检索结果-内蒙古大学图书馆

2024 International Conference on Electronics and Devices, Computational science, ICEDCS 2024

作者： Han, Xinxin Xiong, Xueguan Wang, Liuling Yang, Yuxin Lu, Dandan Southwest University of Science and Technology School of Computer Science and Technology Mianyang China Southwest University of Science and Technology School of National Defense Science Mianyang China Southwest University of Science and Technology School of Economics and Management Mianyang China Southwest University of Science and Technology School of Information Engineering Mianyang China Southwest University of Science and Technology Dept. Engineering Technology Center Mianyang China

ISBN: (纸本)9798331527624

This study investigates an automated COVID-19 diagnosis system based on convolution networks, which aims to improve the effectiveness and accuracy of diagnosis. In a systematic analysis of 1709 chest X-rays, the research team used the ResNet model of deep learning for training and evaluation. Based on a detailed analysis of the confusion matrix generated by the model, the study found that the weighted average accuracy of the model and the recall rate reached 94,04% with an F1 value of up to 0,9403. This data shows better performance of convolutional neural networks in automated diagnosis. The results of the study show that neural network technology can effectively relieve the workload of doctors and provide diagnostic support for future public health events. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Real-Time Decentralized Smile Detection in Virtual Reality Environments

Federated Learning for Real-Time Decentralized Smile Detecti...

引用

Metaverse Computing, Networking and Applications (MetaCom), IEEE International Conference on

作者： Salabat Khan Anwar Ghani Syed Shehreyar Ali Naqvi Murad Ali Khan Muhammad Faseeh Do Hyeun Kim Muhammad Sharif Dept. of Computer Engineering Big Data Research Center Jeju National University South Korea Dept. of Computer Engineering Jeju National University South Korea Dept. of Computer Science Comsats University Islamabad Pakistan

ISBN: (数字)9798331515997

ISBN: (纸本)9798331516000

Facial expression detection is paramount in real-world applications, including patient monitoring, photo selection, and facial protection within the metaverse and virtual reality environments. Among various expressions, detecting smiles poses a significant challenge. Traditional methods relying on low-level face descriptors are being superseded by advancements leveraging Convolutional Neural Networks (CNNs) to enhance smile detection performance. In this research, we introduce and implement three CNN architectures tailored for smile detection from facial images. Our proposed model incorporates a fully convolutional neural network featuring two deep convolutional layers dedicated to smile detection. Additionally, pre-trained LeNet and DenseNet CNNs are employed for this task. The effectiveness of our approach is demonstrated through extensive evaluations of the Hromada dataset, encompassing images with and without smiles within the virtual reality environment. Moreover, we delve into detailed discussions on the practicality and efficacy of CNNs in facial expression detection, explicitly focusing on smile detection in real-time scenarios. Our experiments are conducted within a federated learning framework, enabling model inference and optimization for privacy preservation and scalability of the smile detection system in large-scale virtual reality applications. Through this decentralized approach, we address challenges related to real-time detection, model inference, and collaboration in the metaverse.

关键词： Training Solid modeling Federated learning Metaverse Scalability Collaboration Virtual reality Real-time systems Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Near-Field Codebook Design for General Antenna Arrays

Electromagnetic Near-Field Codebook Design for General Anten...

引用

Asilomar Conference on Signals, systems & computers

作者： Miguel Rodrigo Castellanos Robert W. Heath Dept. of Electrical Engineering and Computer Science University of Tennessee Knoxville TN Dept. of Electrical and Computer Engineering University of California San Diego La Jolla CA

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

Precoding codebooks facilitate efficient channel state information acquisition in high-dimensional MIMO systems. Most codebook designs, however, are agnostic to the antenna array composition and the underlying gain pattern profiles. We leverage an electromagnetic characterization of the antenna array manifold to generalize the codebook design problem. Specifically, we formulate the codebook design problem in a manner that incorporates polarization, near-field propagation and the antenna array characteristics. Our proposed approach is also flexible enough to adapt to different antenna types and even to heterogenous arrays. Our numerical results demonstrate that the electromagnetic-based codebooks achieve higher beamforming gains than approaches that neglect antenna effects.

关键词： Manifolds computers Mutual coupling Precoding Adaptive arrays Receivers MIMO Numerical models Electromagnetics Design optimization

来源：评论

学校读者我要写书评

暂无评论

Vehicle Detection and Speed Estimation Using Deep Learning

Vehicle Detection and Speed Estimation Using Deep Learning

引用

Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), IEEE International Conference on

作者： Vishnu Kumar Mishra Megha Mishra Rajesh Tiwari T Ram Kumar Tarun Dhar Diwan Raj Kumar Patra Dept. of Computer Science and Engineering Malla Reddy Engineering college for Women Hyderabad India Department of Computer Science and Engineering Shri Shankaracharya Technical Campus CSVTU Bhilai India Department of Computer Science and Engineering CMR Engineering College Hyderabad India Dept. of Computer Science and CoE Atal Bihari Vajpayee University Bilaspur Chhattisgarh India

ISBN: (数字)9798331505790

ISBN: (纸本)9798331505806

The use of deep learning algorithms for vehicle detection and speed estimate in traffic surveillance systems is investigated in this research study. Convolutional Neural Networks (CNNs) are the main tool used in this study to solve the problems related to precise and timely monitoring of vehicle movement. By improving the effectiveness and dependability of current systems, the suggested approach hopes to promote traffic management for smart transportation.

