检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Chaudhari, Namrata Agarwal, Reshu Narwade, Meghna Yu, Xinrui Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Department of Electrical and Computer Engineering Research Laboratory ChicagoIL United States

ISBN: (纸本)9781665480093

Harnessing the power of emotional intelligence by analyzing a person's behavioral and linguistic skills can help humans improve their approach to social interactions. In this paper, we propose an artificial intelligence-based stand-alone system that will allow us to classify and analyze facial expressions in real-time and perform sentiment analysis by examining the body of the text (extracted from audio) to understand the opinion expressed by it. This helps us provide a deeper understanding of how humans really feel at a given time. The proposed system uses a deep neural network (DNN) for classifying eight basic emotions based on features extracted from facial expressions and uses pretrained sentiment analysis tools to quantify text (extracted from audio) based on polarity. The system is implemented by extracting the audio and visual cues from real-time scenarios and using these extracted cues to perform facial expression recognition and text sentiment analysis. The integrated system extracts video and audio simultaneously with a frame rate of 4-5 fps. The facial emotion detection system successfully detects facial expressions of faces detected in real-time video with an accuracy of about 86.75%. The speech extracted is converted to text, cleaned, and processed to determine if the attitude of the speaker in a given situation is positive, negative, or neutral. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

High Precision Analog Gauge Reader Using Optical Flow and computer Vision

High Precision Analog Gauge Reader Using Optical Flow and Co...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Chavan, Shruti Yu, Xinrui Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Department of Electrical and Computer Engineering Research Laboratory ChicagoIL United States

ISBN: (纸本)9781665480093

This paper aims at developing algorithms to automate the process of reading analog gauges at different operational industries, healthcare sector and automobiles using Artificial Intelligence (AI) techniques. Proposed algorithms start with video stabilization using optical flow followed by image processing which performs segmentation using HSV color space and morphological operations. Next, Hough transform is applied to determine the dial region and pointer. Using the coordinates locating the pointer in the frame, angle made with minimum valued scale mark is calculated using trigonometry and evaluated reading is displayed in the form of text and a progress bar. The proposed algorithms for Analog Gauge Reader (AGR) is executed using open-source libraries such as OpenCV, NumPy, PIL with Python programming and it is developed in the PyCharm environment. The experimental results show significant decrease in the error with the introduction of image preprocessing and the generalizability of the algorithm to different types of analog gauges captured in different conditions of illuminance. The accuracy and precision of the algorithms is 99% to 100% in the experimental studies. © 2022 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Soccer Player Recognition using Artificial Intelligence and computer Vision

Soccer Player Recognition using Artificial Intelligence and ...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Diop, Charles-Alexandre Pelloux, Baptiste Yu, Xinrui Yi, Won-Jae Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Research Laboratory Department of Electrical and Computer Engineering ChicagoIL United States

ISBN: (纸本)9781665480093

Groundbreaking features and functionalities are available in sports broadcasting programs, specifically in soccer games, such as post-game analysis, tracking of players, tracking of the ball, and associated teams' and players' statistical information. However, viewers don't have control to choose which features to view on-demand and aren't able to interact with any of these functionalities. Our system aims for the fundamental system of an on-demand viewer-driven application that would be able to track players on the field, identify formation changes, follow team strategy changes, and gather all statistical information of the player and the team on a single screen. In order to realize such an application, we focus on developing a method to track players on the field using multiple Artificial Intelligence (AI) and computer vision techniques where our application employs facial recognition and jersey number recognition algorithms. As a live soccer game broadcast would have various camera views of the players, our custom-made database contains captured images from different scenarios of camera views such as different angles and zooms of the player and is used to train the model using Convolutional Neural Network (CNN). Our system is scalable to different types of sports, such as basketball, baseball, volleyball, and more where players have their numbers on their jerseys and would be feasible to apply our system since soccer involves more players on the field than other sports games. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection and Characterization of Human Veins Using Infra-Red Image processing

