检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Varinya Phanichraksaphong Wei-Ho Tsai International Graduate Program of Electrical Engineering and Computer Science (IEECS) National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan

The implementation of Gated Recurrent Neural Networks (GRU) to generate background music (BGM) combines deep learning technology with music that is used for the visual content of a commercial or educational. Indeed, this BGM is necessary to enhance the intended message expressed to the other audience. This work aimed to provide the model network of GRU which is based on RNN to generate multi-label genres of music by using the open source of GTZAN to evaluate the new BGM. Our GRU networks can solve the vanishing gradient problem by utilizing both the reset gate and the update gate on the network. In the results, we achieved a new BGM that synchronized with the human mood which made more variety of sounds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Beamforming and Anti -Jamming with Intelligent Omni-Surfaces

Simultaneous Beamforming and Anti -Jamming with Intelligent ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yuhan Wang Shuhao Zeng Qingyu Liu Boya Di Hongliang Zhang School of Electronic and Computer Engineering Peking University Shenzhen Graduate School China Pengcheng Laboratory China Department of Electrical and Computer Engineering Princeton University USA School of Electronics Peking University China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Wireless transmission is vulnerable to malicious jamming attacks due to the openness of wireless channels, posing a severe threat to wireless communications. Current anti-jamming studies primarily focus on either enhancing desired signals or mitigating jamming, resulting in limited performance. To address this issue, intelligent omni-surface (lOS) is a promising solution. By jointly designing its reflective and refractive properties, the lOS can simultaneously nullify jamming and enhance desired signals. In this paper, we consider an lOS-aided multi-user anti-jamming communication system, aiming to improve desired signals and nullify jamming by optimizing lOS phase shifts and transmit beamforming. However, this is challenging due to the coupled and discrete lOS reflection and refraction phase shifts, the unknown jammer's beamformer, and imperfect jammer-related channel state information. To tackle this, we relax lOS phase shifts to continuous states and optimize with a coupling-aware algorithm using the Cauchy-Schwarz inequality and S-procedure, followed by a local search to recover discrete states. Simulation results show that the proposed scheme significantly improves the sum rate amid jamming attacks.

关键词： Wireless communication Array signal processing Simulation Reflection Jamming Channel state information

来源：评论

学校读者我要写书评

暂无评论

MAZENET: AN ACCURATE, FAST, & SCALABLE DEEP LEARNING SOLUTION FOR STEINER MINIMUM TREES

arXiv

引用

arXiv 2024年

作者： Ramos, Gabriel Díaz Arikan, Toros Baraniuk, Richard G. Rice University United States Department of Electrical and Computer Engineering Smalley-Curl Institute Applied Physics Program United States

The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in integrated circuit design, network optimization, and robot path planning. Since OARSMT is NP-hard, exact algorithms scale poorly with the number of terminals, and so practical solvers sacrifice accuracy for large problems. We propose and study MazeNet, a deep learning-based method that learns to solve the OARSMT from data. MazeNet re-frames OARSMT as a maze-solving task that can be addresssed with a recurrent convolutional neural network (RCNN). A key hallmark of MazeNet is its scalability: we only need to train the RCNN blocks on mazes with a small number of terminals;mazes with a larger number of terminals can be solved simply by replicating the same pre-trained blocks to create a larger network. Across a wide range of experiments, MazeNet achieves perfect OARSMT-solving accuracy, with significantly reduced runtime compared to classical exact algorithms, and with the ability to handle larger numbers of terminals than state-of-the-art approximate algorithms. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Mask, Hairnet, and Handwash Detection System for Food Manufacturing Health and Safety Monitoring

Mask, Hairnet, and Handwash Detection System for Food Manufa...

