Pub Date : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00052
Margi Patel, Upendra Singh
Gender classification is popular because it includes information about male and female social activities. Faces make it difficult to derive gender-discriminating visuals. Gender classification is based on looks. Automatic gender classification is popular because genders include rich social information. Classification has grown increasingly important in many industries. In a conservative society, gender classification can be usedin certain contexts. Identifying gender type is crucial to keeping extremists out of safe locations, especially in sensitive areas. A similar technique is utilized in female-only railway carriages, gender-specific marketing, and temples. Biometrics debates gender classification from facial pictures. Traditional ways categorize hand-crafted features globally and locally. These gender-identification systems need subject knowledge and are ineffective. Human gender identification is easy, but machines struggle. We listed numerous gender classification pre-processing approaches, such as contrast and brightness normalization. To create a gender and age classification framework Deep Belief Networks employs Shifted Filter Responses to identify features. The suggested model achieves 98% and 99% accuracy on the benchmark dataset.
{"title":"Age and Gender Recognition using Deep Learning Technique","authors":"Margi Patel, Upendra Singh","doi":"10.1109/ICSMDI57622.2023.00052","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00052","url":null,"abstract":"Gender classification is popular because it includes information about male and female social activities. Faces make it difficult to derive gender-discriminating visuals. Gender classification is based on looks. Automatic gender classification is popular because genders include rich social information. Classification has grown increasingly important in many industries. In a conservative society, gender classification can be usedin certain contexts. Identifying gender type is crucial to keeping extremists out of safe locations, especially in sensitive areas. A similar technique is utilized in female-only railway carriages, gender-specific marketing, and temples. Biometrics debates gender classification from facial pictures. Traditional ways categorize hand-crafted features globally and locally. These gender-identification systems need subject knowledge and are ineffective. Human gender identification is easy, but machines struggle. We listed numerous gender classification pre-processing approaches, such as contrast and brightness normalization. To create a gender and age classification framework Deep Belief Networks employs Shifted Filter Responses to identify features. The suggested model achieves 98% and 99% accuracy on the benchmark dataset.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127394692","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00013
B. Liya, Pritam S, R. S, Navin K
The internet has evolved a lot in the last 40 years and its early applications has become unrecognizable. Web 1.0 focused on serving static pages is considered as the read-only web, whereas web 2.0 made way for dynamic pages making it as read-write web, which is predominantly experienced. The main problem face here is, as the users of E-commerce applications, is single-point-of-failure (SPOF), which means, the data stored in centralized servers is highly susceptible and vulnerable to attacks. Now, the internet's next evolution enables to develop decentralized applications and adds few other features like trustlessness, distributed, transparent, robust, etc. This also makes web 3.0 as read-write-own web. Now, this evolution wave of decentralization has hit the applications. To overcome this problem, this study has proposed a solution to completely decentralize the E-Commerce platform by using Blockchain in conjunction with smart contracts and utilizes the decentralized storage like IPFS (Inter Planetary File System). This article has developed a system that uses ReactJs as the frontend and the Ethereum blockchain as the backend to execute smart contracts using the EVM (Ethereum Virtual Machine) and to store data in a decentralized way by using IPFS and BigChainDb.
