Pub Date : 2022-11-11DOI: 10.1142/s0219649222500782
Hadeel Albalawi
Alzheimer’s disease (AD) predominantly affects the elderly population with symptoms including, but not limited to, cognitive impairment and memory loss. Predicting AD and mild cognitive impairment (MCI) can lengthen the lifespan of patients and help them to access necessary medical resources. One potential approach to achieve an early diagnosis of AD is to use data mining techniques which explore various characteristic traits related to MCI, cognitively normal (CN), and AD subjects to build classifiers that reveal important contributors to the disease. These classifiers are used by physicians during the AD diagnostic process in a clinical evaluation. In this research, we compare between different data mining algorithms through empirical data approach to deal with the AD diagnosis. Experimental evaluation, using attribute selection methods, and classifiers from rule induction and other classification techniques have been conducted on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI-MERGE). The results illustrate the good classification performance of classifiers with rules in predicting AD.
{"title":"An Experimental Study on Evaluating Alzheimer's Disease Features using Data Mining Techniques","authors":"Hadeel Albalawi","doi":"10.1142/s0219649222500782","DOIUrl":"https://doi.org/10.1142/s0219649222500782","url":null,"abstract":"Alzheimer’s disease (AD) predominantly affects the elderly population with symptoms including, but not limited to, cognitive impairment and memory loss. Predicting AD and mild cognitive impairment (MCI) can lengthen the lifespan of patients and help them to access necessary medical resources. One potential approach to achieve an early diagnosis of AD is to use data mining techniques which explore various characteristic traits related to MCI, cognitively normal (CN), and AD subjects to build classifiers that reveal important contributors to the disease. These classifiers are used by physicians during the AD diagnostic process in a clinical evaluation. In this research, we compare between different data mining algorithms through empirical data approach to deal with the AD diagnosis. Experimental evaluation, using attribute selection methods, and classifiers from rule induction and other classification techniques have been conducted on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI-MERGE). The results illustrate the good classification performance of classifiers with rules in predicting AD.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124159580","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 : 2022-11-10DOI: 10.1142/s0219649222500861
G. N. Gopal, Binsu C. Kovoor
A mathematical model (SEPNS) for rumour spreading on social media is proposed here with the required differential equations. Microscopic observations are considered here to obtain the compartments in this epidemiological model. The predictions based on this model can help social media analysts provide valuable and specific suggestions in business and politics. The equilibrium points are obtained for this model. Later, the stability analysis based on basic reproduction number [Formula: see text] is done for both the rumour free equilibrium and the endemic equilibrium. Finally, numerical simulation of the model is done to understand the influence of different parameters during rumour spread.
{"title":"Modelling and Stability Analysis of a Rumour Propagation Model with Sentiments as Microscopic Observation","authors":"G. N. Gopal, Binsu C. Kovoor","doi":"10.1142/s0219649222500861","DOIUrl":"https://doi.org/10.1142/s0219649222500861","url":null,"abstract":"A mathematical model (SEPNS) for rumour spreading on social media is proposed here with the required differential equations. Microscopic observations are considered here to obtain the compartments in this epidemiological model. The predictions based on this model can help social media analysts provide valuable and specific suggestions in business and politics. The equilibrium points are obtained for this model. Later, the stability analysis based on basic reproduction number [Formula: see text] is done for both the rumour free equilibrium and the endemic equilibrium. Finally, numerical simulation of the model is done to understand the influence of different parameters during rumour spread.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134180672","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 : 2022-11-09DOI: 10.1142/s0219649222500769
Luxing Liu, Yufeng Cai, Yalu Wei, Hongjie Jin, Yin-Pei Teng
China is one of the world’s major producers and consumers of energy. The investment value of China’s energy industry has attracted the attention of investors at home and abroad. Few studies, however, have specifically investigated investment ratings in China’s traditional energy industry. This study, therefore, uses scientific analysis methods to help investors measure the investment value and returns of China’s energy industry. From the perspectives of market performance and earnings management, we select factors that influence stock value evaluation indicators and undertake an empirical analysis using financial statement data for 2020 from the Wind database. Based on a factor analysis of the main financial indicators (e.g. amplitude, turnover rate, gross profit margin of sales, growth rate of operating revenue), we obtain five main factors: stock market performance, trading heat, profit quality, profit scale, and profit potential. The [Formula: see text]-means algorithm in Python is then used to analyse 56 stocks in China’s energy industry, and we divide their investment ratings into six grades: risk stocks, prudent holding, undetermined class, hold rating, ordinary rating, and buy rating. By identifying the group characteristics of different types of stocks, this study can provide a decision-making basis for investors while also having reference value for research institutions, financial departments, and government departments.
