Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497207
L. M. Choong, Wei Kuang
Advance data analytics and machine learning have affected almost every industry and area of scientific research, including engineering. Although limited literature of Machine Learning in optics engineering are found, Machine learning adoption has been valuable and garners a lot of interest in this field [1][2], and the rate of research in this area is growing rapidly [3]. In fiber optic transmission system, an optical transceiver is a core element, responsible for converting electrical signal to light pulses and vice versa. It comprises of housing, optoelectronic devices and PCBA, it has to undergo various characterization and tests at different stages of the manufacturing processes. Optical transceiver characterization is a very complex process with many sub-processes and parameters within those sub-processes which can lead to difficulties using traditional analytics approach. Usually, a tuning process only utilizes key parametric at the point of characterization, it may not be optimized taking considerations of other external factors e.g. product variants, components, testers, software used etc. Machine Learning shines when there are a lot of input parameters to be optimized [1]. This paper describes the application of machine learning techniques in the transmitter characterization algorithm of a high speed optical transceiver module to enhance the tuning algorithm and also improving throughput.
{"title":"Advanced Data Analytics and Supervised Machine Learning in Optics Engineering Analysis","authors":"L. M. Choong, Wei Kuang","doi":"10.1109/ICCOINS49721.2021.9497207","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497207","url":null,"abstract":"Advance data analytics and machine learning have affected almost every industry and area of scientific research, including engineering. Although limited literature of Machine Learning in optics engineering are found, Machine learning adoption has been valuable and garners a lot of interest in this field [1][2], and the rate of research in this area is growing rapidly [3]. In fiber optic transmission system, an optical transceiver is a core element, responsible for converting electrical signal to light pulses and vice versa. It comprises of housing, optoelectronic devices and PCBA, it has to undergo various characterization and tests at different stages of the manufacturing processes. Optical transceiver characterization is a very complex process with many sub-processes and parameters within those sub-processes which can lead to difficulties using traditional analytics approach. Usually, a tuning process only utilizes key parametric at the point of characterization, it may not be optimized taking considerations of other external factors e.g. product variants, components, testers, software used etc. Machine Learning shines when there are a lot of input parameters to be optimized [1]. This paper describes the application of machine learning techniques in the transmitter characterization algorithm of a high speed optical transceiver module to enhance the tuning algorithm and also improving throughput.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121133074","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497229
Onny Fitriana Sitorus, Afif Abdurrozak, Wan Fatimah Wan Achmad, Meyta Dwi Kurniasih, M. H. Hasan
Society 5.0 is associated not only with technological advances, but doing system updates in their respective fields. Respondents obtained were 37 in Universiti Teknologi Petronas (UTP). This study aims to analyze the effectiveness of character value in blended learning. The research model used is a quantitative method with a frequency histogram based on the Likert scale from (1 never to 5 always). This paper describes how to see the connection between one character value indicator and another. This result imply that the character analysis value in blended learning methods in teaching has received positive feedback from students, the average mean (responsibility = 81.08; independently = 85.63; discipline = 74.86; curiosity = 74.32; cooperation = 85.09).
{"title":"Analysis of Effectiveness Character Value in Blended Learning","authors":"Onny Fitriana Sitorus, Afif Abdurrozak, Wan Fatimah Wan Achmad, Meyta Dwi Kurniasih, M. H. Hasan","doi":"10.1109/ICCOINS49721.2021.9497229","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497229","url":null,"abstract":"Society 5.0 is associated not only with technological advances, but doing system updates in their respective fields. Respondents obtained were 37 in Universiti Teknologi Petronas (UTP). This study aims to analyze the effectiveness of character value in blended learning. The research model used is a quantitative method with a frequency histogram based on the Likert scale from (1 never to 5 always). This paper describes how to see the connection between one character value indicator and another. This result imply that the character analysis value in blended learning methods in teaching has received positive feedback from students, the average mean (responsibility = 81.08; independently = 85.63; discipline = 74.86; curiosity = 74.32; cooperation = 85.09).","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129346752","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497178
Abeer Abdullah Abdulmajid Mohammed, D. D. Dominic
Environmental issues are a big concern for all human beings. Environmental Sustainability Awareness can play an essential role in reducing those issues. Moreover, technologies, such as social media, can contribute to rising Environmental Sustainability Awareness if used effectively. Higher education Institutes are an important sector that can educate and increase students, staff, and other stakeholders’ awareness. Therefore, the objective is to study the impact of Social Influence on using Social Media for Environmental Sustainability Awareness in Higher Education Institutes (HEIs) in Malaysia. This research is quantitative. Data will be collected using a questionnaire. Participants are HEIs stakeholders. A simple random sample method will be used. Measures will be identified. And relationships will be evaluated. The analysis will be done using Statistical Package for the Social Sciences (SPSS) and Structural Equation Modeling (SEM). This study is going to contribute to the literature through the framework. Also, report the social influence in using social media for environmental awareness. And can be used to enhance Environmental policies. It will also contribute toward achieving Sustainable development.