{"title":"Decentralized E-Commerce Platform Implemented using Smart Contracts","authors":"B. Liya, Pritam S, R. S, Navin K","doi":"10.1109/ICSMDI57622.2023.00013","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00013","url":null,"abstract":"The internet has evolved a lot in the last 40 years and its early applications has become unrecognizable. Web 1.0 focused on serving static pages is considered as the read-only web, whereas web 2.0 made way for dynamic pages making it as read-write web, which is predominantly experienced. The main problem face here is, as the users of E-commerce applications, is single-point-of-failure (SPOF), which means, the data stored in centralized servers is highly susceptible and vulnerable to attacks. Now, the internet's next evolution enables to develop decentralized applications and adds few other features like trustlessness, distributed, transparent, robust, etc. This also makes web 3.0 as read-write-own web. Now, this evolution wave of decentralization has hit the applications. To overcome this problem, this study has proposed a solution to completely decentralize the E-Commerce platform by using Blockchain in conjunction with smart contracts and utilizes the decentralized storage like IPFS (Inter Planetary File System). This article has developed a system that uses ReactJs as the frontend and the Ethereum blockchain as the backend to execute smart contracts using the EVM (Ethereum Virtual Machine) and to store data in a decentralized way by using IPFS and BigChainDb.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128183445","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00096
Pavan Kumar Mahadasu, Durga Prasad Seetha, S. T. Krishna, B. Venkateswarlu
This article intends to propose a technique for categorizing 3D deformable objects from unprocessed single-view images. The proposed technique is built on an autoencoder, which considers the depth, albedo, and viewpoint of each input image. By considering the symmetry that many object categories exhibit, at least in theory to independently untangle these parts from one another. This manuscript shows the demonstration how, even when shading causes the appearance of an object to be nonsymmetric, Still, the underlying object symmetry by using illumination-related reasoning. Additionally, by forecasting a symmetry probability map that is learned end to end with the other model elements, and represents things that are not symmetric. Experimental results demonstrate that, without assistance or the use of a pre-existing form model, this method is capable of recovering the 3D shape of humanoid faces, cat images, and automobile images with remarkable accuracy from single-view photos. As compared to the level of 2D picture correspondences, show superior accuracy on benchmarks in comparison to another system that makes use of supervision.
{"title":"Image Classification from Unsupervised Learning of 3D Objects","authors":"Pavan Kumar Mahadasu, Durga Prasad Seetha, S. T. Krishna, B. Venkateswarlu","doi":"10.1109/ICSMDI57622.2023.00096","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00096","url":null,"abstract":"This article intends to propose a technique for categorizing 3D deformable objects from unprocessed single-view images. The proposed technique is built on an autoencoder, which considers the depth, albedo, and viewpoint of each input image. By considering the symmetry that many object categories exhibit, at least in theory to independently untangle these parts from one another. This manuscript shows the demonstration how, even when shading causes the appearance of an object to be nonsymmetric, Still, the underlying object symmetry by using illumination-related reasoning. Additionally, by forecasting a symmetry probability map that is learned end to end with the other model elements, and represents things that are not symmetric. Experimental results demonstrate that, without assistance or the use of a pre-existing form model, this method is capable of recovering the 3D shape of humanoid faces, cat images, and automobile images with remarkable accuracy from single-view photos. As compared to the level of 2D picture correspondences, show superior accuracy on benchmarks in comparison to another system that makes use of supervision.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126364151","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00059
Nayana Shivanand, Meenakshi L Rathod, Chetan S
Recently we have seen many Vending machines dispense things like toys, chocolates, shakes, snacks, lottery tickets, etc. Vending machines automatically dispense the different products when a consumer puts a currency or colored or different size token. The requirements for modern vending machines are increasing rapidly due to their ease of use. This research work intends to design a vending machine to sell eight different integrated circuits (ICs). Users can select the desired product and quantity of the product while inserting the currency. The proposed model also shows the available stock and total amount for the entered product. Here, FPGA is used to design the proposed Vending Machine (VM) as FPGAs are more flexible than embedded systems. The proposed vending machine is mainly used to vend the logical gates. It has better advantages as the quantity and amount can be entered according to the user requirements. The developed vending machine can be used in schools, research laboratories etc. FPGAs can be reprogrammed any number of times, consume less power and work faster than CMOS based Vending machines. Finally, the proposed design is simulated using Xilinx 14.7 and then implemented using FPGA kit artic 7.