{"title":"What Can Cluster Analysis Offer Stock Investors? Evidence from the China's Energy Industry","authors":"Luxing Liu, Yufeng Cai, Yalu Wei, Hongjie Jin, Yin-Pei Teng","doi":"10.1142/s0219649222500769","DOIUrl":"https://doi.org/10.1142/s0219649222500769","url":null,"abstract":"China is one of the world’s major producers and consumers of energy. The investment value of China’s energy industry has attracted the attention of investors at home and abroad. Few studies, however, have specifically investigated investment ratings in China’s traditional energy industry. This study, therefore, uses scientific analysis methods to help investors measure the investment value and returns of China’s energy industry. From the perspectives of market performance and earnings management, we select factors that influence stock value evaluation indicators and undertake an empirical analysis using financial statement data for 2020 from the Wind database. Based on a factor analysis of the main financial indicators (e.g. amplitude, turnover rate, gross profit margin of sales, growth rate of operating revenue), we obtain five main factors: stock market performance, trading heat, profit quality, profit scale, and profit potential. The [Formula: see text]-means algorithm in Python is then used to analyse 56 stocks in China’s energy industry, and we divide their investment ratings into six grades: risk stocks, prudent holding, undetermined class, hold rating, ordinary rating, and buy rating. By identifying the group characteristics of different types of stocks, this study can provide a decision-making basis for investors while also having reference value for research institutions, financial departments, and government departments.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114926016","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 : 2022-11-09DOI: 10.1142/s0219649222500824
Mourad Belabed, Abdeslem Dennai
With the exponential and rapid growth of online resources in recent years, there has been a huge increase in the use of search engines; these are also one of the most common ways to navigate the Web content without taking into account, in general, the request meaning by which was successfully added the user’s webpage provides us with a lot of results. This problem has led to the integration of semantics in the search for information on the Web (Semantic Web). The use of semantic tools, such as ontology, WordNet dictionary, semantic similarity measure, etc., has contributed to the semantic search development and more particularly, semantic Metan-search. The success of semantic search is closely linked to the availability of domain ontologies. The objective of this paper is to propose a double model of repetitive semantic search, called Double Metan-Semantic Search Model (2[Formula: see text]-SSM). On the one hand, it is assisted and based on the concepts extracted from the user’s search domain ontology, which will permit the user to choose a concept from this list of concepts and launch their search; on the other hand, it is free, in that the user enters their own concept and launches their search. This is based on WordNet tool, user’s same search domain ontology and the semantic similarity calculation techniques between concepts in the same ontology. The result of this model is a set of URL links. The term Metan indicates that the search is done in depth ([Formula: see text]-SS) via choosing each time a URL result by the user. Its experimentation in the asthma disease field gave very promising results in quantity and quality of information via the URL link results (semantic support).
