Pub Date : 2023-03-01DOI: 10.1109/ICSMDI57622.2023.00035
Shusheng Wang
The significant challenge faced by traditional Ad Hoc network is that when the communication range increases, the chance of encountering nodes and the duration of encounters will increase, resulting in an increase in the corresponding operation and network overhead in each algorithm. Hence, to face with this challenge, this research studies the routing algorithm of wireless mobile communication based on network coding. For our designed scenario, the random direction movement model, and multicast routing algorithm is considered based on network coding searches for the group path family for all receiving nodes in the network. This is then applied to construct the efficient coding scenario. Through the experiment, this study has tested the model with the trained datasets.
{"title":"Routing Algorithm of Wireless Mobile Communication based on Network Coding","authors":"Shusheng Wang","doi":"10.1109/ICSMDI57622.2023.00035","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00035","url":null,"abstract":"The significant challenge faced by traditional Ad Hoc network is that when the communication range increases, the chance of encountering nodes and the duration of encounters will increase, resulting in an increase in the corresponding operation and network overhead in each algorithm. Hence, to face with this challenge, this research studies the routing algorithm of wireless mobile communication based on network coding. For our designed scenario, the random direction movement model, and multicast routing algorithm is considered based on network coding searches for the group path family for all receiving nodes in the network. This is then applied to construct the efficient coding scenario. Through the experiment, this study has tested the model with the trained datasets.","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":"125007850","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/ICSMDI57622.2023.00040
Lien-Yuan Ting
One of the most important elements in the idea of active defense is data collection and data analysis, especially in many cases to analyze the original packets in the network by mainly using the packet capture technology. Therefore, this study discusses about intrusion and defense technology of computer network server with Linux, In the network security analysis system, the storage of original data has become crucial. Big data technology can collect different data for different data types, and can actively use different methods to improve the efficiency of data query. Through the novel design, Snort with good scalability, good portabiIi ty, and open source will be used as the system detection module to organize the rule base in the form of a secondary linked list. Finally, the performance is tested and simulated.
{"title":"Discussion on Intrusion and Defense Technology of Computer Network Server with Linux","authors":"Lien-Yuan Ting","doi":"10.1109/ICSMDI57622.2023.00040","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00040","url":null,"abstract":"One of the most important elements in the idea of active defense is data collection and data analysis, especially in many cases to analyze the original packets in the network by mainly using the packet capture technology. Therefore, this study discusses about intrusion and defense technology of computer network server with Linux, In the network security analysis system, the storage of original data has become crucial. Big data technology can collect different data for different data types, and can actively use different methods to improve the efficiency of data query. Through the novel design, Snort with good scalability, good portabiIi ty, and open source will be used as the system detection module to organize the rule base in the form of a secondary linked list. Finally, the performance is tested and simulated.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"71 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":"125388249","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/ICSMDI57622.2023.00107
A. Varshney, A. P, P. M, Poovendan R, S. Navaneethan
Latency and storage requirements are becoming increasingly important for all applications. One of the most crucial factors in industry is the time lag between production and consumption. These two factors are taken into account for any practical use in any sector. VLSI technology's many techniques allow for the creation of such software. Two approaches were taken in the creation of the Braun multiplier. This multiplier is built using a combination of CMOS and GDI techniques. The multiplier employs the parallel prefix adders. The system's speed may be increased with the use of the Braun multiplier. Tanner V-13 is the Electronic Design and Analysis tool used to create the Braun multiplier. Both complementary metal-oxide semiconductor and germanium-doped indium circuits took this multiplier's output into account.
