检索结果-内蒙古大学图书馆

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Roy, Tonmoy Islam, Md Robiul Miazee, Asif Ahammad Antara, Anika Al Amin Hossain, Sunjim Data Analytics & Information Systems Utah State University Utah United States Computer Science William & Mary Virginia United States Computer Science Maharishi International University Iowa United States Electrical and Electronics Engineering Brac University Dhaka Bangladesh Computer Science Uttara University Dhaka Bangladesh Computer Science Northern University Dhaka Bangladesh

ISBN: (纸本)9798331508227

Over the years, the number of users of social media has increased drastically. People frequently share their thoughts through social platforms, and this leads to an increase in hate content. In this virtual community, individuals share their views, express their feelings, and post photos, videos, blogs, and more. Social networking sites like Facebook and Twitter provide platforms to share vast amounts of content with a single click. However, these platforms do not impose restrictions on the uploaded content, which may include abusive language and explicit images unsuitable for social media. To resolve this issue, a new idea must be implemented to divide the inappropriate content. Numerous studies have been done to automate the process. In this paper, we propose a new Bi-GRU-CNN model to classify whether the text is offensive or not. The combination of the Bi-GRU and CNN models outperforms the existing models. ©2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Automatically Choosing Selection Operator Based on Semantic Information in Evolutionary Feature Construction 20th

Automatically Choosing Selection Operator Based on Semantic...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Zhang, Hengzhe Chen, Qi Xue, Bing Banzhaf, Wolfgang Zhang, Mengjie Centre for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand Department of Computer Science and Engineering Michigan State University East Lansing48824 United States

ISBN: (纸本)9789819970216

In recent years, genetic programming-based evolutionary feature construction has shown great potential in various applications. However, a critical challenge in applying this technique is the need to select an appropriate selection operator with great care. To tackle this issue, this paper introduces a novel approach that leverages the Thompson sampling technique to automatically choose the optimal selection operator based on semantic information of genetic programming models gathered during the evolutionary process. The experimental results on a standard symbolic regression benchmark containing 37 datasets show that the proposed adaptive operator selection algorithm outperforms expert-designed operators, demonstrating the effectiveness of the adaptive operator selection algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Secure-JobChain: Revolutionizing Job Recruitment with Blockchain Technology

Secure-JobChain: Revolutionizing Job Recruitment with Blockc...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Pavithra, S. Geethanjali, S. Vidya, B. Suria, S. Rahul, B.S. Kishore, R. Computer Science and Engineering Rajiv Gandhi College of Engineering and Technology Pondicherry India SRM Institute of Science and Technology Data Science and Business Systems Kattankulathur India SRM Institute of Science and Technology Electronics and Communication Engineering Kattankulathur India

ISBN: (纸本)9798331539948

The traditional job recruitment process is time consuming and also undergoes certain difficulties such as data privacy, lack of transparency, and inefficient credential verification. These difficulties lead to mistrust and also delay the process of hiring. There is a need for improvement in this process that could benefit both the companies and the job applicants. In this paper, a decentralized recruitment platform based on blockchain technology is proposed. This proposed technique will overcome the above-mentioned difficulties by ensuring secure, transparent, and efficient connections between the recruitment companies and the prospective candidates. This solution uses the merits of blockchain i.e., immutability and automation to record job postings, applications, and hiring decisions on an immutable ledger, protecting personal data with cryptographic techniques and automating qualification verification with smart contracts. By implementing the decentralization concepts in Job recruitment, it is proven that the transparency in the interview process is improved by 9 0 and fraud risks are reduced considerably. Moreover, the efficiency of the entire job recruitment process is improved largely. Thus, the decentralized solution proposed in this paper demonstrates its potential in revolutionizing the job recruitment process by providing a secure, transparent and efficient hiring ecosystem. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Flow-Guided Deformable Alignment Network with Self-Supervision for Video Inpainting 48

Flow-Guided Deformable Alignment Network with Self-Supervisi...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Zhiliang Zhang, Kang Sun, Changchang Xuan, Hanyu Yan, Yan Nanjing University of Science and Technology School of Computer Science and Engineering China Illinois Institute of Technology Department of Computer Science United States Anhui University School of Big Data and Statistics China

