检索结果-内蒙古大学图书馆

4th International Conference on Sustainable Technologies for Industry 4.0, STI 2022

作者： Sakib, Shadman Haque Mridha, Md. Afranul Hasan, Nahid Habib, Md. Toasin Mahbub, Md. Shahriar Ahsanullah University of Science and Technology Dept. of Computer Science and Engineering Bangladesh

ISBN: (纸本)9781665490450

Cricket is a long duration game. It can last for several hours or even days. Due to cricket's lengthy nature, it becomes indispensable for viewers to have the option of watching selected interesting events from a cricket match. As cricket videos are unscripted in nature, detecting key events from cricket videos is a big challenge. In this paper, we propose a method to detect 5 key events, namely FOUR, SIX, OUT, NO BALL and WIDE from cricket videos by recognizing the umpire's signal. Analysis of umpire signals is performed using a pretrained Convolutional Neural Network (CNN) architecture, namely I3D. A new dataset, containing 504 videos and 2000 images from cricket matches, is introduced in this work for the detection of key events in cricket. For the tasks of umpire frame detection and umpire signal recognition, test accuracies of 97.76% and 86.14% are achieved respectively. Employing the proposed framework on official cricket match videos, we achieve precision, recall and F1 scores of 95.23%, 86.95% and 90.90% respectively. Furthermore, by evaluating performances of both proposed video-based approach and existing image-based approach on novel cricket videos, we can affirm that the proposed approach outperforms the image-based one. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Grid-Connected Renewable Energy Based Microgrid systems for Residential Use: A Techno-Economic Approach

Design and Analysis of Grid-Connected Renewable Energy Based...

引用

Recent Progresses in Science, engineering and technology (ICRPSET), International Conference on

作者： Md. Feroz Ali Md. Rafiqul Islam Sheikh Mir Md. Julhash Md Ashikuzzaman Dept. of Electrical and Electronic Engineering Pabna University of Science and Technology Pabna Bangladesh Dept. of Electrical and Electronic Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798331509477

ISBN: (纸本)9798331509484

Bangladesh faces a significant power shortage, prompting the need for renewable energy solutions in residential areas. This study analyzes the energy load of a three-story residential building and designs a grid-connected microgrid system incorporating solar PV and wind turbines using HOMER (Hybrid Optimization of Multiple Energy Resources) Pro software. Four configurations combining solar PV, wind turbines, and grid connections were evaluated based on techno-economic performance. The grid-connected solar PV system emerged as the optimal solution, offering the lowest net present cost (NPC) of USD 23,233, a cost of energy (COE) of USD 0.022/kWh, and an operating cost of USD 445 per year. The system generates 25,259 kWh/year, with grid purchases of 14,248 kWh/year and sales of 13,312 kWh/year, resulting in a renewable fraction (RF) of 62.2%. It demonstrates economic viability with a payback period of 6.69 years and a return on investment (ROI) of 10.1%. Additionally, the system significantly reduces CO2 emissions to 9,076 kg/year compared to 15,548 kg/year in the grid-only scenario. These results underscore the potential of grid-connected solar PV systems to enhance energy sustainability and decrease emissions in the residential sector of Bangladesh.

关键词： Radio frequency Renewable energy sources Design engineering Costs Software packages Microgrids Wind turbines Sustainable development Carbon emissions Optimization

来源：评论

学校读者我要写书评

暂无评论

Survey of Lightweight Object Detection Model Methods 4

Survey of Lightweight Object Detection Model Methods

引用

4th International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Yang, Chenhong Gao, Zhengang Hao, Yijun Yang, Ruipeng Ordos Institute of Technology School of Information Engineering Ordos China Ordos Institute of Technology School of Mechanical and Traffic Engineering Ordos China Ordos Kaitu Technology Co. Ltd. Ordos China Co. Ltd. Dept. Of Transmission Management Ordos China

ISBN: (纸本)9798331531225

Deep neural networks have recently achieved significant success in many visual recognition tasks. However, these models suffer from being computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, studying and designing lightweight models is one of the current research hotspots. Building a lightweight object detection algorithm is a challenging task because the model must be carefully designed to minimize parameters and computing resources while achieving high detection performance. In the past 10 years, lightweight algorithm design has made significant progress. In this paper, we summarize lightweight object detection algorithms to further explore new ideas and directions for lightweight network design. This paper divides the lightweight algorithm design into three categories: backbone network, feature fusion network, and attention mechanism. For each category, this paper provides a detailed analysis of the performance, advantages, and limitations of the modules in the object detection task. Then, we briefly introduce some recent successful methods, such as the Mobilenet series and DETR. Finally, we conclude this paper and discuss the challenges and potential directions for future work. The development trend of lightweight design in the field of object detection is examined. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Full-duplex OFDM modulation based FSO-Fiber system for 5G scenario 6

