检索结果-内蒙古大学图书馆

NeuroFusion-Trans: A Novel Transformer-Based EEG-EMG Fusion Model for Assistive Robotics

IEEE Access 2025年 13卷 103245-103263页

作者： Tipu Sultan Guangping Liu Pascal Sikorski Samah Alshathri Walid El-Shafai Madi Babaiasl Aerospace and Mechanical Engineering Department Saint Louis University St. Louis MO USA Computer Science Department Saint Louis University St. Louis MO USA Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh Saudi Arabia Computer Science Department Automated Systems and Computing Laboratory (ASCL) Prince Sultan University Riyadh Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf Egypt

User intent recognition from multimodal neurophysiological signals, particularly electroencephalography (EEG) and electromyography (EMG), is critical for enhancing human-machine interaction in assistive robotics. Recent advances in neurophysiological signal processing have enabled enhanced user intent recognition for assistive robotics and human-machine interfaces. However, achieving high accuracy and real-time adaptability in electromyography (EMG) and electroencephalography (EEG)-based gesture recognition remains challenging due to temporal misalignment, weak cross-modality fusion, and lack of adaptive learning. This paper proposes NeuroFusion-Trans, a novel transformer-based framework that improves EEG-EMG gesture recognition by improving temporal resolution, using cross-modality attention, and integrating adaptive online learning. Temporal resolution enhancement ensures dynamic EEG-EMG synchronization for improved signal alignment. The cross-modality attention mechanism captures interdependencies between EEG and EMG signals, leading to more accurate intent classification. Adaptive online learning enables real-time personalization by dynamically adjusting to user-specific variations. The model is evaluated on two publicly available EEG-EMG upper-limb gesture datasets: Dataset 1 (5,296 for training, 1,324 for validation) and Dataset 2 (5,276 for training, 1,304 for validation). NeuroFusion-Trans achieves state-of-the-art performance, with an accuracy of 97% and 96% and Cohen’s Kappa of 0.97 and 0.95 after online adaptation, significantly outperforming baseline models such as CNN-LSTM, GRU, and LSTMNet. Ablation studies reveal that removing the cross-modality attention mechanism reduces accuracy by 6.1%, underscoring its importance in exploiting the EEG-EMG dependencies. Turning off synchronization leads to a 6.7% performance drop, demonstrating the necessity of real-time learning for robust intent recognition. Furthermore, NeuroFusion-Trans enhances EEG-EMG synchr

关键词： Brain modeling Electromyography Electroencephalography Adaptation models Real-time systems Synchronization Accuracy Transformers Robots Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Performance upper bound of a Grover-mixer quantum alternating operator ansatz

引用

Physical Review A 2025年第1期111卷 012401-012401页

作者： Ningyi Xie Jiahua Xu Tiejin Chen Xinwei Lee Yoshiyuki Saito Nobuyoshi Asai Dongsheng Cai Graduate School of Science and Technology University of Tsukuba 1 Chome-1-1 Tennodai Tsukuba Ibaraki 305-8577 Japan School of Computing and Augmented Intelligence Arizona State University Tempe Arizona 85281 USA Graduate School of Systems and Information Engineering University of Tsukuba 1 Chome-1-1 Tennodai Tsukuba Ibaraki 305-8577 Japan Present address: Singapore Management University Singapore. Graduate School of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima 965-8580 Japan School of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima 965-8580 Japan Faculty of Engineering Information and Systems University of Tsukuba 1 Chome-1-1 Tennodai Tsukuba Ibaraki 305-8577 Japan

The quantum alternating operator ansatz (QAOA) represents a branch of quantum algorithms for solving combinatorial optimization problems. A specific variant, the Grover-mixer (GM) QAOA, ensures uniform amplitude across states that share equivalent objective values. This property makes the algorithm independent of the problem structure, focusing instead on the distribution of objective values within the problem. In this work we provide an alternative proof for the upper bound on the probability of measuring a computational basis state from a GM QAOA circuit with a given depth, which is a critical factor in QAOA cost. Using this, we derive the upper bounds for the probability of sampling an optimal solution and for the approximation ratio of maximum optimization problems, both dependent on the objective value distribution. Through numerical analysis, we link the distribution to the problem size and build the regression models that relate the problem size, QAOA depth, and performance upper bound. Our results suggest that the GM QAOA provides a quadratic enhancement in sampling probability and requires circuit depth that scales exponentially with problem size to maintain consistent performance.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A Perceptual Data Cleansing Model (SDCM) for Reducing the Dirty Data

A Perceptual Data Cleansing Model (SDCM) for Reducing the Di...

