Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099911
Toru Nakamura, T. Isohara
This paper discusses on the fairness on the context of two-sided matching. This paper proposes a new definition of individual fairness for two-sided matching, called Popularity Preserving Fairness (PPF). It is the first definition of individual fairness for two-sided matching that does not have to make the model more complex. The new definition of PPF means that the wish of a person with higher popularity takes priority over that of a lower person. This paper also proposes a relaxed version of PPF with thresholds $k, ell$ because a PPF matching does not always exist. The relaxed definition allows a person $B$ whose popular rank is below that of $A$ within $k$ to match a person whose rank in $B$'s preference order is lower than that of $A$ and lor regards the difference of ranks of matched people is within $ell$ as a not different case. Furthermore, this paper provides an efficient decision algorithm for PPF matching.
本文讨论了双边匹配背景下的公平性问题。本文提出了一种新的双边匹配下的个人公平的定义，称为人气保持公平(PPF)。这是第一个没有使模型变得更复杂的双边匹配的个人公平的定义。PPF的新定义意味着，受欢迎程度高的人的愿望优先于受欢迎程度低的人的愿望。本文还提出了一个放宽版本的PPF，其阈值为$k，因为PPF匹配并不总是存在。宽松定义允许在$k$范围内受欢迎排名低于$ a $的人$B$与在$B$偏好顺序中排名低于$ a $的人配对，并将配对者的排名差异在$ well $范围内视为无差异情况。在此基础上，提出了一种高效的PPF匹配决策算法。
{"title":"Popularity Preserving Fair Matching","authors":"Toru Nakamura, T. Isohara","doi":"10.1109/ESCI56872.2023.10099911","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099911","url":null,"abstract":"This paper discusses on the fairness on the context of two-sided matching. This paper proposes a new definition of individual fairness for two-sided matching, called Popularity Preserving Fairness (PPF). It is the first definition of individual fairness for two-sided matching that does not have to make the model more complex. The new definition of PPF means that the wish of a person with higher popularity takes priority over that of a lower person. This paper also proposes a relaxed version of PPF with thresholds $k, ell$ because a PPF matching does not always exist. The relaxed definition allows a person $B$ whose popular rank is below that of $A$ within $k$ to match a person whose rank in $B$'s preference order is lower than that of $A$ and lor regards the difference of ranks of matched people is within $ell$ as a not different case. Furthermore, this paper provides an efficient decision algorithm for PPF matching.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"45 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":"122347394","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/ESCI56872.2023.10099742
Shreyasi Watve, M. Patil, Arun C. Shinde
The most common and organic method of interpersonal communication is speech. Humanity has long aspired to creating a computer with human-like comprehension and communication abilities. To recognize language (words and phrases) using voice signals, multilingual countries like India must be taken into account. More research on speech has been demanded by specialists over the past ten years. Researchers require a specific database, or previously recorded collection of information, for that specific recognition system when they seek to construct it. There are several speech databases available for European languages, but only a small number for Indian languages. The several Speech Databases developed in various Indian languages for Text to Speech, Speaker Identification and Speech Identification systems are discussed in this article. To accurately identify the spoken language, first need to collect information from speech signal. In the initial step of the pre-processing phase, audio feature based approach were used, and then deep learning and machine learning classification methods. This survey will explore a variety of feature extraction methods as well as classification methods.