引用

International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)

作者： Collien Princess C. Pepito Earl Ryan M. Aleluya Francis Jann A. Alagon Steve E. Clar Jared Jan A. Abayan Carl John O. Salaan Maria Fe P. Bahinting Department of Computer Applications College of Computer Studies Department of Computer Engineering and Mechatronics College of Engineering Department of Electrical Engineering College of Engineering Graduate School of Engineering Mindanao State University-Iligan Institute of Technology Iligan City Philippines

ISBN: (数字)9798350381177

ISBN: (纸本)9798350381184

Food safety is a top concern within food manufacturing facilities, with strict measures in place to ensure the quality and integrity of products. The existing food safety measures typically rely on manual inspections and human vigilance to ensure compliance with safety protocols. These measures, although essential, are prone to human error and limitations in terms of real-time monitoring. Moreover, the global pandemic has underscored the importance of adherence to health and safety guidelines, including the wearing of masks, hairnets, and proper handwashing practices to ensure the well-being of workers and the integrity of food production processes. This research introduces the development of a mask, hairnet, and handwash detection system employing pre-trained deep learning models, specifically YOLOv5 and YOLOv8 (You Only Look Once). Each model was evaluated on various metrics to assess its accuracy and overall performance. The YOLOv8 model showcases outstanding performance in mask and hairnet detection, along with handwash detection. For mask and hairnet detection, it achieved a precision, recall, and F1 score of 100%, and mAP of 99.40%. While handwash detection attained a precision, recall, and F1 score of 100%, and mAP of 92.70%. To provide a comparative analysis between the YOLO models used in the study, the YOLOv5 model was also trained using the same dataset as the YOLOv8 and was evaluated accordingly. Moreover, this study aims to impart significant contributions, particularly in the real-time application of health and safety monitoring within food manufacturing settings.

关键词： YOLO Deep learning Training Analytical models Protocols Food manufacturing Employment

来源：评论

学校读者我要写书评

暂无评论

Saccadic Detection in Virtual Gaming for Dyslexia Classification

Saccadic Detection in Virtual Gaming for Dyslexia Classifica...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yih-Choung Yu Haki Shyntassov Padmanabh Kaushik Lisa Gabel Department of Electrical and Computer Engineering Lafayette College Easton PA USA Department of Psychology and the Neuroscience Program Lafayette College Easton PA USA

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Dyslexia (aka reading disability) is the most common cause of learning disabilities. It affects children across language orthographies, despite adequate intelligence and educational opportunity. Studies have shown that identifying children with dyslexia at young age is crucial to provide effective intervention to improve learning outcomes. Recently we demonstrated that children with reading disability exhibit impaired performance on a virtual maze learning task across language orthographies. Using a machine learning algorithm, we have achieved a classification accuracy up to 80%. This paper presents an algorithm, including image segmentation, synchronization of image and text data, saccade detection, and event alignment, using the eye-gazing data recorded from an eye tracker during maze-solving tasks. The saccadic events detected by this algorithm showed good correlation with the incorrect decisions participants made during maze-solving, which could be an additional variable to be used in the machine learning algorithm to enhance the accuracy for dyslexia classification.

关键词： Image segmentation Machine learning algorithms Correlation Accuracy Signal processing algorithms Predictive models Dyslexia

来源：评论

学校读者我要写书评

暂无评论

Detecting Persons in River Quarry Operations: Aerial Surveillance for Flood Pre-Disaster Monitoring

Detecting Persons in River Quarry Operations: Aerial Surveil...

引用

International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)

作者： Rochelle F. Madulara Earl Ryan M. Aleluya Jeanette C. Pao Steve E. Clar Francis Jann A. Alagon Carl John O. Salaan Maria Fe P. Bahinting Department of Computer Applications College of Computer Studies Department of Computer Engineering and Mechatronics College of Engineering Department of Electrical Engineering College of Engineering Graduate School of Engineering Mindanao State University-Iligan Institute of Technology Iligan City Philippines

