2023 2nd International Conference on Computational Systems and Communication (ICCSC)最新文献

Plant Disease Detection Using Ensemble Learning 基于集成学习的植物病害检测

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10142982

Hari Kishan Kondaveeti, Kalyan Gandhi Ujini, Bikkina Veera Venkata Pavankumar, Bollu Sai Tarun, S. Gopi

{"title":"Plant Disease Detection Using Ensemble Learning","authors":"Hari Kishan Kondaveeti, Kalyan Gandhi Ujini, Bikkina Veera Venkata Pavankumar, Bollu Sai Tarun, S. Gopi","doi":"10.1109/ICCSC56913.2023.10142982","DOIUrl":"https://doi.org/10.1109/ICCSC56913.2023.10142982","url":null,"abstract":"Ensemble learning is a machine learning method that combines the predictions of multiple models in order to make a more accurate prediction. In this study, a plant disease detection system was developed using ensemble learning, with six base models Inception V3, MobileNet, MobileNetV2, VGG16, GoogleNet, and ResNet50 trained on a dataset of 87,000 images of healthy and diseased plant leaves from 38 different classes. The base models achieved accuracies ranging from 72.7% to 97.2% on the plant disease dataset. To improve the accuracy of the system, both soft and hard voting classifiers were applied to the base models. Soft voting involves weighting the predictions of each base model according to their accuracy and taking the class with the highest weighted average as the final prediction. Hard voting consists of simply counting the number of votes cast for each class, and the class with the most votes is selected as the final prediction. Both soft and hard voting significantly improved the accuracy of the system, with the soft voting ensemble achieving an accuracy of 97.8% and the hard voting ensemble achieving an accuracy of 98.3%. The results of this study demonstrate the effectiveness of using ensemble learning for plant disease detection and the potential for such a system to assist in the accurate and efficient identification of plant diseases.","PeriodicalId":184366,"journal":{"name":"2023 2nd International Conference on Computational Systems and Communication (ICCSC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126476930","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

Choice Of Distance Metrics in DBSCAN Based Color Template Matching Applied to Real-Time Human Shoe Detection 基于DBSCAN的颜色模板匹配中距离度量的选择应用于人体鞋的实时检测

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10143023

Debarshi Brahma, Pritam Paral, A. Chatterjee

引用次数: 0

A Solid Waste Management System Using Smart Bins in a Decentralized Manner in Ethereum Blockchain Network for Incentivization 在以太坊区块链网络中以分散的方式使用智能垃圾箱的固体废物管理系统进行激励

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10142986

Amitha K A, Raja Varma Pamba

引用次数: 0

Vehicle Door Safety System 车门安全系统

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10143020

Abilash Sivasankar, Kumaran U

引用次数: 0

Secure Multimodal Biometric System Based on Robust LSB-DWT Digital Watermarking Algorithm 基于鲁棒LSB-DWT数字水印算法的安全多模态生物识别系统

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10142972

P. G, K. S, Manimuthu Ayyannan, Selvam N, B. K, Neelam Sanjeev Kumar

{"title":"Secure Multimodal Biometric System Based on Robust LSB-DWT Digital Watermarking Algorithm","authors":"P. G, K. S, Manimuthu Ayyannan, Selvam N, B. K, Neelam Sanjeev Kumar","doi":"10.1109/ICCSC56913.2023.10142972","DOIUrl":"https://doi.org/10.1109/ICCSC56913.2023.10142972","url":null,"abstract":"In contemporary year, multimedia data is transmitted and accessed through Internet. Despite of its advantages, unauthorized copying, distribution and hacking of data has created security issues. So secure transmission and access of the biometric data has to be suggested. A single biometric identification is not preferable in most highly secured areas due to their parody attacks and ageing. These limitations can be overcome by deploying this system that incorporate information from multiple sources for personnel identification. In this project multiple sources are incorporated using Digital watermarking algorithm comprising both the spatial and frequency domain approach. Even though the digital watermarking scheme is highly secured, network hackers may easily trap the image and it's key. So to increase the security, encryption and decryption of watermarked image using RSA algorithm is employed at the transmission and the reception side respectively. So the cipher text image is alone transmitted in the network increasing the security of the multimodal data. The Stillness of this proposed scheme is measured by Quality Index (QI), Similarity of the original and the recovered images for various attacks and Peak Signal to Noise Ratio (PSNR).","PeriodicalId":184366,"journal":{"name":"2023 2nd International Conference on Computational Systems and Communication (ICCSC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125348654","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 Systematic Extraction and Outburst Susceptibility Assessment of Glacial lakes in High Mountain Regions using Landsat 8 Imagery 基于Landsat 8影像的高山冰湖系统提取及溃决敏感性评价

