Scalable Computing-Practice and Experience最新文献

{"title":"Using Machine Learning Algorithms to Design Personalized Exercise Programs for Health and Wellness","authors":"Yan Lu","doi":"10.12694/scpe.v24i3.2340","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2340","url":null,"abstract":"The research paper showcases an elaborate study of machine learning, which is used in healthcare or medical platforms and can be used by healthcare professionals to adopt better diagnostic instruments and tools for examining medical issues or images. The paper highlights that a machine learning algorithm can be utilized in X-rays or MRI scans to examine disease and health issues. This paper will also discuss how this algorithm can help healthcare professionals, doctors, and nurses make accurate diagnoses for better services and patient outcomes. One of the major advantages of using the secondary research method in the following research is the abundance of the literature. All the data being used here are previously collected and evaluated with the result, and using these will increase the impact of the study overall. This method saves resources, including money, time, and manpower. This research method allows the researcher to build new knowledge and draw new conclusions based on existing expertise and knowledge. The chosen research philosophy is the Interpretivism research philosophy. The chosen research approach here is the inductive research approach. The chosen research design for this study is exploratory. All these help the research to achieve its objectives and reach the proposed goal of this research.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136072255","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":"Application of improved Apriori Algorithm in Innovation and Entrepreneurship Engineering Education Platform","authors":"Xuanyuan Wu, Yi Xiao, Anhua Liu","doi":"10.12694/scpe.v24i3.2307","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2307","url":null,"abstract":"The implementation of innovation and entrepreneurship education is inseparable from professional education, so it is important for the rich data in the education platform to mine the connection between professional courses and between grades and courses. The study of association rule algorithm based on education data mining improves the time performance efficiency and accuracy of Apriori algorithm. The study improves the time efficiencies of Apriori algorithm by maintaining Map table and splitting transaction database; the accuracy is improved by using mixed criteria to measure the accuracy and filtering deformation rules based on the inference of confidence. The results of the validation of the time efficiency of the algorithm show that the running time of the improved algorithm in solving frequent itemsets is improved by about 93.86%, 92.48% and 92.76%, respectively, compared with the other three algorithms. The running time of the algorithm for generating frequent itemsets of all orders is about 91.35 ms, which is 66.13% and 83.72% better than the Apriori algorithm and AprioriTid algorithm, respectively. The mining results of student examination data based on the education platform are reasonable and practical, which are of good practical significance for the innovation and entrepreneurship engineering education platform to develop training plans and improve teaching quality.is assumed.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136072286","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":"Deep Learning-Based Education Decision Support System for Student E-learning Performance Prediction","authors":"Sudha Prathyusha Jakkaladiki, Martina Janečková, Jan Krunčík, Filip Malý, Tereza Otčenášková","doi":"10.12694/scpe.v24i3.2188","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2188","url":null,"abstract":"Information Technology (IT) and its advancements change the education environment. Conventional classroom education has been transformed into a modernized form. Education field decision-makers are always searching for new technologies that provide fast solutions to support Education Decision Support Systems (EDSS). There is a significant need for an effective decision support system to utilize student data which helps the university in making the right decisions. The Electronic learning system (e-learning) provides a live forum for faculties and students to connect with learning portals and virtually execute educational activities. Even though these modern approaches support the education system, active student participation still needs to be improved. Moreover, accurately measuring student performance using collected attributes remains difficult for parents and teachers. Therefore, this paper seeks to understand and predict student performance using effective data processing and a deep learning-based decision model. The implementation of EDSS starts with data preprocessing, Extraction-Transformation-Load (ETL), a data mart area to store the extracted data with Online Analytical Processing (OLAP) processing, and decision-making using Deep Graph Convolutional Neural Network (DGCNN). The statistical evaluation is based on the student dataset from the Kaggle repository. The analyzed results depict that the proposed EDSS model on an independent data mart with efficient decision support and OLAP provides a better platform to make academic decisions and help educators to make necessary decisions notified to the students.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136071894","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":"Analysis, Prediction and Classification of Skin Cancer using Artificial Intelligence - A Brief Study and Review","authors":"Madhavi Latha Pandala, None S. Periyanayagi","doi":"10.12694/scpe.v24i3.2241","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2241","url":null,"abstract":"World Health Organization (WHO) records that skin cancer has vigorously affected people in recent decades. Worldwide, many people are affected by skin cancer, and its affected count will increase yearly. Hence, skin cancer has become a threatening disease. Skin cancer prediction at an earlier time is becoming the higher priority and most challenging task worldwide. A computer-based diagnosis is needed to perform the automatic prognosis of skin cancer. It assists dermatologists in many ways, including the prediction of skin cancer at the earlier stages, easy to diagnose and effective. Nowadays, artificial intelligence based machine learning approaches have been implemented for an early prediction of cancer in the skin through medical images. This paper is focused on a detailed, comprehensive review of skin cancer analysis, forecast, and algorithmic-based procedures for classifying skin diseases. Moreover, this review paper focused on various stages of algorithm approaches for skin tumor detection like pre-processing data, segmenting data, feature selection, and disease classifier. This detailed review of neoplasm diseases like cancer on the skin is done based on machine and deep learning algorithms to help further research.