2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)最新文献

{"title":"Supporting End User Comprehension in Intelligent Decision Support Systems Using Data Visualisation Techniques","authors":"Maneerat Rumsamrong, A. Chiou","doi":"10.1109/CSDE53843.2021.9718413","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718413","url":null,"abstract":"This project explores the use of data visualisation techniques to render the outcome of an inference process using graphics, symbolic and schemas in stylised pictograms that supports understanding. The example demonstrated in this paper is a continuation of CRISIS-Expert, an intelligent decision support system that accepts multiple input of various data types and then generate an outcome which is further rendered into symbols that within reason is, understandable by the end user.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124818728","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":"Automated passive measures: the next step in reducing the carbon footprint of our buildings","authors":"Nishita Ramessur, M. Gooroochurn","doi":"10.1109/CSDE53843.2021.9718458","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718458","url":null,"abstract":"Passive design is well acclaimed to be a key cornerstone for the design of green buildings, especially when relating to their energy performance and carbon footprint. However, due to the vagaries in the prevailing climate at a project site, passive measures are limited in their ability to ascertain an optimal use of natural resources available at the project site, while also working under certain circumstances against the provision of adequate indoor environmental conditions. The purpose of this project is to showcase the automation of passive measures by an automated daylighting and shading device for vertical glazed surfaces, which has the main objective of increasing daylight in a space while preventing direct sunlight from penetrating the space. During the year and throughout the day the solar azimuth and elevation is constantly changing which makes it of utmost importance for the device to be able to modulate and adapt to the changing solar azimuth and elevation angles. As the position of the sun changes throughout the day and over the course of the whole year; the blinds and shading equipment often have to be adjusted manually by the user at different times of the day. If this is not done, direct sunlight may enter the building and heat the space which results in a higher cooling load. Moreover, direct sunlight can cause glare problems. The proposed mechatronics system orients itself automatically based on the solar azimuth and elevation angles with respect to the particular orientation of the façade it is installed on. It also monitors the ambient light levels in the room and controls the artificial light accordingly. The system can be used in two modes; the overhang and the louver position, hence providing an all-in-one external shading device for glazed surfaces to deal with low, medium and high angle sun, and hence brings the much-needed flexibility to control heat gains through glazing. Research findings show that modulating the heat gains admitted through the glazing can have a significant influence on influencing the indoor thermal conditions, hence lending credit to the proposed system. It is also equipped with a WIFI module and a user interface to allow the user to control the system manually. The implementation and testing of the prototype provided conclusive results for the daylight monitoring, manual control and automatic control.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124854185","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 Preliminary Study of Convolutional Neural Network Architectures for Breast Cancer Image Classification","authors":"S. Khairi, M. Bakar, M. A. Alias, S. A. Bakar, C. Liong","doi":"10.1109/CSDE53843.2021.9718500","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718500","url":null,"abstract":"Breast cancer is one of the most common cancer with high mortality rate worldwide. Classification of breast cancer images is an important clinical issue related to accurate early diagnosis and treatment plan preparation. However, it is still uncertain which model is effective for classifying breast cancer images. For medical image analysis, deep learning models have proved to yield excellent outcomes in classification tasks. Hence, this study compared the performance of the most common deep learning models which is convolutional neural networks for breast cancer classification on the histopathology images. A total of 7,909 images were extracted from BreakHis database that comprised of 2,480 benign and 5,429 malignant samples. The images are of four different magnifications which are 40X, 100X, 200X and 400X. This study focused on comparing the state-of the-art architectures, namely, AlexNet, GoogleNet and ResNet 18 to evaluate the performance of model in classifying the breast cancer images. The models were examined through a multiclass classification analysis in terms of accuracy, sensitivity, specificity and F-Score. The experimental results indicated that ResNet18 was the most effective method with an accuracy of 94.8% with 70 min 31 sec time taken for computation. The research findings are expected to facilitate the radiologist in classifying the breast cancer images and hence planning proper treatment for patients.