B. Pavitra, D. Singh, S. Sharma, Mohammad Farukh Hashmi
In the last decades the health care developments highly rise the level of ages of world population. This improvement was accompanied by increasing the diseases related with elder like Dementia, which Alzheimer’s disease represents the most common form. The present studies aim to design and implementation a medical system for improving the life of Alzheimer’s disease persons and ease the burden of their caregivers. AI is transforming the practice of medicine. It’s helping doctors diagnose patients more accurately, make predictions about patient’s future health, and recommend better treatments. AI goes beyond the foundations of deep learning to give you insight into the nuances of applying AI to medical use cases. Diagnosis is about identifying disease. By building an algorithm we can diagnosis chest X-ray and determine whether it contains disease, another algorithm that will look at brain MRIs and identify the location of tumours in those brain MRIs health of the patients lab values and their demographics and use those to predict the risk of an event. A Smart IOT Interactive Assistance is a technological device that continuously monitors the stability of an Alzheimer’s patient, indicates their position on a map, automatically reminds them to take their prescriptions, and has a call button for any emergencies they could experience during the day. The system has two components, one of which the patient wears and the other of which is an IoT platform application utilized by the caregiver. The motion processing unit sensor, GPS, heart rate sensor with microcontrollers, and LCD display were used to construct the wearable device. An Internet of Things (IoT) platform supports this device, allowing the caregiver to communicate with the patient from any location.
{"title":"Dementia prediction using novel IOTM (Internet of Things in Medical) architecture framework","authors":"B. Pavitra, D. Singh, S. Sharma, Mohammad Farukh Hashmi","doi":"10.3233/ida-237431","DOIUrl":"https://doi.org/10.3233/ida-237431","url":null,"abstract":"In the last decades the health care developments highly rise the level of ages of world population. This improvement was accompanied by increasing the diseases related with elder like Dementia, which Alzheimer’s disease represents the most common form. The present studies aim to design and implementation a medical system for improving the life of Alzheimer’s disease persons and ease the burden of their caregivers. AI is transforming the practice of medicine. It’s helping doctors diagnose patients more accurately, make predictions about patient’s future health, and recommend better treatments. AI goes beyond the foundations of deep learning to give you insight into the nuances of applying AI to medical use cases. Diagnosis is about identifying disease. By building an algorithm we can diagnosis chest X-ray and determine whether it contains disease, another algorithm that will look at brain MRIs and identify the location of tumours in those brain MRIs health of the patients lab values and their demographics and use those to predict the risk of an event. A Smart IOT Interactive Assistance is a technological device that continuously monitors the stability of an Alzheimer’s patient, indicates their position on a map, automatically reminds them to take their prescriptions, and has a call button for any emergencies they could experience during the day. The system has two components, one of which the patient wears and the other of which is an IoT platform application utilized by the caregiver. The motion processing unit sensor, GPS, heart rate sensor with microcontrollers, and LCD display were used to construct the wearable device. An Internet of Things (IoT) platform supports this device, allowing the caregiver to communicate with the patient from any location.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44070221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rami Baazeem, P. Maheshwary, D. Binjawhar, K. Gulati, Shubham Joshi, Stephen Ojo, P. Pareek, Prashant Kumar Shukla
Nanomaterials are finding increasingly diverse medical uses as technology advances. Researchers are constantly being introduced to new and improved methods, and these applications see widespread use for both diagnostic and therapeutic purposes. Early disease detection, efficient drug delivery, cosmetics and health care products, biosensors, miniaturisation techniques, surface improvement in implantable biomaterials, improved nanofibers in medical textiles, etc. are all examples of how biomedical nanotechnology has made a difference in the medical field. The nanoparticles are introduced deliberately for therapeutic purposes or accidentally from the environment; they will eventually reach and penetrate the human body. The exposed nanoparticles interact with human blood, which carries them to various tissues. An essential aspect of blood rheology in the microcirculation is its malleability. As a result, nanomaterial may cause structural abnormalities in erythrocytes. Echinocyte development is a typical example of an induced morphological alteration. The length of time it takes for these side effects to disappear after taking a nano medication also matters. Haemolyses could result from the dangerous concentration. In this experiment, human blood is exposed to varying concentrations of chosen nanomaterial with potential medical applications. The morphological modifications induced were studied by looking at images of erythrocyte cells. That’s a picture of a cell taken using a digital optical microscope, by the way. We used MATLAB, an image-analysis programme, to study the morphometric features. Human lymphocyte cells were used in the cytotoxic analysis.
