Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470555
Aishwary Awasthi, Ramesh Chandra Tripathi, T. Thiruvenkadam
Computerized medical image segmentation is a vital tool for diagnosing and treating trendy illnesses. a ramification trendy strategies had been proposed to section medical pictures, but most modern them could not acquire excellent accuracy. Recently, multi-scale convolutional neural networks (MSCNNs) have been extensively used to clear up medical image segmentation tasks. MSCNNs take benefit modern day the dimensions-invariant function represented by the convolutional kernels, which lets the model capture objects with a couple of scales. The fusion brand new a couple of MSCNNs improves model accuracy. Moreover, MSCNNs were successfully applied in clinical imaging modalities, including CT, MRI, ultrasound, virtual pathology, and histology. This paper gives a complete review of modern-day the 49a2d564f1275e1c4e633abc331547db ultra-modern MSCNNs in clinical picture segmentation, such as the underlying model design, datasets, and the latest application and research developments. This paper additionally affords targeted utility examples and discusses ability destiny research guidelines. it's miles was hoping that the review will provide an informative reference for scientific photo segmentation studies
{"title":"Real-Time Semantic Segmentation of Medical Images Using Convolutional Neural Networks","authors":"Aishwary Awasthi, Ramesh Chandra Tripathi, T. Thiruvenkadam","doi":"10.1109/ICOCWC60930.2024.10470555","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470555","url":null,"abstract":"Computerized medical image segmentation is a vital tool for diagnosing and treating trendy illnesses. a ramification trendy strategies had been proposed to section medical pictures, but most modern them could not acquire excellent accuracy. Recently, multi-scale convolutional neural networks (MSCNNs) have been extensively used to clear up medical image segmentation tasks. MSCNNs take benefit modern day the dimensions-invariant function represented by the convolutional kernels, which lets the model capture objects with a couple of scales. The fusion brand new a couple of MSCNNs improves model accuracy. Moreover, MSCNNs were successfully applied in clinical imaging modalities, including CT, MRI, ultrasound, virtual pathology, and histology. This paper gives a complete review of modern-day the 49a2d564f1275e1c4e633abc331547db ultra-modern MSCNNs in clinical picture segmentation, such as the underlying model design, datasets, and the latest application and research developments. This paper additionally affords targeted utility examples and discusses ability destiny research guidelines. it's miles was hoping that the review will provide an informative reference for scientific photo segmentation studies","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"61 39","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529600","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470592
Shambhu Bharadwaj, Prabhu A, Vipin Solanki
Weed detection is an essential assignment in agricultural settings. Negative environmental results, crop yield loss, and mechanical weeding hard work prices related to weed management have necessitated the improvement of automation solutions to discover and treat weeds. Hyperspectral imaging (HSI) is a promising method that can produce abundant statistics about the spectral residences of flowers. This generation has been used in weed detection packages to classify weeds from crops, and these days deep mastering has been used to provide high accuracy prices in this discipline. In this abstract, we explore the utility of HSI for weed detection. We define current demanding situations that require further research earlier than automatic weed detection structures using HSI grow to be widely available. In particular, the presently available algorithms lack robustness and scalability, and further improvements in gadget-gaining knowledge of algorithms and techniques are wished to conquer those constraints, in addition to advancing the computational capabilities of these structures. Moreover, we discuss the potential of HSI as a weed detection answer in various contexts, including agroforestry and precision farming. In conclusion, we advise that the software of HSI for automatic weed detection has the massive capability to reduce labor fees related to weed manipulation, improve farming performance, and in the end, boom crop yields. Weed detection is a first-rate challenge inside the agricultural enterprise, as guide weed control is costly, time-consuming, and the correct identity of weeds is rigid. Hyper Spectral photo evaluation (HSIA) offers an alternative to guide weed detection, considering the rapid and effective mapping of weed-infested land without the need for guide labor. HSIA may be used to routinely detect the spectral signature of weed species, allowing for correct identity and brief remedy. This method uses hyperspectral scanners to gather spectral records, which are then analyzed using photo-type algorithms. These algorithms classify the collected spectral records into the various weed species and allow website online-specific weed mapping for correct weed manipulation. HSIA-based totally weed detection permits farmers to precisely target their weed management measures, reduce the chance of crop harm, and store time and assets.