ISBN: (数字)9798350381177

ISBN: (纸本)9798350381184

During the flood disaster preparedness procedure, warning dissemination followed by response decision-making and implementation is usually time-consuming for disaster preparedness teams. Some inaccessible areas that are also prone to flooding is a crucial challenge for the disaster preparedness team in disseminating the early warnings, which may result in endangering the lives of people living in those areas. Moreover, the disaster preparedness team is dedicated to overseeing and managing river quarrying activities, as these are areas where workers or individuals are at high risk of flooding disasters. In this study, an Unmanned Aerial Vehicle (UAV) with Person Detection System that can assist the disaster preparedness team for flood pre-disaster monitoring was introduced. The study investigated the performance of advanced deep learning models, particularly on You Only Look Once, for accurate person detection utilizing UAV imagery focusing in a river-quarry setting. A novel approach to data collection was also presented, specialized datasets were created for capturing river quarry-specific scenarios and used this in facilitating realistic model training. Two models were evaluated in this study, the YOLOv5 model and YOLOv8 model, through their precision, recall, F1-score, and mAP performance. The trained YOLOv5 model showed better performance with 97.70% precision, 94.10% recall, 95.10% F1-Score, and 64.50% mAP than the YOLOv8 model. The significant difference of 2.00% for precision, 3.80% for recall, 3.00% for F1-score, and 0.40% for mAP, between YOLOv5 model and YOLOv8 model, provided beneficial findings for optimizing model selection for person detection using UAV imagery considering other areas needed for pre-disaster monitoring.

关键词： YOLO Training Disasters Surveillance Autonomous aerial vehicles Mathematical models Rivers

来源：评论

学校读者我要写书评

暂无评论

SB21: Portable Watermelon Ripeness Detector Through Acoustics Analysis and Spectral Identification 14

SB21: Portable Watermelon Ripeness Detector Through Acoustic...

引用

14th IEEE International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management, HNICEM 2022

作者： Balakit, Raymart B. Dela Cruz, Jennifer C. Reaño, Rose Anne L. Castillo, Acer Jay G. Garcia, Christian Julius R. Libang, Ma. Caira Gail M. Mallapre, Joshua S. Navarro, Anthony D. Pangyarihan, Rosemarie L. Pariño, Krisha Mae N. Wenceslao, Erecha B. Mapua University School of Graduate Studies School of Electrical Electronics and Computer Engineering Manila Philippines Polytechnic University of the Philippines-Sto. Tomas Branch Department of Electronics Engineering Batangas Philippines

ISBN: (纸本)9781665464932

Watermelon is one of the most challenging fruits to determine if it is ripe, unripe, or overripe. Monitoring its quality is essential for boosting its marketability and productivity. Manual methods used in identifying its maturity level depend on tapping, color inspection, and the number of days. While they are useful, their accuracy and precision are limited due to reliance on guesswork. This study aims to provide a non-destructive method for watermelon ripeness detection of Sugar Baby variety through Acoustics Analysis and Spectral Identification using Fast Fourier Transform and Near-Infrared Spectroscopy (NIRS). A portable and automated device is designed, consisting of processes including the detection of sound and internal content qualities using NIRS sensor and microphone, assessing the wavelength and frequencies acquired, and interpreting the findings in line with the standard values set. K-Nearest Neighbor technique is employed, where transformed signals are passed through computation, comparing, and voting. A total of 300 watermelon samples were evaluated and 30 respondents were also surveyed to assess the effectiveness of the device. Results revealed that utilizing both NIRS and Fast Fourier Transform can effectively detect watermelon ripeness with high accuracy of 90.7%. The automated watermelon ripeness detector is strongly preferred over manual detection. © 2022 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Ethical Issues in Near-Future Socially Supportive Smart Assistants for Older Adults

IEEE Transactions on Technology and Society

引用

IEEE Transactions on Technology and Society 2023年第4期4卷 291-301页

作者： London, Alex John Razin, Yosef S. Borenstein, Jason Eslami, Motahhare Perkins, Russell Robinette, Paul Carnegie Mellon University Department of Philosophy PittsburghPA15213 United States Georgia Institute of Technology School of Aerospace Engineering AtlantaGA30332 United States Georgia Institute of Technology School of Public Policy and Office of Graduate Education AtlantaGA30332 United States Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA15213 United States University of Massachusetts Lowell Department of Electrical and Computer Engineering LowellMA01854 United States