{"title":"Deployment of Braun Multiplier Using Novel Adder Formulations","authors":"A. Varshney, A. P, P. M, Poovendan R, S. Navaneethan","doi":"10.1109/ICSMDI57622.2023.00107","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00107","url":null,"abstract":"Latency and storage requirements are becoming increasingly important for all applications. One of the most crucial factors in industry is the time lag between production and consumption. These two factors are taken into account for any practical use in any sector. VLSI technology's many techniques allow for the creation of such software. Two approaches were taken in the creation of the Braun multiplier. This multiplier is built using a combination of CMOS and GDI techniques. The multiplier employs the parallel prefix adders. The system's speed may be increased with the use of the Braun multiplier. Tanner V-13 is the Electronic Design and Analysis tool used to create the Braun multiplier. Both complementary metal-oxide semiconductor and germanium-doped indium circuits took this multiplier's output into account.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"332 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":"124676818","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}
One of the highest-produced crops in the world, Dry Bean faces an extreme genetic diverse species in their crops. The quality of the seed is influencing in production of crops. Consequently, the classification of the seeds has become the need of the hour for production as well as marketing in order to avail the agricultural principles of sustainable systems. This research aims to develop a method which helps to obtain even varieties of seeds from the production of crops. In the literature, very few works have been developed for the Dry beans classification. In this work, an ensemble model for the classification called ELDB is developed where ELDB stands for Ensemble Learning classifier for Dry Beans. The proposed method uses the philosophy of ensemble of ensembles to develop a robust classifier to classify Dry beans effectively. Based on the different extracted features, ELDB is trained, an ensemble of Random Forest and XGboost. The proposed ensemble model has the highest performance score compared to other methods with class-wise accuracies such as Seker, Barbunya, Bombay, Cali, Horoz, Sira and Dermason with 96.94%, 96.06%, 91.95%, 96.32%, 96.16%, 95.9% and 98.42% respectively. The overall performance of the proposed method has been compared with the state-of-art method over various measures like accuracy, precision, recall and F1-score, where the proposed method performance are 95.96%, 95.71%, 95.84% and 95.97% respectively.
{"title":"Dry Beans Classification using Ensemble Learning","authors":"Sakshi Shriya, Vipin Kumar, Prem Shankar Singh Aydav","doi":"10.1109/ICSMDI57622.2023.00065","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00065","url":null,"abstract":"One of the highest-produced crops in the world, Dry Bean faces an extreme genetic diverse species in their crops. The quality of the seed is influencing in production of crops. Consequently, the classification of the seeds has become the need of the hour for production as well as marketing in order to avail the agricultural principles of sustainable systems. This research aims to develop a method which helps to obtain even varieties of seeds from the production of crops. In the literature, very few works have been developed for the Dry beans classification. In this work, an ensemble model for the classification called ELDB is developed where ELDB stands for Ensemble Learning classifier for Dry Beans. The proposed method uses the philosophy of ensemble of ensembles to develop a robust classifier to classify Dry beans effectively. Based on the different extracted features, ELDB is trained, an ensemble of Random Forest and XGboost. The proposed ensemble model has the highest performance score compared to other methods with class-wise accuracies such as Seker, Barbunya, Bombay, Cali, Horoz, Sira and Dermason with 96.94%, 96.06%, 91.95%, 96.32%, 96.16%, 95.9% and 98.42% respectively. The overall performance of the proposed method has been compared with the state-of-art method over various measures like accuracy, precision, recall and F1-score, where the proposed method performance are 95.96%, 95.71%, 95.84% and 95.97% respectively.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"19 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":"116676776","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/ICSMDI57622.2023.00020
Nalifa Begam J, Dhivya Priya E L, K. Sivasankari, A. S. Kumar, K.R. Priya Dharshini
Multimodal biometric systems are able to overcome some of these shortcomings, as mono-model biometric systems present a number of security issues and often offer unacceptable error rates. By combining two or more biometric systems into one identification system, multimodal biometrics improve the accuracy of authentication. However, the characteristics of a single biometric system should be statistically independent of the features of different biometrics systems. This article proposes a multimodal biometric system that can recognize fingerprints, faces and iris patterns. The system is applied to a point level that is consistent with different means of normalization and fusion. Compatibility scores are generated when query and database images are matched. The Fusion module combines the normalized and weighted sum scores to determine compatibility scores. The cumulative rule is used to combine these individual adjusted scores and their weights into a total score. Weights associated with each biometric attribute indicate how important that attribute is to the user, this system establishes an identity that is more trustworthy than individual biometric systems that establish identities by analyzing individual fingerprints. In a multimodal biometric system, multiple biometric properties are combined to enhance authentication performance and to reduce fraudulent access. The designed scheme exceeds single biometric systems in terms of reliability and accuracy.