{"title":"Automating Weed Detection Through Hyper Spectral Image Analysis","authors":"Shambhu Bharadwaj, Prabhu A, Vipin Solanki","doi":"10.1109/ICOCWC60930.2024.10470592","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470592","url":null,"abstract":"Weed detection is an essential assignment in agricultural settings. Negative environmental results, crop yield loss, and mechanical weeding hard work prices related to weed management have necessitated the improvement of automation solutions to discover and treat weeds. Hyperspectral imaging (HSI) is a promising method that can produce abundant statistics about the spectral residences of flowers. This generation has been used in weed detection packages to classify weeds from crops, and these days deep mastering has been used to provide high accuracy prices in this discipline. In this abstract, we explore the utility of HSI for weed detection. We define current demanding situations that require further research earlier than automatic weed detection structures using HSI grow to be widely available. In particular, the presently available algorithms lack robustness and scalability, and further improvements in gadget-gaining knowledge of algorithms and techniques are wished to conquer those constraints, in addition to advancing the computational capabilities of these structures. Moreover, we discuss the potential of HSI as a weed detection answer in various contexts, including agroforestry and precision farming. In conclusion, we advise that the software of HSI for automatic weed detection has the massive capability to reduce labor fees related to weed manipulation, improve farming performance, and in the end, boom crop yields. Weed detection is a first-rate challenge inside the agricultural enterprise, as guide weed control is costly, time-consuming, and the correct identity of weeds is rigid. Hyper Spectral photo evaluation (HSIA) offers an alternative to guide weed detection, considering the rapid and effective mapping of weed-infested land without the need for guide labor. HSIA may be used to routinely detect the spectral signature of weed species, allowing for correct identity and brief remedy. This method uses hyperspectral scanners to gather spectral records, which are then analyzed using photo-type algorithms. These algorithms classify the collected spectral records into the various weed species and allow website online-specific weed mapping for correct weed manipulation. HSIA-based totally weed detection permits farmers to precisely target their weed management measures, reduce the chance of crop harm, and store time and assets.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"27 6","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529665","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}
Self-supervised representation is trendy in developing new gadget-mastering techniques to enhance diagnostic accuracy for diagnosing modern cardiac abnormalities. In this paper, we speak about the applicability and capacity of present-day self-supervised illustration to gain modern knowledge for analyzing cardiac abnormalities on echocardiograms. We talk about the impact of modern-day supervised and unsupervised gaining knowledge state modern techniques on feature extraction from echocardiogram facts. We also speak about the unsupervised mastering techniques for characteristic extraction, including a self-supervised representation trendy model for directly detecting cutting-edge cardiac abnormalities. The proposed model combines recurrent neural networks with a car-encoder to extract useful excessive-level functions from echocardiogram information and classify the abnormality. We exhibit the accuracy modern our proposed model with the experimental results on two echocardiography datasets. Our proposed version finished promising outcomes and outperformed existing processes. The results imply our proposed version's capacity to enhance the generalization of trendy cardiac abnormality analysis and reduce the education time…