关键词： Deep learning YOLO Statistical analysis Vehicle detection Surveillance Estimation Traffic control Cameras Trajectory Automobiles

来源：评论

学校读者我要写书评

暂无评论

Design and Implement Driveway Door Access Control by Using VLC and RFID Technology 12

Design and Implement Driveway Door Access Control by Using V...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Hung, Chi-Huang Fanjiang, Yong-Yi Li, Cheng-Yen Chiu, Sheng-Wei Hung, Tzu-Chieh Chiang, Meng-Huan Fu Jen Catholic University Lee-Ming Institute of Technology Graduate Institute of Applied Science and Engineering Dept. of Information Technology New Taipei City Taiwan Fu Jen Catholic University Graduate Institute of Applied Science and Engineering Dept. of Computer Science and Information Engineering New Taipei City Taiwan Fu Jen Catholic University Graduate Institute of Applied Science and Engineering New Taipei City Taiwan Lee-Ming Institute of Technology Dept. of Vehicle Engineering New Taipei City Taiwan Kang Chiao International School Dept. of International High School New Taipei City Taiwan

ISBN: (纸本)9798350340181

In recent years, the application of radiofrequency identification technology in smart access control systems has become a trend. Users only need to take out the RFID electronic key and approach the sensor of the gate to open the gate through signal induction. For housewives who always have a lot of bags and bags in their hands, there is no need to free up one hand to find the key to open the door and avoid being in a hurry. However, it is relatively inconvenient for drivers. Instead, it is much more convenient to use wireless controllers or license plate recognition. This study proposes a system that combines RFID with optical communication technology and vehicle headlights to open the garage door with a light code. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

A Field Practical Approach to Memory Bandwidth Allocation for Consolidating Multi-Domain Automotive Applications on a Single SoC

A Field Practical Approach to Memory Bandwidth Allocation fo...

引用

IEEE Symposium on Real-Time and Embedded Technology and Applications

作者： Hayeon Park Jiwoong Lee Hoyong Lee Taekyoung Kwon Wan Choi Sangmi Moon Chang-Gun Lee Dept. of Computer Science and Engineering Seoul National University Republic of Korea Dept. of Electrical and Computer Engineering Seoul National University Republic of Korea Dept. of IT Artificial Intelligence Korea Nazarene University Republic of Korea

ISBN: (数字)9798331543402

ISBN: (纸本)9798331543419

Along with the advent of a high-end SoC with multiple CPU clusters and many GPUs, the automotive industry has a strong motivation to consolidate multi-domain applications on such a single SoC for wiring harness reduction and space/weight saving. For this, it is essential to bound their mutual interferences among CPU+GPU clusters on the system memory since advanced automotive applications use huge size code/data like autonomous driving and multi-screen infotainment. In order to guarantee memory bandwidth to each cluster, this paper proposes a cluster-level memory access regulation that aggregates the total memory access amount by each cluster (by all CPU cores and GPUs within the cluster) and throttles the cluster if it exceeds the given threshold. Then, we propose a few-shot measurement based optimal memory bandwidth allocation that can find a near optimal solution with only a few measurements, which is practically essential to save the system development cost. Our extensive experiments on a real SoC board say that our proposed techniques successfully regulate each cluster's memory bandwidth usage within ± 10 % margin of the allocated bandwidth. Also, our optimization can achieve a near-optimal utility with less than 0.6 % loss on average compared to the real optimal, with only a few measurements (mostly three measurements) instead of 25 measurements needed for the real optimal.

关键词： Wiring Costs Memory management Automotive applications Bandwidth Channel allocation Regulation Loss measurement Timing Optimization

来源：评论

学校读者我要写书评

暂无评论

Development of IoT-based Scale Sensor to Measure AWD system Water Level in Crop Field

Development of IoT-based Scale Sensor to Measure AWD System ...