{"title":"A Double Metan-Semantic Search Model Based on Ontology and Semantic Similarity: Asthma Disease","authors":"Mourad Belabed, Abdeslem Dennai","doi":"10.1142/s0219649222500824","DOIUrl":"https://doi.org/10.1142/s0219649222500824","url":null,"abstract":"With the exponential and rapid growth of online resources in recent years, there has been a huge increase in the use of search engines; these are also one of the most common ways to navigate the Web content without taking into account, in general, the request meaning by which was successfully added the user’s webpage provides us with a lot of results. This problem has led to the integration of semantics in the search for information on the Web (Semantic Web). The use of semantic tools, such as ontology, WordNet dictionary, semantic similarity measure, etc., has contributed to the semantic search development and more particularly, semantic Metan-search. The success of semantic search is closely linked to the availability of domain ontologies. The objective of this paper is to propose a double model of repetitive semantic search, called Double Metan-Semantic Search Model (2[Formula: see text]-SSM). On the one hand, it is assisted and based on the concepts extracted from the user’s search domain ontology, which will permit the user to choose a concept from this list of concepts and launch their search; on the other hand, it is free, in that the user enters their own concept and launches their search. This is based on WordNet tool, user’s same search domain ontology and the semantic similarity calculation techniques between concepts in the same ontology. The result of this model is a set of URL links. The term Metan indicates that the search is done in depth ([Formula: see text]-SS) via choosing each time a URL result by the user. Its experimentation in the asthma disease field gave very promising results in quantity and quality of information via the URL link results (semantic support).","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132849542","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 : 2022-11-07DOI: 10.1142/s0219649222500885
F. Abu-Amara, Jawad Ahmad
Several chaos-based image encryption schemes have been proposed in the last decade. Each encryption scheme has pros and cons regarding its speed, complexity, and security. This paper proposes a new chaotic map called Power-Chaotic Map (PCM). Characteristics of the proposed PCM, such as chaotic behaviour, randomness, sensitivity, and s-unimodality, are investigated. As an application of the proposed chaotic map, an image encryption scheme is proposed to encrypt greyscale and text images. The proposed three-phase image encryption scheme performs a series of substitution and permutation operations. The Pixel-Level phase utilises the PCM’s generated keystreams to perform the substitution operation of image pixels. The Row-Level phase permutates, via a proposed pseudorandom number generator, pixel locations of each row and then shuffles row locations. Finally, the Column-Level phase performs a substitution operation on pixels of each column. Performance of the proposed PCM-based image encryption scheme is investigated through histogram analysis, statistical correlation analysis, key sensitivity, encryption performance of text images, and permutation and substitution properties. Experimental results indicate that the PCM has a wider range of chaotic behaviour than well-known one-dimensional maps, meets the s-unimodality property, has high sensitivity, and generates keystreams with random-like behaviour. Furthermore, results indicate that the PCM-based image encryption scheme provides high encryption security for text images, high key sensitivity, immunity against brute-force attacks, strong statistical correlation results, strong encryption performance, and low computational complexity.
{"title":"A Proposal of a New Chaotic Map for Application in the Image Encryption Domain","authors":"F. Abu-Amara, Jawad Ahmad","doi":"10.1142/s0219649222500885","DOIUrl":"https://doi.org/10.1142/s0219649222500885","url":null,"abstract":"Several chaos-based image encryption schemes have been proposed in the last decade. Each encryption scheme has pros and cons regarding its speed, complexity, and security. This paper proposes a new chaotic map called Power-Chaotic Map (PCM). Characteristics of the proposed PCM, such as chaotic behaviour, randomness, sensitivity, and s-unimodality, are investigated. As an application of the proposed chaotic map, an image encryption scheme is proposed to encrypt greyscale and text images. The proposed three-phase image encryption scheme performs a series of substitution and permutation operations. The Pixel-Level phase utilises the PCM’s generated keystreams to perform the substitution operation of image pixels. The Row-Level phase permutates, via a proposed pseudorandom number generator, pixel locations of each row and then shuffles row locations. Finally, the Column-Level phase performs a substitution operation on pixels of each column. Performance of the proposed PCM-based image encryption scheme is investigated through histogram analysis, statistical correlation analysis, key sensitivity, encryption performance of text images, and permutation and substitution properties. Experimental results indicate that the PCM has a wider range of chaotic behaviour than well-known one-dimensional maps, meets the s-unimodality property, has high sensitivity, and generates keystreams with random-like behaviour. Furthermore, results indicate that the PCM-based image encryption scheme provides high encryption security for text images, high key sensitivity, immunity against brute-force attacks, strong statistical correlation results, strong encryption performance, and low computational complexity.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996756","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}
Recent studies have highlighted several mental health problems in India, caused by factors such as lack of trained counsellors and a stigma associated with discussing mental health. These challenges have raised an increasing need for alternate methods that can be used to detect a person’s emotion and monitor their mental health. Existing research in this field explores several approaches ranging from studying body language to analysing micro-expressions to detect a person’s emotions. However, these solutions often rely on techniques that invade people’s privacy and thus face challenges with mass adoption. The goal is to build a solution that can detect people’s emotions, in a non-invasive manner. This research proposes a journaling web application wherein the users enter their daily reflections. The application extracts the user’s typing patterns (keystroke data) and primary phone usage data. It uses this data to train an ensemble machine learning model, which can then detect the user’s emotions. The proposed solution has various applications in today’s world. People can use it to keep track of their emotions and study their emotional health. Also, any individual family can use this application to detect early signs of anxiety or depression amongst the members.
