检索结果-内蒙古大学图书馆

2023 IEEE Renewable Energy and Sustainable E-Mobility Conference, RESEM 2023

作者： Paramathma, Krishna Kumar, Mekala Ajay Ranjith, Puttakokkula Santhosh Reddy, Chinthalapalli Siva Kalasalingam Academy of Research and Education Department of Electrical and Electronics Engineering Tamil Nadu India

ISBN: (纸本)9798350311327

Agriculture plays a vital role in GDP growth of our country and mainstay occupation for the people. As per UN projection, the rise in population of India would be around 1.64 billion in 2050. Based on the facts, more pressure will be kept on the farmers to increase the crop productivity. In order to meet the demand and to reduce the stress faced by farmers, our project aims to develop AI based applications to detect the type of soil, type of plants to be cultivated to the soil type and fertilizers to be used to eliminate the nutrient shortages in the soil. The AI based app will select the type of crop based on soil report received from test center. In addition Image processing technology is utilized to detect the diseases of the plant and recommend the chemicals. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

LCC-LCC Compensation based Dual Active Bridge Bidirectional WPT for Electric Vehicle Application 5

LCC-LCC Compensation based Dual Active Bridge Bidirectional ...

引用

5th IEEE International Transportation Electrification Conference, ITEC-India 2023

作者： Venkatesan, M. Narayanamoorthi, R. Balaji, C. Savio, A. Dominic Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Chennai603203 India

ISBN: (纸本)9798350337808

Bidirectional Wireless Power Transfer (BWPT) for EV applications is a viable answer to the impending power grid volatility and charging concerns. The Dual Active Bridge (DAB) stands out because to its properties, which include bidirectional operation (vehicle to grid, vehicle to vehicle, and grid to vehicle) and comparably high efficiency, despite the fact that various isolated DC-DC converter topologies find applications in BWPT. Compensation network topologies like SP, PP, and PS can offer either constant current operation (CCO) or constant voltage operation (CVO). However, these topologies comprise harmonics that lead to high power consumption during charging. This study reports on the LCC-LCC hybrid correction, which aims to offer a constant output with minimal total harmonic distortion (THD) and a smooth transition between CCO and CVO. The DAB with LCC compensation, which offers a broad working range, high power density, and the previously described benefits, is presented in the article. The proposed DAB and LCC-LCC compensation are simulated in the MATLAB environment for a power rating of 3.7kW and achieve an efficiency of 96%. An experimental model was developed for a 3.7kW power rating for comparative analysis. © 2023 IEEE.

关键词： DC-DC converters

来源：评论

学校读者我要写书评

暂无评论

Efficiency Enhancement of PM6:Y6 Organic Solar Cells Via OghmaNano Software Optimisation 3

Efficiency Enhancement of PM6:Y6 Organic Solar Cells Via Ogh...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Krishnakumar, Karthika Grover, Ashish Kumar, Pardeep Mriirs Department of Electronics and Communication Engineering Haryana Faridabad India Mriirs Department of Electrical and Electronics Engineering Haryana Faridabad India Mriirs Department of Applied Sciences Haryana Faridabad India

ISBN: (纸本)9798350319125

The emergence of organic solar cells (OSCs) presents a viable option to replace inorganic solar cells, but the efficiency of OSCs remains limited. To enhance the performance of OSCs, this study utilised OghmaNano software to design and simulate an OSC structure. The study examined the optimal thickness of the active layer, electron transport layer (ETL) thickness, hole transport layer (HTL) thickness, different ETL and HTL materials, and the effect of varying the density of states (DoS) in the active layer on OSC performance. Through systematic simulations, an optimized power conversion efficiency (PCE) of 21.06% was achieved. The simulation findings showed a considerable agreement with the experimental study results, indicating the potential applicability of the used programme for organic solar cell optimisation and performance development. Furthermore, the simulated findings obtained in this work were compared to the realistic outcomes mentioned in existing literature. © 2023 IEEE.

关键词： Efficiency OghmaNano Organic Solar Cells PM6 Simulation Y6

来源：评论

学校读者我要写书评

暂无评论

Attention-based Deep Learning for Epileptic Seizure Type Detection 2

Attention-based Deep Learning for Epileptic Seizure Type Det...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Shankar, Anand Chakraborty, Debaleena Dandapat, Samarendra Barma, Shovan Saikia, Manob Jyoti University of North Florida Biomedical Sensors and Systems Lab JacksonvilleFL32224 United States Indian Institute of Information Technology Guwahati Electronics and Communication Engineering Department India Indian Institute of Technology Guwahati Electronics and Electrical Engineering Department Assam India University of North Florida Department of Electrical Engineering JacksonvilleFL32224 United States