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136072013","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":"Application of Improving ABC in Cold Chain Low Carbon Logistics Path Planning","authors":"Xiazu Bai","doi":"10.12694/scpe.v24i3.2357","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2357","url":null,"abstract":"The market has set higher efficiency and environmental requirements for cold chain logistics, and path planning plays an important role. This study proposes a low-carbon cold chain logistics path planning model based on an improved artificial bee colony algorithm (this paragraph refers to ”fusion algorithm”). The study first establishes the fusion algorithm. Then, in response to the shortcomings of this algorithm, the artificial fish swarm algorithm and genetic algorithm are used to improve it. The final results express that the shortest distance for solving Eil51 using this algorithm is 421.38, the longest distance is 448.58, and the average distance is 439.34; The shortest distance for solving Ulysses22 is 72.46, the longest distance is 73.63, and the average distance is 72.84. The average convergence times for Eil51 and Ulysses22 are 133.57 and 7.86, and the optimal performance ratios for relative error are 0.0076 and 0.0051. The robust performance ratios are 0.0362 and 0.0117. The optimal total cost solution and the average value for solving the relevant distribution problem are 47,894.6 yuan and 48,562.7 yuan, respectively. In summary, the model proposed in the study has good application effects in cold chain low-carbon logistics path planning, and has a certain promoting effect on the development of cold chain logistics.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136071685","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":"Efficient Net-based Transfer Learning Technique for Facial Autism Detection","authors":"Tariq Saeed Mian","doi":"10.12694/scpe.v24i3.2233","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2233","url":null,"abstract":"Autism Spectrum Disorder is a neurological disorder in which an individual faces life-long effects in communication and interaction with others. Nowadays, the Autism Spectrum disorder ratio is increasing drastically more than ever before. Autism can be identified at all developmental levels as a ”behavioural condition,” and its symptoms often arise between the ages of two and four. The ASD issue starts during puberty and persists through adolescence and adulthood. Children with ASD use both nonverbal and verbal behaviour to communicate, and they struggle with joint attention and social reciprocity. Children with autism are frequently socially isolated as a result of these problems. Through very expensive and time-consuming screening exams, autism spectrum features can be identified. As one of the possible mirrors of the brain, children’s faces can be utilised as a biomarker and as a quick and convenient technique for the early identification of ASD. An effective, genuine, and automatic method of face-based spectrum disorder identification is required. In this study we compare the transfer learning approach used for autism identification with the convolutional neural network (CNN)-based efficient-net strategy to identify autistic children using facial images. We used an open-source Kaggle dataset and evaluated the model performance in terms of accuracy, confusion matrix, precision, recall, and F1 measure. Efficient shows an accuracy of 97% on the benchmark dataset and beats the baseline technique of transfer learning-based approaches. This study can be used to help medical professionals validate their initial screening procedures for finding youngsters with ASD disease.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136071903","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":"Big Data in Healthcare - A Comprehensive Bibliometric Analysis of Current Research Trends","authors":"Aijaz Reshi, Arif Shah, Shabana Shafi, Majid Hussain Qadri","doi":"10.12694/scpe.v24i3.2155","DOIUrl":"https://doi.org/10.12694/scpe.v24i3.2155","url":null,"abstract":"The primary purpose of this study is to perform a comprehensive bibliometric analysis of research landscape of big data in healthcare. Big data as a significant technology used in healthcare during the past decade has led to the exponential growth in scientific literature. This study is focused on analysis of many crucial bibliometric indicators such as, overall research output, author productivity, institutional productivity, country wise productivity, collaboration analysis, research trends along with a thematic focus of research output in big data and healthcare. The analysis has been performed on 2294 research articles published in 1018 publication sources from SCOPUS and Web of Science databases. The initial results of the study performed from year 2012 reveals that in the first year 6 research articles were published in the given domain. Then every year the growth of published articles in the field was exponential, however years 2019 to 2021 were the most productive and incremental in terms of number of publications. The analysis results of the study present the performance analysis of research production in terms of annual scientific production, most globally cited articles, author’s production over the time, most productive countries, and most relevant affiliations. In addition, the science mapping analysis including the indicators such as, keyword Co-occurrence, Thematic Mapping, Most Relevant Authors, annual source distribution, and collaboration Network analysis has been presented. The study delivers expedient contribution to the field of study by noticeably offering comprehensive analysis results regarding research hotspots and trends, thematic emphasis, and future direction of research in the field. These outcomes will aid researchers in big data and healthcare in planning and designing the research and the challenges and opportunities needed to be explored.