{"title":"Self-Supervised Representation Learning for Diagnosis of Cardiac Abnormalities on Echocardiograms","authors":"Ramkumar Krishnamoorthy, Ajay Agrawal, Puneet Agarwal","doi":"10.1109/ICOCWC60930.2024.10470471","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470471","url":null,"abstract":"Self-supervised representation is trendy in developing new gadget-mastering techniques to enhance diagnostic accuracy for diagnosing modern cardiac abnormalities. In this paper, we speak about the applicability and capacity of present-day self-supervised illustration to gain modern knowledge for analyzing cardiac abnormalities on echocardiograms. We talk about the impact of modern-day supervised and unsupervised gaining knowledge state modern techniques on feature extraction from echocardiogram facts. We also speak about the unsupervised mastering techniques for characteristic extraction, including a self-supervised representation trendy model for directly detecting cutting-edge cardiac abnormalities. The proposed model combines recurrent neural networks with a car-encoder to extract useful excessive-level functions from echocardiogram information and classify the abnormality. We exhibit the accuracy modern our proposed model with the experimental results on two echocardiography datasets. Our proposed version finished promising outcomes and outperformed existing processes. The results imply our proposed version's capacity to enhance the generalization of trendy cardiac abnormality analysis and reduce the education time…","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"48 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529668","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470897
Xuejun Yuan, Mingqi Ye
The analysis of enterprise financial status is the key to enterprise management, which has an important impact on investment decision, risk control and strategic planning of enterprises. Although traditional financial analysis methods can meet the needs of enterprises to a certain extent, there are limitations in dealing with complex problems. In recent years, with the development of data mining technology, decision tree, as an effective classification and prediction tool, has been gradually applied to the study of enterprise financial status. The purpose of this paper is to discuss the application of decision tree in the analysis of enterprise financial situation, and to analyze its effect and challenge in practical application.
{"title":"Corporate Financial Situation System Based on Decision Tree and SVM","authors":"Xuejun Yuan, Mingqi Ye","doi":"10.1109/ICOCWC60930.2024.10470897","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470897","url":null,"abstract":"The analysis of enterprise financial status is the key to enterprise management, which has an important impact on investment decision, risk control and strategic planning of enterprises. Although traditional financial analysis methods can meet the needs of enterprises to a certain extent, there are limitations in dealing with complex problems. In recent years, with the development of data mining technology, decision tree, as an effective classification and prediction tool, has been gradually applied to the study of enterprise financial status. The purpose of this paper is to discuss the application of decision tree in the analysis of enterprise financial situation, and to analyze its effect and challenge in practical application.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"124 1-4","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529689","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470932
Pankaj Saraswat, R. Naaz, K. R
Convolutional Recurrent Neural Networks (CRNNs) are artificial neural networks used in scientific photo recognition. CRNNs are composed of numerous convolutional and recurrent layers, designed to map enter snapshots to typically complicated labels along with exam outcomes or diagnoses. It makes them an effective device for scientific photograph popularity, as they could learn from big datasets correctly and make correct predictions. An average CRNN structure will encompass numerous convolutional layers that extract photograph functions, observed using a recurrent neural community (RNN) that encodes the temporal family members among capabilities. The output of the RNN is then decoded into a label using a completely connected layer. Compared to different strategies, CRNNs can extract high-stage semantic and temporal features from uncooked scientific pictures with better accuracy and pace. they're also able to leverage massive datasets and are consequently favored for packages in which huge quantities of categorized records are to be had.