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121069068","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 Conceptual Framework to Enhance Business Performance using Social Media: An Australian Context","authors":"Meena Jha, Suresh Khatiwada, Lily D Li","doi":"10.1109/CSDE53843.2021.9718492","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718492","url":null,"abstract":"Social media has a capacity to offer online communication replacing physical proximity, and has completely transformed the way businesses are done today in the digital world. Using social media for marketing is very much cost-effective for reaching out to a geographically diverse range of customer base. Business performances can be enhanced by reaching out to a wider range of prospective customers and satisfying the need of the existing customers. Business performance requires tracking business metrics and measurable key performance indicators to show the progress of business goals. Social media is a great platform to track key business performance indicators for Small and Medium Enterprises (SMEs) in a cost-effective manner. However, in Australia, only 33% of SMEs are using social media and hence are not benefitted from the advantages social media provides in improving business performances. This paper presents a literature review on the use of social media, social media analytics (SMA), social media marketing (SMM), and how they can be used by SMEs to enhance their business performances. This study introduces a new conceptual framework assisting SMEs in developing their presence on social media and using social media to enhance their business performances based on social media use, social media analytics, and social media marketing. The conceptual framework also aims to enhance the technical, operational, conceptual, and relationship competency of SMEs.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122402883","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":"Enumerating Minimal Generators from Closed Itemsets – Toward Effective Compression of Negative Association Rules","authors":"K. Iwanuma, Kento Yajima, Yoshitaka Yamamoto","doi":"10.1109/CSDE53843.2021.9718380","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718380","url":null,"abstract":"Negative association rules are valuable and essential for expressing various latent properties which hide in big data. The number of valid negative association rules, however, always becomes so huge, thus an effective compression method of the set of negative rules is quite important. Minimal generators are very useful for compressing the set of valid negative rules. In this paper, we study several efficient algorithms for enumerating minimal generators from given closed itemsets. Especially we propose a novel enumeration algorithm which does not use any support computation, but uses an eager hash search in a top-down tree search. We show experimental results for evaluating our enumeration algorithms, and confirm very good performance of the enumeration method without support computation.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126142784","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 Machine Learning Approach for Predicting Therapeutic Adherence to Osteoporosis Treatment","authors":"Ggaliwango Marvin, Md. Golam Rabiul Alam","doi":"10.1109/CSDE53843.2021.9718416","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718416","url":null,"abstract":"Osteoporosis is a great disability burden with an expected cost increase of almost 50% by 2025. Due to its long term treatment, 50–70% of the patients withdraw from their osteoporosis medications within the first year of initiation. This necessitates an urgent need for improved osteoporosis and pharmacologic management tools most especially for pregnant women, postmenopausal women and the elderly to ensure therapeutic adherence of the patients during treatment. In this paper, we developed and tested accuracy of Machine Learning Models for predicting therapeutic adherence of patients to enable health professionals to compatibly decide on the therapeutic treatments and approaches for osteoporosis treatment and pharmacologic management of their patients. We were the first to develop and test Machine Learning Models for Predicting Therapeutic Adherence treatments. The ML Model accuracy results are summarized as classical metrics where the ExtraTree Model exhibited the highest accuracy of 100%, 85.0%, 94.5% on the training, testing and overall dataset respectively using Synthetic Minority Over-sampling Technique Support Vector Machine Learning (SMOTE-SVM).","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126596327","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":"Older Adults and Digital Game Trends, Challenges and Benefits","authors":"Nurul Farinah Mohsin, S. K. Jali, Mohamad Imran Bandan, N. Jali, A. Jupit","doi":"10.1109/CSDE53843.2021.9718445","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718445","url":null,"abstract":"The usage of digital games is not limited to entertainment purposes. It can be used in healthcare and social science studies focusing on older adults as the main subject. The objectives of this review are to identify the challenges related to older adults, the benefits they gained using the digital game, and the method used in previous studies. There are 27 articles reviewed based on keywords searched in Scopus database. These studies are evaluated regarding their approaches, challenges and benefits of digital games highlighted in their studies. Finally, several improvable points in the current approaches are highlighted and suggestions are provided as further works.