ISBN: (纸本)9798350370188

The majority of the research studies surrounded by detection of seizures rather than discriminating seizure types using EEG. Identifying specific seizure types is crucial for diagnosis and treatment. EEG signal variability among seizure types presents a challenge, but deep neural networks, especially with attention mechanisms, show promise for accurate analysis. In this work, a well-recognized recurrent network, Long Short-Term Memory lined with self-attention mechanism has been designed to categorize four types of seizure, including focal non-specific, generalized non-specific, simple partial, and complex partial seizures. For validation, the Temple University Hospital EEG database has been used. The idea has attained classification accuracy, specificity, precision, and F1-score of 92.2%, 97.5%, 92.1 %, and 92.2% respectively. Additionally, it has displayed notable area under the ROC. In a comparative study, this method has demonstrated superior performance. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Real-Time Speech Emotion Recognition Using Hybrid Transformer Networks for Mental Health Monitoring

Real-Time Speech Emotion Recognition Using Hybrid Transforme...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Durga, P. Janani Basha, C. H. Hussaian Christopher, Nelson Kennedy Babu Senthilkumar, S. Kumar, N. Rathina Kavitha, M. E.G.S. Pillay Engineering College Department of Electronics and Communication Engineering Tamil Nadu Nagapattinam611002 India Sr University Department of Electrical and Electronics Engineering Telangana Hanumakonda50637 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai602105 India Sns College of Engineering Department of Artificial Intelligence and Data Science Tamilnadu Coimbatore641107 India

ISBN: (纸本)9798331509828

This study proposes a hybrid method to multi dialect speech recognition using the transfer learning with transformer-based architecture. The primary objective of this method is to enhance the automatic speech recognition (ASR) across the different dialectal variations of specific language. The transfer learning methods are utilized to modify the base model that was trained on high resource language to manage the multiple dialects with limited labelled data for each dialect. This is achieved by using pre trained transformer methods such as Wav2Vec2.0 and Whisper. An approach which employs dialect specific embeddings is presented. It enables the method to capture data and differentiate between prosodic elements and phonetic that are distinctive to a variety of dialects. Data augmentation technique are utilized in order to overcome the limited availability of labelled data for low resource dialects. These methods are utilized to increase the efficiency of training set and enhance the robustness of the method. Evaluation of the method is carried out using multi dialect speech datasets which include Arabic MGB-3 and common voice. These datasets represent a variety of dialects that are spoken in various linguistic regions. The result of this study indicates that the transformer-based method is effective in managing difficulties of dialectal variances while the reliability is reduced on different datasets. Different real-world applications are provided by the proposed method for improving voice enabled applications. Furthermore, this method leads the way for the development of ASR method that are more accurate and independent in locations that have a significant linguistic variation. © 2025 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Investigation of 2D nanomaterials on Indium Phosphide-based plasmonic devices for sensing in the optical communication band 5

Investigation of 2D nanomaterials on Indium Phosphide-based ...

引用

5th International Conference on Devices for Integrated Circuit, DevIC 2023

作者： Shukla, Sambhavi Tripathy, Yash Sanghi, Kshitij Arora, Pankaj Birla Institute of Technology and Science Department of Electrical and Electronics Engineering Rajasthan Pilani India

ISBN: (纸本)9798350347265

2D nanomaterials have gained much attention because of better molecular interaction with the target surface. It is the study of the effect of these biorecognition layers that we present in this paper, over the Indium Phosphide (InP) layer with different plasmonic metals coated on a glass prism. We consider Molybdenum disulfide, Black Phosphorus, and Fluorinated Graphene (FG) to bio-functionalize the top surface of the proposed sensing devices. InP is used as a dielectric material that enhances the overall performance parameters in terms of sensitivity and Figure of Merit (FOM). The optical output is evaluated by capturing the reflected light from a prism-based coupling arrangement. Simulations are carried out for the optimization of layer thicknesses of various plasmonic metals (Gold (Au), Silver (Ag), and Aluminum (A1)) followed by studying the effect of three different 2D nanomaterials, over the top surface of the proposed device. Finally, the results of the proposed configuration are compared, and it is found that Ag-InP-FG shows the best sensitivity and FOM of 131 0/RIU and 655 RI -1 respectively. Such appreciable numbers of performance parameters provide a potential for the proposed plasmonic devices to be employed in the sensing applications at the nanoscale. © 2023 IEEE.

关键词： Indium phosphide

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Explainable AI-NLP Framework for Text Categorization

Evaluation of the Explainable AI-NLP Framework for Text Cate...

引用

2024 International Conference on Communication, Computer Sciences and engineering, IC3SE 2024

作者： Singh, Amar Preet Gupta, Gaurav Soumya, K. Noida Institute Of Engineering And Technology Department Of Electrical & Electronics Engineering Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India

ISBN: (纸本)9798350366846

Although there has been a decrease in interpretability, significant progress has lately been achieved in developing state-of-the-art models. This assessment provides a thorough analysis of Explainable AI (XAI) within the framework of Natural Language Processing (NLP). This study examines the fundamental classification of descriptions in addition to the many techniques for producing and displaying explanations. The purpose of the survey is to provide a comprehensive study of the many approaches and strategies used to clarify the models' predictions, making it a helpful tool for people who develop NLP models. Additionally, we draw attention to the gaps in the current literature and urge further investigation into potential avenues for this crucial field of study. An experiment is also conducted and the results are discussed in this article. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Power system frequency profile improvement using satin bowerbird optimized tilt fractional cascade controller with reduced data based cost function