{"title":"Social Influence on the Use of Social Media Towards Environmental Sustainability Awareness in HEI","authors":"Abeer Abdullah Abdulmajid Mohammed, D. D. Dominic","doi":"10.1109/ICCOINS49721.2021.9497178","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497178","url":null,"abstract":"Environmental issues are a big concern for all human beings. Environmental Sustainability Awareness can play an essential role in reducing those issues. Moreover, technologies, such as social media, can contribute to rising Environmental Sustainability Awareness if used effectively. Higher education Institutes are an important sector that can educate and increase students, staff, and other stakeholders’ awareness. Therefore, the objective is to study the impact of Social Influence on using Social Media for Environmental Sustainability Awareness in Higher Education Institutes (HEIs) in Malaysia. This research is quantitative. Data will be collected using a questionnaire. Participants are HEIs stakeholders. A simple random sample method will be used. Measures will be identified. And relationships will be evaluated. The analysis will be done using Statistical Package for the Social Sciences (SPSS) and Structural Equation Modeling (SEM). This study is going to contribute to the literature through the framework. Also, report the social influence in using social media for environmental awareness. And can be used to enhance Environmental policies. It will also contribute toward achieving Sustainable development.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129203790","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497196
Miza Shazwani Kamarulzaman, N. H. Hassan, N. A. A. Bakar, N. Maarop, Ganthan Narayana Samy, N. Aziz
With the rapid digitalisation of the economy nowadays, it is becoming increasingly important for organisations to embrace digital innovation. The emergence of blockchain technology illustrates digital innovation's disruptive impact and, at the same time, poses challenges to organisations. This study has been assisting government organisations in blockchain adoption that is reflected in far-reaching measures in terms of technology, organisation, and environment. Based on this framework, this research builds on an empirical study to explore the technology, organisation, environment and trust adoption of blockchain technology. This proposed framework aims to assist the government in developing blockchain adoption based on the baseline theory models, which are Technology, Organization, Environment (TOE), emphasis on trust and other blockchain adoption theories. This research uses a conventional literature review to identify the factors influencing blockchain adoption. Preliminary investigation has been conducted prior to develop the proposed framework. The interview session was conducted to verify the availability of the blockchain technology in government organisations. The proposed conceptual model can be valuable to government organisations and may assist those government organisations which consider blockchain technology in the organisation to be more secure.