{"title":"Review of Features and Classification for Spoken Indian Language Recognition using Deep Learning and Machine Learning Techniques","authors":"Shreyasi Watve, M. Patil, Arun C. Shinde","doi":"10.1109/ESCI56872.2023.10099742","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099742","url":null,"abstract":"The most common and organic method of interpersonal communication is speech. Humanity has long aspired to creating a computer with human-like comprehension and communication abilities. To recognize language (words and phrases) using voice signals, multilingual countries like India must be taken into account. More research on speech has been demanded by specialists over the past ten years. Researchers require a specific database, or previously recorded collection of information, for that specific recognition system when they seek to construct it. There are several speech databases available for European languages, but only a small number for Indian languages. The several Speech Databases developed in various Indian languages for Text to Speech, Speaker Identification and Speech Identification systems are discussed in this article. To accurately identify the spoken language, first need to collect information from speech signal. In the initial step of the pre-processing phase, audio feature based approach were used, and then deep learning and machine learning classification methods. This survey will explore a variety of feature extraction methods as well as classification methods.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","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":"122866430","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/ESCI56872.2023.10099726
Pradnya Desai, S. Sandbhor, A. Kaushik
Any country's economic progress, especially economic expansion, depends heavily on the building industry. The construction industry consumes tremendous amount of money, time and energy. Over the last two decades, many reports and studies have concluded that quality and productivity are decreasing due to defective work. The corrective activities of addressing defects and rework, consume time and cost. Even though there are several reasons for cost and time overrun, rework has a significant effect. It is essential to emphasize the impact of construction rework, construction defects and waste generated through research. Use of soft computing methods is recommended to increase the general efficiency of the construction projects. The goal of this research study is to undertake a bibliographic survey of the relevant literature on construction rework, construction defects and the application of Artificial Intelligence (AI) and Building Information Modeling (BIM) to optimize the output. The time considered for this survey is from the year 2007–2022. This bibliographic analysis contains statistics on citations, important journals, countries, authors contributing to the domain of knowledge based on search engine on Web of Science database. The results of the study highlight the current publication trends emphasizing on the necessity of applying BIM-based AI techniques to defects, rework and waste management. Study shows the quantum of work done in the domain from Indian context, highlighting the need for research.
任何国家的经济发展，特别是经济扩张，都在很大程度上依赖于建筑业。建筑业耗费大量的金钱、时间和精力。在过去的二十年里，许多报告和研究得出结论，由于工作缺陷，质量和生产力正在下降。解决缺陷和返工的纠正活动消耗时间和成本。尽管造成成本和时间超支的原因有很多，但返工的影响还是很大的。通过研究，必须强调施工返工、施工缺陷和产生的废物的影响。建议采用软计算方法来提高施工项目的综合效率。本研究的目的是对建筑返工、建筑缺陷以及人工智能(AI)和建筑信息模型(BIM)应用的相关文献进行书目调查，以优化输出。本次调查考虑的时间为2007-2022年。本文通过Web of Science数据库的搜索引擎，对该领域文献的引文、重要期刊、国家、作者等进行统计。该研究的结果突出了当前的出版趋势，强调了将基于bim的人工智能技术应用于缺陷、返工和废物管理的必要性。研究显示，在印度背景下，该领域完成了大量工作，突出了研究的必要性。
{"title":"AI and BIM-based Construction defects, rework, and waste optimization","authors":"Pradnya Desai, S. Sandbhor, A. Kaushik","doi":"10.1109/ESCI56872.2023.10099726","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099726","url":null,"abstract":"Any country's economic progress, especially economic expansion, depends heavily on the building industry. The construction industry consumes tremendous amount of money, time and energy. Over the last two decades, many reports and studies have concluded that quality and productivity are decreasing due to defective work. The corrective activities of addressing defects and rework, consume time and cost. Even though there are several reasons for cost and time overrun, rework has a significant effect. It is essential to emphasize the impact of construction rework, construction defects and waste generated through research. Use of soft computing methods is recommended to increase the general efficiency of the construction projects. The goal of this research study is to undertake a bibliographic survey of the relevant literature on construction rework, construction defects and the application of Artificial Intelligence (AI) and Building Information Modeling (BIM) to optimize the output. The time considered for this survey is from the year 2007–2022. This bibliographic analysis contains statistics on citations, important journals, countries, authors contributing to the domain of knowledge based on search engine on Web of Science database. The results of the study highlight the current publication trends emphasizing on the necessity of applying BIM-based AI techniques to defects, rework and waste management. Study shows the quantum of work done in the domain from Indian context, highlighting the need for research.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"27 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":"115500708","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/ESCI56872.2023.10099875
Anuradha Yenkikar, C. Babu
Forecasting companies' stock market prices are one the interesting topics for analysts and researchers. Although a company's stock price can be unpredictable, long-term forecasts can help but it is dependent on many factors such as the company's business model, change in leadership, and investors' mood. It has been found to be insufficient to predict stock values just on the basis of historical data or textual information. Previous research in sentiment analysis have shown a strong correlation between the movement of stock prices and the publication of news stories. At different levels, a number of sentiment analysis research have been attempted utilizing methods. In this paper, we made a comparison of various Machine Learning methods on five datasets of financial news related to the company and domains in which the company. Encouraging results are obtained using 13 models i.e., Linear Regression, Ridge Regression, Lasso Regression, Random Forest, Naive Bayes, Logistic Regression, LSTM, ARIMA, Logistic Regression, Support Vector Machines, Decision Tree, Boosted Tree, and ensemble method which depict polarity of news articles being positive or negative and the accuracies are 93.90%, 92.31 %, 92.27%, 85.44%, 84.65%, 84.65%, 94.73%, 90.13%, 82%, 83%, 72%, 70%, 95.11 % respectively.