{"title":"Digital image processing for evaluating the impact of designated nanoparticles in biomedical applications","authors":"Rami Baazeem, P. Maheshwary, D. Binjawhar, K. Gulati, Shubham Joshi, Stephen Ojo, P. Pareek, Prashant Kumar Shukla","doi":"10.3233/ida-237435","DOIUrl":"https://doi.org/10.3233/ida-237435","url":null,"abstract":"Nanomaterials are finding increasingly diverse medical uses as technology advances. Researchers are constantly being introduced to new and improved methods, and these applications see widespread use for both diagnostic and therapeutic purposes. Early disease detection, efficient drug delivery, cosmetics and health care products, biosensors, miniaturisation techniques, surface improvement in implantable biomaterials, improved nanofibers in medical textiles, etc. are all examples of how biomedical nanotechnology has made a difference in the medical field. The nanoparticles are introduced deliberately for therapeutic purposes or accidentally from the environment; they will eventually reach and penetrate the human body. The exposed nanoparticles interact with human blood, which carries them to various tissues. An essential aspect of blood rheology in the microcirculation is its malleability. As a result, nanomaterial may cause structural abnormalities in erythrocytes. Echinocyte development is a typical example of an induced morphological alteration. The length of time it takes for these side effects to disappear after taking a nano medication also matters. Haemolyses could result from the dangerous concentration. In this experiment, human blood is exposed to varying concentrations of chosen nanomaterial with potential medical applications. The morphological modifications induced were studied by looking at images of erythrocyte cells. That’s a picture of a cell taken using a digital optical microscope, by the way. We used MATLAB, an image-analysis programme, to study the morphometric features. Human lymphocyte cells were used in the cytotoxic analysis.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48956273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Editorial","authors":"","doi":"10.3233/ida-239006","DOIUrl":"https://doi.org/10.3233/ida-239006","url":null,"abstract":"","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42676519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Prasanna, Chinna Babu Jyothi, M. S. Kumar, J. Prabhu, A. Saif, Dinesh Jackson Samuel
Cephalometric analysis is used to identify problems in the development of the skull, evaluate their treatment, and plan for possible surgical interventions. The paper aims to develop a Convolutional Neural Network that will analyze the head position on an X-ray image. It takes place in such a way that it recognizes whether the image is suitable and, if not, suggests a change in the position of the head for correction. This paper addresses the exact rotation of the head with a change in the range of a few degrees of rotation. The objective is to predict the correct head position to take an X-ray image for further Cephalometric analysis. The changes in the degree of rotations were categorized into 5 classes. Deep learning models predict the correct head position for Cephalometric analysis. An X-ray image dataset on the head is generated using CT scan images. The generated images are categorized into 5 classes based on a few degrees of rotations. A set of four deep-learning models were then used to generate the generated X-Ray images for analysis. This research work makes use of four CNN-based networks. These networks are trained on a dataset to predict the accurate head position on generated X-Ray images for analysis. Two networks of VGG-Net, one is the U-Net and the last is of the ResNet type. The experimental analysis ascertains that VGG-4 outperformed the VGG-3, U-Net, and ResNet in estimating the head position to take an X-ray on a test dataset with a measured accuracy of 98%. It is due to the incorrectly classified images are classified that are directly adjacent to the correct ones at intervals and the misclassification rate is significantly reduced.
