The use of machine learning technologies by the world's most profitable companies to personalise their offerings is commonplace. However, not all companies using machine learning technologies succeed in creating and capturing value. Academic research has studied value creation through the use of information technologies, but this field of research tends to consider information technology as a homogeneous phenomenon, not considering the unique characteristics of machine learning technologies. This literature review aims to study the extent to which value creation and value capture through machine learning technologies are being investigated in the field of information systems. Evidence is found of a paucity of publications focusing on value creation through the use of ML in the enterprise, and none on value capture. This study's contribution is to provide a better understanding of the use of machine learning technologies in information systems as a social and business practice.
{"title":"The Role of Machine Learning in Creating and Capturing Value","authors":"Ricardo Costa-Climent","doi":"10.4018/ijssci.312229","DOIUrl":"https://doi.org/10.4018/ijssci.312229","url":null,"abstract":"The use of machine learning technologies by the world's most profitable companies to personalise their offerings is commonplace. However, not all companies using machine learning technologies succeed in creating and capturing value. Academic research has studied value creation through the use of information technologies, but this field of research tends to consider information technology as a homogeneous phenomenon, not considering the unique characteristics of machine learning technologies. This literature review aims to study the extent to which value creation and value capture through machine learning technologies are being investigated in the field of information systems. Evidence is found of a paucity of publications focusing on value creation through the use of ML in the enterprise, and none on value capture. This study's contribution is to provide a better understanding of the use of machine learning technologies in information systems as a social and business practice.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125872287","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}
Sudeshna Sani, Abhijit Bera, D. Mitra, Kalyani Maity Das
Global public health will be severely impacted by the successive waves of emerging COVID-19 disease. Since 2019 people get sick and die in our daily lives placing a massive burden on our health system. One of the crucial factors that has led to the virus's fast spread is a protracted clinical testing gap before discovering of a positive or negative result. A detection system based on deep learning was developed by using chest X-ray(CXR) images of Covid19 patient and healthy people. In this regard the Convolution Neural Network along with other DNNs have been proved to produce good results. To improve the COVID-19 detection accuracy, we developed model using the deep learning(CNN) approach where we observed an accuracy of 96%. We validated the accuracy by using same dataset through a pretrained VGG16 model and an LSTM model which produced excellent reliable results. Our aim of this research is to implement a reliable Deep Learning model to detect presence of Covid-19 in case of limited availability of chest-Xray images.
{"title":"COVID-19 Detection Using Chest X-Ray Images Based on Deep Learning","authors":"Sudeshna Sani, Abhijit Bera, D. Mitra, Kalyani Maity Das","doi":"10.4018/ijssci.312556","DOIUrl":"https://doi.org/10.4018/ijssci.312556","url":null,"abstract":"Global public health will be severely impacted by the successive waves of emerging COVID-19 disease. Since 2019 people get sick and die in our daily lives placing a massive burden on our health system. One of the crucial factors that has led to the virus's fast spread is a protracted clinical testing gap before discovering of a positive or negative result. A detection system based on deep learning was developed by using chest X-ray(CXR) images of Covid19 patient and healthy people. In this regard the Convolution Neural Network along with other DNNs have been proved to produce good results. To improve the COVID-19 detection accuracy, we developed model using the deep learning(CNN) approach where we observed an accuracy of 96%. We validated the accuracy by using same dataset through a pretrained VGG16 model and an LSTM model which produced excellent reliable results. Our aim of this research is to implement a reliable Deep Learning model to detect presence of Covid-19 in case of limited availability of chest-Xray images.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"27 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121796439","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}
This paper describes a current steering 8-bit DAC architecture for low power and high-speed assistance in AI networks. This design is most suitable for 5G and next-generation high-speed communication systems on chip (SoCs). This DAC keeps a constant load current and leads to faster operations in wideband portable device applications. The design is based on weighted current transmission through current mirrors wherein current reduces from MSB to LSB continuously. By choosing a low current for LSB, the power dissipation reduces. Power and area are also reduced by using a 2-bit binary to thermometer decoder. The DAC's integral nonlinearity (INL) and differential nonlinearity (DNL) are found to be within 0.4 and 0.9 LSB, respectively. The DAC's highest operating speed is 1GHz, with a power dissipation of around 24.2 mW with the supply voltage of 1.8v using 180nm CMOS technology.