引用

Smart Computing and Application (ICSCA), International Conference on

作者： Mohammad Azmi Al-Madi Ahmed Abdel-Wahab Mohammed AlShanty Shaikhan Bawazeer Mohammed AlZahrani Department of Computer Sciences Faculty of Science and Information Technology Al-Zaytoonah University of Jordan Amman Jordan Faculty of Computer Studies Arab Open University Riyadh Saudi Arabia Deprtment of Systems and Computers Engineering Al-Azhar University Cairo Egypt

Data cleansing approaches aim at revealing and reducing different types of outsourced errors. Such errors introduce a major issue as data cleansing often involves costly computations and time consumption. Data cleansing is complicated as most of the errors within the obtained data emerge in different forms, such as typos, duplicates, noncompliance with business rules, outdated data, and missing values. In this paper, the Supervised Dataset Cleaning Model (SDCM) is proposed in order to detect and reduce different types of outsourced errors that are stored in the data repository according to the supervised cleaning rules that are practiced from the previous cleaning processes. The findings indicates that the cleaning execution time can be reduced with this supervised model and the accuracy of the model is also increased when it covers the entire training rules and classified error types derived from the data warehouse. There are some expected future directions, which include: implementing full scale of SDCM and comparing the results obtained with different current methods. By comparing different data cleaning algorithms with SDCM, a knowledge gap is likely to arise in the search for further future improvements.

关键词： Training Computational modeling Supervised learning Clustering algorithms Data warehouses Cleaning Data models

来源：评论

学校读者我要写书评

暂无评论

Program memory optimization for automatically generated tests for AUTOSAR RTE

Program memory optimization for automatically generated test...

引用

2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021

作者： Vlasicek, Kristijan Vidovic, Ivan Teslic, Nikola Pekez, Nenad Institute RT-RK Osijek Llc for Information Technology Osijek Croatia Computer Science and Information Technology Osijek Faculty of Electrical Engineering Osijek Croatia Faculty of Technical Science University of Novi Sad Serbia RT-RK Institute for Computer Based Systems Serbia

ISBN: (纸本)9781665404174

With the technological advancements in the automotive industry, the need for more electronic components has increased as well as for the appropriate software, that is, appropriate drivers. The development of such software is usually based on the AUTOSAR standard, while the required electronics use embedded computer systems. Considering that the embedded computer systems have limited resources, the software needs to be optimized. In this paper, the program memory of the considered software was optimized. The optimization was done using the following methods: introduction of generic functions, extraction of repetitive functions in the header files and dead code elimination. The optimization methods were applied by changing a code fragment written in C programming language. In that way, the program memory optimization method could be applied to all software components (SWCs) using Test Environment Generator (TEG). Afterward, the program code testing was done on a testing board. The results of the testing on board prove the functionality of the optimized program code. The applied methods optimized the memory usage (6.16% reduction) and preserved the functionality of the program code to an appropriate extent. © 2021 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Proposing System to Recognize Emotions in Public Network Using Phobert Deep Learning Model 9

Proposing System to Recognize Emotions in Public Network Usi...

引用

9th NAFOSTED Conference on Information and computer science, NICS 2022

作者： Huu, Phat Nguyen Anh, Tuan Nguyen Phi, Long Hoang Dang, Dinh Dang Le Bao, Chau Nguyen Minh, Quang Tran School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam Hanoi-Amsterdam Highschool for the Gifted Hanoi Viet Nam Ho Chi Minh City University of Technology Faculty of Computer Science and Engineering Department of Information Systems Hochiminh Viet Nam Vietnam National University Hochiminh HoChiMinh City Viet Nam

