2023 IEEE Region 10 Symposium (TENSYMP)最新文献_第7页

Automatic Multi-Class Collective Motion Recognition Using a Decision Forest Extracted from Neural Networks 基于神经网络决策森林的多类集体运动自动识别

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223653

Shadi Abpeikar, Kathryn E. Kasmarik, M. Garratt

{"title":"Automatic Multi-Class Collective Motion Recognition Using a Decision Forest Extracted from Neural Networks","authors":"Shadi Abpeikar, Kathryn E. Kasmarik, M. Garratt","doi":"10.1109/TENSYMP55890.2023.10223653","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223653","url":null,"abstract":"This paper presents an approach to machine recognition of multiple classes of collective motion behaviours. Previous work has demonstrated that it is possible to distinguish structured collective motion from random, unstructured motion. However, it has proved difficult to use such techniques for automatically recognising specific collective motion variants such as moving in a line versus moving in a group. To enable a knowledge base to recognise multiple classes of collective motion, this paper proposes a decision forest approach. The proposed approach extracts machine-understandable knowledge from a neural network trained to automatically recognise collective motions. The main advantage of this approach is that besides being automatic, it is fast, accurate and easy to use. We show that our deep neural network achieves 90.30% accuracy for multi-class labelling of collective motion behaviours, which is more accurate than shallow neural networks for this problem. Furthermore, a knowledge base extracted using the decision forest on the deep neural network can recognise the class of random behaviour and the eight classes of collective motion behaviours with 88.81% accuracy in just 0.03 seconds, which is only 1.49% less accurate than the original deep neural network, but over 100 times faster.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129782169","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

iSynth - An open-source, technology independent, logic synthesis tool iSynth -一个开源，技术独立，逻辑合成工具

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223634

A. Das

{"title":"iSynth - An open-source, technology independent, logic synthesis tool","authors":"A. Das","doi":"10.1109/TENSYMP55890.2023.10223634","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223634","url":null,"abstract":"Logic synthesis is an extremely important step in the VLSI chip design. Register Transfer Level (RTL) code is translated to logic gates in this step. These gates are manufactured on silicon at the end to get the final silicon. There are plenty of Electronic Design Automation (EDA) [2] tools available in the ecosystem for synthesis. But all of them need technology library from fabrication factories. It is not easy to get those library files for students and researchers for independent research. And they are extremely expensive. While the tech libraries are must for accurate results, a lot of design analysis can be done without them. This analysis can reveal a lot of issues early in the design without spending a lot. Technology independent synthesis tool [5] is the gateway for that. No one else has tried to develop a synthesis tool before using Icarus Verilog (iVerilog) extension framework. The novelty of this approach is that the Verilog compiler remains outside the tool. So, the tool remains light and does not carry the heavy compiler with it. Icarus Verilog, popularly known as iVerilog, is an established open-source mixed language compiler-simulator-synthesis framework [1]. It is covered by GPL. It has wonderful application programming interface (API) which can be used to create extension programs of iVerilog. We had used this extension capability to develop another tool in past - iLint [3]. This time we have developed the new synthesis tool. This tool is supposed to work with any version of iVerilog. We have tested the tool with iVerilog version 10, 11, 12 and 13 extensively and found to be working fine with these versions. The EDA tools are absolutely must in the field of VLSI design. There are many companies which develop EDA tools, but they are extremely costly. Open-source EDA tools plays a vital role in this area. In this paper we have described such a tool, which we have developed and named it - iSynth.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134378183","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

Zea Mays Multi-Disease Classification and Severity Assessment with EfficientNetV2 Variants 高效netv2变异的玉米多病分类和严重程度评估

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223621

Ivan Roy S. Evangelista, M. Cabatuan, Lorelyn Joy T. Milagrosa, A. Bandala, Ronnie S. Concepcion, Elmer P. Dadios