{"title":"Design of Low-Power High-Speed 8 Bit CMOS Current Steering DAC for AI Applications","authors":"B. Krishna, S. S. Gill, Amod Kumar","doi":"10.4018/ijssci.304801","DOIUrl":"https://doi.org/10.4018/ijssci.304801","url":null,"abstract":"This paper describes a current steering 8-bit DAC architecture for low power and high-speed assistance in AI networks. This design is most suitable for 5G and next-generation high-speed communication systems on chip (SoCs). This DAC keeps a constant load current and leads to faster operations in wideband portable device applications. The design is based on weighted current transmission through current mirrors wherein current reduces from MSB to LSB continuously. By choosing a low current for LSB, the power dissipation reduces. Power and area are also reduced by using a 2-bit binary to thermometer decoder. The DAC's integral nonlinearity (INL) and differential nonlinearity (DNL) are found to be within 0.4 and 0.9 LSB, respectively. The DAC's highest operating speed is 1GHz, with a power dissipation of around 24.2 mW with the supply voltage of 1.8v using 180nm CMOS technology.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127364638","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 exponential growth of complex data in object-relational databases (ORDB) raises the need for efficient storage with scalability, consistency, and partition tolerance. The migration towards NoSQL (not only structured query language) datastores is the best fit for distributed complex data. Unfortunately, very few studies provide solutions for ORDB migration to NoSQL. This paper reports on how to achieve the migration of complex data from ORDB to a document-oriented NoSQL database. The proposed approach focused on the P3 process that involves three major stages: (P1) the preprocessing stage to access and extract the database features using SQL queries, (P2) the processing stage to provide the data mapping by using a list of mapping rules between the source and target models, and (P3) the post-processing stage to store and request the migrated data within the NoSQL context. A thorough experiments on two real-life databases veriðes the P3 process improves the performance of data migration with complex schema structures.
{"title":"P3 Process for Object-Relational Data Migration to NoSQL Document-Oriented Datastore","authors":"A. Aggoune, Mohamed Sofiane Namoune","doi":"10.4018/ijssci.309994","DOIUrl":"https://doi.org/10.4018/ijssci.309994","url":null,"abstract":"The exponential growth of complex data in object-relational databases (ORDB) raises the need for efficient storage with scalability, consistency, and partition tolerance. The migration towards NoSQL (not only structured query language) datastores is the best fit for distributed complex data. Unfortunately, very few studies provide solutions for ORDB migration to NoSQL. This paper reports on how to achieve the migration of complex data from ORDB to a document-oriented NoSQL database. The proposed approach focused on the P3 process that involves three major stages: (P1) the preprocessing stage to access and extract the database features using SQL queries, (P2) the processing stage to provide the data mapping by using a list of mapping rules between the source and target models, and (P3) the post-processing stage to store and request the migrated data within the NoSQL context. A thorough experiments on two real-life databases veriðes the P3 process improves the performance of data migration with complex schema structures.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130635859","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}
In the traditional system, various researchers have suggested different resource scheduling and optimization algorithms. However, still, there is a scope to reduce Bandwidth, latency, energy consumption, and total communication cost in the Fog environment. in this work discussion is done on various performance challenges that are experienced in the Fog Environment based on 6G networks and explore the role of optimization techniques to overcome these challenges This work is focused on the Comparison of PSO, GA, and Round-Robin algorithm on parameters Cost, makespan, average execution time, and energy consumption for the resource management in the Fog environment. This study also represents which technique among the Group behavior species, Social Behaviour, and Pre-emptive type is better for achieving QoS for resource management in the Fog environment for the 6G network. In this work, we have discussed various resource scheduling problems that may be faced in the future, and what type of improvement can be considered in terms of IoT devices and 6G networks.