{"title":"Convolutional Recurrent Neural Networks for Medical Image Recognition","authors":"Pankaj Saraswat, R. Naaz, K. R","doi":"10.1109/ICOCWC60930.2024.10470932","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470932","url":null,"abstract":"Convolutional Recurrent Neural Networks (CRNNs) are artificial neural networks used in scientific photo recognition. CRNNs are composed of numerous convolutional and recurrent layers, designed to map enter snapshots to typically complicated labels along with exam outcomes or diagnoses. It makes them an effective device for scientific photograph popularity, as they could learn from big datasets correctly and make correct predictions. An average CRNN structure will encompass numerous convolutional layers that extract photograph functions, observed using a recurrent neural community (RNN) that encodes the temporal family members among capabilities. The output of the RNN is then decoded into a label using a completely connected layer. Compared to different strategies, CRNNs can extract high-stage semantic and temporal features from uncooked scientific pictures with better accuracy and pace. they're also able to leverage massive datasets and are consequently favored for packages in which huge quantities of categorized records are to be had.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"219 ","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529726","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470779
Ruchika Malhotra, Vaibhavi Rajesh Mishra
Health and financial data are collected by the healthcare business. Due to electronic payment improvements, financial fraud monitoring has become expensive for healthcare service providers. Thus, fraud detection requires ongoing development. This study proposes the ensemble fraud detection classifier to increase performance. Ensemble classifiers use many machine learning detection algorithms. The evaluation focuses on accuracy, precision, and recall metrics. In a side-by-side comparison, the proposed ensemble classifiers excel beyond NB, RF, and KNN. Specifically, the ensemble method boasts an accuracy of 99.46, precision of 98.38, and a recall of 98.58, surpassing other classifiers. Future work in this study aims to integrate a hybrid model tailored to address imbalances in datasets and real-time responsiveness in financial transactions with improved accuracy.
{"title":"Utilizing Machine Learning for Identification of Financial Fraud in the Healthcare Sector","authors":"Ruchika Malhotra, Vaibhavi Rajesh Mishra","doi":"10.1109/ICOCWC60930.2024.10470779","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470779","url":null,"abstract":"Health and financial data are collected by the healthcare business. Due to electronic payment improvements, financial fraud monitoring has become expensive for healthcare service providers. Thus, fraud detection requires ongoing development. This study proposes the ensemble fraud detection classifier to increase performance. Ensemble classifiers use many machine learning detection algorithms. The evaluation focuses on accuracy, precision, and recall metrics. In a side-by-side comparison, the proposed ensemble classifiers excel beyond NB, RF, and KNN. Specifically, the ensemble method boasts an accuracy of 99.46, precision of 98.38, and a recall of 98.58, surpassing other classifiers. Future work in this study aims to integrate a hybrid model tailored to address imbalances in datasets and real-time responsiveness in financial transactions with improved accuracy.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"59 27","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529608","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470829
Deeplata Sharma, M. N. Nachappa, Rakesh Kumar Yadav
This technical abstract examines the pleasantness of carriers (quality of service) in numerous mobility protocols for Wi-Fi neighborhood place networks (WLAN). Quality of service is a measure of the level of service provided with the aid of a network and influences the supply, throughput, latency, jitter, and packet loss of packages. The research investigates the impact of mobility on quality of service in WLAN surroundings. An evaluation of the two fundamental mobility protocols., mobile IP and Proxy cellular IP, is executed in theoretical simulation surroundings. The effects of the assessment show that cell IP wireless advanced the quality of service on scalability, handoff delay, and packet loss. Additionally, this analysis suggests that Proxy cellular IP can successfully assist mobility in WLANs while providing suitable ranges of quality of service. With the consequences of these studies, gadget directors and network architects now have a higher understanding of the impact of mobility on the quality of service of WLANs.
