检索结果-内蒙古大学图书馆

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Hossain, Md Junayed Rahman, Shoptorshi Monir, Md Fahad Ahmed, Tarem Department of Computer Science & Engineering Bangladesh Virginia Polytechnic Institute and State University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331504847

Real-time object detection is pivotal in various computer vision and robotics applications, such as security surveillance, autonomous navigation, and interactive systems. This study evaluates several object detection algorithms under low illumination conditions, comparing traditional methods including SIFT, SURF, ORB, BRISK, KAZE, and AKAZE with the deep learning model YOLOv5. To simulate these conditions, we utilized the COCO dataset and implemented a sequence of preprocessing procedures, such as adjusting the gamma correction throughout the dataset, introducing Gaussian noise, and equalizing the histogram to improve image contrast. Here, YOLOv5 exhibited superior performance, achieving a detection accuracy of 92.47% and a processing time of 45 milliseconds per image. Traditional algorithms like SURF and KAZE, although slower, demonstrated precision rates of 78.54% and 76.86%, respectively. YOLOv5 also identified the highest number of key points and matches. Our findings indicate that while YOLOv5 excels in real-time detection under low-light conditions, traditional methods are effective for specific tasks in resource-constrained environments. This study benchmarks these algorithms and proposes a hybrid approach to enhance real-time object detection systems under low illumination conditions. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Coffee Bean Binary Classification Through Deep Learning Techniques 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Islamy, Fajrul Muchtar, Kahlil Arnia, Fitri Dawood, Rahmad Febriana, Alifya Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Master of Computer Science Program BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Coffee beans are one of the high-value commodities in Indonesia, but the sorting method for the quality of coffee beans still uses visual methods and sieves with mechanical machines. This study aims to provide an alternative to classifying coffee beans using Deep Learning algorithms, such as the ResNet-18 and MobileNetV2. The dataset used is USK-COFFEE which consists of two classes, the normal coffee bean class, and the defect coffee bean class. The models were trained using the balanced and imbalanced datasets, meaning that two scenarios were performed. From the results of this study, the accuracy value for the ResNet-18 model was 91.50% when trained on the balanced dataset and 90.87% on the imbalanced dataset. It outperformed the MobileNetV2 architecture, which only achieved 0.8125 and 0.8112 accuracy scores when trained on the balanced and imbalanced datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Applying t-Distributed Stochastic Neighbor Embedding for Improving Fingerprinting-Based Localization System

IEEE Sensors Letters

引用

IEEE Sensors Letters 2023年第9期7卷 1页

作者： Tarekegn, Getaneh Berie Tai, Li-Chia Lin, Hsin-Piao Tesfaw, Belayneh Abebe Juang, Rong-Terng Hsu, Huan-Chia Huang, Kai-Lun Singh, Kanishk National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu30010 Taiwan National Yang Ming Chiao Tung University Institute of Electrical and Control Engineering Hsinchu30010 Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei10608 Taiwan National Taipei University of Technology Department of Electrical Engineering and Computer Science Taipei10608 Taiwan Feng Chia University Department of Electronic Engineering Taichung40724 Taiwan Industrial Technology Research Institute Information and Communications Research Laboratories Hsinchu310401 Taiwan

Large-scale location estimation is crucial for many artificial intelligence Internet of Things (IoT) applications in the era of smart cities. This letter proposes a deep learning-based outdoor positioning scheme for large-scale wireless settings using fingerprinting techniques. We first developed a feature extraction technique using t-distributed stochastic neighbor embedding (t-SNE) to extract dominant and distinguishable features while eliminating noises from the radio fingerprints. Afterward, we developed a deep learning-based coarse-fine localization framework to improve positioning performance significantly. Based on our numerical analysis, the proposed scheme reduces computation time by 64.41%, and the average positioning error is 38 cm. Therefore, the proposed approach significantly improved positioning accuracy and reduced computation time. © 2017 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Review of thermal performance enhancement of Solar Air Heater using baffles on absorber plate 16

Review of thermal performance enhancement of Solar Air Heate...