{"title":"Resource Scheduling in Fog Environment Using Optimization Algorithms for 6G Networks","authors":"Gaurav Goel, Rajeev Tiwari","doi":"10.4018/ijssci.304440","DOIUrl":"https://doi.org/10.4018/ijssci.304440","url":null,"abstract":"In the traditional system, various researchers have suggested different resource scheduling and optimization algorithms. However, still, there is a scope to reduce Bandwidth, latency, energy consumption, and total communication cost in the Fog environment. in this work discussion is done on various performance challenges that are experienced in the Fog Environment based on 6G networks and explore the role of optimization techniques to overcome these challenges This work is focused on the Comparison of PSO, GA, and Round-Robin algorithm on parameters Cost, makespan, average execution time, and energy consumption for the resource management in the Fog environment. This study also represents which technique among the Group behavior species, Social Behaviour, and Pre-emptive type is better for achieving QoS for resource management in the Fog environment for the 6G network. In this work, we have discussed various resource scheduling problems that may be faced in the future, and what type of improvement can be considered in terms of IoT devices and 6G networks.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133064764","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}
Agriculture is the country's mainstay. Plant diseases reduce production and thus product prices. Clearly, prices of edible and non-edible goods rose dramatically after the outbreak. We can save plants and correct pricing inconsistencies using automated disease detection. Using light detection and range (LIDAR) to identify plant diseases lets farmers handle dense volumes with minimal human intervention. To address the limitations of passive systems like climate, light variations, viewing angle, and canopy architecture, LIDAR sensors are used. The DSRC was used to receive an alert signal from the cloud server and convey it to farmers in real-time via cluster heads. For each concept, we evaluate its strengths and weaknesses, as well as the potential for future research. This research work aims to improve the way deep neural networks identify plant diseases. Google Net, Inceptionv3, Res Net 50, and Improved Vgg19 are evaluated before Biased CNN. Finally, our proposed Biased CNN (B-CNN) methodology boosted farmers' production by 93% per area.
农业是这个国家的支柱产业。植物病害降低产量，从而降低产品价格。显然，疫情爆发后，食用和非食用商品的价格大幅上涨。我们可以通过自动疾病检测来拯救植物并纠正价格不一致。利用光探测和测距(激光雷达)来识别植物病害，农民可以在最少的人为干预下处理密集的植物。为了解决被动系统的局限性，如气候、光线变化、视角和树冠结构，使用了激光雷达传感器。DSRC用于接收来自云服务器的警报信号，并通过集群头将其实时传递给农民。对于每个概念，我们评估其优点和缺点，以及未来研究的潜力。本研究旨在改进深度神经网络识别植物病害的方法。Google Net、Inceptionv3、Res Net 50和Improved Vgg19在Biased CNN之前进行了评估。最后，我们提出的Biased CNN (B-CNN)方法使农民的亩产提高了93%。
{"title":"An Improvement of Yield Production Rate for Crops by Predicting Disease Rate Using Intelligent Decision Systems","authors":"M. U. Rani, N. Selvam, L. Deborah","doi":"10.4018/ijssci.291714","DOIUrl":"https://doi.org/10.4018/ijssci.291714","url":null,"abstract":"Agriculture is the country's mainstay. Plant diseases reduce production and thus product prices. Clearly, prices of edible and non-edible goods rose dramatically after the outbreak. We can save plants and correct pricing inconsistencies using automated disease detection. Using light detection and range (LIDAR) to identify plant diseases lets farmers handle dense volumes with minimal human intervention. To address the limitations of passive systems like climate, light variations, viewing angle, and canopy architecture, LIDAR sensors are used. The DSRC was used to receive an alert signal from the cloud server and convey it to farmers in real-time via cluster heads. For each concept, we evaluate its strengths and weaknesses, as well as the potential for future research. This research work aims to improve the way deep neural networks identify plant diseases. Google Net, Inceptionv3, Res Net 50, and Improved Vgg19 are evaluated before Biased CNN. Finally, our proposed Biased CNN (B-CNN) methodology boosted farmers' production by 93% per area.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131789554","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 growing number of connected IoT devices and their continuous data collection will generate huge amounts of data in the near future. Edge computing has emerged as a new paradigm in recent years for reducing network congestion and offering real-time IoT applications. Processing the large amount of data generated by such IoT devices requires the development of a scalable edge computing environment. Accordingly, applications deployed in an edge computing environment need to be scalable enough to handle the enormous amount of data generated by IoT devices. The performance of MSA and monolithic architecture is analyzed and compared to develop a scalable edge computing environment. An auto-scaling approach is described to handle multiple concurrent requests at runtime. Minikube is used to perform auto-scaling operation of containerized microservices on resource constraint edge node. Considering performance of both the architecture and according to the results and discussions, MSA is a better choice for building scalable edge computing environment.