{"title":"FPGA based Vending Machine For Logical Gates","authors":"Nayana Shivanand, Meenakshi L Rathod, Chetan S","doi":"10.1109/ICSMDI57622.2023.00059","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00059","url":null,"abstract":"Recently we have seen many Vending machines dispense things like toys, chocolates, shakes, snacks, lottery tickets, etc. Vending machines automatically dispense the different products when a consumer puts a currency or colored or different size token. The requirements for modern vending machines are increasing rapidly due to their ease of use. This research work intends to design a vending machine to sell eight different integrated circuits (ICs). Users can select the desired product and quantity of the product while inserting the currency. The proposed model also shows the available stock and total amount for the entered product. Here, FPGA is used to design the proposed Vending Machine (VM) as FPGAs are more flexible than embedded systems. The proposed vending machine is mainly used to vend the logical gates. It has better advantages as the quantity and amount can be entered according to the user requirements. The developed vending machine can be used in schools, research laboratories etc. FPGAs can be reprogrammed any number of times, consume less power and work faster than CMOS based Vending machines. Finally, the proposed design is simulated using Xilinx 14.7 and then implemented using FPGA kit artic 7.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121872051","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00061
T. Jebaseeli, Navin Kumar M, Angeleen Subagar, Santhosh A
Cardiovascular disease is one of the primary reasons for death in the world today. It has evolved into one of the most challenging illnesses to identify. By a recent WHO research, heart disorders are on the rise. As a result, 17.9 million people die each year. As the population increased, this became increasingly difficult to diagnose and initiate treatment during the initial stages. When it comes to forecasting coronary heart disease, medical analysis of data encounters a huge challenge. Electronic health record systems are currently used to handle the data of patients in hospitals. The huge amount of information created by the medical industry is being misused. A new approach is required to reduce costs and accurately predict heart disease. Hospitals can use appropriate decision support systems to reduce the cost of clinical tests. Several types of research offer barely a glimpse of optimism for employing machine learning approaches for predicting cardiac disease. The proposed study suggests a unique strategy for finding key characteristics via a machine learning approach throughout this work, which would also improve the precision of cardiovascular risk diagnosis. Diverse characteristic correlations and classification algorithms are used to establish the statistical model. Using the Improved random forest with Hyper - parameters tweaking in the classification algorithm for cardiovascular disease, a better reliability with an acceptable accuracy of 94.5% has been obtained. This approach may be valuable to healthcare professionals in their treatment as a decision assistance system.
{"title":"Cardio Vascular Disease Prediction and Classification Report Generation using Data Mining Technique","authors":"T. Jebaseeli, Navin Kumar M, Angeleen Subagar, Santhosh A","doi":"10.1109/ICSMDI57622.2023.00061","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00061","url":null,"abstract":"Cardiovascular disease is one of the primary reasons for death in the world today. It has evolved into one of the most challenging illnesses to identify. By a recent WHO research, heart disorders are on the rise. As a result, 17.9 million people die each year. As the population increased, this became increasingly difficult to diagnose and initiate treatment during the initial stages. When it comes to forecasting coronary heart disease, medical analysis of data encounters a huge challenge. Electronic health record systems are currently used to handle the data of patients in hospitals. The huge amount of information created by the medical industry is being misused. A new approach is required to reduce costs and accurately predict heart disease. Hospitals can use appropriate decision support systems to reduce the cost of clinical tests. Several types of research offer barely a glimpse of optimism for employing machine learning approaches for predicting cardiac disease. The proposed study suggests a unique strategy for finding key characteristics via a machine learning approach throughout this work, which would also improve the precision of cardiovascular risk diagnosis. Diverse characteristic correlations and classification algorithms are used to establish the statistical model. Using the Improved random forest with Hyper - parameters tweaking in the classification algorithm for cardiovascular disease, a better reliability with an acceptable accuracy of 94.5% has been obtained. This approach may be valuable to healthcare professionals in their treatment as a decision assistance system.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128316857","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00019
Aishwarya Prakash, S. Chauhan
Thousands of gigabytes of data are produced each minute by everyone in today's society. This data is being stored in clouds worldwide. The study addressed these security issues in a variety of ways. This research suggests a cloud computing security architecture based on cryptography and steganography. In addition to using symmetric and steganographic techniques, the model is said to meet all security standards, such as security resilience, secrecy, authentication, integrity, and non-repudiation. This method employs the Advanced Encryption Standard (AES) 256 and steganography to provide multilayer encryption and decryption at both the transmitter and receiver sides, boosting cloud storage security. This security paradigm delivers transparency to cloud users and service providers to alleviate security worries. The suggested model is written in Python and operates on the Amazon Web Services cloud. While compared to the old method, this approach enhances data security and saves time when uploading and downloading text files.