引用

Journal of computer and Communications 2024年第9期12卷 141-159页

作者： Jean Ndoumbe Brice Ekobo Akoa Gaelle Patricia Talotsing Frederic Franck Kounga Samuel Kaissassou Bertin Chouanmo Njo Laboratory of Computer Engineering Data Science and Artificial Intelligence Department of Computer & Telecommunications Engineering National Higher Polytechnic School Douala Cameroon Laboratory of Electrical Engineering Mechatronics and Signal Processing Department of Electrical & Telecommunications Engineering National Advanced School of Engineering Yaound Cameroon Mobile Computing and Networking Research Laboratory Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada DigiPlus SARL Bonamoussadi Douala Cameroon

The detection and characterization of human veins using infrared (IR) image processing have gained significant attention due to its potential applications in biometric identification, medical diagnostics, and vein-based authentication systems. This paper presents a low-cost approach for automatic detection and characterization of human veins from IR images. The proposed method uses image processing techniques including segmentation, feature extraction, and, pattern recognition algorithms. Initially, the IR images are preprocessed to enhance vein structures and reduce noise. Subsequently, a CLAHE algorithm is employed to extract vein regions based on their unique IR absorption properties. Features such as vein thickness, orientation, and branching patterns are extracted using mathematical morphology and directional filters. Finally, a classification framework is implemented to categorize veins and distinguish them from surrounding tissues or artifacts. A setup based on Raspberry Pi was used. Experimental results of IR images demonstrate the effectiveness and robustness of the proposed approach in accurately detecting and characterizing human. The developed system shows promising for integration into applications requiring reliable and secure identification based on vein patterns. Our work provides an effective and low-cost solution for nursing staff in low and middle-income countries to perform a safe and accurate venipuncture.

关键词： Vein Detection Blood Radiation Infrared Image CLAHE Algorithm Raspberry Pi

来源：评论

学校读者我要写书评

暂无评论

MCFTNet: Multimodal Cross-Layer Fusion Transformer Network for Hyperspectral and LiDAR Data Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12803-12818页

作者： Huang, Wei Wu, Tianren Zhang, Xueyu Li, Liangliang Lv, Ming Jia, Zhenhong Zhao, Xiaobin Ma, Hongbing Vivone, Gemine Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi830017 China Guangxi University School of Computer and Electronic Information Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Tsinghua University Department of Electronic Engineering Beijing100084 China National Research Council Tito85050 Italy National Biodiversity Future Center NBFC Palermo90133 Italy

Remote sensing image classification is a popular yet challenging field. Many researchers have combined convolutional neural networks (CNNs) and Transformers for hyperspectral imaging (HSI) classification tasks. However, in traditional Transformers, shallow-level information does not propagate well to deeper layers, which can lead to spatial variations and overfitting. Moreover, traditional Transformer models use an external classification token (CLS token) that is randomly initialized and often struggles to generalize effectively. In this article, we combine the strengths of HSI and light detection and ranging (LiDAR) data, using LiDAR as an external CLS token, which significantly enhances classification accuracy and reliability. We propose a new multimodal cross-layer fusion transformer network (MCFTNet), integrating CNNs with the latest Transformer networks. It includes a CNN for extracting spatial features and a hybrid cross-patch attention mechanism for land cover classification, leveraging LiDAR data to generate CLS and HSI patch tokens. More importantly, to reduce the loss of valuable information during the layer-by-layer propagation, we designed cross-layer skip connections. Through adaptive learning, these cross-layer fusions help address the gradient vanishing problem in deep networks while preserving early-layer features. This enables the model to better integrate information from different layers, enhancing both its stability and performance. We carried out in-depth experiments on commonly used benchmark datasets, specifically, the University of Houston dataset, the Trento dataset, and the University of Southern Mississippi Gulf Park dataset. We compared the results of the proposed MCFTNet model with those obtained from state-of-the-art Transformer models, classical CNNs, and traditional classifiers. As a result, the MCFTNet model outshones them all in terms of performance. © 2008-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Coverage analysis and handover strategy in RF/VLC heterogeneous networks