{"title":"Scalable Edge Computing Environment Based on the Containerized Microservices and Minikube","authors":"Nitin Rathore, A. Rajavat","doi":"10.4018/ijssci.312560","DOIUrl":"https://doi.org/10.4018/ijssci.312560","url":null,"abstract":"The growing number of connected IoT devices and their continuous data collection will generate huge amounts of data in the near future. Edge computing has emerged as a new paradigm in recent years for reducing network congestion and offering real-time IoT applications. Processing the large amount of data generated by such IoT devices requires the development of a scalable edge computing environment. Accordingly, applications deployed in an edge computing environment need to be scalable enough to handle the enormous amount of data generated by IoT devices. The performance of MSA and monolithic architecture is analyzed and compared to develop a scalable edge computing environment. An auto-scaling approach is described to handle multiple concurrent requests at runtime. Minikube is used to perform auto-scaling operation of containerized microservices on resource constraint edge node. Considering performance of both the architecture and according to the results and discussions, MSA is a better choice for building scalable edge computing environment.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"19 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133817654","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 tomato crop is a strategic crop in the Egyptian market with high commercial value and large production. However, tomato diseases can cause huge losses and reduce yields. This work aims to use deep learning to construct a robust intelligent system for detecting tomato crop diseases to help farmers and agricultural workers by comparing the performance of four different recent state-of-the-art deep learning models to recognize 9 different diseases of tomatoes. In order to maximize the system's generalization ability, data augmentation, fine-tuning, label smoothing, and dataset enrichment techniques were investigated. The best-performing model achieved an average accuracy of 99.12% with a hold-out test set from the original dataset and an accuracy of 71.43% with new images downloaded from the Internet that had never been seen before. Training and testing were performed on a computer, and the final model was deployed on a smartphone for real-time on-site disease classification.
{"title":"A Robust Intelligent System for Detecting Tomato Crop Diseases Using Deep Learning","authors":"M. Afify, Mohamed Loey, A. Elsawy","doi":"10.4018/ijssci.304439","DOIUrl":"https://doi.org/10.4018/ijssci.304439","url":null,"abstract":"The tomato crop is a strategic crop in the Egyptian market with high commercial value and large production. However, tomato diseases can cause huge losses and reduce yields. This work aims to use deep learning to construct a robust intelligent system for detecting tomato crop diseases to help farmers and agricultural workers by comparing the performance of four different recent state-of-the-art deep learning models to recognize 9 different diseases of tomatoes. In order to maximize the system's generalization ability, data augmentation, fine-tuning, label smoothing, and dataset enrichment techniques were investigated. The best-performing model achieved an average accuracy of 99.12% with a hold-out test set from the original dataset and an accuracy of 71.43% with new images downloaded from the Internet that had never been seen before. Training and testing were performed on a computer, and the final model was deployed on a smartphone for real-time on-site disease classification.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133873671","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}
M. Chopra, Sunil K. Singh, Akhil Sharma, Shabeg Singh Gill
Text-to-picture alludes to the conversion of a textual description into a semantically similar image.The automatic synthesis of top-quality pictures from text portrayals is both exciting and useful at the same time.Current AI systems have shown significant advances in the field,but the work is still far from complete. Recent advances in the field of Deep Learning have resulted in the introduction of generative models that are capable of generating realistic images when trained appropriately.In this paper,authors will review the advancements in architectures for solving the problem of image synthesis using a text description.They begin by studying the concepts of the standard GAN, how the DCGAN has been used for the task at hand is followed by the StackGAN with uses a stack of two GANs to generate an image through iterative refinement & StackGAN++ which uses multiple GANs in a tree-like structure making the task of generating images from the text more generalized. They look at the AttnGAN which uses an attentional model to generate sub-regions of an image based on the description.
