2022 IEEE VLSI Device Circuit and System (VLSI DCS)最新文献_第4页

VLSI Routing Optimization Using Hybrid PSO Based on Reinforcement Learning 基于强化学习的混合粒子群算法的VLSI路由优化

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811434

Pradyut Nath, Sumagna Dey, Subhrapratim Nath, A. Shankar, J. Sing, Subir Kumar Sarkar

{"title":"VLSI Routing Optimization Using Hybrid PSO Based on Reinforcement Learning","authors":"Pradyut Nath, Sumagna Dey, Subhrapratim Nath, A. Shankar, J. Sing, Subir Kumar Sarkar","doi":"10.1109/VLSIDCS53788.2022.9811434","DOIUrl":"https://doi.org/10.1109/VLSIDCS53788.2022.9811434","url":null,"abstract":"Rapid advances in Very Large-Scale Integration (VLSI) technology demand wire length minimization of the circuits in VLSI physical layer design to ensure routing optimization. With the growing dimension of the circuits and increased complexity, only transformation of VLSI routing problem into Non-Polynomial (NP) complete Rectilinear Minimal Spanning Tree (RMST) problem and solving it with traditional approaches results in non-optimal solutions. This brings the need for metaheuristic algorithms. Using metaheuristic algorithms, finding the optimal placement of Steiner points by approximation became easier to optimize the routing path, but sometime with major deviation. In this proposed work, A hybrid Particle swarm optimization (PSO) is used which optimizes and estimates using a value Iteration matrix, obtained using Reinforcement Learning (RL). This RL guided PSO generates much better solutions safely and with more consistency when compared with existing metaheuristic-based routing algorithms. The collected findings demonstrate that the proposed methodology has a lot of potential in VLSI routing optimization.","PeriodicalId":307414,"journal":{"name":"2022 IEEE VLSI Device Circuit and System (VLSI DCS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115692901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Silicide on Oxide Based Carrier Selective Front Contact for 24% Efficient PERC Solar Cell 二氧化硅基载流子选择性前接触的24%高效PERC太阳能电池

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811447

Savita Kashyap, R. Pandey, Jaya Madan, Rajnish Sharma

{"title":"Silicide on Oxide Based Carrier Selective Front Contact for 24% Efficient PERC Solar Cell","authors":"Savita Kashyap, R. Pandey, Jaya Madan, Rajnish Sharma","doi":"10.1109/VLSIDCS53788.2022.9811447","DOIUrl":"https://doi.org/10.1109/VLSIDCS53788.2022.9811447","url":null,"abstract":"Passivated emitter rear contact (PERC) based solar cells are currently regarded as a strong contender for large production in the photovoltaic (PV) industry owing to its superior light absorption properties. However, feasible fabrication of PERC devices with minimum contact recombination loss is a challenging task. Therefore, to diminish this factor, poly-silicon on oxide (POLO) as a carrier selective contact is employed in PERC device and processed through Silvaco-TCAD tool. In this proposed work, the concept of silicide electrostatically doped (ED) has been adopted to avoid the need for actual physical doping in polysilicon (poly-Si) layer on the front surface. Also, the impact of three different metal silicides such as ErSi0.25 (3 eV), ErSi0.82 (3.75 eV) and YbSi2 (3.95 eV) to induce the n-type ED region has been studied and analyzed. The overall performance of the PERC device is investigated with the help of PV parameters, EBD, current-density (J-V) curve and EQE. ED-POLO PERC solar cell reflects higher PV parameters such as short circuit current density (JSC) of 40.86 mA/cm2, open-circuit voltage (VOC) of 0.728 V, fill-factor (FF) of 80.76% and power conversion efficiency (PCE) of 24.02% at optimized silicide WF of 3 eV. The reported work of silicide in carrier selective contact-based PERC device may open a path to enhance the device performance.","PeriodicalId":307414,"journal":{"name":"2022 IEEE VLSI Device Circuit and System (VLSI DCS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127231736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Multimodal Medical Imaging Using Modern Deep Learning Approaches 使用现代深度学习方法的多模态医学成像