引用

Applied Optics 2025年第15期64卷 4160-4173页

作者： Feng, Renhai Guo, Yatong Yousaf, Muhammad Zain Khan, Baseem Luo, Liping School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Physics and Electronic Engineering Xinjiang Normal University Ürümqi830054 China Center for Renewable Energy and Microgrids Huanjiang Laboratory Zhejiang University Zhejiang Zhuji311816 China School of Electrical and Information Engineering Hubei University of Automotive Technology Shiyan China School of Aeronautics and Astronautics Zhejiang University Hangzhou310027 China Department of Electrical and Computer Engineering Hawassa University Hawassa Ethiopia School of Electronics and Information Guangxi Minzu University Nanning530006 China Guangxi Colleges Universities Engineering Research Center for Multi-modal Information Intelligent Sensing Processing and Application Nanning530006 China

Coverage analysis in heterogeneous networks (HetNets) remains insufficient, especially under user mobility and diverse association strategies. To address this, this paper proposes a contact probability and coverage approximation based on association strategy (CPCA-AS) to analyze the coverage probability (CPr) in visible light communication (VLC) and radio frequency (RF) HetNets. Based on the proposed stochastic geometry framework, CPCA-AS evaluates coverage performance under various configurations, including RF-only, VLC-only, and hybrid RF/VLC scenarios. The model incorporates a contact probability mechanism and considers two strategies: opportunistic VLC and maximum received signal power (MRSP). For VLC networks, CPCA-AS utilizes the Gil-Pelaez inversion theorem, and Laplace transforms to efficiently approximate CPr. For RF networks, Markov and Gamma inequalities form conservative accurate approximations and lower bounds. CPCA-AS effectively captures the influence of the photodetector’s field-of-view (FoV) on interference and association behavior. Monte Carlo simulations validate the accuracy of the CPCA-AS. Results demonstrate that CPCA-AS improves CPr. The opportunistic VLC strategy performs better in high-interference and large FoV scenarios. In contrast, the MRSP strategy is more effective in low-interference and low-rate environments. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Multiframe weak target track-before-detect based on pseudo-spectrum in mixed coordinates

引用

Chinese Journal of Aeronautics 2022年第5期35卷 97-113页

作者： Liangliang WANG Gongjian ZHOU Thiagalingam KIRUBARAJAN School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin 150001China Key Laboratory of Marine Environmental Monitoring and Information Processing Ministry of Industry and Information TechnologyHarbin 150001China Department of Electrical and Computer Engineering McMaster UniversityONHamilton L8S 4K1Canada

Traditional multiframe Track-Before-Detect(TBD)may incur adverse integration loss resulting from model mismatch in sensor *** suboptimal integration strategy may cause target envelope *** address these issues,a pseudo-spectrum-based multiframe TBD in mixed coordinates is proposed *** data search for energy integration is conducted based on an accurate model in the x-y plane while target energy is integrated based on pseudo-spectrum in sensor *** algorithm performance is improved since the model mismatch is eliminated,and the pseudo-spectrum based integration facilitates well maintained target *** detailed multiframe integration procedure and theoretical target integrated envelope are ***,to cope with the unknown target velocity,a velocity filter bank based on pseudo-spectrum in mixed coordinates is *** effect of velocity mismatch on algorithm performance is analyzed and an efficient method for filter bank design is ***,a parameter estimation method using characteristics of integrated envelope is presented for improved target polar position and Cartesian velocity ***,numerical results are provided to demonstrate the effectiveness of the proposed method.

关键词： Mixed coordinates Multiframe detection Pseudo-spectrum Track-before-detect Weak target detection

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification Through Speech Data Analysis 23

Emotion Classification Through Speech Data Analysis

引用

Proceedings of the Winter Simulation Conference

作者： Luzalen Marcos Kristiina Valter Mai Abdolreza Abhari Resilience Engineering Lab Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto Canada Distributed Systems and Multimedia Processing (DSMP) Lab Department of Computer Science Toronto Metropolitan University Toronto Canada