{"title":"Comparison of Machine Learning Algorithm for Stock Price Prediction Using Sentiment Analysis","authors":"Anuradha Yenkikar, C. Babu","doi":"10.1109/ESCI56872.2023.10099875","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099875","url":null,"abstract":"Forecasting companies' stock market prices are one the interesting topics for analysts and researchers. Although a company's stock price can be unpredictable, long-term forecasts can help but it is dependent on many factors such as the company's business model, change in leadership, and investors' mood. It has been found to be insufficient to predict stock values just on the basis of historical data or textual information. Previous research in sentiment analysis have shown a strong correlation between the movement of stock prices and the publication of news stories. At different levels, a number of sentiment analysis research have been attempted utilizing methods. In this paper, we made a comparison of various Machine Learning methods on five datasets of financial news related to the company and domains in which the company. Encouraging results are obtained using 13 models i.e., Linear Regression, Ridge Regression, Lasso Regression, Random Forest, Naive Bayes, Logistic Regression, LSTM, ARIMA, Logistic Regression, Support Vector Machines, Decision Tree, Boosted Tree, and ensemble method which depict polarity of news articles being positive or negative and the accuracies are 93.90%, 92.31 %, 92.27%, 85.44%, 84.65%, 84.65%, 94.73%, 90.13%, 82%, 83%, 72%, 70%, 95.11 % respectively.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"228 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":"116272167","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/ESCI56872.2023.10099745
Mudassar Husain Naikwadi, K. Patil
Wireless radio spectrum is a limited resource. Increasing demand for more spectrum bands has led to the notion of its efficient and intelligent utilization. Cognitive radio technology is the front runner in dynamic spectrum access. Basic spectrum management tasks of sensing, mobility, sharing and decision have been improved by using machine learning techniques. Real time sensing and related operations thereafter involve considerable time delays leading to decreased throughput. Spectrum Inference has emerged as an effective solution to this problem. In this work we have analyzed machine learning based spectrum inference techniques for real world dataset. Spectrum band occupancy prediction has been formulated as a regression problem. Three regression based approaches namely linear regression interactions, SVM based regression and decision tree regression have been evaluated. It has been observed that fine tree regression gives the best performance. To optimize the performance in terms of prediction speed and accuracy we have investigated the use of improved and increased number of features. With addition of a single additional feature the prediction speed has increased by 4.73 times and prediction accuracy by 3%. However the training time has increased by 1.24 times.