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811498

Rahul Chanumolu, Likhita Alla, Pavankumar Chirala, Naveen Chand Chennampalli, B. Kolla

{"title":"Multimodal Medical Imaging Using Modern Deep Learning Approaches","authors":"Rahul Chanumolu, Likhita Alla, Pavankumar Chirala, Naveen Chand Chennampalli, B. Kolla","doi":"10.1109/VLSIDCS53788.2022.9811498","DOIUrl":"https://doi.org/10.1109/VLSIDCS53788.2022.9811498","url":null,"abstract":"Multimodal medical imaging is gaining prominence in clinical practice as well as in research studies. Multimodal image analysis (MIA) in conjunction with ensemble learning strategies gave rise to explosion in popularity and adding special benefits for medical-related applications. Inspired by recent successes of deep learning techniques in medical imaging, we design an algorithmic structure that enables supervised MIA with Cross-Modality Fusion at preprocessing stage, the classifier level as well as the decision-making step. Using deep convolutional neural networks, we proposed an algorithm for image segmentation to determine the lesions caused by soft tissue tumors. This is done using multi-modal images by MRI tomography as well as PET. The NN built with multimodal images performs better than networks built with single-modal images. In the case of tumor segmentation, an image that is fused within the neural network (i.e., fused within the convolutional layer or totally joined layers) is more effective as compared to using pictures that fuse the network's output. This work offers specific recommendations for the development and application of MIA.","PeriodicalId":307414,"journal":{"name":"2022 IEEE VLSI Device Circuit and System (VLSI DCS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123540576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Deep CNN Framework for Distress Detection Using Facial Expression 基于面部表情的深度CNN遇险检测框架

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811487

Bikramjit Das, Debanjan Ghosh, A. Choudhuri, Ankan Goswami, Avinandan Bhakta, Mahamuda Sultana, Suman Bhattacharya

{"title":"A Deep CNN Framework for Distress Detection Using Facial Expression","authors":"Bikramjit Das, Debanjan Ghosh, A. Choudhuri, Ankan Goswami, Avinandan Bhakta, Mahamuda Sultana, Suman Bhattacharya","doi":"10.1109/VLSIDCS53788.2022.9811487","DOIUrl":"https://doi.org/10.1109/VLSIDCS53788.2022.9811487","url":null,"abstract":"Recent medical developments have projected panic attacks as a forerunner in high-stress job environments. This medical cause has emerged to a considerable extent due to the masses’ lifestyle and food consumption habits. Assessment and prevention of such attacks have become imperative to arrest the situation. In this regard, the present study attempts to detect human distress from facial expressions. Convolutional Neural Networks (CNN) serves as one of the best feature extractors. AlexNet being one of the primitive CNN models, has been employed to study the stress content in a facial expression.AlexNet can perform multi-GPU training, which widely reduces the training time for larger models. Training other models comparatively require higher computations that result in escalated time and energy, which might cause consequent lesser efficiency. We have achieved a training accuracy of 93.4%, and validation accuracy of 92.5% —the image set comprised 35340 images generated from 593 video sequences from 123 people at 30fps. Although AlexNet being one of the primitive CNN models, the results of this study are motivating.","PeriodicalId":307414,"journal":{"name":"2022 IEEE VLSI Device Circuit and System (VLSI DCS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123375062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Early Alzheimer’s Disease Detection Using Semi-Supervised GAN Based on Deep Learning 基于深度学习的半监督GAN早期阿尔茨海默病检测