引用

16th International Conference on Development and Application Systems, DAS 2022

作者： Ifrim, Visarion-Catalin Grosu, Oana Vasilica University 'tefan cel Mare' of Suceava Faculty of Electrical Engineering and Computer Science Department of Electrical Engineering Suceava Romania

ISBN: (纸本)9781665481625

Of all renewable energies, solar energy is abundantly available and can meet current energy requirements if captured and used wisely. Solar hot air heaters are used to capture suns thermal energy and release it to a fluid present in the system. Most often this fluid is air, which after the heat transfer made between it and the absorption surface, it's used either to heat spaces or to dry various farming products. For high efficiency the absorber plate of the system must capture solar energy in as much as possible and retain energy in the presence of sunlight and release it in the absence thereof. The indoor environment to achieve a greenhouse effect without energy loss and a complete heat transfer through the absorption surface and the fluid are desirable to achieve better performances. Improving heat transfer is achievable by using obstacles on the absorber surface that break the present laminar flow and creates vortexes or eddy currents that take over a greater amount of thermal energy from the absorption surface. This work presents various investigations carried out on solar air heaters with deflectors on the absorber plate. The results obtained are summarized and referred in the paper. © 2022 IEEE.

关键词： Laminar flow

来源：评论

学校读者我要写书评

暂无评论

Continuous Wavelet Transform Spectral Image Based Epileptic Episode Classification 25

Continuous Wavelet Transform Spectral Image Based Epileptic ...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Nuhi-Alamin, Md. Sarkar, Ajay Krishno Talukder, Md. Simul Hasan Aljaidi, Mohammad Swapnil, Safkat Shahrier Rajshahi University of Engineering & Technology Department of Electrical and Electronic Engineering Rajshahi Bangladesh Dhaka University of Engineering & Technology Department of Electrical and Electronic Engineering Gazipur Bangladesh Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331540012

Numerous individuals globally, regardless of age, have the neurological condition epilepsy. Recurrent seizures compromised motor and sensory abilities, and a hindered normal lifestyle are all signs of epilepsy. By seeing or manually examining electroencephalogram (EEG) data, neurologists can make the diagnosis of epileptic seizures. In this paper, a continuous wavelet transform spectral image-based epileptic episode classification technique is proposed. The EEG signal was first converted into 227x227 RGB images using CWT. Then these images were used to create an image dataset, and classification was performed using the proposed deep ensemble epileptic seizure classifier (DE-ESC). DE-ESC ensembled Dense-net-169, Dense-net-201, and Inception-V3. This proposed method obtained 100% accuracy (Ac), precision (Pr), recall, and F1 Score, respectively. © 2024 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Fiber-Optic Raman Probe for On-line EAF Slag Analysis

Fiber-Optic Raman Probe for On-line EAF Slag Analysis

引用

AISTech 2023 Iron and Steel Technology Conference and Exposition

作者： Zhang, Bohong Tekle, Hanok O’Malley, Ronald J. Sander, Todd Smith, Jeffrey D. Bartlett, Laura Mumtaz, Farhan Gerald, Rex E. Huang, Jie Department of Electrical and Computer Engineering Missouri University of Science and Technology RollaMO65409 United States Department of Materials Science and Engineering Missouri University of Science and Technology RollaMO65409 United States

ISBN: (纸本)9780930767211

In Electric Arc Furnace (EAF) steelmaking, the push for improved efficiency requires accurate analysis of the chemical composition of its slag system to control slag foaming, provide refractory protection, and maintain high furnace iron yield. Therefore, the ability to obtain real-time slag chemistry data would provide a useful tool to improve the control and efficiency of the process. The work reported here aims to assess the structure and chemistry of EAF slags at high temperatures using a portable fiber-optic Raman probe. The ability to relate Raman spectra peaks to chemistry and structure is demonstrated in experimental result with EAF slags at 1550°C. © 2023 by the Association for Iron & Steel Technology.

关键词： Alkalinity

来源：评论

学校读者我要写书评

暂无评论

Facilitating Safe Automated Navigation in Ice with Cooperating Autonomous Vehicles

Facilitating Safe Automated Navigation in Ice with Cooperati...

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Kio, Onoise G. Afolabi, Faruq McGregor, Alexander Garvin, Matthew Gash, Robert Allison, Robert S. York University Department of Electrical Engineering and Computer Science Toronto Canada National Research Council Canada Ocean Coastal and River Engineering Research Center St. John's Canada

ISBN: (纸本)9798331540081

Autonomous shipping has gained much interest in the last decade stemming from several desirable safety and environmental benefits. A significant boost to Canada's autonomous shipping drive would be adequately monitoring ice conditions in shipping environments with unmanned assets and calculating safe navigation routes for autonomous ships. A workflow was created to simulate an unmanned aerial vehicle (UAV) cooperating with a maritime autonomous surface ship (MASS) to facilitate the MASS's safe navigation through an icy waterway. Both vehicles were modeled as MATLAB Simulink's Sim3D objects operating in an icy shipping environment representing a section of Canada's St Lawrence Seaway and built with Unreal Game Engine version 4.26.2. The UAV performed regular ice-condition-monitoring flights over the shipping environment with its vision and LiDAR sensors. Maps of Ice Numerals (IN) pertaining to the MASS's class were developed from processed data from the UAV's sensors. They served as inputs to a Rapidly Exploring Random Tree (RRT) algorithm that estimated safe obstacle free routes for the MASS through the shipping environment. Colour-coded hazard maps specifying safe and hazardous waterway regimes were also developed from IN maps. Hazard maps could serve as navigational aids to operators monitoring MASS operations in hazardous environments. Results obtained from testing the workflow on the MA TLAB Simulink + Unreal Engine simulation environment produced the desired INs and hazard maps with safe navigation routes for the MASS. These results show the possibility of having autonomous assets corporate to facilitate safe autonomous navigation in ice. © 2024 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