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122261297","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":"Predicting Effectiveness of Marketing through Analyzing Emotional Context in Advertisement using Deep Learning","authors":"Sheikh Mohammad Arafat, Rifatul Islam, Ishraque Arefin Rafi, Md. Rashedul Islam, Md. Golam Rabiul Alam","doi":"10.1109/CSDE53843.2021.9718411","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718411","url":null,"abstract":"In this modern age, marketing strategy is becoming a new challenge for both the local and worldwide companies. Basically, both the local and global brands are trying to increase their product selling rate and grab the attention of buyers. Therefore, they are promoting advertisements on every media platform. However, they are not aware of the utilization of emotional states in audio or video advertisements. Hence, the effectiveness of marketing is decreasing day by day. Therefore, we lead this study to recognize a successful advertisement and identify the rate of the emotional states which make a good impact in people's mind to purchase the product. To find out the emotional states, we have implemented deep learning and supervised machine learning algorithms as well as feature extraction methods such as LSTM-RNN, XGBOOST, Naive Bayes, Multiple Linear Regression, MFCC, Zero-Crossing Rate, Power Spectral Density and Short Time Energy. After that, we have evaluated the rate of the emotional states to Figure out the liking and purchase intent which makes an advertisement successful.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131763663","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":"Identification and Prioritisation of Electricity Driving Factors for Power Supply Sustainability: A Case of Developing and Underdeveloped Nations","authors":"Hanif Auwal Ibrahim, M. Ayomoh","doi":"10.1109/CSDE53843.2021.9718450","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718450","url":null,"abstract":"The demand for electricity is on the rise in most developing and underdeveloped countries. Amongst other reasons, this is also largely premised on the recent migration to a more dominating virtual world of transactions and general systemic operations as a result of the current pandemic. The rapid increase in the demand for electricity has left a huge supply deficit. The booming electricity demand is attributed to various driving factors. This paper has focused on identification and prioritisation of factors that drive power availability and sustainability in developing economies. The Hybrid Structural Interaction Matrix (HSIM) was deployed to implement the weight based prioritisation model with hierarchical structural layout of the interacting factors. This would guide and enable policy makers and researchers to make a more informed decision on addressing issues of growing electricity demand and inadequate supply via the consideration of weighted prioritised driving factors for optimal allocation of resources.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133745252","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":"Investigating Hourly Global Horizontal Irradiance Forecasting Using Long Short-Term Memory","authors":"Asma Z. Yamani, Sarah N. Alyami","doi":"10.1109/CSDE53843.2021.9718423","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718423","url":null,"abstract":"Solar energy is one of the cleanest renewable energy sources available. Several studies proposed models for Global Horizontal Irradiance (GHI) forecasting, which showed that deep learning models such as Long Short-Term Memory (LSTM) could be successful at this task. However, these models needed relatively large amounts of training data to reach excellent accuracy, which may be challenging for locations where only limited data are available. This experiment aims to determine the minimum amount of historical data needed by researchers to forecast GHI one hour ahead, using a deep learning LSTM model whilst maintaining an excellent accuracy range measured by nRMSE. To achieve this objective, we trained an LSTM model with different amounts of training data, starting with five years of training data then gradually reducing the amount by one year in each trial until using only one year of training data. The accuracy of the model in terms of nRMSE is reported in each trial. The experiments were conducted using historical GHI and meteorological data from three locations in Saudi Arabia. It is concluded that it is possible for an LSTM model to achieve excellent GHI forecasting accuracy (nRMSE<10%) using only two years of training data.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133959123","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}