{"title":"Deep learning models for predicting the position of the head on an X-ray image for Cephalometric analysis","authors":"K. Prasanna, Chinna Babu Jyothi, M. S. Kumar, J. Prabhu, A. Saif, Dinesh Jackson Samuel","doi":"10.3233/ida-237430","DOIUrl":"https://doi.org/10.3233/ida-237430","url":null,"abstract":"Cephalometric analysis is used to identify problems in the development of the skull, evaluate their treatment, and plan for possible surgical interventions. The paper aims to develop a Convolutional Neural Network that will analyze the head position on an X-ray image. It takes place in such a way that it recognizes whether the image is suitable and, if not, suggests a change in the position of the head for correction. This paper addresses the exact rotation of the head with a change in the range of a few degrees of rotation. The objective is to predict the correct head position to take an X-ray image for further Cephalometric analysis. The changes in the degree of rotations were categorized into 5 classes. Deep learning models predict the correct head position for Cephalometric analysis. An X-ray image dataset on the head is generated using CT scan images. The generated images are categorized into 5 classes based on a few degrees of rotations. A set of four deep-learning models were then used to generate the generated X-Ray images for analysis. This research work makes use of four CNN-based networks. These networks are trained on a dataset to predict the accurate head position on generated X-Ray images for analysis. Two networks of VGG-Net, one is the U-Net and the last is of the ResNet type. The experimental analysis ascertains that VGG-4 outperformed the VGG-3, U-Net, and ResNet in estimating the head position to take an X-ray on a test dataset with a measured accuracy of 98%. It is due to the incorrectly classified images are classified that are directly adjacent to the correct ones at intervals and the misclassification rate is significantly reduced.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48116235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ana Vieira, João Carneiro, Paulo Novais, Juan Corchado, Goreti Marreiros
A large percentage of the worldwide population is affected by chronic diseases, leading to a burden of the patient and the national healthcare systems. Recommendation systems are used for the personalization of healthcare due to their capacity of performing predictive analyses based on the patient’s clinical data. This systematic literature review presents four research questions to provide an overall state of the art of the use of recommendation systems applied to the healthcare of patients with chronic diseases. Disease management was identified as the main purpose of the systems proposed in the literature. However, few solutions provide support to physicians in the clinical decision-making. Ontologies and rule-based systems were the artificial intelligence techniques most used in the systems since they can easily implement clinical guidelines. Current challenges of these systems include the low adherence, data sparsity, heterogeneous data, and explainability, that affect the success of the recommendation system. The results also show that there are few systems that provide support to patients with multiple chronic conditions. The findings of this literature review should be considered in the development of future recommendation systems that aim to support the management of chronic diseases.
{"title":"A systematic review on recommendation systems applied to chronic diseases","authors":"Ana Vieira, João Carneiro, Paulo Novais, Juan Corchado, Goreti Marreiros","doi":"10.3233/ida-220394","DOIUrl":"https://doi.org/10.3233/ida-220394","url":null,"abstract":"A large percentage of the worldwide population is affected by chronic diseases, leading to a burden of the patient and the national healthcare systems. Recommendation systems are used for the personalization of healthcare due to their capacity of performing predictive analyses based on the patient’s clinical data. This systematic literature review presents four research questions to provide an overall state of the art of the use of recommendation systems applied to the healthcare of patients with chronic diseases. Disease management was identified as the main purpose of the systems proposed in the literature. However, few solutions provide support to physicians in the clinical decision-making. Ontologies and rule-based systems were the artificial intelligence techniques most used in the systems since they can easily implement clinical guidelines. Current challenges of these systems include the low adherence, data sparsity, heterogeneous data, and explainability, that affect the success of the recommendation system. The results also show that there are few systems that provide support to patients with multiple chronic conditions. The findings of this literature review should be considered in the development of future recommendation systems that aim to support the management of chronic diseases.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":"310 2","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138527040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wan-Shu Cheng, Pengchi Huang, Jheng-Yu Huang, Ju-Chin Chen, K. W. Lin
The amount of information nowadays is rapidly growing. Aside from valuable information, information that is unrelated to a target or is meaningless is also growing. Big data and broader digital technologies are considered the primary components of smart city governance and planning. Big data analysis is considered to define a new era in urban planning, research, and policy. Effective data mining and pattern detection techniques are becoming very important these days. Processing such a large amount of data entails the use of data mining, a technique that clarifies the association between valid information and excludes irrelevant data to implement a practical decision tree. A large amount of data affects processing time and I/O costs during data mining. This study proposes to distribute data among multiple clients and distribute a large amount of data computation equally to improve the resource cost problem of exploration. Following that, the main server consolidates the computation results and generates the survey results. Experiment results show that the proposed algorithm is superior, thus allowing a larger amount of data to be processed while producing high-quality results.