引用

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Md Shahriar Kabir Khalid Mahmud Niloy Md Imon Hossen Sumaiya Afrose Md. Ismail Hossain Mofazzol Dept. of Electrical & Electronics Engineering American International University-Bangladesh Dept. of Computer Science Engineering Uttara University Dhaka Bangladesh

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

The paper introduces an innovative Internet of Things (IoT)-based scale sensor that measures the water level in the alternate wetting and drying (AWD) system and displays data in the mobile app to enable remote monitoring. The AWD system mainly consists of 30 cm of PVC pipe or bamboo with a diameter of 10-15 cm inserted into the paddy field, with a lower 20 cm buried in the soil and tiny holes at the bottom to allow field water to enter. The water level within the pipe indicates the field's water level, especially the underground water level. The AWD method optimizes water usage and reduces methane emissions by watering periodically and drying rice fields instead of maintaining continuous flooding. The current manual measurement process for water level needs to go to crop fields daily with a scale, which is difficult for continuous and remote monitoring. The developed scale sensor has IoT connectivity that removes the difficulties. The scale sensor works based on conductive rain sensors to precisely detect each centimeter rise or fall of water. The sensor consists of two open conductive layers that create a short circuit when the water level touches them by raising, triggering the microcontroller to register a voltage drop. The scale can measure up to 20 cm as it has 20 conductive layers, which fulfill the requirements. It has a 1 cm resolution, and in the test, it shows 95-99% accuracy. So, the sensor can effectively measure the water level in the AWD system, and further research is required to add an automatic irrigation system with the sensor so that the whole process can be controlled remotely.

关键词： Irrigation Accuracy Microcontrollers Crops Soil Robot sensing systems Mobile applications Timing Internet of Things Remote monitoring

来源：评论

学校读者我要写书评

暂无评论

PhishGuard: A Convolutional Neural Network-Based Model for Detecting Phishing URLs with Explainability Analysis

PhishGuard: A Convolutional Neural Network-Based Model for D...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Md Robiul Islam Md Mahamodul Islam Mst. Suraiya Afrin Anika Antara Nujhat Tabassum Al Amin Dept. of Computer Science and Engineering Uttara University Dhaka Bangladesh Dept. of Informatics University of Oslo Oslo Norway Dept. of Building Engineering and Construction Management Khulna University of Engineering and Technology (KUET) Khulna Bangladesh Dept. of Electrical and Electronics Engineering BRAC University Dhaka Bangladesh Dept. of Electrical and Computer Engineering North South University Dhaka Bangladesh Dept. of Computer Science American International University Bangladesh (AIUB) Dhaka Bangladesh

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Abstract-Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models’ decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a $1 D$ Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85 %. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL.

关键词： Uniform resource locators Deep learning Analytical models Accuracy Phishing Organizations Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Information Flow in Multimodal Large Language Models

arXiv

引用

arXiv 2024年

作者： Zhang, Zhi Yadav, Srishti Han, Fengze Shutova, Ekaterina ILLC University of Amsterdam Netherlands Dept. of Computer Science University of Copenhagen Denmark Dept. of Computer Engineering Technical University of Munich Germany

The recent advancements in auto-regressive multimodal large language models (MLLMs) have demonstrated promising progress for vision-language tasks. While there exists a variety of studies investigating the processing of linguistic information within large language models, little is currently known about the inner working mechanism of MLLMs and how linguistic and visual information interact within these models. In this study, we aim to fill this gap by examining the information flow between different modalities—language and vision—in MLLMs, focusing on visual question answering. Specifically, given an image-question pair as input, we investigate where in the model and how the visual and linguistic information are combined to generate the final prediction. Conducting experiments with a series of models from the LLaVA series, we find that there are two distinct stages in the process of integration of the two modalities. In the lower layers, the model first transfers the more general visual features of the whole image into the representations of (linguistic) question tokens. In the middle layers, it once again transfers visual information about specific objects relevant to the question to the respective token positions of the question. Finally, in the higher layers, the resulting multimodal representation is propagated to the last position of the input sequence for the final prediction. Overall, our findings provide a new and comprehensive perspective on the spatial and functional aspects of image and language processing in the MLLMs, thereby facilitating future research into multimodal information localization and editing. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Deep Defense: A Hybrid LSTM-ANN Architecture for Intelligent Intrusion Detection system

Deep Defense: A Hybrid LSTM-ANN Architecture for Intelligent...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Mohit Shadeja Shashwat Singh Ayushi Prakash Dept. of Computer Science and Engineering Ajay Kumar Garg Engineering College Ghaziabad Uttar Pradesh India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

The rapidly evolving cyber threat landscape requires innovative and adaptive intrusion detection solutions. Traditional signature-based intrusion detection systems, despite their high accuracy, are inherently inflexible and susceptible to evasion tactics, making them ineffective against novel and sophisticated attacks. In contrast, machine learning-powered anomaly-based intrusion detection systems demonstrate improved detection capabilities, but their advantages are often outweighed by substantial drawbacks, including significant computational resource requirements when the dataset and its features for behavior analysis increase. Also, there are high power consumption and latency issues in communication that compromise network performance. This study proposes a hybrid ANN-LSTM approach for performing deep packet inspection and efficiently detecting malicious network packets. By analyzing binary container data, our model reduces time and space complexity, thereby mitigating the computational resources and power consumption challenges but also increasing the efficiency of intrusion detection by 3%, making it more intelligent than various established IDS.

关键词： Power demand Computational modeling Intrusion detection Machine learning computer architecture Inspection Containers Feature extraction Data models Computational intelligence

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：