{"title":"Multimodal Efficient Bioscrypt Authentication using MATLAB","authors":"Nalifa Begam J, Dhivya Priya E L, K. Sivasankari, A. S. Kumar, K.R. Priya Dharshini","doi":"10.1109/ICSMDI57622.2023.00020","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00020","url":null,"abstract":"Multimodal biometric systems are able to overcome some of these shortcomings, as mono-model biometric systems present a number of security issues and often offer unacceptable error rates. By combining two or more biometric systems into one identification system, multimodal biometrics improve the accuracy of authentication. However, the characteristics of a single biometric system should be statistically independent of the features of different biometrics systems. This article proposes a multimodal biometric system that can recognize fingerprints, faces and iris patterns. The system is applied to a point level that is consistent with different means of normalization and fusion. Compatibility scores are generated when query and database images are matched. The Fusion module combines the normalized and weighted sum scores to determine compatibility scores. The cumulative rule is used to combine these individual adjusted scores and their weights into a total score. Weights associated with each biometric attribute indicate how important that attribute is to the user, this system establishes an identity that is more trustworthy than individual biometric systems that establish identities by analyzing individual fingerprints. In a multimodal biometric system, multiple biometric properties are combined to enhance authentication performance and to reduce fraudulent access. The designed scheme exceeds single biometric systems in terms of reliability and accuracy.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"59 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":"124366608","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/ICSMDI57622.2023.00075
Sowmya Prakash, K. Harshitha, A.O. Charitha, C. Janvitha, K. Indu
Computer-aided diagnosis (CAD), a field of medical analysis, is rapidly advancing in a large range and is becoming more complex. Computer-aided recently, there has been a lot of interest in diagnostics for the reason inaccurate medical diagnosis could result in significantly misleading therapies. Machine learning (ML) is a key component of computer-aided diagnostic examinations. A simple equation cannot identify an organ in the body with the required accuracy. Therefore, pattern recognition requires learning from examples. Using pattern detection techniques and machine learning (ML) techniques, it is possible to improve the accuracy of diagnosing diseases and making appropriate treatment decisions in the medical field It is important to them that decisions are made objectively. Machine Learning (ML) provides a reliable approach to the development of improved, automated algorithms for the analysis of high- dimensional, multi-modal biological data. This survey article compares various machine learning approaches and algorithms for a variety of diseases' detection. The range of Machine Learning (ML) methods and methods utilized in the medical diagnosis and decision- making are analyzed
{"title":"Computer-Aided Diagnosis using Machine Learning Techniques","authors":"Sowmya Prakash, K. Harshitha, A.O. Charitha, C. Janvitha, K. Indu","doi":"10.1109/ICSMDI57622.2023.00075","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00075","url":null,"abstract":"Computer-aided diagnosis (CAD), a field of medical analysis, is rapidly advancing in a large range and is becoming more complex. Computer-aided recently, there has been a lot of interest in diagnostics for the reason inaccurate medical diagnosis could result in significantly misleading therapies. Machine learning (ML) is a key component of computer-aided diagnostic examinations. A simple equation cannot identify an organ in the body with the required accuracy. Therefore, pattern recognition requires learning from examples. Using pattern detection techniques and machine learning (ML) techniques, it is possible to improve the accuracy of diagnosing diseases and making appropriate treatment decisions in the medical field It is important to them that decisions are made objectively. Machine Learning (ML) provides a reliable approach to the development of improved, automated algorithms for the analysis of high- dimensional, multi-modal biological data. This survey article compares various machine learning approaches and algorithms for a variety of diseases' detection. The range of Machine Learning (ML) methods and methods utilized in the medical diagnosis and decision- making are analyzed","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"5 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":"128445299","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/ICSMDI57622.2023.00044
Yenduri Harshitha Lakshmi, Y. Sangeetha, Kuncham Pushpa Sri Vyshnavi, Shaik Fyzulla
Internet is playing a crucial role in each person's lives. If people are having any kind of doubts regarding any issues, they simply search them in internet If people need to go somewhere new, they simply look up the rankings on the internet. In the same way, if there is a need to visit any consulting agency, internet plays a major role in discovering a high-quality consulting firm on Google. In this study, a new we bsite has been created for L&Tsoftware technologies. The developed website can be used to locate the products and services provided by the consultancy without any physical visit People can also easily find job openings, and they can clear their doubts by using the contact page remotely. The developed website is further advanced by using MERNSTACK, HTML, CSS,andJAVA SCRIPT. The MERNSTACK is used to create multipage web packages. The web packages made with the help of MERNSTACK are more scalable when compared to different internet programs. The best feature here in the website is Latency. This determines the postponement between request and reaction. In the networking domain, if any statistics is requested from few different devices connected to the network, then the time taken for receiving the primary response is referred to as latency. So, the decrease in the latency will fasten the conversation. Hence, maintaining a low latency on the provided community or net is very critical. Here, 42ms time has been consumed with low latency. So, website works very rapid in terms of verbal exchange. Slowing down facts speeds after a client reaches its monthly information restriction is a not unusual practice among net carrier companies and cellular carriers that is referred to as throttling.