{"title":"A fast and distributed C4.5 algorithm for urban big data","authors":"Wan-Shu Cheng, Pengchi Huang, Jheng-Yu Huang, Ju-Chin Chen, K. W. Lin","doi":"10.3233/ida-220753","DOIUrl":"https://doi.org/10.3233/ida-220753","url":null,"abstract":"The amount of information nowadays is rapidly growing. Aside from valuable information, information that is unrelated to a target or is meaningless is also growing. Big data and broader digital technologies are considered the primary components of smart city governance and planning. Big data analysis is considered to define a new era in urban planning, research, and policy. Effective data mining and pattern detection techniques are becoming very important these days. Processing such a large amount of data entails the use of data mining, a technique that clarifies the association between valid information and excludes irrelevant data to implement a practical decision tree. A large amount of data affects processing time and I/O costs during data mining. This study proposes to distribute data among multiple clients and distribute a large amount of data computation equally to improve the resource cost problem of exploration. Following that, the main server consolidates the computation results and generates the survey results. Experiment results show that the proposed algorithm is superior, thus allowing a larger amount of data to be processed while producing high-quality results.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44015817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As an important part of digital building, building internet of things (BIoT) plays a positive role in promoting the construction of smart cities. Existing schemes utilize blockchain to achieve trusted data storage in BIoT. However, the full-copy storage mechanism of blockchain and the management requirements of massive data have brought computing and storage challenges to edge nodes with limited resources. Therefore, a data management scheme for BIoT based on blockchain sharding is proposed. The scheme proposes a hybrid storage mechanism, which uses inter-planetary file system (IPFS) to ensure the integrity and availability of data outside the chain, and reduces the storage overhead of edge nodes. Based on the hybrid storage mechanism, the sharding algorithm is designed to divide the blockchain into multiple shards, and the storage overhead and computing overhead are offloaded to each shard, which effectively balances the computing and storage overhead of edge nodes. Finally, comparative analysis was made with existing schemes, and effectiveness of proposed scheme was verified from the perspectives of storage overhead, computation overhead, access delay and throughput. Results show that proposed scheme can effectively reduce storage overhead and computing overhead of edge nodes in BIoT scenario.
{"title":"Data management scheme for building internet of things based on blockchain sharding","authors":"Xu Wang, Wenhu Zheng, Jinlong Wang, Xiaoyun Xiong, Yumin Shen, Wei Mu, Zengliang Fan","doi":"10.3233/ida-220757","DOIUrl":"https://doi.org/10.3233/ida-220757","url":null,"abstract":"As an important part of digital building, building internet of things (BIoT) plays a positive role in promoting the construction of smart cities. Existing schemes utilize blockchain to achieve trusted data storage in BIoT. However, the full-copy storage mechanism of blockchain and the management requirements of massive data have brought computing and storage challenges to edge nodes with limited resources. Therefore, a data management scheme for BIoT based on blockchain sharding is proposed. The scheme proposes a hybrid storage mechanism, which uses inter-planetary file system (IPFS) to ensure the integrity and availability of data outside the chain, and reduces the storage overhead of edge nodes. Based on the hybrid storage mechanism, the sharding algorithm is designed to divide the blockchain into multiple shards, and the storage overhead and computing overhead are offloaded to each shard, which effectively balances the computing and storage overhead of edge nodes. Finally, comparative analysis was made with existing schemes, and effectiveness of proposed scheme was verified from the perspectives of storage overhead, computation overhead, access delay and throughput. Results show that proposed scheme can effectively reduce storage overhead and computing overhead of edge nodes in BIoT scenario.