ISBN: (纸本)9781728163277

Video inpainting aims to utilize plausible contents to fill missing regions in the video. State-of-the-art video inpainting methods typically generate the missing contents of the target frame (current frame) by aggregating the temporal information of reference frames (neighboring frames) aligned using deformable convolution. However, these deformable convolution alignment networks often suffer from offset overflow during training, resulting in unsatisfactory alignment, thereby obtaining compromised inpainting performance. In this paper, we propose a self-supervised Flow-Guided Deformable Alignment (FGDA) network for aligning reference frames at the feature level. FGDA computes the residual of the optical flow as the offsets. This design can effectively reduce the burden of offsets learning, thereby avoiding offset overflow. Furthermore, a gradient-weighted reconstruction loss for supervised completed frame reconstruction is designed, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed texture regions, so that detail textures get more attention during training. Experiments show that FGDA-based video inpainting model trained with gradient-weighted reconstruction loss outperforms the state-of-the-art by a significant margin in terms of PSNR and SSIM with relative improvements of 6.2% and 2.1%, respectively. © 2023 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Leaving None Behind: data-Free Domain Incremental Learning for Major Depressive Disorder Detection

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 758-770页

作者： Chen, Tao Guo, Yanrong Hao, Shijie Hong, Richang Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data China Hefei University of Technology Ministry of Education and School of Computer Science and Information Engineering Hefei230009 China

While deep learning techniques have shown promising performance in the Major Depressive Disorder (MDD) detection task, they still face limitations in real-world scenarios. Specifically, given the data scarcity, some efforts have resorted to aggregating data from different domains to expand the data volume. However, their effectiveness is currently limited by the domain gap and data privacy. Additionally, the class imbalance issue is particularly severe in our application, leading to biased classifying performance accordingly. To address these challenges, we propose data-Free Domain Incremental Learning for the MDD detection (DIL-MDD) task, accommodating multiple feature distributions by only accessing well-trained models from previous domains and the data in the current domain. Specifically, DIL-MDD consists of two key modules: Adaptive Class-tailored Threshold Learning (ACTL) and data-Free Domain Alignment (DFDA). The first module measures the discrepancy between the outputs of two sequential domains, based on which we learn a class-tailored threshold adaptively. Building on this, we differentiate between samples that either exhibit similarities or dissimilarities with the previous domain, where this similar sample set is identified to investigate the feature distribution of the historical data. The second module imposes an alignment constraint to narrow the gap between these two sample sets, thereby exploring the expertise of the previous domain. To validate the effectiveness of the proposed method, we conduct extensive experiments on the public MDD datasets, i.e., DAIC-WOZ, MODMA, and CMDC. We also apply our method to another mental health condition, Autism Spectrum Disorder (ASD), to further demonstrate its applicability. Finally, the ablation studies validate the superiority of the proposed modules. © 2010-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Barrier Function-Based Backstepping Fractional-Order Sliding Mode Control for Quad-Rotor Unmanned Aerial Vehicle under External Disturbances

引用

IEEE Transactions on Aerospace and Electronic Systems 2024年第1期60卷 716-728页

作者： Liu, Bowen Wang, Yingxun Mofid, Omid Mobayen, Saleh Khooban, Mohammad Hassan Beihang University School of Automation Science and Electrical Engineering Beijing100191 China University of Zanjan Department of Electrical Engineering Zanjan45371-38791 Iran National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliou64002 Taiwan Aarhus University Department of Electrical and Computer Engineering Aarhus8200 Denmark

The main control objective for the quad-rotor system is the attitude and position tracking control which is accomplished in this article using the backstepping fractional-order sliding mode control approach combined with the adaptive tuning based barrier function theory. The quad-rotor's dynamical model is obtained at the appearance of the disturbance that is entered to the quad-rotor system by an exterior force. Hence, the attitude and position tracking errors between the quad-rotor's actual states and their desired trajectory are defined. Afterward, the fractional-order sliding surfaces are defined to guarantee finite-time reachability of the defined tracking error. The designed fractional-order surface eases the control process due to the removal of the high-derivative of virtual controllers. Then, the extended adaptive barrier function laws named fractional-order-based adaptive barrier function laws are employed to eliminate the knowledge of the upper bounds of external disturbances. The Lyapunov theory concept mixed with the backstepping control strategy is used to demonstrate that the fractional-order sliding surface reaches the neighborhood of origin in the finite time. Finally, simulation results in various scenarios on the MATLAB/ Simulink environment are provided to show that the designed control procedure in this article is an efficient control technique to assure that attitude and position's trajectories of the quad-rotor system track desired trajectories properly in the existence of the external disturbances. Moreover, the designed method is compared to the existing method to validate the efficiency of the proposed method. Lastly, experimental results using the Speedgoat real-time target machine is implemented to assure validity of the recommended method. © 1965-2011 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining 42