This paper considers novel ethical issues pertaining to near-future artificial intelligence (AI) systems that seek to support, maintain, or enhance the capabilities of older adults as they age and experience cognitive decline. In particular, we focus on smart assistants (SAs) that would seek to provide proactive assistance and mediate social interactions between users and other members of their social or support networks. Such systems would potentially have significant utility for users and their caregivers if they could reduce the cognitive load for tasks that help older adults maintain their autonomy and independence. However, proactively supporting even simple tasks, such as providing the user with a summary of a meeting or a conversation, would require a future SA to engage with ethical aspects of human interactions which computational systems currently have difficulty identifying, tracking, and navigating. If SAs fail to perceive ethically relevant aspects of social interactions, the resulting deficit in moral discernment would threaten important aspects of user autonomy and well-being. After describing the dynamic that generates these ethical challenges, we note how simple strategies for prompting user oversight of such systems might also undermine their utility. We conclude by considering how near-future SAs could exacerbate current worries about privacy, commodification of users, trust calibration and injustice. © 2020 IEEE.

关键词： Cognitive systems

来源：评论

学校读者我要写书评

暂无评论

Quality Improvements in the electrical Design of Typical DC-DC Electronic Power Converter for High-Voltage Applications 8

Quality Improvements in the Electrical Design of Typical DC-...

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Recto, King Harold A. Escoto, Miguel T. Hernandez, Noel B. Ateneo de Manila University Department of Electronics Computer and Communications Engineering Quezon City Philippines Electrical and Electronics Engineering Institute University of the Philippines Diliman Quezon City Philippines Centro Escolar University Post-doctoral Program in Quality Management of the Graduate School Manila Philippines

ISBN: (纸本)9781665491068

The green transition has brought about a worldwide-shift to the use of renewables as alternative energy sources. Because of this, high voltage DC has been a field of interest in power electronics due to its capability in efficiently transmitting power to reach remote areas. Typical DC-DC electronic power converter design has the capability of boosting voltage level to a certain extent but not enough for high-voltage applications. Using the DMAIC Approach of the Six Sigma, quality improvements in the design was proposed to stabilize operating frequency, bring up the output voltage from 100 VDC to 4,000 VDC and provide at least 10% margin of error in the apparent power measured at the output side to offset inherent losses in the electrical design. These proposed quality improvements were sustained by designing a control circuit that would ensure the attainment of the parameters set in the Define Phase of the DMAIC Approach. The result of the study is a practical 12 VDC to 4,000 VDC boost converter design that has incorporated all the proposed quality improvements. © 2022 IEEE.

关键词： Six sigma

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning for Human-Object Interaction Detection 2

Ensemble Deep Learning for Human-Object Interaction Detectio...

引用

2nd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2022

作者： Mansour, Ahmed E. Mohammed, Ammar Elsayed, Hussein Abd El Atty Ramly, Salwa H. El Ain Shams University Faculty of Engineering Electronics and Electrical Communication Department Cairo Egypt Cairo University Faculty of Graduate Studies of Statistical Researches Computer Science Department Cairo Egypt

ISBN: (纸本)9781665466776

Human-object interaction (HOI) detection is the task of predicting the visual relationships between humans and their surroundings in images and videos by locating and inferring the interactions between human-object pairs. The majority of existing models have approached this task by detecting human and object instances and predicting interactions between them using a single model and relying on visual features to differentiate between different actions. In this article, we propose a novel method for solving the HOI detection problem by employing ensemble voting on simple models that use only spatial features to predict human-object pair actions. Additionally, we solve the false-positive pairs generated by mis-grouping and non-interaction objects in the image using a bipartite matching. Our proposed approach outperforms many state-of-the-art models on the V-COCO dataset while requiring less inference time. © 2022 IEEE.

关键词： Visualization Computational modeling Object detection Predictive models Feature extraction Ubiquitous computing Prediction algorithms

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：