自主智能(英文)最新文献

{"title":"An automatic product recommendation system in e-commerce using Flamingo Search Optimizer and Fuzzy Temporal Multi Neural Classifier","authors":"B. Manikandan, P. Rama, S. Chakaravarthi","doi":"10.32629/jai.v6i2.568","DOIUrl":"https://doi.org/10.32629/jai.v6i2.568","url":null,"abstract":"In this paper, a new automatic product recommendation system (APRS) is proposed to recommend the suitable products to the customer in e-commerce by analyzing the customers’ reviews. This recommendation system applies semantic aware data preprocessing, feature selection and extraction and classification. The initial level data preprocessing including blank space and stop word removal. Moreover, we use a Flamingo Search Optimizer (FSO) for optimizing the features that are extracted in the initial level data preprocessing. In addition, a new Fuzzy Temporal Multi Neural Classification Algorithm (FTMNCA) is proposed for performing effective classification that is helpful to make effective decision on prediction process. In addition, the proposed automatic product recommendation system recommends the suitable products to the customers according to the classification result. Finally, the proposed system is evaluated by conducting various experiments and proved as superior than the available systems in terms of prediction accuracy, precision, recall and f-measure.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44400084","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}

{"title":"Challenges and solutions of Artificial Intelligence-based fault location methods in power system lines","authors":"Azad Hussein Zubair, K. Younis","doi":"10.32629/jai.v6i2.642","DOIUrl":"https://doi.org/10.32629/jai.v6i2.642","url":null,"abstract":"The accurate and efficient location of faults in power system lines is crucial for ensuring reliable and uninterrupted power supply. In recent years, Artificial Intelligence (AI) has been increasingly used in fault location methods, promising to improve the accuracy and efficiency of fault location. However, AI-based fault location methods also face challenges such as data quality, interpretability, and model robustness. Review method: This paper presents a review of the challenges and solutions of AI-based fault location methods in power system lines. The review is based on a comprehensive analysis of existing literature and research studies, focusing on the challenges associated with AI-based fault location methods and the solutions proposed to address these challenges. Content: The paper discusses the challenges associated with AI-based fault location methods in power system lines, including data quality, interpretability, and model robustness. The review presents several solutions to address these challenges, including data preprocessing techniques to improve data quality, explainable AI methods to enhance interpretability, and robustness validation techniques to improve model robustness. The accurate and efficient location of faults in power system lines is crucial for ensuring reliable and uninterrupted power supply. AI-based fault location methods have the potential to improve the accuracy and efficiency of fault location. However, these methods also face challenges such as data quality, interpretability, and model robustness. Addressing these challenges through techniques such as data preprocessing, explainable AI, and robustness validation can help to improve the accuracy and reliability of AI-based fault location methods.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43248874","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}

{"title":"Heterogeneity issues in IoT-driven devices and services","authors":"S. K. Gupta, Radha Raman Chandan, Rupesh Shukla, Prabhdeep Singh, A. Pandey, Amit Kumar Jaiswal","doi":"10.32629/jai.v6i2.588","DOIUrl":"https://doi.org/10.32629/jai.v6i2.588","url":null,"abstract":"Internet of Things (IoT), which connects billions of devices and services to the Internet, is viewed as the future industrial and intellectual revolution in technology. These connected devices are available in a variety of types. Different technologies and standards use various protocols to interact with each other. Due to these difficulties with heterogeneity, the application of IoT on a broad scale is difficult. This inspired us to identify the problems from the literature and offer solutions to solve the IoT scalability problem. This study is based on the systematic literature review (SLR) to identify the diverse problems and their solutions. We chose 81 primary sources in total. We found 14 distinct IoT heterogeneity concerns after extracting and interpreting the data. The following issues have been noted as potential obstacles: heterogeneity in data formats, heterogeneity of devices, heterogeneity in communication, and interoperability difficulty because of heterogeneity. From the perspectives of digital libraries and timeframes, the stated challenges have been addressed. Additionally, we have discovered 81 solutions in total for these problems, with at least 5 different answers for every issue. In the future, we will use a multi-criteria decision-making issue to classify the problems and evaluate the solutions.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46314942","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}