ISBN: (纸本)9798350369663

Good quality healthcare services require effective communication between the patient and the healthcare provider. This work will help improve the areas of healthcare systems automation and optimization by applying Speech Emotion Recognition (SER) in health consultations to prevent miscommunication between patients and healthcare providers. Crowd-Sourced Emotional Multimodal Actors Dataset (CREMA-D) was used to compare the performances of different machine learning models in classifying emotions. Before feeding the raw dataset to the models, exploratory data analysis was done to determine features that should be considered for future analysis. Our results showed that depending on the emotion, there are some syllables in the text that were emphasized or took time to be pronounced by the speaker. After data analysis, the dataset was fed into different models and determined that the Support Vector Machine (SVM) is a machine-learning model for SER.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient AES 32-Bit Architecture Resistant to Fault Attacks

引用

computers, Materials & Continua 2022年第2期70卷 3667-3683页

作者： Hassen Mestiri Imen Barraj Abdullah Alsir Mohamed Mohsen Machhout Department of Computer Engineering College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Higher Institute of Applied Sciences and Technology of Sousse University of SousseTunisia Electronics and Micro-Electronics Laboratory Faculty of Sciences of MonastirUniversity of MonastirTunisia METS Research Group Electrical Engineering DepartmentNational Engineers School of SfaxUniversity of SfaxTunisia Higher Institute of Computer Science and Multimedia of Gabes University of GabesTunisia

The Advanced Encryption Standard cryptographic algorithm,named AES,is implemented in cryptographic circuits to ensure high security level to any system which required confidentiality and secure information *** of the most effective physical attacks against the hardware implementation of AES is fault attacks which can extract secret *** now,a several AES fault detection schemes against fault injection attacks have been *** this paper,so as to ensure a high level of security against fault injection attacks,a new efficient fault detection scheme based on the AES architecture modification has been *** this reason,the AES 32-bit round is divided into two half rounds and input and pipeline registers are implemented between *** proposed scheme is independent of the procedure the AES is ***,it can be implemented to secure the pipeline and iterative *** evaluate the robustness of the proposed fault detection scheme against fault injection attacks,we conduct a transient and permanent fault attacks and then we determine the fault detection capability;it is about 99.88585%and 99.9069%for transient and permanent faults *** have modeled the AES fault detection scheme using VHDL hardware language and through hardware FPGA *** FPGA results demonstrate that our scheme can efficiently protect the AES hardware implementation against fault *** can be simply implemented with low *** addition,the FPGA implementation performances prove the low area overhead and the high efficiency and working frequency for the proposed AES detection scheme.

关键词： Security cryptographic circuits AES hardware implementation fault detection fault attacks

来源：评论

学校读者我要写书评

暂无评论

Active-IRS-Enabled Energy-Efficiency Optimizations for UAV-Based 6G Mobile Wireless Networks 57

Active-IRS-Enabled Energy-Efficiency Optimizations for UAV-B...

引用

57th Annual Conference on Information Sciences and Systems, CISS 2023

作者： Wang, Fei Zhang, Xi Southwest University Chongqing Key Laboratory of Non-linear Circuit and Intelligent Information Processing College of Electronic and Information Engineering Chongqing400715 China Texas AandM University Networking and Information Systems Laboratory Department of Electrical and Computer Engineering College StationTX77843 United States

ISBN: (纸本)9781665451819

We propose the novel scheme to solve a multi-objective optimization problem over an unmanned aerial vehicle (UAV) communications system to jointly minimize the energy consumption of the UAV and ground users (GUs). In particular, the UAV communicates with multiple GUs using active intelligent reflecting surfaces (IRSs), which can actively amplify and thus significantly enhance the strengths of reflected signals. We develop an energy minimization scheme based on the multi-objective hierarchical deep reinforcement learning (DRL), by decomposing the formulated optimization problem into two-layered subproblems. By solving the upper-level subproblem, we derive the optimal UAV trajectory and GUs scheduling strategies to minimize the UAV's energy consumption. By solving the lower-level subproblem, we obtain the IRS's phase shifts and amplification factors and GUs' transmit/receive beamforming to minimize the GUs' energy consumption. Finally, we validate and evaluate the proposed schemes through simulations, which show that the UAV's and GUs' energy consumption can be significantly reduced by using the active IRS, when the thermal noise powers at the IRS are much smaller than those at the UAV and GUs. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

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：