{"title":"An Ensemble-Based Machine Learning Model for Emotion and Mental Health Detection","authors":"Annapurna Jonnalagadda, Manan Rajvir, Shovan Singh, S. Chandramouliswaran, Joshua George, Firuz Kamalov","doi":"10.1142/s0219649222500757","DOIUrl":"https://doi.org/10.1142/s0219649222500757","url":null,"abstract":"Recent studies have highlighted several mental health problems in India, caused by factors such as lack of trained counsellors and a stigma associated with discussing mental health. These challenges have raised an increasing need for alternate methods that can be used to detect a person’s emotion and monitor their mental health. Existing research in this field explores several approaches ranging from studying body language to analysing micro-expressions to detect a person’s emotions. However, these solutions often rely on techniques that invade people’s privacy and thus face challenges with mass adoption. The goal is to build a solution that can detect people’s emotions, in a non-invasive manner. This research proposes a journaling web application wherein the users enter their daily reflections. The application extracts the user’s typing patterns (keystroke data) and primary phone usage data. It uses this data to train an ensemble machine learning model, which can then detect the user’s emotions. The proposed solution has various applications in today’s world. People can use it to keep track of their emotions and study their emotional health. Also, any individual family can use this application to detect early signs of anxiety or depression amongst the members.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124929337","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 : 2022-11-03DOI: 10.1142/s0219649222500770
Li Xiao
E-government has become an important direction for the development of our government. Measuring national and regional e-government development indicators can help government agencies better understand the actual situation of e-government. This paper is based on E-government Development Index, including the Online Services Index (OSI), Telecommunications Infrastructure Index (TII) and Human Capital Index (HCI). The development of e-government in Guilin is evaluated by using the methods of index change analysis and comparative analysis. The relevant data of this paper come from Guangxi Statistical Yearbook, Guilin Economic and Social Statistical Yearbook and the official website of Guilin Bureau of Statistics. From the study of Guilin e-government data, we judged that Guilin e-government is in the trend of rapid development and comprehensive and coordinated development. Through its development trend, we can judge that in the future, Guilin e-government will continue to develop, but at the same time, if we do not deal with the relationship between development speed and development content, it will also bring great trouble to Guilin e-government. Therefore, we put forward the following development suggestions: (1) Guilin e-government should strengthen technological innovation and development, and create an intelligent e-government platform. (2) Guilin e-government will make government services more targeted and build a service platform for special groups. (3) Guilin e-government should formulate e-government policies and improve institutional innovation.