{"title":"A systematic review on video encryption algorithms: A future research","authors":"Avnish Kanungo, Ayushi Srivastava, Saniya Anklesaria, Prathamesh P. Churi","doi":"10.32629/jai.v6i2.665","DOIUrl":"https://doi.org/10.32629/jai.v6i2.665","url":null,"abstract":"Video Encryption is widely used in many real-time applications today. Despite numerous video encryption techniques that are available today, the challenges such as time and space complexity, real time latency, scalability and vulnerability towards few attacks still exist in the research domain, however few algorithms have achieved acceptable computational complexity, but in such cases vulnerability to certain attacks (differential, statistical, plain text attack, and cipher text attacks) are still a threat to secure video transmission. To the best of our knowledge, a comprehensive but detailed systematic literature review on video encryption is needed for the researchers in the scientific community. This paper, therefore, presents a systematic literature review of 30 scientific documents extracted from platforms like scopus and web of science. The paper, comprehensively addresses, various techniques of video encryption and encoding, different evaluation parameters to testify the performance of the algorithms and discusses the challenges of the existing video encryption algorithms. After careful investigation, it has been observed the approaches which involve encryption of the video data post the same has been encoded is the most efficient and scalable approach towards video encryption. In addition, it also implies that in near future, the proposed algorithms, must be evaluated based on the various categorization of parameters illustrated in this paper.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49622316","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}

{"title":"Applications of Artificial Intelligence in the field of therapies focused on orofacial cleft repair and rehabilitation","authors":"Ranjith Raveendran, Sameera G Nath, P. Suresh","doi":"10.32629/jai.v6i2.681","DOIUrl":"https://doi.org/10.32629/jai.v6i2.681","url":null,"abstract":"Orofacial clefts are common congenital malformations with genetic and environmental risk factors. The management of cleft lip and palate spreads over the course of the child’s development into adulthood. Currently Artificial Intelligence (AI) has gained much popularity in the dental field. AI is of much help in the multidisciplinary management of cleft lip and cleft palate repair starting right from the prenatal period itself. This review focuses on the available documentation in the literature that has thrown light on the recent applications of AI in cleft lip and palate cases.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41832084","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}

{"title":"Hybrid Chaos Particle Swarm Optimization algorithm for smart Cloud Service System based on optimization resource scheduling and allocation","authors":"V. P. Gil Jiménez, A. Al-Jumaily, A. Sali, D. Al-Jumeily","doi":"10.32629/jai.v6i2.652","DOIUrl":"https://doi.org/10.32629/jai.v6i2.652","url":null,"abstract":"To enhance the smart Cloud Service System for diverse user requirements in 5G and other service networks, this study leverages resource utilization and multi-tenancy network slicing operation costs. Specifically, we propose a multi-tenancy network resource allocation strategy based on the Chaos Particle Swarm Optimization (CPSO) algorithm. In a multi-tenancy network (MTN), we lease the wireless spectrum resources of the infrastructure provider’s base station, construct access service slices as network slice services, and offer network access services to users. Introduce detailed formulation of the relationship between MTN and users, represented as a multi-master and multi-slave construct that defines the strategy space and profit function after MTN decision-making. Reverse induction is used to analyze the proposed model, and a distributed iterative algorithm is proposed to obtain the optimal throughput demand of users and the optimal slice cost of MTN. Simulation results demonstrate that the proposed strategy can effectively enhance resource utilization and user satisfaction while reducing energy consumption.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42038919","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}

{"title":"Predication of smart building energy consumption based on deep learning algorithm","authors":"Suqi Wang, E. Zawawi, Qi Jie Kwong, Rui Wang, Junya Deng","doi":"10.32629/jai.v6i2.691","DOIUrl":"https://doi.org/10.32629/jai.v6i2.691","url":null,"abstract":"Since smart cities have received extensive attention in recent years, and there is no more research data on energy consumption in smart cities. In order to improve the energy consumption prediction accuracy of intelligent buildings, a building energy consumption prediction method based on deep learning algorithm is proposed. By predicting the power consumption, we can analyze whether the energy consumption of the building is reasonable, so as to make further management actions. First of all, the specifies the overall data processing system by using the method of cloud computing, and the overall data is stored and calculated by means of cloud computing. In order to verify the effectiveness of the algorithm in this paper, the algorithm in this paper is applied to commercial buildings, and the data is compared with other algorithms. The results show that, whether compared with the data regression model or with other learning methods, the algorithm in this paper has obvious advantages in prediction accuracy and stability, and can be used to predict the energy consumption of buildings.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43645729","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}