ISBN: (纸本)9781665454223

People can receive information faster especially in the 4.0 revolution with the continuous development of revolutions. The information can affect our emotional, psychological and spiritual well-being, especially in the recent high school graduation exam across the country. Therefore, we propose to build a user emotion analysis system in a public network with the PhoBert training model in the paper. Besides, we built our dataset aggregated from social networks, articles, blogs, etc. We next use the PhoBert model to solve the processing data problems. The simulation results have shown an accuracy of 86.5% on the training and 81.32% on the validation dataset with a training time of 3 hours (about 180 minutes). The results also show that we can build a warning system to avoid health and psychological effects with great emotion. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition System via Facial Expressions and Speech Using Machine Learning and Deep Learning Techniques

引用

SN computer science 2023年第4期4卷 363页

作者： Chaudhari, Aayushi Bhatt, Chintan Nguyen, Thanh Thi Patel, Nisarg Chavda, Kirtan Sarda, Kalind U & P U. Patel Department of Computer Engineering Chandubhai S. Patel Institute of Technology Charotar University of Science And Technology (CHARUSAT) Gujarat Changa 388421 India Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Knowledge Corridor Gujarat Gandhinagar 382007 India School of Information Technology Faculty of Science Engineering and Built Environment Deakin University Victoria 3216 Australia Bishop University 2600 College St Sherbrooke J1M 1Z7 QC Canada Crest Data Systems Private Limited Gandhinagar Highway Makarba Gujarat Ahmedabad 380051 India Programmer Analyst Meditab Software Pvt Ltd Kalasagar Mall Ghatlodiya Gujarat Ahmedabad 380061 India

Patients in hospitals frequently exhibit psychological issues such as sadness, pessimism, eccentricity, and anxiety. However, hospitals normally lack tools and facilities to continuously monitor the psychological health of patients. It is desirable to identify depression in patients so that it can be managed by instantly providing better therapy. This can be possible by advances in machine learning for image processing with notable applications in the domain of emotion recognition using facial expressions. In this paper, we have proposed two different methods, i.e. facial expression detection and voice analysis, to predict emotions. For facial expression recognition, we have used two approaches, one is the use of Gabor filters for feature extraction with support vector machine for classification and another is using convolutional neural network (CNN). For voice analysis, we extracted mel-frequency cepstral coefficients from speech data and, based on those features, predicted the emotions of the speech using a CNN model. Experimental results show that our proposed emotion recognition methods obtained high accuracy and thus could be potentially deployed to real-world applications. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： CNN Deep learning Expressions Facial emotion Machine learning Speech SVM

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Classification Using Combined Machine Learning and Deep Learning Approach

引用

computers, Materials & Continua 2022年第9期72卷 5117-5134页

作者： Hiam Alquran Wan Azani Mustafa Isam Abu Qasmieh Yasmeen Mohd Yacob Mohammed Alsalatie Yazan Al-Issa Ali Mohammad Alqudah Department of Biomedical Engineering Jordan University of Science and TechnologyIrbid22110Jordan Department of Biomedical Systems and Informatics Engineering Yarmouk University 556Irbid21163Jordan Faculty of Electrical Engineering Technology Campus Pauh PutraUniversiti Malaysia Perlis02000ArauPerlisMalaysia Advanced Computing Centre of Excellence(CoE)Universiti Malaysia Perlis(UniMAP)02000ArauPerlisMalaysia The Institute of Biomedical Technology King Hussein Medical CenterRoyal Jordanian Medical ServiceAmman11855Jordan Department of Computer Engineering Yarmouk UniversityIrbid21163Jordan

Cervical cancer is screened by pap smear methodology for detection and classification *** smear images of the cervical region are employed to detect and classify the abnormality of cervical *** this paper,we proposed the first system that it ables to classify the pap smear images into a seven classes *** smear images are exploited to design a computer-aided diagnoses system to classify the abnormality in cervical images *** features that have been extracted using ResNet101 are employed to discriminate seven classes of images in Support Vector Machine(SVM)*** success of this proposed system in distinguishing between the levels of normal cases with 100%accuracy and 100%*** top of that,it can distinguish between normal and abnormal cases with an accuracy of 100%.The high level of abnormality is then studied and classified with a high *** the other hand,the low level of abnormality is studied separately and classified into two classes,mild and moderate dysplasia,with∼92%*** proposed system is a built-in cascading manner with five models of polynomial(SVM)*** overall accuracy in training for all cases is 100%,while the overall test for all seven classes is around 92%in the test phase and overall accuracy reaches 97.3%.The proposed system facilitates the process of detection and classification of cervical cells in pap smear images and leads to early diagnosis of cervical cancer,which may lead to an increase in the survival rate in women.