Full-duplex OFDM modulation based FSO-Fiber system for 5G sc...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Arya, Vivek Kumari, Meet Chauhan, Rahul Sharma, Neha Dept. of ECE Haridwar India Chandigarh University Dept. of ECE Mohali India Graphic Era Hill University Computer Science and Engineering Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9798350304480

A full-duplex 40/40Gbps orthogonal frequency division multiplexing (OFDM) basics free space optics (FSO)-fiber system is presented. The performance is measured under different turbulences effects with fiber impairments. The simulation results indicate that faithful fiber and FSO transmission ranges of 40km and 350m under turbulences effects is obtained. It is also observed that fiber-FSO link indicates best performance compared to fiber and FSO links with signal to noise ratio of 25dB in upstream and 10dB downstream direction. Also, the designed system shows that best performance than other existing ones for fifth generation (5G) applications. © 2023 IEEE.

关键词： free space optics (FSO) orthogonal frequency division multiplexing (OFDM) quadrature amplitude modulation (QAM) turbulence

来源：评论

学校读者我要写书评

暂无评论

Investigating Patient Behavior and Experience in Healthcare Settings to Improve Service Quality

Investigating Patient Behavior and Experience in Healthcare ...

引用

2024 OPJU International technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Chandra, Pradeep Kumar Ramesh, B. Anandhi, R.J. Singla, Atul Prakash Raj, M. Al-Ghazi, Hussein Jamil Hamid LLloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Lovely Professional University Phagwara India St. Martin's Engineering College Dept. of Cse Telangana Secunderabad India National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq

ISBN: (纸本)9798350373783

This study explains ways to enhance patient healthcare experiences. The proposed system integrates real-time patient feedback analysis, predictive modeling, individualized therapeutic concepts, digital user interface improvements, and sensitivity training. After comprehensive empirical research, the proposed strategy consistently outperformed well-known strategies in key performance indicators. With sentiment analysis tools, clinicians may instantly reply to patient remarks in real time. Predictive modeling using advanced machine learning made patient happiness predictions easier. Personalized treatment concepts employ combined filtering to adapt healthcare to each person. Digital tools will be simple and effective, DEO stated. Empathy training for healthcare personnel demonstrated the method's human-centeredness. Regular poll analysis, less complex predictive modeling, generic therapy, little digital interface optimization, and less empathy training were used. The proposed approach outperformed them. The recommended strategy worked because of real-time responsiveness, independence, and patient concentration. Because it considers how each patient contact is unique and varies over time, the recommended strategy transforms healthcare delivery. This strategy shows how to provide patient-centered care as healthcare evolves. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Generation and Implementation of Random Number Architecture using Difference Expansion for Digital Circuits 3

Generation and Implementation of Random Number Architecture ...

引用

3rd International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2022

作者： Devi, S Nithya Sasipriya, S. Dr. N.G.P. Institute of Technology Dept. of Electronics and Communication Engineering Coimbatore641048 India Sri Krishna College of Engineering and Technology Dept. of Electronics and Communication Engineering Coimbatore641008 India

ISBN: (数字)9781665410052

ISBN: (纸本)9781665410052

Unified logic and very large-scale integration (VLSI) circuitry have been created to generate random numbers from various distributions such as uniform, exponential, and Gauss distributions. An arithmetic iteration notion is used to implement several architectural levels in the proposed system. Fast speed, low power consumption, and great output accuracy make this random number generator ideal for communications systems and other models that need multi-distribution random numbers. The difference expansion approach and linear feedback shift register (LFSR) bit switching are recommended to generate random numbers. Besides this, the randomization is unpredictably random. Predictable binary sequences have been a major drawback of earlier randomization approaches. Differential characteristics construct the sequence and keep things simple in this technique. It also aims to simplify the circuit and use less energy. Power, delay, and a lookup table are used to make performance comparisons. The proposed architecture was tested and evaluated using Xilinx. Simulation results demonstrate that the proposed model outperforms standard random generators using Slices, Area, and Look Up Tables. According to the research findings, the proposed Difference Expansion-based Random Generation (DERG) has reduced latency and consumes less power. © 2022 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Mobility and Privacy-aware Computation Offloading with Energy Harvesting in MEC-enabled Networks

Mobility and Privacy-aware Computation Offloading with Energ...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Bi, Jing Niu, Siyu Yuan, Haitao Zhai, Jiahui Zhang, Jia Zhou, MengChu College of Computer Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Southern Methodist University Dept. of Computer Science DallasTX75275 United States New Jersey Institute of Technology Dept. of Electrical and Computer Engineering NewarkNJ07102 United States

