex and not easily scalable expert rules. To address these issues, we employ slicing techniques to reduce the interference of extraneous code on the detection process, apply normalisation techniques to eliminate the differences between different compiler versions and use particle swarm optimisation algorithms to determine the similarity between contracts, thus improving the accuracy and efficiency of detection. In addition, we combine a variety of features such as static analysis, dynamic analysis and symbolic execution to gain a more comprehensive understanding of contract characteristics and behaviours for more accurate vulnerability identification. Experimental results show that the scheme significantly improves the detection capability and provides a new solution for the security detection of smart contracts.

To ensure the quality of semantic communication, an optimization scheme for multiple-input and multiple-output (MIMO) antenna design using in semantic-based mobile is proposed and verified. The... Show More

To ensure the quality of semantic communication, an optimization scheme for multiple-input and multiple-output (MIMO) antenna design using in semantic-based mobile is proposed and verified. The scheme is based on a modified algorithm MOEA/D-BH, which integrates the black-hole (BH) algorithm into multi-objective EA based on decomposition (MOEA/D). By introducing controllable absorption distance and neighborhood learning mechanism, MOEA/D-BH can deal with high-dimension parameters well in a multi-objective optimization problem. Thus, in a limited design space, a satisfied antenna can be optimized by proposed scheme efficiently. This can be a feasible candidate scheme for MIMO antenna design. A single-band and dual-band MIMO antenna, which are applied for semantic-based mobile system, are optimized by proposed scheme sharing the same model. Both the data of simulation and measurement show good electrical and MIMO performances in the working frequency band. Thus not only the performance of the semantic communication definitely improved, but also it provides useful exploration for the development of intelligent semantic mobile systems.

Music generation became a platform for creative expression, promoting artistic innovation, personalized experiences, and cultural integration, with implications for education and creative industry... Show More

Music generation became a platform for creative expression, promoting artistic innovation, personalized experiences, and cultural integration, with implications for education and creative industry development. But generating music that resonates emotionally is a challenge. Therefore, we introduce a new framework called the Sequence-to-Music Transformer Framework for Music Generation. This framework employs a simple encoder-decoder Transformer to model music by transforming its fundamental notes into a sequence of discrete tokens. The model learns to generate this sequence token by token. The encoder extracts melodic features of the music, while the decoder uses these extracted features to generate the music sequence. Generation is performed in an auto-regressive manner, meaning the model generates tokens based on previously observed tokens. Music melodic features are integrated into the decoder through cross-attention layers, and the generation process concludes when “end” is generated. The experimental results achieve state-of-the-art performance on a wide range of datasets.

In recent years, as fire image detection has become a research hotspot. One class of methods is color-based methods, which are very sensitive to brightness and shadows. As a result, the number of... Show More

In recent years, as fire image detection has become a research hotspot. One class of methods is color-based methods, which are very sensitive to brightness and shadows. As a result, the number of false alarms generated by these methods is high. Aiming at the task requirements of airborne binocular vision obstacle avoidance and target tracking, this paper establishes the verification platform architecture of UAV (Unmanned Aerial Vehicle) binocular vision obstacle avoidance and target tracking. For the update and maintenance of boundary regions, we can also continuously extract richer information from the boundary, make more elaborate plans, and develop an incremental method to detect locally updated maps within the boundary. The fire point can be independently and quickly identified through deep learning to extinguish the fire accurately. Assuming that the system incorrectly identifies 2 out of 80 non-fire sources as fire sources, so the results indicate a precision of about 88%, a recall of 90%. However, the traditional fire detection is around 80%.

This article presents a comprehensive analysis of the application and effect of ChatGPT, an advanced AI chatbot model, on global information management across various industries such as healthcare... Show More

This article presents a comprehensive analysis of the application and effect of ChatGPT, an advanced AI chatbot model, on global information management across various industries such as healthcare, industry, education, and more. Leveraging a dataset obtained from the Scopus database encompassing research papers from 2022 to 2023, this study investigates the influence of ChatGPT by examining publisher impact, authorship patterns based on Lotka's Law, country-specific scientific production, and keyword distribution. The analysis sheds light on prominent publishers, prolific authors, geographic distribution of research contributions, and prevailing research themes. By understanding the impact of ChatGPT in these sectors, this research contributes to the advancement of knowledge and facilitates informed decision-making regarding the responsible and effective utilization of artificial intelligence (AI) chatbot technologies in global information management.

Anomaly detection is critical in industrial inspection, where identifying defects significantly impacts product quality and safety. Existing models, primarily based on convolutional neural networks... Show More

Anomaly detection is critical in industrial inspection, where identifying defects significantly impacts product quality and safety. Existing models, primarily based on convolutional neural networks (CNNs), struggle with noise sensitivity and insufficient resolution for fine-grained feature discrimination. To address these issues, we propose a two-stage few-shot anomaly detection network that enhances semantic feature granularity and generalization. The network includes a coarse-grained anomaly detection module, a multi-scale channel attention module, and a fine-grained detection module. The coarse-grained module identifies abnormal regions, serving as the initial filter. The multi-scale channel attention module focuses on anomalous features, enhancing sensitivity to fine-grained characteristics. This step overcomes limitations in discerning subtle yet critical anomalies. The fine-grained detection module refines feature maps, enhancing generalization. Experimental results on the MVTec dataset show an image-level Area under the region of convergence (AUROC) of 92.3% and a pixel-level AUROC of 95.3%, a 1% to 2% improvement over leading FSAD methods.

The task of reconstructing a 3D cube from a 2D measurement is not well-defined in spectral imaging. Unfortunately, existing Deep Unfolding Network (DU) and End-to-End (E2E) approaches can't strike... Show More

The task of reconstructing a 3D cube from a 2D measurement is not well-defined in spectral imaging. Unfortunately, existing Deep Unfolding Network (DU) and End-to-End (E2E) approaches can't strike an optimal balance between computational complexity and reconstruction quality. The goal of this study is to think about ways to merge the E2E's violent mapping with DU's iterative method. Our proposed deep learning framework, the Reversible-prior-based Spectral-Spatial Transformer, combines the high-quality reconstruction capabilities of DU with the advantages of having fewer parameters and lower computing cost, similar to the E2E approach. SST-ReversibleNet uses a reversible prior to project the end-to-end mapping reconstruction results back into the measurement space, construct the residuals between the reprojection and the actual measurement, and improve reconstruction accuracy. Extensive trials show that our SST-ReversibleNet outperforms cutting-edge approaches by at least 0.8 dB and only use 34.3% Params and 44.1% giga floating-point operations per second (GFLOP).

In this work, a simple yet robust neighboring-aware hierarchical-based clustering approach (NHC) is developed. NHC employs its dynamic technique to take into account the surroundings of each point... Show More

In this work, a simple yet robust neighboring-aware hierarchical-based clustering approach (NHC) is developed. NHC employs its dynamic technique to take into account the surroundings of each point when clustering, making it extremely competitive. NHC offers a straightforward design and reliable clustering. It comprises two key techniques, namely, neighboring- aware and filtering and merging. While the proposed neighboring-aware technique helps find the most coherent clusters, filtering and merging help reach the desired number of clusters during the clustering process. The NHC's performance, which includes all evaluation metrics and run time, has been thoroughly tested against nine clustering rivals using four similarity measures on several real-world numerical and textual datasets. The evaluation is done in two phases. First, we compare NHC to three common clustering methods and show its efficacy through empirical analysis. Second, a comparison with six relevant, contemporary competitors highlights NHC's extremely competitive performance.