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136072017","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":"Application of Association Rule Mining Algorithm based on 5G Technology in Information Management System","authors":"Juan Gao, Zidi Chen","doi":"10.12694/scpe.v24i2.2150","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2150","url":null,"abstract":"In this paper, an application method of association rule mining algorithm based on 5G technology in information management system is proposed to solve the problems of long running time and low processing efficiency in traditional financial information processing system. The association rule mining algorithm's employment in information management systems is the main topic of this research study, which is based on 5G technology. The efficiency and efficacy of information management systems have a lot of room to grow with the introduction of 5G. Large datasets may be mined for patterns and associations using the potent approach known as association rule mining. We want to improve the performance of information management systems by fusing association rule mining with the capabilities of 5G technology. The experimental findings indicate that in the first group of trials, the traditional system’s time for information mining is identical to that of the developed system, which is around one minute. The typical system's time to mine financial information, however, steadily grows with the amount of experimental data. The difference between the two is most obvious in the sixth experiment. Because the design system can delve deeply into the financial information, the overall information mining time of the financial information management system based on the association rule mining algorithm of the design is shorter. It is confirmed that the system for automatically processing financial information described in this study has a high level of processing accuracy and a positive processing outcome.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73234313","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":"Research Highlight Generation with ELMo Contextual Embeddings","authors":"Tohida Rehman, Debarshi Kumar Sanyal, S. Chattopadhyay","doi":"10.12694/scpe.v24i2.2238","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2238","url":null,"abstract":"With the advent of digital publishing and online databases, the volume of textual data generated by scientific research has increased exponentially. This makes it increasingly difficult for academics to keep up with new breakthroughs and synthesise important information for their own work. Abstracts have long been a standard feature of scientific papers, providing a concise summary of the paper's content and main findings. In recent years, some journals have begun to provide research highlights as an additional summary of the paper. The aim of this article is to create research highlights automatically by using various sections of a research paper as input. We employ a pointer-generator network with a coverage mechanism and pretrained ELMo contextual embeddings to generate the highlights. Our experiments shows that the proposed model outperforms several competitive models in the literature in terms of ROUGE, METEOR, BERTScore, and MoverScore metrics.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86514285","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":"Information Monitoring of Transmission Lines Based on Internet of Things Technology","authors":"Wei-hao Du, Jiaying Wang, Guozhu Yang, Sijia Zheng, Yajie Zhao","doi":"10.12694/scpe.v24i2.2145","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2145","url":null,"abstract":"To solve the problem of difficult real-time monitoring of current transmission lines, this article proposes an information-based monitoring system for transmission lines based on Internet of Things technology. The system utilizes the characteristics of strong scalability, good fault tolerance, low power consumption, and low cost of the Internet of Things. Taking the ultra-low power consumption MSP430 microcontroller and CC2430 radio frequency module as the core, a line monitoring system based on the Internet of Things is designed. The proposed design uses ZigBee wireless sensor network technology which is powered by solar energy. The collection, transmission, processing and judgment of various environmental parameters of the line are realized. The data information is transferred to the monitoring center of the upper computer through GPRS. When there is an abnormality, it can send a mobile phone short message to the person in charge to feedback the abnormal content in time. The distribution network's load symmetry allowed for the development of several locating procedures. For the three-phase symmetric scheme, the fault location approach based on line supply characteristics was employed, and for the three-phase asymmetric scheme, the fault location technique based on line impedance is proposed. One of the most vital uses for the Internet of Things is in the mitigation of power transmission line failures and disasters. Improved power transmission dependability, less financial loss, and fewer power outages are all possible thanks to the Internet of Things' cutting-edge sensing and communication technology. This research introduced the use of IoT in online monitoring system of electricity transmission line with a focus on the characteristics of the construction and development of smart grid. The results indicated that the system's highest temperature difference is 0.31 C, while the maximum humidity difference is 1.38%. The system increases the safety and manageability of electricity transmission while also fostering the widespread adoption and technical integration of the smart grid and the Internet of Things.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79381823","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}