ISBN: (纸本)9781665410205

Many new IoT applications have emerged with the fast evolution of 5G and the Internet of Things (IoT). These applications place higher demands on network energy consumption and processing capabilities. Mobile edge computing (MEC) significantly enhances execution efficiency, while energy harvesting (EH) modules further augment the operational features of IoT devices. However, existing studies mainly concentrate on energy consumption and latency problems, often neglecting issues about user mobility and potential privacy leakage within the MEC environment. Therefore, optimizing computation offloading and resource allocation for MEC-enabled IoT networks is essential. This work proposes an innovative architecture with EH for collaborative computing between multiple mobile devices (MDs) and MEC servers. To tackle the problem, this work also proposes an advanced hybrid algorithm named Self-adaptive Bat Optimizer with Genetic operations and individual update of Grey wolf optimizer (SBG2). With SBG2, this work aims to minimize the energy consumption of MDs while providing user mobility and privacy protection. Simulation experiments show that SBG2 reduces energy consumption by 79.15%, 93.20%, and 89.58%, respectively, compared to the other three typical algorithms. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENTAL STUDY ON RAPID TEST FOR STATIC MODULUS OF ELASTICITY OF CONCRETE BY 40℃ WARM WATER CURING

引用

AIJ Journal of technology and Design 2023年第71期29卷 29-33页

作者： Otsuka, Shuzo Nakata, Yoshihisa Aramaki, Takumi Shibusawa, Jinichi Ueda, Yutaro Dept. of Building Technologists Monotsukuri Institute of Technologists Japan Dept. of Architecture College of Science and Technology Nihon Univ. Japan Nexco-East Engineering Co. Ltd. Japan Graduate School of Technologists Monotsukuri Institute of Technologists Japan

This study investigated the effects of various factors on the applicability of static modulus of elastic to early determination by warm water curing at 40℃. As a result, it was clarified that even if pre-curing time, type of coarse aggregate, Bulk volume of coarse aggregate per unit volume of concrete and concrete temperature were different, static elastic modulus of concrete using various cements could be estimated by the linear equation. © 2023 Architectural Institute of Japan. All rights reserved.

关键词： Curing

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of CNN Models on the Classification of Dyslexic Handwriting 4

Comparative Study of CNN Models on the Classification of Dys...

引用

4th IEEE Bombay Section Signature Conference, IBSSC 2022

作者： Sreekumar, Subha Lijiya, A. National Institute of Technology Calicut Dept. Computer Science and Engineering India

ISBN: (纸本)9781665492911

Developmental Dyslexia, one of the learning disabilities is a topic of scientific interest in a variety of disciplines such as psychology, speech and language therapy, data science, etc. While the reason for Dyslexia and its symptoms are still being researched by psychologists, data science is providing ways to intervene and detect them with the aid of technological advancements. Dyslexia is a neurological condition that impairs reading comprehension and has long-lasting impacts. But timely detection and intervention programs can alleviate its effects to a certain extent. This study aims to classify images of handwritten English characters into three classes namely: normal, corrected, and reversed, where normal class refers to normal handwriting, and corrected or reversed constitutes handwriting of children with Dyslexia. The dataset used for the study is available publicly on Kaggle. The building of an efficient CNN (Convolutional Neural Network) model for classifying dyslexic handwriting is the major emphasis of this work. This is accomplished by comparing several CNN models and evaluating how well they detect Dyslexia on the same dataset. The proposed CNN approach has demonstrated a sizable improvement in reliably classifying dyslexic handwritten images. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Minimum Switch Count Nine-Level Inverter With Low Voltage Stress for Photovoltaics Application 1

Minimum Switch Count Nine-Level Inverter With Low Voltage St...

引用

1st IEEE IAS Global Conference on Emerging Technologies, GlobConET 2022

作者： Baksi, Swapan Kumar Kumar Behera, Ranjan Indian Institute of Technology Patna Dept. of Electrical Engineering Patna India

ISBN: (数字)9781665443579

ISBN: (纸本)9781665443579

In order to achieve higher voltage level counts from a Multilevel inverter, more numbers of switches and or multiple input dc sources are required to construct it. The cost, volume and control complexities of such multilevel inverters are increased due to involvement of more number of switches and input dc source. A new nine-level inverter with single input dc-source using minimum number of switches. The switched-capacitor theory is considered to develop the proposed inverter. Owing to reduced voltage and current stress, lower rating switches are used to constitute the proposed inverters. Results in reduced switching and conduction losses. Unipolar multicarrier based sine PWM technique is used to control the proposed inverter. The proposed inverter is compared with the existing nine level topologies in terms of switch count, voltage stress, current stress, numbers of passive *** analysis is given for evaluation of power loss and selection of passive components. MATLAB/Simulink software is used for simulation of the proposed inverter to validate the theoretical analysis. © 2022 IEEE.

关键词： Pulse width modulation

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：