本技术摘要探讨了 Wi-Fi 邻区网络（WLAN）众多移动协议中载波的舒适性（服务质量）。服务质量是对借助网络提供的服务水平的衡量，影响着数据包的供应、吞吐量、延迟、抖动和数据包丢失。本研究调查了移动性对 WLAN 环境中服务质量的影响。在理论模拟环境中对移动 IP 和代理蜂窝 IP 这两种基本移动协议进行了评估。评估结果表明，无线蜂窝 IP 在可扩展性、切换延迟和数据包丢失方面提高了服务质量。此外，该分析表明，代理蜂窝 IP 可以成功地协助 WLAN 的移动性，同时提供适当范围的服务质量。有了这些研究结果，设备主管和网络架构师现在对移动性对 WLAN 服务质量的影响有了更深入的了解。
{"title":"Investigation of Quality of Service in Various Mobility Protocols for Wireless Local Area Networks","authors":"Deeplata Sharma, M. N. Nachappa, Rakesh Kumar Yadav","doi":"10.1109/ICOCWC60930.2024.10470829","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470829","url":null,"abstract":"This technical abstract examines the pleasantness of carriers (quality of service) in numerous mobility protocols for Wi-Fi neighborhood place networks (WLAN). Quality of service is a measure of the level of service provided with the aid of a network and influences the supply, throughput, latency, jitter, and packet loss of packages. The research investigates the impact of mobility on quality of service in WLAN surroundings. An evaluation of the two fundamental mobility protocols., mobile IP and Proxy cellular IP, is executed in theoretical simulation surroundings. The effects of the assessment show that cell IP wireless advanced the quality of service on scalability, handoff delay, and packet loss. Additionally, this analysis suggests that Proxy cellular IP can successfully assist mobility in WLANs while providing suitable ranges of quality of service. With the consequences of these studies, gadget directors and network architects now have a higher understanding of the impact of mobility on the quality of service of WLANs.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"45 18","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529781","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470561
Meenu Shukla, Amit Kumar, Prerna Mahajan
Reliable fault tolerance and restoration for VLSI structures is a technique for autonomously keeping system performance within the occasion of a tool failure. It is done through the implementation of fault detection and isolation, fault correction, and restoration mechanisms, which allow for the gadget to pick out and get over component disasters. Fault tolerance is essential for dependable computing in the fairly incorporated and complicated surroundings of VLSI structures. The approach can assist in holding machine capability even for the duration of transient errors, taking into account the continuous operation of the gadget. Fault tolerance includes an extensive variety of techniques together with, but no longer confined to, gadget redundancy, failure detection, self-recuperation, and restoration. Redundancy is hired to defend in opposition to unmarried factors of failure situations, even as failure detection and correction mechanisms offer mechanisms for figuring out and mitigating errors. Fault tolerance and restoration may be similarly stronger with self-healing strategies and healing protocols, which may be used for restoring a gadget country in the event of a crash or device errors. Strong fault tolerance and recuperation strategies offer dependable methods for maintaining the nation of the machine, making an allowance for reliable and uninterrupted gadget performance.
{"title":"Reliable Fault Tolerance and Recovery for VLSI Systems","authors":"Meenu Shukla, Amit Kumar, Prerna Mahajan","doi":"10.1109/ICOCWC60930.2024.10470561","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470561","url":null,"abstract":"Reliable fault tolerance and restoration for VLSI structures is a technique for autonomously keeping system performance within the occasion of a tool failure. It is done through the implementation of fault detection and isolation, fault correction, and restoration mechanisms, which allow for the gadget to pick out and get over component disasters. Fault tolerance is essential for dependable computing in the fairly incorporated and complicated surroundings of VLSI structures. The approach can assist in holding machine capability even for the duration of transient errors, taking into account the continuous operation of the gadget. Fault tolerance includes an extensive variety of techniques together with, but no longer confined to, gadget redundancy, failure detection, self-recuperation, and restoration. Redundancy is hired to defend in opposition to unmarried factors of failure situations, even as failure detection and correction mechanisms offer mechanisms for figuring out and mitigating errors. Fault tolerance and restoration may be similarly stronger with self-healing strategies and healing protocols, which may be used for restoring a gadget country in the event of a crash or device errors. Strong fault tolerance and recuperation strategies offer dependable methods for maintaining the nation of the machine, making an allowance for reliable and uninterrupted gadget performance.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"137 ","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529732","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470475
Rajendra P. Pandey, Rahul Pawar, Girija Shankar Sahoo
this paper offers an investigation into the usage of applied cryptography for stopping unauthorized get entry. After introducing the simple cryptography standards, an evaluation of various cryptographic protocols is mentioned. Furthermore, capacity programs for applying cryptography are mentioned, together with authentication protocols, digital signature schemes, encryption algorithms, and get right of entry to manage systems. The paper additionally examines the current traits of the use of more robust cryptography so that it will, in addition, enhance safety systems. A comparison of numerous safety systems is offered, and the feasible advantages and downsides of a more potent cryptography version are discussed. Ultimately, the consequences of using more robust cryptography consideration close to criminal and privacy issues.