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shi, Shaohuai Pan, Xinglin Chu, Xiaowen Li, Bo Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Hong Kong Baptist University Department of Computer Science Hong Kong Data Science and Analytics Thrust Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired visual neural network for stop-and-go wave perception in high-density crowd 4

Bio-inspired visual neural network for stop-and-go wave perc...

引用

4th International Conference on computer Vision, Application, and Algorithm, CVAA 2024

作者： Jiang, Wei Hu, Bin State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Department of Computer Science College of Computer Science & Technology Guizhou University Guiyang550025 China Artificial Intelligence Research Institute of Guizhou University Guizhou University Guiyang550025 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

In high-density crowd, a unique visual motion effect called stop-and-go wave occurs, which could evolve to trampling and compression incidents. However, few computational models have been reported for stop-and-go wave perception form the angle of computer vision. On the bases of the neural structures of the locusts’ vision systems and the frequency resonance properties of the interneuronal (INs) neurons in locust’s brains, this paper investigates a bio-inspired visual neural network (sgWPNN) for stop-and-go wave perception in high-density crowd scenes. The proposed sgWPNN firstly visually stabilizes the image frames;and then converts the spatial intensity visual information to the frequency domain for extracting crowd’s motion cues;finally, sgWPNN output membrane potential impulses to identify the occurring of stop-and-go wave in the field of view. Videos filmed high-density crowd activities in two scenarios demonstrate the effectiveness of sgWPNN in the perception against to the unique stop-and-go wave effect in moving crowd scenes. This work discusses the biological inspired processing of dynamic visual information in crowd activity perception, which can provide some new ideas for crowd activity detection and behavior analysis. © 2025 SPIE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural Computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Facial Expressions and EEG Signals for Emotion Recognition Using Deep2 Face Algorithm 10

Facial Expressions and EEG Signals for Emotion Recognition U...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Swetha, S. Babu, Nirmal Varghese Karunya Institute of Technology and Science Division of Computer Science and Engineering Karunya Nagar Tamil Nadu Coimbatore India Karunya Institute of Technology and Science Division of Data Science and Cyber Security Karunya Nagar Tamil Nadu Coimbatore India

ISBN: (纸本)9798350384369

Emotions, the essence of human connection and understanding, take center stage in this pioneering research on emotion recognition. We look at identifying common emotions including joy, sorrow, neutral, anger, fear, and surprise. Introducing an innovative approach, we seamlessly blend advanced computer vision algorithms and intricate signal processing techniques to concurrently analyze facial expressions and EEG signals. The heart of our methodology lies in the utilization of the state-of- the-art Deep Face Analyzer, guided by the deep2face algorithm for meticulous interpretation of facial features, coupled with a spectrographic analyzer translating EEG signals into spectrograms. The overarching goal is to enhance the accuracy and resilience of emotion recognition, with the added dimension of a real-time Waveform Extractor for dynamic evaluation of audio signals. Within the landscape of diverse algorithms and modalities, the Hybrid Model (CNN + LSTM) emerges as a standout performer, achieving an impressive 88.2% accuracy by synergizing facial expressions and EEG signals. The strategic integration of long short-term memory (LSTM) networks with convolutional neural networks (CNNs) underscores the model's exceptional capacity to capture the nuanced intricacies of human emotions. Beyond mere technological advancement, this study underscores the importance of embracing multiple modalities for a holistic understanding of emotions, positioning the Hybrid Model as a powerful and nuanced tool for precise and multiclass emotion identification across diverse real-world scenarios. In essence, our research charts a path where the realm of emotions converges with technological innovation, fostering a deeper understanding of the human experience © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：