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":"264 9","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41290409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Code search, which locates code snippets in large code repositories based on natural language queries entered by developers, has become increasingly popular in the software development process. It has the potential to improve the efficiency of software developers. Recent studies have demonstrated the effectiveness of using deep learning techniques to represent queries and codes accurately for code search. In specific, pre-trained models of programming languages have recently achieved significant progress in code searching. However, we argue that aligning programming and natural languages are crucial as there are two different modalities. Existing pre-train models based approaches for code search do not effectively consider implicit alignments of representations across modalities (inter-modal representation). Moreover, the existing methods do not take into account the consistency constraint of intra-modal representations, making the model ineffective. As a result, we propose a novel code search method that optimizes both intra-modal and inter-modal representation learning. The alignment of the representation between the two modalities is achieved by introducing contrastive learning. Furthermore, the consistency of intra-modal feature representation is constrained by KL-divergence. Our experimental results confirm the model’s effectiveness on seven different test datasets. This paper proposes a code search method that significantly improves existing methods. Our source code is publicly available on GitHub.1
{"title":"I2R: Intra and inter-modal representation learning for code search","authors":"Xu Zhang, Yanzheng Xiang, Zejie Liu, Xiaoyu Hu, Deyu Zhou","doi":"10.3233/ida-230082","DOIUrl":"https://doi.org/10.3233/ida-230082","url":null,"abstract":"Code search, which locates code snippets in large code repositories based on natural language queries entered by developers, has become increasingly popular in the software development process. It has the potential to improve the efficiency of software developers. Recent studies have demonstrated the effectiveness of using deep learning techniques to represent queries and codes accurately for code search. In specific, pre-trained models of programming languages have recently achieved significant progress in code searching. However, we argue that aligning programming and natural languages are crucial as there are two different modalities. Existing pre-train models based approaches for code search do not effectively consider implicit alignments of representations across modalities (inter-modal representation). Moreover, the existing methods do not take into account the consistency constraint of intra-modal representations, making the model ineffective. As a result, we propose a novel code search method that optimizes both intra-modal and inter-modal representation learning. The alignment of the representation between the two modalities is achieved by introducing contrastive learning. Furthermore, the consistency of intra-modal feature representation is constrained by KL-divergence. Our experimental results confirm the model’s effectiveness on seven different test datasets. This paper proposes a code search method that significantly improves existing methods. Our source code is publicly available on GitHub.1","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45514729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jie Yang, Zhenhao Jiang, Tingting Pan, Yueqi Chen, W. Pedrycz
Data-imbalanced problems are present in many applications. A big gap in the number of samples in different classes induces classifiers to skew to the majority class and thus diminish the performance of learning and quality of obtained results. Most data level imbalanced learning approaches generate new samples only using the information associated with the minority samples through linearly generating or data distribution fitting. Different from these algorithms, we propose a novel oversampling method based on generative adversarial networks (GANs), named OS-GAN. In this method, GAN is assigned to learn the distribution characteristics of the minority class from some selected majority samples but not random noise. As a result, samples released by the trained generator carry information of both majority and minority classes. Furthermore, the central regularization makes the distribution of all synthetic samples not restricted to the domain of the minority class, which can improve the generalization of learning models or algorithms. Experimental results reported on 14 datasets and one high-dimensional dataset show that OS-GAN outperforms 14 commonly used resampling techniques in terms of G-mean, accuracy and F1-score.
{"title":"Oversampling method based on GAN for tabular binary classification problems","authors":"Jie Yang, Zhenhao Jiang, Tingting Pan, Yueqi Chen, W. Pedrycz","doi":"10.3233/ida-220383","DOIUrl":"https://doi.org/10.3233/ida-220383","url":null,"abstract":"Data-imbalanced problems are present in many applications. A big gap in the number of samples in different classes induces classifiers to skew to the majority class and thus diminish the performance of learning and quality of obtained results. Most data level imbalanced learning approaches generate new samples only using the information associated with the minority samples through linearly generating or data distribution fitting. Different from these algorithms, we propose a novel oversampling method based on generative adversarial networks (GANs), named OS-GAN. In this method, GAN is assigned to learn the distribution characteristics of the minority class from some selected majority samples but not random noise. As a result, samples released by the trained generator carry information of both majority and minority classes. Furthermore, the central regularization makes the distribution of all synthetic samples not restricted to the domain of the minority class, which can improve the generalization of learning models or algorithms. Experimental results reported on 14 datasets and one high-dimensional dataset show that OS-GAN outperforms 14 commonly used resampling techniques in terms of G-mean, accuracy and F1-score.