关键词： Classification deep learning machine learning pap smear images resnet101 support vector machines

来源：评论

学校读者我要写书评

暂无评论

Constrained Intelligent Frequency Control in an AC Microgrid: An Online Reinforcement Learning Based PID Tuning Approach

Constrained Intelligent Frequency Control in an AC Microgrid...

引用

IEEE General Meeting Power& Energy Society

作者： K. Nosrati A. Tepljakov E. Petlenkov V. Skiparev J. Belikov Y. Levron Department of Computer Systems Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa Israel

Variable output power in isolated microgrids (MGs) threatens frequency stability and may even degrade power quality. In response, intelligent control methods have been developed and applied to frequency deviation control systems with excellent results. Nevertheless, a potential problem is that the application of such advanced techniques with a large search space is not enough to deal with highly dynamic environment and real-time operations of MGs. In this light, the present study introduces a flexible artificial neural network (ANN)-based frequency deviation control solution in a constrained structure that operates as follows. First, the stable controller parameter space of the PID-based AC microgrid is derived by using the stability boundary locus method. Then, the controller parameters are tuned and updated online by searching for an optimal combination of the coefficients with consideration of output variations sensed by a constrained ANN in the derived reduced parameter space. To accomplish this step, a reinforcement learning technique is applied to train the ANN-based tuners. The performance of the proposed technique has been verified under a given scenario to demonstrate how the reduced parameter space should facilitate the optimization procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating the Perception of the Elderly Population About Comfort, Safety and Security When Using Active Modes of Transport 11th

Investigating the Perception of the Elderly Population Ab...

引用

11th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2022

作者： Felício, Soraia Hora, Joana Ferreira, Marta Campos Abrantes, Diogo Luna, Fábio Silva, Jorge Coimbra, Miguel Galvão, Teresa Faculty of Engineering of the University of Porto Rua Dr. Roberto Frias s/n Porto4200-465 Portugal INESC TEC - Institute for Systems and Computer Engineering Technology and Science R. Dr. Roberto Frias s/n Porto4200-465 Portugal Faculty of Sciences of the University of Porto Rua do Campo Alegre s/n Porto4169-007 Portugal Bosch Security Systems R. Pardala Zona Ind. de Ovar Estrada Nacional 109 Aptd. 653 Aveiro Portugal

ISBN: (纸本)9783031320286

Promoting active modes of transport, such as walking and cycling, has a positive impact on environmental sustainability and the health and well-being of citizens. This study explores the elderly population’s perception of comfort, safety and security when using active modes of transport. It begins with a systematic review of the literature considering research works that relate to active travel, the elderly population, and random forest. Then a questionnaire was applied to 653 participants and the results were analyzed. This analysis consisted of using statistics to evaluate the socio-demographic profile, the preferences regarding the use of active modes of this population, and the importance given to each dimension: comfort, safety, distance, and time, comparing these indicators through the Wilcoxon Rank Sum test and the Random Forest algorithm. The results showed that people over 56 years old walk as much as younger people. Furthermore, the importance given by this group of people to indicators referring to active modes is related to safety and security, distance, time, and comfort. The statistical results of the Wilcoxon Rank Sum test indicate the most important indicators: Adequate Travel Distance & Time and Existence of Commercial Areas by age group [0–55], and Absence of Allergenics and Existence of Green Areas by age group [56+]. Finally, the Random Forest algorithm provides the relative importance for both age groups, [0–55] and [56+], where the indicators that stand out in the [56+] age group, which is the focus of our study, are air quality, adequate travel distance & time, adequate crowd density, adequate thermal sensation, absence of allergenic, good street illumination level, adequate traffic volume, and adequate noise level. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Air quality

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：