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811458

S. Saravanakumar, T.M.Saravanan

{"title":"Early Alzheimer’s Disease Detection Using Semi-Supervised GAN Based on Deep Learning","authors":"S. Saravanakumar, T.M.Saravanan","doi":"10.1109/VLSIDCS53788.2022.9811458","DOIUrl":"https://doi.org/10.1109/VLSIDCS53788.2022.9811458","url":null,"abstract":"Alzheimer’s disease (AD) prediction accuracy is crucial for minimising memory loss and enhancing Alzheimer’s disease patients’ quality of life. Neuroimaging has been explored as a possible method for diagnosing Alzheimer’s disease for the past decade. The goal of this study is to create a deep learning- an alzheimer’s disease assessment from beginning to finish ahead of schedule on. The semi-supervised generative adversarial network is designed to detect the presence of Alzheimer’s disease in magnetic resonance imaging data automatically. A model mapping is established on the original picture and Before the semi-supervised Generative Adversarial Network classifier predicts the AD, the segmented result is used to efficiently partition the left and right side hippocampal volume, and The deep feature from the segmented area is derived with convolution computational intelligence morphological operations. The current study uses the alzheimer’s disease neuroimaging Initiative dataset to conduct the experiment. This method presents a revolutionary deep learning framework for detecting alzheimer’s disease that can be used to patient data from the adult situation to improve medicine and standard of living.","PeriodicalId":307414,"journal":{"name":"2022 IEEE VLSI Device Circuit and System (VLSI DCS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125965685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Study of Adsorption Behaviour of Nucleobases on Si and P doped WSe2: DFT Approach 核碱基在Si和P掺杂WSe2上的吸附行为研究:DFT方法

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811470

K. Timsina, Somsher Lepcha, Bibek Chettri, P. Chettri, B. Sharma

{"title":"Study of Adsorption Behaviour of Nucleobases on Si and P doped WSe2: DFT Approach","authors":"K. Timsina, Somsher Lepcha, Bibek Chettri, P. Chettri, B. Sharma","doi":"10.1109/VLSIDCS53788.2022.9811470","DOIUrl":"https://doi.org/10.1109/VLSIDCS53788.2022.9811470","url":null,"abstract":"Our study is based on the study of interaction between the nucleobase and Si and P doped WSe2 using the first principle calculation. The nucleobases used to study the adsorption properties are Adenine (A) and Cytosine (C). The adsorption energy (E<inf>ab</inf>) for different nucleobases was larger for P-WSe<inf>2</inf> than Si-WSe<inf>2</inf>. The adsorption energy of stable P-WSe<inf>2</inf> was -4.16eV and -3.79eV for A and C, respectively. This suggested the strong interaction between them. The band gap and density of state (DOS) were calculated to understand the electrical behaviour during the interaction. The band gap also decreased after interaction with C and A. Recovery time of Si-WSe<inf>2</inf> was longer as compared to P-WSe<inf>2</inf>. P-WSe<inf>2</inf> has the shortest recovery time of 2.5×10<sup>-65</sup> sec for A molecule. All these results suggested that Si-WSe<inf>2</inf> could be used as a sensing material to detect biomolecules. Also, potential of Si-WSe<inf>2</inf> and P-WSe<inf>2</inf> in distinguishing nucleobase types could be explored further for their use as a biosensing substrate in DNA sequencing.","PeriodicalId":307414,"journal":{"name":"2022 IEEE VLSI Device Circuit and System (VLSI DCS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132215094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

State of the Art and Future Perspectives in III-V Nanometer-Scale MOSFETs III-V纳米mosfet的研究现状与展望

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811490

S. Dey, Kalyan Biswas, A. Sarkar

引用次数: 0

Linearity Performance of Double Metal Negative Capacitance Field-Effect Transistors: A Numerical Study 双金属负电容场效应晶体管线性性能的数值研究

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811468

Yash Pathak, B. Malhotra, R. Chaujar

引用次数: 1

Smart ECG Monitoring and Analysis System Using Machine Learning 基于机器学习的智能心电监测与分析系统

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/vlsidcs53788.2022.9811433

SarabTej Singh, Megha Bhushan

引用次数: 13

Machine Learning-Based Intrusion Detection System For Healthcare Data 基于机器学习的医疗数据入侵检测系统

2022 IEEE VLSI Device Circuit and System (VLSI DCS) Pub Date : 2022-02-26 DOI: 10.1109/VLSIDCS53788.2022.9811465

Amit Kumar Balyan, S. Ahuja, S. K. Sharma, U. Lilhore

引用次数: 6