Journal of Engineering Research (Kuwait)

引用

Journal of engineering Research (Kuwait) 2023年第4期11卷 414-424页

作者： Chinta, Durga Prasad Jatoth, Ravi Kumar Biswal, Monalisa Department of Electrical Engineering National Institute of Technology Chhattisgarh Raipur 492010 India Department of Electronics and Communication Engineering National Institute of Technology Telangana Warangal 506004 India

The objectives of the automatic generation control (AGC) are attained via secondary control mechanism with optimal controller gains. The best solutions of these gains are identified by population search-based algorithms with the help of performance metrices. The controller design issues of AGC treat these performance metrics as a cost function. This paper introduces a new performance measure implemented with dominated samples information extracted from the frequency and tie line power changes. This new integral square error (NISE) is incorporated in fitness function and tested on isolated and multi area interconnected power system scenarios with satin bowerbird optimizer to tune the controller gains. Additionally, integral-tilt proportional-fractional order derivative controller is proposed in this paper and comparisons are made with popular controllers to show the merits in terms of AGC specifications. Optimal gain parameters of all controllers are achieved with existing integral square error and the proposed NISE cost functions and extensive simulations are carried out to illustrate the merits of the work. Studies are also expanded to nonlinear systems in order to evaluate the adaptability, performance improvement, and effectiveness of the suggested cost function, controller, and tuning method. © 2023 The Author(s)

关键词： Automatic generation control Integral square error Performance index Satin bowerbird optimizer

来源：评论

学校读者我要写书评

暂无评论

Optimisation and Evaluation of Breadth First Search with oneAPI/SYCL on Intel FPGAs: From Describing Algorithms to Describing Architectures 24

Optimisation and Evaluation of Breadth First Search with one...

引用

12th International Workshop on OpenCL and SYCL, IWOCL 2024

作者： Olgu, Kaan Kenter, Tobias Nunez-Yanez, Jose McIntosh-Smith, Simon School of Electrical & Electronics Engineering University of Bristol United Kingdom Paderborn Center for Parallel Computing Department of Computer Science Paderborn University Germany Dept. Electrical Engineering Linkoping University Sweden

ISBN: (纸本)9798400717901

FPGAs are often used in scientific fields to process graph algorithms due to their energy efficiency, reconfigurability, and fine-grained parallelism. However, these algorithms face challenges in memory access patterns, scalability, and programmability. The SYCL2020 implementation in the Intel oneAPI toolchain supports FPGA targets alongside SYCL2020 features like modern C++ with a single-source offloading to improve programmability. This study analysed the Breadth-First Search algorithm on Stratix 10 FPGA with the Intel oneAPI toolchain. The implementation was done in two phases. At first, we applied the typical optimisations proposed in the official guidelines alongside an automatic cache to achieve proper pipelining and improve random memory accesses performance. However, limitations occurred with fine-grained parallelism, and it was competitive only to some related work that utilised hardware-description languages or established high-level synthesis tools. For the second phase, we added bit-level representations of data in memory, banking in on-chip memory, and fine-grained control over parallel data streams. The second implementation was generally superior or on par with all compared designs, outperforming other works in 10 out of 15 tested datasets, including various synthetic RMAT and real-world datasets, with a peak performance of 1021 MTEPS. © 2024 Owner/Author.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based FPN and MT-CNN Face Mask Detection System 9

Deep Learning Based FPN and MT-CNN Face Mask Detection Syste...

引用

9th International Conference on Science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Nirmaladevi, J. Poornachandra, S. Jayavardhini, P. Ragsana, R.V. Mahalakame, R.M. Bannari Amman Institute of Technology Department of Information Science And Engineering Tamil Nadu Erode638401 India St Peter's College of Engineering Department of Electronics And Communications Engineering Tamil Nadu Chennai600054 India Bannari Amman Institute of Technology Department of Electrical And Electronics Engineering Tamil Nadu Erode638401 India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365092

In this study, we provide a novel face mask identification method that utilizes FPN and MT-CNN models trained using deep learning. Images of persons with and without face masks were used to test the proposed models. The FPN model got 97.3% accuracy while the MT-CNN model got 98.1% accuracy. Both models performed better than previous methods of face mask detection. However, the MT-CNN model beat the FPN model in both accuracy and efficiency, possibly because to its capacity to recognize face landmarks and angles, whereas the FPN model demonstrated computational efficiency. In particular, the work emphasizes the promise of deep learning-based models for face mask recognition and hints that such models might offer a dependable and effective way of ensuring compliance with face mask laws in public places. Optimizing the models' performance, assessing the models in a variety of real-world circumstances, delving into the ethical implications, and creating user-friendly and accessible face mask detection systems are all potential future paths for study. © 2024 IEEE.

关键词： COVID-19

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：