{"title":"Contactless methods to acquire heart and respiratory signals—A review","authors":"Pushparaj Pal, Amod Kumar, G. Saini","doi":"10.32629/jai.v6i1.715","DOIUrl":"https://doi.org/10.32629/jai.v6i1.715","url":null,"abstract":"The vital sign is the most important parameter for the internal health status of any subject in time. Every person is witnessed of COVID-19 global pandemic viruses. The world population has faced this problem globally. Collecting the infected person’s sample data in a contact-based approach may lead to the spreading of the disease. On the other hand, if we use a non-contact-based approach for the collection, it is somehow far better and breaks the chain of virus spreading. This radar-based technique is preferred in non-contact vital sign detection so that any person gets to their health status prior and according to that doctor can diagnose the proper treatment. The radar-based signal is targeted to the subject’s chest. Due to the chest wall displacement main vital sign parameters of the heart and respiration of the individual’s health are being captured. These captured signals are called vital signs, with this it is very helpful that the pre-diagnosis and treatment can be recommended by doctors or health service providers. Some patients due to their movement may be older or children for a long-time use skin irritation or allergy type of problems may face. On the other hand, some patients may be COVID-19 infected disease and burn patients. Hence, it is not possible to connect as both cases are unexpected for the required purpose. For constant and continuous measurement, existing contact-based methods are not fruitful hence non-contact-based approach is adopted. Non-contact-based vital sign detection is preferably due to several problems occurring. This paper presents a state-of-the-art review of recent monitoring methods and techniques for health monitoring in medical fields of operations. These methods and techniques are used as a tool to acquire, visualize and analyze the sampled data collected in any environment either indoor or outdoor.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43021579","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}

{"title":"Artificial neural networks algorithms for prediction of human hair loss related autoimmune disorder problem","authors":"Shabnam Sayyad, Farook Sayyad","doi":"10.32629/jai.v6i2.606","DOIUrl":"https://doi.org/10.32629/jai.v6i2.606","url":null,"abstract":"In this study, artificial neural networks (ANNs) are being used to diagnose hair loss in patients. An autoimmune condition known as Alopecia Areata (AA) results in hair loss in the affected area. The most recent figures from throughout the world show that AA affects 1 in 1000 persons and has a 2% incidence rate. Based on the look of photographs with healthy hair in the dataset, machine learning techniques were employed to classify the conditions. Before making predictions, each of these ANNs algorithms creates a prediction model using pictures of healthy hair. The aim of this study is to evaluate the accuracy of neural networks for alopecia detection in human subjects. The study presents a classification framework for distinguishing between healthy hairs (HHs) and Alopecia Areata (AA). The framework incorporates Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement and segmentation techniques to enhance the quality of the images. Additionally, Data Augmentation (DA) is employed to generate additional data and improve the precision of the proposed framework. To extract features from the images, two powerful techniques are utilized. The Visual Geometry Group (VGG), which consists of very deep convolutional networks designed for large-scale image recognition, is employed. VGG networks have proven to be effective in learning complex features directly from data, eliminating the need for manual feature extraction. Additionally, a Convolutional Neural Network (CNN), a deep learning network architecture specifically designed for image processing tasks, is employed. To create a machine learning model for classification, the Support Vector Machine (SVM) approach is utilized. SVM is a widely used algorithm in supervised learning, capable of solving both classification and regression problems. Its versatility and effectiveness make it a suitable choice for the classification task in this study. By combining the CLAHE enhancement, segmentation, data augmentation, feature extraction using VGG and CNN, and classification using SVM, the proposed framework aims to accurately classify HHs and AA cases.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43296258","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}

{"title":"Multidisciplinary research approach in advancement of science & technology","authors":"Pushparaj Pal, Amod Kumar, G. Saini","doi":"10.32629/jai.v6i2.742","DOIUrl":"https://doi.org/10.32629/jai.v6i2.742","url":null,"abstract":"<p>N/A</p>","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46528169","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}