{"title":"Zea Mays Multi-Disease Classification and Severity Assessment with EfficientNetV2 Variants","authors":"Ivan Roy S. Evangelista, M. Cabatuan, Lorelyn Joy T. Milagrosa, A. Bandala, Ronnie S. Concepcion, Elmer P. Dadios","doi":"10.1109/TENSYMP55890.2023.10223621","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223621","url":null,"abstract":"Despite the advances achieved in crop protection and management, crop diseases remain a problem for corn farmers. Numerous studies have presented the efficacy of corn disease detection and classification using machine learning-based vision detectors. However, many of these models rely on datasets with lab-based images that do not depict the real-world accurately. In this study, a vision-based corn disease detector and classifier is developed with EfficientNetV2 as base architecture. In addition, an algorithm for evaluating the severity of the disease has also been created. Two datasets were built to train the models, the common corn diseases (CCD) and corn disease severity (CDS). The EfficientNetV2-B0, B1, B2, B3, and S models, pre-trained on ImageN et, were explored for feature extraction. A custom classifier head is incorporated into the EfficientNetV2-based model to complete the architecture. It consists of a single convolutional neural network (CNN) and two fully connected layers. Transfer learning and fine-tuning were employed to improve the performance. The models were evaluated based on accuracy, cross-entropy loss, precision, recall, and F1-score. The EfficientNetV2B2 model performed best on the disease classification task, with an accuracy of 95.74%. The EfficientNetV2B3 is the top performer in the disease severity assessment task, with an accuracy of 98.73%. The EfficientNetV2S also surpassed other proposed models in PlantVillage (PV) dataset with an accuracy of 99.52%.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129057285","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

A SIW Cavity Backed Dual Band Filtenna for X-Band and Ku-Band Applications with Controllable Radiation Nulls 一种用于x波段和ku波段可控辐射零值应用的SIW腔背双频滤波器

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223675

Abhishek Patel, T. Kumar, M. Parihar

引用次数: 0

Improving the Accuracy of Gait Detection Using Computer Vision 利用计算机视觉提高步态检测的准确性

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223625

Sota Sugiyama, Yuna Ogiso, Masataka Yamamoto, Y. Ishige, H. Takemura, N. Aikawa

引用次数: 0

Schmitt-Trigger-Based Low Power SRAM Implemented Using 45-nm CMOS Technology 采用45纳米CMOS技术实现的基于施密特触发器的低功耗SRAM

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223482

Rochelle B. Oruga, Camille Valerie D. Dimalibot, Jolina May D. Matibag, Francine Cyrill R. Gregori, Ralph Gerard B. Sangalang

{"title":"Schmitt-Trigger-Based Low Power SRAM Implemented Using 45-nm CMOS Technology","authors":"Rochelle B. Oruga, Camille Valerie D. Dimalibot, Jolina May D. Matibag, Francine Cyrill R. Gregori, Ralph Gerard B. Sangalang","doi":"10.1109/TENSYMP55890.2023.10223482","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223482","url":null,"abstract":"This paper presents a Schmitt-trigger-based SRAM with a separated read port, which significantly improves read static noise margin (RSNM) and consumes low energy. Post-layout simulation results show that the proposed design performed better than the conventional 6T SRAM cell. The SNM of the designed cell is 1.16 mV higher than the conventional 6T SRAM cell in write mode, and 232.37 mV and 207.46 mV in read mode 1 and 0, respectively. The impact of the process, voltage, and temperature variations on cell performance parameters such as read, write and hold SNM, power per access, power per bit, delay, and energy per bit was investigated. Aside from this, the DNM of the cell was also measured to determine the noise tolerance of the cell during the write operation. Monte Carlo simulation results verified how robust the proposed cell is. The design was implemented in a 45-nm technology in which the cell occupies 4.53×4.53 µm2 and the system is 568.55×568.55 µm2. This cell consumes only 0.396 fJ, which is lower than the energy per bit consumed on the 6T conventional cell which is 7.265 fJ. All-corner simulation results show that the proposed cell is suitable for low-power applications.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115948065","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

Deep Reinforcement Learning based Intelligent Traffic Control 基于深度强化学习的智能交通控制

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223639

Arpan Nookala, Eeshaan Asodekar, Aryan Solanki, Narendra Bhagat, D. Karia

引用次数: 0

Gain Scheduled Output Feedback Controller with Low Computational Burden 低计算负担的增益调度输出反馈控制器

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223674

Gan Chen

引用次数: 0

Evaluation of the Economic Benefits of Community Energy Storage Systems for Prosumers 面向产消户的社区储能系统经济效益评价

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223670

K.B.J. Anuradha, J. Iria, C. Mediwaththe

引用次数: 0

Scalable Prediction of Potato Pests and Diseases with Insights from Mobile Sensing for Rabi 2021–22 基于移动传感的Rabi 2021-22马铃薯病虫害可扩展预测

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223626

Swagatam Bose Choudhury, Vidit Patil, Abhishek Kumar, R. Kulat, Sanat Sarangi, Hemavathy B, S. Pappula

引用次数: 0