在当今社会，每个人每分钟都会产生数千千兆字节的数据。这些数据被存储在全球的云中。该研究以多种方式解决了这些安全问题。本研究提出了一种基于密码学和隐写术的云计算安全架构。除了使用对称和隐写技术外，据说该模型还满足所有安全标准，例如安全弹性、保密性、身份验证、完整性和不可否认性。该方法采用高级加密标准AES (Advanced Encryption Standard) 256和隐写技术，在发送端和接收端都提供多层加解密，提高了云存储的安全性。这种安全范例为云用户和服务提供商提供了透明度，从而减轻了安全方面的担忧。建议的模型是用Python编写的，并在Amazon Web Services云上运行。与旧方法相比，该方法提高了数据安全性，并节省了上传和下载文本文件的时间。
{"title":"Exploring Innovative Methods for Enhancing Data Security in Computing","authors":"Aishwarya Prakash, S. Chauhan","doi":"10.1109/ICSMDI57622.2023.00019","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00019","url":null,"abstract":"Thousands of gigabytes of data are produced each minute by everyone in today's society. This data is being stored in clouds worldwide. The study addressed these security issues in a variety of ways. This research suggests a cloud computing security architecture based on cryptography and steganography. In addition to using symmetric and steganographic techniques, the model is said to meet all security standards, such as security resilience, secrecy, authentication, integrity, and non-repudiation. This method employs the Advanced Encryption Standard (AES) 256 and steganography to provide multilayer encryption and decryption at both the transmitter and receiver sides, boosting cloud storage security. This security paradigm delivers transparency to cloud users and service providers to alleviate security worries. The suggested model is written in Python and operates on the Amazon Web Services cloud. While compared to the old method, this approach enhances data security and saves time when uploading and downloading text files.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132458817","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00016
Srijeet Gopalan, Rohit Verma, Shivani Jaswal
The emergence of smart health facilitates readily available healthcare services. Increased demand for medical services, on the other hand, necessitates additional computing and storage resources near patients/users for smart sensing, analysis and processing. Fog Computing (FC) is a rapidly evolving field, which is considered as a valuable addition to the cloud to address issues such as unpredictable latency, resource constraints, confidentiality, and easy accessibility. Since information can be easily stored and assessed relatively close to sources of information on native fog nodes, it is relatively safe as compared to cloud computing. Still, the existing fog models face number of challenges, and focuses on one of two things: accuracy of data obtained or low turnaround time, not both. This paper proposes SPATS, a Secure AES encryption enabled Privacy Assured Telehealth System that addresses privacy and security threats in a fog environment by integrating stacking classifier in fog devices and deploying it in a real-world application of automatic health analysis. The AES encryption technology is used to ensure privacy and security from attackers while sensitive data is stored in cloud. A detailed experimentation and analysis have been done using EHR dataset from real-world medical services to assess the performance of SPATS. The results of the experiments reveal that the proposed system accurately predicts the health condition. When compared to existing machine learning techniques, the suggested approach achieves a better prediction accuracy.
{"title":"A Secure and Privacy Preserving Telehealth Solution in Fog Based Environment","authors":"Srijeet Gopalan, Rohit Verma, Shivani Jaswal","doi":"10.1109/ICSMDI57622.2023.00016","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00016","url":null,"abstract":"The emergence of smart health facilitates readily available healthcare services. Increased demand for medical services, on the other hand, necessitates additional computing and storage resources near patients/users for smart sensing, analysis and processing. Fog Computing (FC) is a rapidly evolving field, which is considered as a valuable addition to the cloud to address issues such as unpredictable latency, resource constraints, confidentiality, and easy accessibility. Since information can be easily stored and assessed relatively close to sources of information on native fog nodes, it is relatively safe as compared to cloud computing. Still, the existing fog models face number of challenges, and focuses on one of two things: accuracy of data obtained or low turnaround time, not both. This paper proposes SPATS, a Secure AES encryption enabled Privacy Assured Telehealth System that addresses privacy and security threats in a fog environment by integrating stacking classifier in fog devices and deploying it in a real-world application of automatic health analysis. The AES encryption technology is used to ensure privacy and security from attackers while sensitive data is stored in cloud. A detailed experimentation and analysis have been done using EHR dataset from real-world medical services to assess the performance of SPATS. The results of the experiments reveal that the proposed system accurately predicts the health condition. When compared to existing machine learning techniques, the suggested approach achieves a better prediction accuracy.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133231445","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00100
Luoli, Amit Yadav, Asif Khan
With the emergence of Internet of Things (IoT) applications that provide services based on location information. The Radio Frequency Identification (RFID) technology is considered as one of the key technologies of the Internet of Things' sensing layer. In the Internet of Things (IoT) domain, further research on the positioning technology of RFID nodes has significant practical implications. Initially, this article analyzes a variety of existing RFID indoor positioning technologies and then focuses on fingerprint positioning technology to improve the traditional fingerprint positioning algorithm and finally demonstrates that the improved algorithm delivers more accurate positioning through MATLAB simulation.