{"title":"A Comparative Study of Generative Adversarial Networks for Text-to-Image Synthesis","authors":"M. Chopra, Sunil K. Singh, Akhil Sharma, Shabeg Singh Gill","doi":"10.4018/ijssci.300364","DOIUrl":"https://doi.org/10.4018/ijssci.300364","url":null,"abstract":"Text-to-picture alludes to the conversion of a textual description into a semantically similar image.The automatic synthesis of top-quality pictures from text portrayals is both exciting and useful at the same time.Current AI systems have shown significant advances in the field,but the work is still far from complete. Recent advances in the field of Deep Learning have resulted in the introduction of generative models that are capable of generating realistic images when trained appropriately.In this paper,authors will review the advancements in architectures for solving the problem of image synthesis using a text description.They begin by studying the concepts of the standard GAN, how the DCGAN has been used for the task at hand is followed by the StackGAN with uses a stack of two GANs to generate an image through iterative refinement & StackGAN++ which uses multiple GANs in a tree-like structure making the task of generating images from the text more generalized. They look at the AttnGAN which uses an attentional model to generate sub-regions of an image based on the description.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116893675","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}
Dementia is a neurological disease that that encompasses a wide range of conditions like verbal communication, problem-solving, and other judgment abilities that are severely sufficient to interfere with daily life. It is among the leading causes of vulnerability among the elderly all over the world. A considerable amount of research has been conducted in this area so that we can perform early detection of the disease, yet further research into its betterment is still an emerging trend. This article compares the performance of multiple machine learning models for dementia detection and classification using brain MRI data, including support vector machine, random forest, AdaBoost, and XGBoost. Meanwhile, the research conducts a systematic assessment of papers for the clinical categorization of dementia using ML algorithms and neuroimaging data. The authors used 373 participants from the OASIS database. Among the tested models, RF model exhibited the best performance with 83.92% accuracy, 87.5% precision, 81.67% recall, 84.48% F1-score, 81.67% sensitivity, and 88.46% specificity.
{"title":"Performance Comparison of Machine Learning Algorithms for Dementia Progression Detection","authors":"Tripti Tripathi, R. Kumar","doi":"10.4018/ijssci.312553","DOIUrl":"https://doi.org/10.4018/ijssci.312553","url":null,"abstract":"Dementia is a neurological disease that that encompasses a wide range of conditions like verbal communication, problem-solving, and other judgment abilities that are severely sufficient to interfere with daily life. It is among the leading causes of vulnerability among the elderly all over the world. A considerable amount of research has been conducted in this area so that we can perform early detection of the disease, yet further research into its betterment is still an emerging trend. This article compares the performance of multiple machine learning models for dementia detection and classification using brain MRI data, including support vector machine, random forest, AdaBoost, and XGBoost. Meanwhile, the research conducts a systematic assessment of papers for the clinical categorization of dementia using ML algorithms and neuroimaging data. The authors used 373 participants from the OASIS database. Among the tested models, RF model exhibited the best performance with 83.92% accuracy, 87.5% precision, 81.67% recall, 84.48% F1-score, 81.67% sensitivity, and 88.46% specificity.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117006689","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：