{"title":"Study on Evaluation of Development of Guilin E-Government Based on E-Government Development Index","authors":"Li Xiao","doi":"10.1142/s0219649222500770","DOIUrl":"https://doi.org/10.1142/s0219649222500770","url":null,"abstract":"E-government has become an important direction for the development of our government. Measuring national and regional e-government development indicators can help government agencies better understand the actual situation of e-government. This paper is based on E-government Development Index, including the Online Services Index (OSI), Telecommunications Infrastructure Index (TII) and Human Capital Index (HCI). The development of e-government in Guilin is evaluated by using the methods of index change analysis and comparative analysis. The relevant data of this paper come from Guangxi Statistical Yearbook, Guilin Economic and Social Statistical Yearbook and the official website of Guilin Bureau of Statistics. From the study of Guilin e-government data, we judged that Guilin e-government is in the trend of rapid development and comprehensive and coordinated development. Through its development trend, we can judge that in the future, Guilin e-government will continue to develop, but at the same time, if we do not deal with the relationship between development speed and development content, it will also bring great trouble to Guilin e-government. Therefore, we put forward the following development suggestions: (1) Guilin e-government should strengthen technological innovation and development, and create an intelligent e-government platform. (2) Guilin e-government will make government services more targeted and build a service platform for special groups. (3) Guilin e-government should formulate e-government policies and improve institutional innovation.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115670701","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 : 2022-11-02DOI: 10.1142/s0219649222500836
H. B. Abdalla, B. Abuhaija
Data over the internet has been increasing everyday, and automatic mining of essential information from an enormous amount of data has become a challenging task today for an organisation with a huge dataset. In recent years, the prominent technology in the domain of Information Technology (IT) is big data, which is unstructured data that solves the computational complexity of classical database systems. The data is fast and big and typically derived from multiple and independent sources. The three main challenges are data accessing, semantics, and domain knowledge for various big data utilisations and complexities raised by big data volumes. One of the major limitations is the classification of big data. This paper introduces well-defined classification methodologies employed for big data classification. This paper reviews 50 research papers based on classification methods of big data, and such methodologies are primarily categorised into six different categories, namely K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Fuzzy-based method, Bayesian-based method, Random Forest, and Decision Tree. In addition, detailed analysis and discussion are carried out by considering classification techniques, dataset utilised, evaluation metrics, semantic similarity measures, and publication year. In addition, research gaps and issues for several traditional big data classification techniques are explained to expand investigators’ works to provide effective big data management.
{"title":"Comprehensive Analysis of Various Big Data Classification Techniques: A Challenging Overview","authors":"H. B. Abdalla, B. Abuhaija","doi":"10.1142/s0219649222500836","DOIUrl":"https://doi.org/10.1142/s0219649222500836","url":null,"abstract":"Data over the internet has been increasing everyday, and automatic mining of essential information from an enormous amount of data has become a challenging task today for an organisation with a huge dataset. In recent years, the prominent technology in the domain of Information Technology (IT) is big data, which is unstructured data that solves the computational complexity of classical database systems. The data is fast and big and typically derived from multiple and independent sources. The three main challenges are data accessing, semantics, and domain knowledge for various big data utilisations and complexities raised by big data volumes. One of the major limitations is the classification of big data. This paper introduces well-defined classification methodologies employed for big data classification. This paper reviews 50 research papers based on classification methods of big data, and such methodologies are primarily categorised into six different categories, namely K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Fuzzy-based method, Bayesian-based method, Random Forest, and Decision Tree. In addition, detailed analysis and discussion are carried out by considering classification techniques, dataset utilised, evaluation metrics, semantic similarity measures, and publication year. In addition, research gaps and issues for several traditional big data classification techniques are explained to expand investigators’ works to provide effective big data management.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131328013","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 : 2022-10-22DOI: 10.1142/s0219649222500794
Juhua Wu, Qide Zhang, Lei Tao, Xiaoyun Lu
Prediction is an important way to analyse stroke risk management. This study explored the critical influencing factors of stroke, used the classical multilayer perception (MLP) and radial basis function (RBF) machine learning (ML) algorithms to develop the model for stroke prediction. The two models were trained with Bagging and Boosting ensemble learning algorithms. The performances of the prediction models were also compared with other classical ML algorithms. The result showed that (1) total cholesterol (TC) and other nine factors were selected as principal factors for the stroke prediction; (2) the MLP model outperformed RBF model in terms of accuracy, generalization and inter-rater reliability; (3) ensemble algorithm was superior to single algorithms for high-dimension dataset in this study. It may come to the conclusion that this study improved the stroke prediction methods and contributed much to the prevention of stroke.