{"title":"Spectrum Inference in Cognitive Radio Networks with Machine Learning","authors":"Mudassar Husain Naikwadi, K. Patil","doi":"10.1109/ESCI56872.2023.10099745","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099745","url":null,"abstract":"Wireless radio spectrum is a limited resource. Increasing demand for more spectrum bands has led to the notion of its efficient and intelligent utilization. Cognitive radio technology is the front runner in dynamic spectrum access. Basic spectrum management tasks of sensing, mobility, sharing and decision have been improved by using machine learning techniques. Real time sensing and related operations thereafter involve considerable time delays leading to decreased throughput. Spectrum Inference has emerged as an effective solution to this problem. In this work we have analyzed machine learning based spectrum inference techniques for real world dataset. Spectrum band occupancy prediction has been formulated as a regression problem. Three regression based approaches namely linear regression interactions, SVM based regression and decision tree regression have been evaluated. It has been observed that fine tree regression gives the best performance. To optimize the performance in terms of prediction speed and accuracy we have investigated the use of improved and increased number of features. With addition of a single additional feature the prediction speed has increased by 4.73 times and prediction accuracy by 3%. However the training time has increased by 1.24 times.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"1 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":"123410092","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/ESCI56872.2023.10099658
Reshma S. Gaykar, V. Khanaa, S. Joshi
Hadoop is an inexpensive analytical tool as compared to the other distributed storage in market as it does not need any standalone machines and works on group of commodity hardware. It is a distributed storage system along with this it achieves parallelization of larger data collections. With MapReduce, HDFS (Hadoop distributed file system) provides solution for the system where processing huge datasets is a requirement. Few of the main reasons of stragglers in assorted Hadoop clusters are load inconsistency during storing, resource friction throughout scheduling tasks, hardware downturn due to excessive usage, as well as software configuration issues while managing the cluster. Hadoop's performance lows down in a heterogeneous network due to the technical heterogeneity. We used a supervised machine learning (ML) technique to identify straggler nodes in an eminently distributed network in this article. The suggested technique identifies the proper slow-running job (Straggler) in the network and assign it to other node in the stack to complete the operation with quick succession. Virtual Machine (VM) identifier, network bandwidth consumption, number of processors and its load, memory load and other parameters included in the full data set are utilized for recognition. Various feature extraction methodologies have been utilized to develop its training system. The whole data set was processed for heterogenous features on the dataset. We analyzed our approach using our suggested classifier after doing comprehensive empirical work. As out-turn, the system outperforms using typical machine learning models in classification performance.
{"title":"Mitigation of Straggler in Virtual Machine Stack Using Supervised Learning Methodology","authors":"Reshma S. Gaykar, V. Khanaa, S. Joshi","doi":"10.1109/ESCI56872.2023.10099658","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099658","url":null,"abstract":"Hadoop is an inexpensive analytical tool as compared to the other distributed storage in market as it does not need any standalone machines and works on group of commodity hardware. It is a distributed storage system along with this it achieves parallelization of larger data collections. With MapReduce, HDFS (Hadoop distributed file system) provides solution for the system where processing huge datasets is a requirement. Few of the main reasons of stragglers in assorted Hadoop clusters are load inconsistency during storing, resource friction throughout scheduling tasks, hardware downturn due to excessive usage, as well as software configuration issues while managing the cluster. Hadoop's performance lows down in a heterogeneous network due to the technical heterogeneity. We used a supervised machine learning (ML) technique to identify straggler nodes in an eminently distributed network in this article. The suggested technique identifies the proper slow-running job (Straggler) in the network and assign it to other node in the stack to complete the operation with quick succession. Virtual Machine (VM) identifier, network bandwidth consumption, number of processors and its load, memory load and other parameters included in the full data set are utilized for recognition. Various feature extraction methodologies have been utilized to develop its training system. The whole data set was processed for heterogenous features on the dataset. We analyzed our approach using our suggested classifier after doing comprehensive empirical work. As out-turn, the system outperforms using typical machine learning models in classification performance.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"23 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":"131281640","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/ESCI56872.2023.10099592
Limark Dcunha, Larren Dsouza, G. Ramanan, S. Chaudhari
A broker creates a connection between the buyer and seller under India's traditional land registration system. For instance, the broker would compile and gather all essential physical paperwork that serves as evidence of the transaction if someone wanted to buy or sell a piece of land. Brokers ensure that the land or property is registered with a legitimate government institution, where all the information is entered in a ledger, and that the full transaction is finalized after which, a sale is made between the two parties. Since anyone with the necessary access rights can readily view or change the papers in this situation, there is a chance that the important documents will be lost or tampered with, thereby endangering the tangible proof of ownership. The process is still largely physical with less digitization and as a result, this sort of system is slow, insecure, and unorganized. In this traditional method, the risk of corruption and fraud during the execution of the necessary transaction is also high. Hence, a new system has been proposed which uses smart contracts to handle transactions of assets among the participants in the network. It has been proposed to implement a permissioned blockchain-based land registration system on Hyperledger Fabric, which enables a decentralised, transparent, and secure way to conduct transactions between the parties. The old method has been examined and analysed while also considering that blockchain technology enables improved transparency, Integrity maintenance, and portability.