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10142974

Jagadeesh Thati, S. Ari

{"title":"A Systematic Extraction and Outburst Susceptibility Assessment of Glacial lakes in High Mountain Regions using Landsat 8 Imagery","authors":"Jagadeesh Thati, S. Ari","doi":"10.1109/ICCSC56913.2023.10142974","DOIUrl":"https://doi.org/10.1109/ICCSC56913.2023.10142974","url":null,"abstract":"Extracting glacial lake regions from satellite images is critical for determining the risk of glacial lake outbursts. Most previously reported techniques rely heavily on field surveys, which are time-consuming, expensive, and labor-intensive. As a result, an automatic and dependable system is required to extract glacial lake areas from satellite imagery accurately. Landsat8 satellite images with low contrast and heterogeneous backgrounds present significant challenges for extracting information in the glacial lake area. To address these issues, a quick shift segmentation technique is proposed in this paper to extract the glacial lake area precisely. After the enhanced water features have been obtained using the modified normalized difference water index (MNDWI) technique, the proposed method is used to extract the glacial lake area. The area threshold is also used to assess the vulnerability of the glacial lake area to outbursts. The proposed method is tested using data collected from the Landsat 8 satellite over three years in high mountain regions. According to qualitative and quantitative performance analysis, the proposed method outperforms previously reported state-of-the-art methods for determining glacial lake area.","PeriodicalId":184366,"journal":{"name":"2023 2nd International Conference on Computational Systems and Communication (ICCSC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128967381","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

Fuzzy Logic-Based Trajectory Planning for Mobile Robots in an Uncertain and Complex Environment 不确定复杂环境下基于模糊逻辑的移动机器人轨迹规划

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10142983

Mahyar Teymournezhad, O. K. Sahingoz

引用次数: 1

Method for Feature Selection Based on Inference of Gene Regulatory Networks 基于基因调控网络推理的特征选择方法

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10143012

Nimrita Koul

引用次数: 0

Transfer Learning for Bird Species Identification 鸟类物种识别的迁移学习

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10142979

Hari Kishan Kondaveeti, Kottakota Sai Sanjay, Karnam Shyam, Rayachoti Aniruth, S. Gopi, Samparthi V S Kumar

{"title":"Transfer Learning for Bird Species Identification","authors":"Hari Kishan Kondaveeti, Kottakota Sai Sanjay, Karnam Shyam, Rayachoti Aniruth, S. Gopi, Samparthi V S Kumar","doi":"10.1109/ICCSC56913.2023.10142979","DOIUrl":"https://doi.org/10.1109/ICCSC56913.2023.10142979","url":null,"abstract":"Monitoring and conservation of bird species play a crucial role in preserving biodiversity and maintaining the balance of the ecosystem. To address this, we have developed an automatic bird recognition system, known as the birdhouse, using the Arduino and Keras deep learning frameworks. The system is equipped with a PIR sensor that activates an ESP-32 camera to capture an image of the bird and send it to the server for processing. The deep learning model, trained using transfer learning with the MobileNetV2 architecture, is deployed with the python flask framework and is able to accurately predict the bird species with 95% test accuracy. The identified bird species is then notified to the users via the telegram application, along with the captured image of the bird. MobileNetV2 is a powerful deep learning architecture that is well-suited for deployment on resource-constrained devices such as the ESP-32 camera used in the birdhouse system. The use of transfer learning allows the model to be trained on a large dataset and then fine-tuned for the specific task of bird species recognition.","PeriodicalId":184366,"journal":{"name":"2023 2nd International Conference on Computational Systems and Communication (ICCSC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133034391","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 Literature Survey on Estimating Uncertainty in Deep Learning Models: Ensuring safety in Intelligent Systems 深度学习模型中不确定性估计的文献综述:确保智能系统的安全

2023 2nd International Conference on Computational Systems and Communication (ICCSC) Pub Date : 2023-03-03 DOI: 10.1109/ICCSC56913.2023.10143025

Soja Salim, Jayasudha Js

引用次数: 0