{"title":"A Website for a Consultancy using Mern Stack","authors":"Yenduri Harshitha Lakshmi, Y. Sangeetha, Kuncham Pushpa Sri Vyshnavi, Shaik Fyzulla","doi":"10.1109/ICSMDI57622.2023.00044","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00044","url":null,"abstract":"Internet is playing a crucial role in each person's lives. If people are having any kind of doubts regarding any issues, they simply search them in internet If people need to go somewhere new, they simply look up the rankings on the internet. In the same way, if there is a need to visit any consulting agency, internet plays a major role in discovering a high-quality consulting firm on Google. In this study, a new we bsite has been created for L&Tsoftware technologies. The developed website can be used to locate the products and services provided by the consultancy without any physical visit People can also easily find job openings, and they can clear their doubts by using the contact page remotely. The developed website is further advanced by using MERNSTACK, HTML, CSS,andJAVA SCRIPT. The MERNSTACK is used to create multipage web packages. The web packages made with the help of MERNSTACK are more scalable when compared to different internet programs. The best feature here in the website is Latency. This determines the postponement between request and reaction. In the networking domain, if any statistics is requested from few different devices connected to the network, then the time taken for receiving the primary response is referred to as latency. So, the decrease in the latency will fasten the conversation. Hence, maintaining a low latency on the provided community or net is very critical. Here, 42ms time has been consumed with low latency. So, website works very rapid in terms of verbal exchange. Slowing down facts speeds after a client reaches its monthly information restriction is a not unusual practice among net carrier companies and cellular carriers that is referred to as throttling.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"57 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":"127030771","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/ICSMDI57622.2023.00022
Devansh Singh, Mrs Vimmi Malhotra
There has been a lot of buzz about blockchain technology lately, thanks to the success of digital currencies like Bitcoin and Ethereum. All of these applications of blockchain technology have received a lot of attention. Bitcoin and Ethereum were able to process 7 and 15 TPS, respectively, when they were launched, whereas VISA and PayPal were able to process 1700 and 193 TPS. Scalability, which may be described as the capability to modify the block size to accommodate the rising traffic, is the most significant barrier to the widespread adoption of blockchain technology. This article aims to examine blockchain applications, including their applications, smart contracts, and the solutions to those problems. It is vital to scale blockchains while maintaining their fundamentally decentralised nature to appreciate these technologies' promise fully. The successful implementation of scalability solutions is necessary for several reasons, including the provision of services whose performance is on par with that of prevalent technologies, the support of innovative applications, and the maintenance of the workload produced by an expanding user base. In the future, this study will be extended by considering the options that contributors provide as an initiative towards resolving these issues.
{"title":"A Review on the Capability and Smart Contract Potential of Block chain Technology","authors":"Devansh Singh, Mrs Vimmi Malhotra","doi":"10.1109/ICSMDI57622.2023.00022","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00022","url":null,"abstract":"There has been a lot of buzz about blockchain technology lately, thanks to the success of digital currencies like Bitcoin and Ethereum. All of these applications of blockchain technology have received a lot of attention. Bitcoin and Ethereum were able to process 7 and 15 TPS, respectively, when they were launched, whereas VISA and PayPal were able to process 1700 and 193 TPS. Scalability, which may be described as the capability to modify the block size to accommodate the rising traffic, is the most significant barrier to the widespread adoption of blockchain technology. This article aims to examine blockchain applications, including their applications, smart contracts, and the solutions to those problems. It is vital to scale blockchains while maintaining their fundamentally decentralised nature to appreciate these technologies' promise fully. The successful implementation of scalability solutions is necessary for several reasons, including the provision of services whose performance is on par with that of prevalent technologies, the support of innovative applications, and the maintenance of the workload produced by an expanding user base. In the future, this study will be extended by considering the options that contributors provide as an initiative towards resolving these issues.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"16 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":"131924311","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/ICSMDI57622.2023.00018
Luka Jovanovic, Maja Kljajić, Vule Mizdraković, Vladimir Marevic, M. Zivkovic, N. Bačanin
Retaining customers is of great importance for all subscription-based financial institutions. Having in mind that even a small change in customer churn can have a significant impact on a company's profits and overall value of the company, proper customer churn management is a prerequisite. When it comes to banks, the key issue is identifying reasons (factors) that lead to contract termination between a customer and a bank. This paper offers a new model for forecasting customer churn and determines the contribution of variables that could lead to losing a customer. This work presents a novel artificial intelligence approach for predicting churn using the XGboost methods. A novel metaheuristic algorithm is proposed and tasked with se-lecting optimal hyperparameters for the XGBoost algorithm. The performance of the algorithm has been evaluated on real-world data and compared to several cutting-edge algorithms, attaining the best performance, with the highest accuracy of approximately 97%, which proves presumption that customer credit card churn could be forecast with high precision. Additionally, the best models have been subjected to SHAP analysis to determine feature impact. Attained results show that features that belong to customer account information have the strongest impact on customer turnover, while personal customer information does not have or has little contribution. Features with the highest SHAP values are total transaction count and amount over the last 12 months and total revolving card balance.