{"title":"A Blockchain-Based Approach to Streamlining Land Registration using Hyperledger Fabric","authors":"Limark Dcunha, Larren Dsouza, G. Ramanan, S. Chaudhari","doi":"10.1109/ESCI56872.2023.10099592","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099592","url":null,"abstract":"A broker creates a connection between the buyer and seller under India's traditional land registration system. For instance, the broker would compile and gather all essential physical paperwork that serves as evidence of the transaction if someone wanted to buy or sell a piece of land. Brokers ensure that the land or property is registered with a legitimate government institution, where all the information is entered in a ledger, and that the full transaction is finalized after which, a sale is made between the two parties. Since anyone with the necessary access rights can readily view or change the papers in this situation, there is a chance that the important documents will be lost or tampered with, thereby endangering the tangible proof of ownership. The process is still largely physical with less digitization and as a result, this sort of system is slow, insecure, and unorganized. In this traditional method, the risk of corruption and fraud during the execution of the necessary transaction is also high. Hence, a new system has been proposed which uses smart contracts to handle transactions of assets among the participants in the network. It has been proposed to implement a permissioned blockchain-based land registration system on Hyperledger Fabric, which enables a decentralised, transparent, and secure way to conduct transactions between the parties. The old method has been examined and analysed while also considering that blockchain technology enables improved transparency, Integrity maintenance, and portability.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"10 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":"129461020","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}
The detrimental effects of diabetes are currently affecting a sizeable section of the population worldwide, and many of these individuals are not being properly diagnosed. This could eventually lead to significant health issues like kidney failure and vision blindness. Chances of heart attacks and strokes increase by two to three times due to diabetes. Thus, this work has considered a total of 520 instances with included 17 features such as polyuria, gender, age, sudden weight loss, polydipsia, polyphagia, weakness, irritability, genital thrush, itching, vision blurring, muscle stiffness, alopecia, delayed healing, delayed healing, and obesity to classify the type of diabetes at an early stage to avoid such risk. Various Machine Learning (ML) methods can be employed to accurately classify the disease. The objective of this research is to predict diabetes with the help of a variety of machine learning (ML) methods and to identify the most efficient model with the highest accuracy. A total 8 classification algorithms are used for the performance measurement, these are Support Vector Classifier (SVC), Gaussian Naive Bayes (GNB), Random Forest (RF), Decision Tree Classifier (DTC), Logistic Regression (LR), Extra Tree Classifier (ETC), K-Nearest Neighbors (KNN), and XGBoost (XGB) because these models gave the highest accuracy for this dataset. After comparative analysis, the results present that Extra Tree Classifier (ETC) has the highest accuracy, i.e., 98.55%, and can be considered the best and efficient ML classification technique for diagnosing diabetes based on mentioned parameters.
糖尿病的有害影响目前正在影响全球相当一部分人口，其中许多人没有得到适当的诊断。这最终可能导致严重的健康问题，如肾衰竭和视力失明。由于糖尿病，心脏病发作和中风的几率增加了两到三倍。因此，本研究共考虑了520例患者，包括17个特征，如多尿、性别、年龄、体重突然减轻、多饮、多食、虚弱、易怒、生殖器鹅口疮、瘙痒、视力模糊、肌肉僵硬、脱发、延迟愈合、延迟愈合和肥胖，以便在早期对糖尿病进行类型分类，以避免此类风险。可以使用各种机器学习(ML)方法来准确分类疾病。本研究的目的是借助各种机器学习(ML)方法来预测糖尿病，并以最高的准确性确定最有效的模型。总共有8种分类算法用于性能测量，它们是支持向量分类器(SVC)、高斯朴素贝叶斯(GNB)、随机森林(RF)、决策树分类器(DTC)、逻辑回归(LR)、额外树分类器(ETC)、k近邻(KNN)和XGBoost (XGB)，因为这些模型为该数据集提供了最高的精度。通过对比分析，结果表明Extra Tree Classifier (ETC)的准确率最高，达到98.55%，可以认为是基于上述参数诊断糖尿病的最佳和有效的ML分类技术。
{"title":"Comparative Approach for Early Diabetes Detection with Machine Learning","authors":"Shilpi Harnal, Arpit Jain, Anshika, Anurita Singh Rathore, Vidhu Baggan, Gagandeep Kaur, Rajni Bala","doi":"10.1109/ESCI56872.2023.10100186","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100186","url":null,"abstract":"The detrimental effects of diabetes are currently affecting a sizeable section of the population worldwide, and many of these individuals are not being properly diagnosed. This could eventually lead to significant health issues like kidney failure and vision blindness. Chances of heart attacks and strokes increase by two to three times due to diabetes. Thus, this work has considered a total of 520 instances with included 17 features such as polyuria, gender, age, sudden