{"title":"Influencing Factors Analysis and Prediction Model Development of Stroke: The Machine Learning Approach","authors":"Juhua Wu, Qide Zhang, Lei Tao, Xiaoyun Lu","doi":"10.1142/s0219649222500794","DOIUrl":"https://doi.org/10.1142/s0219649222500794","url":null,"abstract":"Prediction is an important way to analyse stroke risk management. This study explored the critical influencing factors of stroke, used the classical multilayer perception (MLP) and radial basis function (RBF) machine learning (ML) algorithms to develop the model for stroke prediction. The two models were trained with Bagging and Boosting ensemble learning algorithms. The performances of the prediction models were also compared with other classical ML algorithms. The result showed that (1) total cholesterol (TC) and other nine factors were selected as principal factors for the stroke prediction; (2) the MLP model outperformed RBF model in terms of accuracy, generalization and inter-rater reliability; (3) ensemble algorithm was superior to single algorithms for high-dimension dataset in this study. It may come to the conclusion that this study improved the stroke prediction methods and contributed much to the prevention of stroke.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124259400","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 : 2022-07-29DOI: 10.1142/s0219649222500708
M. Atan, Rosli Mahmood
Research shows that data-driven decision making using business analytics can create competitive advantages for organisations. However, this can only happen if the organisations successfully accept and use the business analytics effectively. Many studies reported business analytics implementation in large organisations, and fewer studies focus on Small and Medium Enterprises (SMEs). Furthermore, SMEs are scoring lower scores in technology absorption. Therefore, it is essential to examine the business analytics adoption among SMEs. Previous research has reported that relative advantage and compatibility were the most highlighted factors under the technology dimension in adopting innovative technologies. However, the literature reported inconsistent findings on the significance of relative advantage and compatibility in adopting various technologies. Therefore, this research conducted a quantitative survey-based study to examine the significance of relative advantage and compatibility in predicting business analytics adoption among SMEs. The sample was selected using systematic random sampling from a Malaysian national entrepreneurs database. There were 241 SMEs that responded to the online survey sent by email. The analysis using the partial least squares structural equation modelling (PLS-SEM) informed that relative advantage was significantly related to business analytics adoption; however, compatibility did not influence the business analytics adoption by SMEs in Malaysia. This finding shows that the better the relative advantage of business analytics SMEs know, the higher the possibility of adoption. In addition, less compatibility of the SMEs in Malaysia hindered the business analytics adoption. This study contributes to the theoretical aspect, which statistically informed the finding out of inconsistent gaps in technology adoption. Furthermore, this study also contributes to the practical aspect, in which managers, owners, vendors, and policy-makers can use these findings to spur and facilitate business analytics adoption among SMEs in developing countries.
{"title":"The Role of Technology in Predicting Business Analytics Adoption in SMEs","authors":"M. Atan, Rosli Mahmood","doi":"10.1142/s0219649222500708","DOIUrl":"https://doi.org/10.1142/s0219649222500708","url":null,"abstract":"Research shows that data-driven decision making using business analytics can create competitive advantages for organisations. However, this can only happen if the organisations successfully accept and use the business analytics effectively. Many studies reported business analytics implementation in large organisations, and fewer studies focus on Small and Medium Enterprises (SMEs). Furthermore, SMEs are scoring lower scores in technology absorption. Therefore, it is essential to examine the business analytics adoption among SMEs. Previous research has reported that relative advantage and compatibility were the most highlighted factors under the technology dimension in adopting innovative technologies. However, the literature reported inconsistent findings on the significance of relative advantage and compatibility in adopting various technologies. Therefore, this research conducted a quantitative survey-based study to examine the significance of relative advantage and compatibility in predicting business analytics adoption among SMEs. The sample was selected using systematic random sampling from a Malaysian national entrepreneurs database. There were 241 SMEs that responded to the online survey sent by email. The analysis using the partial least squares structural equation modelling (PLS-SEM) informed that relative advantage was significantly related to business analytics adoption; however, compatibility did not influence the business analytics adoption by SMEs in Malaysia. This finding shows that the better the relative advantage of business analytics SMEs know, the higher the possibility of adoption. In addition, less compatibility of the SMEs in Malaysia hindered the business analytics adoption. This study contributes to the theoretical aspect, which statistically informed the finding out of inconsistent gaps in technology adoption. Furthermore, this study also contributes to the practical aspect, in which managers, owners, vendors, and policy-makers can use these findings to spur and facilitate business analytics adoption among SMEs in developing countries.","PeriodicalId":127309,"journal":{"name":"J. Inf. Knowl. Manag.","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126608174","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：