{"title":"An Investigation of the Use of Applied Cryptography for Preventing Unauthorized Access","authors":"Rajendra P. Pandey, Rahul Pawar, Girija Shankar Sahoo","doi":"10.1109/ICOCWC60930.2024.10470475","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470475","url":null,"abstract":"this paper offers an investigation into the usage of applied cryptography for stopping unauthorized get entry. After introducing the simple cryptography standards, an evaluation of various cryptographic protocols is mentioned. Furthermore, capacity programs for applying cryptography are mentioned, together with authentication protocols, digital signature schemes, encryption algorithms, and get right of entry to manage systems. The paper additionally examines the current traits of the use of more robust cryptography so that it will, in addition, enhance safety systems. A comparison of numerous safety systems is offered, and the feasible advantages and downsides of a more potent cryptography version are discussed. Ultimately, the consequences of using more robust cryptography consideration close to criminal and privacy issues.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"76 30","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529577","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}
Pub Date : 2024-01-29DOI: 10.1109/ICOCWC60930.2024.10470908
Umesh Kumar Singh, K. R, Pankaj Saraswat
In recent years, scientific imagery has ended up with an increasing number of essential approaches for diagnosing and monitoring many sicknesses. As a result, scientific photo classification has become a crucial research area. Deep learning procedures have opened new avenues for the medical photo category, with current tendencies because of recurrent neural networks (RNNs). Recurrent neural networks are robust neural networks that could discover ways to version temporal or sequential systems. Using RNNs, researchers can train a deep community in a supervised fashion without the need for manual photo segmentation. It has been validated to improve performance in scientific image type, with examples in the skin lesion category and lung nodule classification. The latest paintings have additionally validated the usage of RNNs to find latent features in clinical imagery, including latent anatomical systems and covariate relationships between disorder states. This type of evaluation can be beneficial in developing greater correct classifiers for medical images, similar to presenting a higher know-how of the imaging records. In precis, recurrent neural networks (RNNs) display promise in improving the accuracy of medical image class obligations. RNNs are crucial to discovering new features and covariate relationships between disease states in medical pics. With ongoing advances, RNNs will offer powerful equipment for scientific imaging.
{"title":"Recurrent Neural Networks for Improved Medical Image Classification","authors":"Umesh Kumar Singh, K. R, Pankaj Saraswat","doi":"10.1109/ICOCWC60930.2024.10470908","DOIUrl":"https://doi.org/10.1109/ICOCWC60930.2024.10470908","url":null,"abstract":"In recent years, scientific imagery has ended up with an increasing number of essential approaches for diagnosing and monitoring many sicknesses. As a result, scientific photo classification has become a crucial research area. Deep learning procedures have opened new avenues for the medical photo category, with current tendencies because of recurrent neural networks (RNNs). Recurrent neural networks are robust neural networks that could discover ways to version temporal or sequential systems. Using RNNs, researchers can train a deep community in a supervised fashion without the need for manual photo segmentation. It has been validated to improve performance in scientific image type, with examples in the skin lesion category and lung nodule classification. The latest paintings have additionally validated the usage of RNNs to find latent features in clinical imagery, including latent anatomical systems and covariate relationships between disorder states. This type of evaluation can be beneficial in developing greater correct classifiers for medical images, similar to presenting a higher know-how of the imaging records. In precis, recurrent neural networks (RNNs) display promise in improving the accuracy of medical image class obligations. RNNs are crucial to discovering new features and covariate relationships between disease states in medical pics. With ongoing advances, RNNs will offer powerful equipment for scientific imaging.","PeriodicalId":518901,"journal":{"name":"2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC)","volume":"28 6","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529920","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：