{"title":"Research on Indoor Positioning Technology of RFID Nodes in the Internet of Things (IoT)","authors":"Luoli, Amit Yadav, Asif Khan","doi":"10.1109/ICSMDI57622.2023.00100","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00100","url":null,"abstract":"With the emergence of Internet of Things (IoT) applications that provide services based on location information. The Radio Frequency Identification (RFID) technology is considered as one of the key technologies of the Internet of Things' sensing layer. In the Internet of Things (IoT) domain, further research on the positioning technology of RFID nodes has significant practical implications. Initially, this article analyzes a variety of existing RFID indoor positioning technologies and then focuses on fingerprint positioning technology to improve the traditional fingerprint positioning algorithm and finally demonstrates that the improved algorithm delivers more accurate positioning through MATLAB simulation.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019704","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00071
B. Babu, G.Akshay Reddy, D.Kushal Goud, K. Naveen, K. T. Reddy
The advancement in wireless communication technology has led to various security challenges in networks. To combat these issues, Network Intrusion Detection Systems (NIDS) are employed to identify attacks. To enhance their accuracy in detecting intruders, various machine learning techniques have been previously used with NIDS. This paper presents a new approach that utilizes machine learning techniques to identify intrusions. The findings of our model indicate that it outperforms other methods, such as Naive Bayes, in terms of accuracy. Our method resulted in a performance time of 1.26 minutes, an accuracy rate of 97.38%, and an error rate of 0.25%.
{"title":"Network Intrusion Detection using Machine Learning Algorithms","authors":"B. Babu, G.Akshay Reddy, D.Kushal Goud, K. Naveen, K. T. Reddy","doi":"10.1109/ICSMDI57622.2023.00071","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00071","url":null,"abstract":"The advancement in wireless communication technology has led to various security challenges in networks. To combat these issues, Network Intrusion Detection Systems (NIDS) are employed to identify attacks. To enhance their accuracy in detecting intruders, various machine learning techniques have been previously used with NIDS. This paper presents a new approach that utilizes machine learning techniques to identify intrusions. The findings of our model indicate that it outperforms other methods, such as Naive Bayes, in terms of accuracy. Our method resulted in a performance time of 1.26 minutes, an accuracy rate of 97.38%, and an error rate of 0.25%.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114446648","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 : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00080
M. S. Rao, Birudugadda Kalyani, Baswani Vathsalya, Karri Dhanunjay, Alasandalapalli Lakshmi Narayana
This paper presents a strategy for discovering flaws in web applications through Machine Learning (ML). Web-based applications are especially troublesome to examine attributed to their variety and extensive usage of custom development methodologies. As little more than a basis, machine learning is extremely useful in website safety: It just might combine cognitive knowledge of web app terminology with automated software approaches based on verbally reported information. Mitch tool is the foremost machine learning strategy towards black-box investigation for Cross-Site Request Forgery (C.S.R.F) problems, was built using these principles. Mitch-helped us find Thirty-five recently developed cross-site request forgeries (C.S.R. Fs) in twenty wide fields, together with 3 main C.S.R. Fs in industry applications.
{"title":"Cross-Site Request Forgery as an Example of Machine Learning for Web Vulnerability Detection","authors":"M. S. Rao, Birudugadda Kalyani, Baswani Vathsalya, Karri Dhanunjay, Alasandalapalli Lakshmi Narayana","doi":"10.1109/ICSMDI57622.2023.00080","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00080","url":null,"abstract":"This paper presents a strategy for discovering flaws in web applications through Machine Learning (ML). Web-based applications are especially troublesome to examine attributed to their variety and extensive usage of custom development methodologies. As little more than a basis, machine learning is extremely useful in website safety: It just might combine cognitive knowledge of web app terminology with automated software approaches based on verbally reported information. Mitch tool is the foremost machine learning strategy towards black-box investigation for Cross-Site Request Forgery (C.S.R.F) problems, was built using these principles. Mitch-helped us find Thirty-five recently developed cross-site request forgeries (C.S.R. Fs) in twenty wide fields, together with 3 main C.S.R. Fs in industry applications.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128293601","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：