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43542303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Biswas, Sourav Banerjee, Uttam Ghosh, U. Biswas
The growing smart cities in urban areas are becoming more intelligent day by day. Massive storage and high computational resources are required to provide smart services in urban areas. It can be provided through intelligence cloud computing. The establishment of large-scale cloud data centres is rapidly increasing to provide utility-based services in urban areas. Enormous energy consumption of data centres has a destructive effect on the environment. Due to the enormous energy consumption of data centres, a massive amount of greenhouse gases (GHG) are emitted into the environment. Virtual Machine (VM) consolidation can enable energy efficiency to reduce energy consumption of cloud data centres. The reduce energy consumption can increases the Service Level Agreement (SLA) violation. Therefore, in this research, an energy-efficient dynamic VM consolidation model has been proposed to reduce the energy consumption of cloud data centres and curb SLA violations. Novel algorithms have been proposed to accomplished the VM consolidation. A new status of any host called an almost overload host has been introduced, and determined by a novel algorithm based on the Naive Bayes Classifier Machine Learning (ML) model. A new algorithm based on the exponential binary search is proposed to perform the VM selection. Finally, a new Modified Power-Aware Best Fit Decreasing (MPABFD) VM allocation policy is proposed to allocate all VMs. The proposed model has been compared with certain well-known baseline algorithms. The comparison exhibits that the proposed model improves the energy consumption by 25% and SLA violation by 87%.
城市地区不断发展的智慧城市日益智能化。城市智能服务需要海量存储和高计算资源。它可以通过智能云计算提供。大规模云数据中心的建立正在迅速增加，以便在城市地区提供基于公用事业的服务。数据中心的巨大能源消耗对环境造成了破坏性影响。由于数据中心的巨大能源消耗，大量的温室气体(GHG)排放到环境中。虚拟机(VM)整合可以提高能源效率，降低云数据中心的能源消耗。能源消耗的减少会增加违反SLA (Service Level Agreement)的情况。因此，本研究提出了一种节能的动态VM整合模型，以降低云数据中心的能源消耗并抑制SLA违规。提出了新的算法来完成虚拟机整合。引入了一种新的主机状态，称为几乎过载的主机，并由一种基于朴素贝叶斯分类器机器学习(ML)模型的新算法确定。提出了一种基于指数二叉搜索的虚拟机选择算法。最后，提出了一种改进的MPABFD (Power-Aware Best Fit reduction)虚拟机分配策略来分配所有虚拟机。将该模型与一些已知的基线算法进行了比较。比较表明，所提出的模型将能耗提高了25%，SLA违规率降低了87%。
{"title":"Design of an energy efficient dynamic virtual machine consolidation model for smart cities in urban areas","authors":"N. Biswas, Sourav Banerjee, Uttam Ghosh, U. Biswas","doi":"10.3233/ida-220754","DOIUrl":"https://doi.org/10.3233/ida-220754","url":null,"abstract":"The growing smart cities in urban areas are becoming more intelligent day by day. Massive storage and high computational resources are required to provide smart services in urban areas. It can be provided through intelligence cloud computing. The establishment of large-scale cloud data centres is rapidly increasing to provide utility-based services in urban areas. Enormous energy consumption of data centres has a destructive effect on the environment. Due to the enormous energy consumption of data centres, a massive amount of greenhouse gases (GHG) are emitted into the environment. Virtual Machine (VM) consolidation can enable energy efficiency to reduce energy consumption of cloud data centres. The reduce energy consumption can increases the Service Level Agreement (SLA) violation. Therefore, in this research, an energy-efficient dynamic VM consolidation model has been proposed to reduce the energy consumption of cloud data centres and curb SLA violations. Novel algorithms have been proposed to accomplished the VM consolidation. A new status of any host called an almost overload host has been introduced, and determined by a novel algorithm based on the Naive Bayes Classifier Machine Learning (ML) model. A new algorithm based on the exponential binary search is proposed to perform the VM selection. Finally, a new Modified Power-Aware Best Fit Decreasing (MPABFD) VM allocation policy is proposed to allocate all VMs. The proposed model has been compared with certain well-known baseline algorithms. The comparison exhibits that the proposed model improves the energy consumption by 25% and SLA violation by 87%.","PeriodicalId":50355,"journal":{"name":"Intelligent Data Analysis","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46587638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：