{"title":"Predicting Credit Card Churn: Application of XGBoost Tuned by Modified Sine Cosine Algorithm","authors":"Luka Jovanovic, Maja Kljajić, Vule Mizdraković, Vladimir Marevic, M. Zivkovic, N. Bačanin","doi":"10.1109/ICSMDI57622.2023.00018","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00018","url":null,"abstract":"Retaining customers is of great importance for all subscription-based financial institutions. Having in mind that even a small change in customer churn can have a significant impact on a company's profits and overall value of the company, proper customer churn management is a prerequisite. When it comes to banks, the key issue is identifying reasons (factors) that lead to contract termination between a customer and a bank. This paper offers a new model for forecasting customer churn and determines the contribution of variables that could lead to losing a customer. This work presents a novel artificial intelligence approach for predicting churn using the XGboost methods. A novel metaheuristic algorithm is proposed and tasked with se-lecting optimal hyperparameters for the XGBoost algorithm. The performance of the algorithm has been evaluated on real-world data and compared to several cutting-edge algorithms, attaining the best performance, with the highest accuracy of approximately 97%, which proves presumption that customer credit card churn could be forecast with high precision. Additionally, the best models have been subjected to SHAP analysis to determine feature impact. Attained results show that features that belong to customer account information have the strongest impact on customer turnover, while personal customer information does not have or has little contribution. Features with the highest SHAP values are total transaction count and amount over the last 12 months and total revolving card balance.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"61 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":"132038264","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/ICSMDI57622.2023.00084
Haifu Li
Due to the changes in the camera angle or the working direction of the athlete in the sports video, this method cannot perform an effective regional analysis. Hence, the efficient analysis of images is essential for the action recognition, hence, this paper studies the video image information mining algorithms for badminton on-the-spot tactics analysis. The designed system contains the image segmentation, action recognition and the badminton on-the-spot tactics analysis. To perform image segmentation, the FCM model is considered To perform action recognition, based on the obtained skeleton data, the model is trained by the action label data to classify it. An efficient action representation can capture both static and kinematic information. Then, the system is verified through the real-time data sets. The proposed model is proven to be efficient.
{"title":"Video Image Information Mining Algorithms for Badminton on-the-Spot Tactics Analysis","authors":"Haifu Li","doi":"10.1109/ICSMDI57622.2023.00084","DOIUrl":"https://doi.org/10.1109/ICSMDI57622.2023.00084","url":null,"abstract":"Due to the changes in the camera angle or the working direction of the athlete in the sports video, this method cannot perform an effective regional analysis. Hence, the efficient analysis of images is essential for the action recognition, hence, this paper studies the video image information mining algorithms for badminton on-the-spot tactics analysis. The designed system contains the image segmentation, action recognition and the badminton on-the-spot tactics analysis. To perform image segmentation, the FCM model is considered To perform action recognition, based on the obtained skeleton data, the model is trained by the action label data to classify it. An efficient action representation can capture both static and kinematic information. Then, the system is verified through the real-time data sets. The proposed model is proven to be efficient.","PeriodicalId":373017,"journal":{"name":"2023 3rd International Conference on Smart Data Intelligence (ICSMDI)","volume":"19 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":"132609092","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：