Stability of nonlinear systems with slow and fast time variation and switching: the common equilibrium case 63

Stability of nonlinear systems with slow and fast time varia...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Liberzon, Daniel Shim, Hyungbo University of Illinois Urbana-Champaign Coordinated Science Laboratory UrbanaIL61801 United States Seoul National University Department of Electrical and Computer Engineering Korea Republic of

ISBN: (纸本)9798350316339

In this paper we consider a class of nonlinear systems with two kinds of inputs: one is slowly-varying, the other is fast-varying and periodic, and both are only piecewise continuous. Under the assumption that the origin is a common equilibrium for all values of the input signals, we provide sufficient conditions under which this equilibrium is semi-globally exponentially stable. Our approach is based on considering the (partial) average system which averages out the fast variation but retains the slow variation, and which can be used to approximate the original system in a certain sense. The stability conditions involve the existence of a suitable Lyapunov function for this average system, along with a bound on the total variation of the slowly-varying input. © 2024 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Generalized Helmholtz Decomposition for Modal Analysis of Electromagnetic Problems in Inhomogeneous Media

Generalized Helmholtz Decomposition for Modal Analysis of El...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-Monterey 2023

作者： Zhu, Jie Roth, Thomas E. Chew, Weng Cho Na, Dong-Yeop Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN United States Pohang University of Science and Technology Department of Electrical Engineering Gyeongbuk Pohang Korea Republic of

ISBN: (纸本)9781733509633

Potential-based formulation with generalized Lorenz gauge can be used in the quantization of electromagnetic fields in inhomogeneous media [1]. However, one often faces the redundancy of modes when finding eigenmodes from potential-based formulation. In free space, this can be explained by the connection to the well-known Helmholtz decomposition. In this work, the Helmholtz decomposition is generalized to its generalized form, echoing the use of generalized Lorenz gauge in inhomogeneous media [2]. Electromagnetics eigenvalue problems are formulated using vector potential formulation which is often used in numerical quantization [1]. The properties of the differential operators are mathematically analyzed. Orthogonality relations between the two classes of modes are proved in both continuous and discrete space. Completeness of two sets of modes and the orthogonality relations are numerically validated in inhomogeneous anisotropic media. This work serves as a foundation for numerical quantization of electromagnetic fields in inhomogeneous media with potential-based formulation. © 2023 ACES.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Probabilistic Constellation Shaping and Precoding for Multi-user VLC Systems

Joint Design of Probabilistic Constellation Shaping and Prec...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Nguyen, Thang K. Pham, Thanh V. Le, Hoang D. Nguyen, Chuyen T. Pham, Anh T. The University of Aizu Computer Communications Lab. Japan Shizuoka University Department of Mathematical and Systems Engineering Japan Hanoi University of Science & Technology School of Electrical and Electronic Engineering Viet Nam

ISBN: (纸本)9798350351255

This paper proposes a joint design of probabilistic constellation shaping (PCS) and precoding to enhance the sum-rate performance of multi-user visible light communications (VLC) broadcast channels subject to signal amplitude constraint. In the proposed design, the transmission probabilities of bipolar M-pulse amplitude modulation (M-PAM) symbols for each user and the transmit precoding matrix are jointly optimized to improve the sum-rate performance. The joint design problem is shown to be a complex non-convex problem due to the non-convexity of the objective function. To tackle the problem, the firefly algorithm (FA), a nature-inspired heuristic optimization approach, is employed to solve a local optima to the original non-convex optimization problem. The FA-based approach, however, suffers from high computational complexity. Therefore, we propose a low-complexity design based on zero-forcing (ZF) precoding, which is solved using an alternating optimization (AO) approach. Simulation results reveal that the proposed joint design with PCS significantly improves the sum-rate performance compared to the conventional design with uniform signaling. Some insights into the optimal symbol distributions of the two joint design approaches are also provided. © 2024 IEEE.

关键词： Convex optimization

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：