weight loss, polydipsia, polyphagia, weakness, irritability, genital thrush, itching, vision blurring, muscle stiffness, alopecia, delayed healing, delayed healing, and obesity to classify the type of diabetes at an early stage to avoid such risk. Various Machine Learning (ML) methods can be employed to accurately classify the disease. The objective of this research is to predict diabetes with the help of a variety of machine learning (ML) methods and to identify the most efficient model with the highest accuracy. A total 8 classification algorithms are used for the performance measurement, these are Support Vector Classifier (SVC), Gaussian Naive Bayes (GNB), Random Forest (RF), Decision Tree Classifier (DTC), Logistic Regression (LR), Extra Tree Classifier (ETC), K-Nearest Neighbors (KNN), and XGBoost (XGB) because these models gave the highest accuracy for this dataset. After comparative analysis, the results present that Extra Tree Classifier (ETC) has the highest accuracy, i.e., 98.55%, and can be considered the best and efficient ML classification technique for diagnosing diabetes based on mentioned parameters.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"127 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132984248","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/ESCI56872.2023.10100018
H. Studiawan, Ahmad Firdaus, B. Pratomo, T. Ahmad
Drones, also known as UAVs (unmanned aerial vehicles), are unmanned devices that provide unique functionality, enabling area surveillance, inspections, and surveys. In recent years, the rapid growth of drones has also raised several security concerns related to illegal activities, making them a source of evidence. Therefore, it is very important for digital forensic examiners to have the ability to analyze the source of content stored on drones. If the drone encounters a problem or has an accident, it is necessary to carry out a forensic analysis of the device. In this paper, we build a drone forensic timeline using the log2timeline plaso. This timeline records all drone activities. We then propose to apply Sigma rules to detect anomalies in the drone timeline. With this technique, digital forensic examiners can detect anomalous activities that occur on drones.
{"title":"Anomaly Detection on Drone Forensic Timeline with Sigma Rules","authors":"H. Studiawan, Ahmad Firdaus, B. Pratomo, T. Ahmad","doi":"10.1109/ESCI56872.2023.10100018","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100018","url":null,"abstract":"Drones, also known as UAVs (unmanned aerial vehicles), are unmanned devices that provide unique functionality, enabling area surveillance, inspections, and surveys. In recent years, the rapid growth of drones has also raised several security concerns related to illegal activities, making them a source of evidence. Therefore, it is very important for digital forensic examiners to have the ability to analyze the source of content stored on drones. If the drone encounters a problem or has an accident, it is necessary to carry out a forensic analysis of the device. In this paper, we build a drone forensic timeline using the log2timeline plaso. This timeline records all drone activities. We then propose to apply Sigma rules to detect anomalies in the drone timeline. With this technique, digital forensic examiners can detect anomalous activities that occur on drones.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"31 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":"133278435","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/ESCI56872.2023.10099586
K. S. Sagale, Mahadeo D. Kokate, R. Agrawal
An education sector across the globe is facing numerous challenges. It is being one of the most badly affected sectors due to Covid-19. This paper presents a perspective on applying Cloud Computing technologies in the field of education at several abstraction levels. In addition, it proposes Education and Learning as a Service model and Decision-Making Matrix for an Organization.
{"title":"Application of Cloud Computing in an Education Sector through Education and Learning as a Service and its Cost Benefit Analysis","authors":"K. S. Sagale, Mahadeo D. Kokate, R. Agrawal","doi":"10.1109/ESCI56872.2023.10099586","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099586","url":null,"abstract":"An education sector across the globe is facing numerous challenges. It is being one of the most badly affected sectors due to Covid-19. This paper presents a perspective on applying Cloud Computing technologies in the field of education at several abstraction levels. In addition, it proposes Education and Learning as a Service model and Decision-Making Matrix for an Organization.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"42 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":"132039861","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：