{"title":"Factors Influencing Blockchain Adoption in Government Organization : A Proposed Framework","authors":"Miza Shazwani Kamarulzaman, N. H. Hassan, N. A. A. Bakar, N. Maarop, Ganthan Narayana Samy, N. Aziz","doi":"10.1109/ICCOINS49721.2021.9497196","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497196","url":null,"abstract":"With the rapid digitalisation of the economy nowadays, it is becoming increasingly important for organisations to embrace digital innovation. The emergence of blockchain technology illustrates digital innovation's disruptive impact and, at the same time, poses challenges to organisations. This study has been assisting government organisations in blockchain adoption that is reflected in far-reaching measures in terms of technology, organisation, and environment. Based on this framework, this research builds on an empirical study to explore the technology, organisation, environment and trust adoption of blockchain technology. This proposed framework aims to assist the government in developing blockchain adoption based on the baseline theory models, which are Technology, Organization, Environment (TOE), emphasis on trust and other blockchain adoption theories. This research uses a conventional literature review to identify the factors influencing blockchain adoption. Preliminary investigation has been conducted prior to develop the proposed framework. The interview session was conducted to verify the availability of the blockchain technology in government organisations. The proposed conceptual model can be valuable to government organisations and may assist those government organisations which consider blockchain technology in the organisation to be more secure.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114854360","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497198
S. Teoh, Vooi Voon Yap, H. Nisar
This paper presents an improved convolutional neural network (CNN) architecture for accurate visual crowd counting in crowd images. Comprehensive analysis on the performance and inference speed of the network model are also presented. Multi-column convolutional neural network (MCNN) for visual crowd counting through predicted density map is widely used in previous works, however this method has limitation in predicting a quality density map. Instead, the proposed network is constructed by using the powerful CNN layers, dense layers, and one regressor node with whole image-based inference. Therefore, it is less computationally intensive and inference speed can be increased. Experiments have been conducted on Mall dataset. Moreover, benchmarking on different CNN architectures have been conducted. The proposed network shows promising counting accuracy and reasonable inference speed against the existing state-of-art approaches.
{"title":"Fast Regression Convolutional Neural Network for Visual Crowd Counting","authors":"S. Teoh, Vooi Voon Yap, H. Nisar","doi":"10.1109/ICCOINS49721.2021.9497198","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497198","url":null,"abstract":"This paper presents an improved convolutional neural network (CNN) architecture for accurate visual crowd counting in crowd images. Comprehensive analysis on the performance and inference speed of the network model are also presented. Multi-column convolutional neural network (MCNN) for visual crowd counting through predicted density map is widely used in previous works, however this method has limitation in predicting a quality density map. Instead, the proposed network is constructed by using the powerful CNN layers, dense layers, and one regressor node with whole image-based inference. Therefore, it is less computationally intensive and inference speed can be increased. Experiments have been conducted on Mall dataset. Moreover, benchmarking on different CNN architectures have been conducted. The proposed network shows promising counting accuracy and reasonable inference speed against the existing state-of-art approaches.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124222092","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497192
Gary Foo Xiang G, K. Savita, Maythem K. Abbas, Jebul Suroso, S. Widyaningsih, Sri Suparti
Gamification understood as the use of game design elements in the other contexts for the purpose of engagement has become a hot topic in years. The role of gamification in promoting learner’ learning has been investigated empirically by many scholars. To date, mixed results about the effectiveness of gamification have been reported, and researchers frequently argue that the inappropriateness of certain techniques may have contributed to these mixed findings, especially toward disaster subject. Relatively little research that stated gamification in the disaster is an effective approach to learn the subject. Moreover, disasters and emergencies have been increasing all over the world. Disaster mitigation measures are those that eliminate or reduce the impacts and risks of hazards through proactive measures taken before an emergency or disaster occurs. Today, with technological advancement, acquiring knowledge and its application is regarded as the only effective way to prevent disasters or reducing its effects. The research also aimed to review the importance of gamification integration to support the existing education and the effect of different methods of education on disaster mitigation among Indonesia community. In this regard, having the gamification to disaster educational is possible for people to acquire and increase the level of knowledge, which in return, increases the motivation and engagement of the learner. The results showed that gamification integration positively affects learner’ learning compare to existing traditional classroom method.
{"title":"The Development of the Educational Contents for Disaster Mitigation in Indonesia","authors":"Gary Foo Xiang G, K. Savita, Maythem K. Abbas, Jebul Suroso, S. Widyaningsih, Sri Suparti","doi":"10.1109/ICCOINS49721.2021.9497192","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497192","url":null,"abstract":"Gamification understood as the use of game design elements in the other contexts for the purpose of engagement has become a hot topic in years. The role of gamification in promoting learner’ learning has been investigated empirically by many scholars. To date, mixed results about the effectiveness of gamification have been reported, and researchers frequently argue that the inappropriateness of certain techniques may have contributed to these mixed findings, especially toward disaster subject. Relatively little research that stated gamification in the disaster is an effective approach to learn the subject. Moreover, disasters and emergencies have been increasing all over the world. Disaster mitigation measures are those that eliminate or reduce the impacts and risks of hazards through proactive measures taken before an emergency or disaster occurs. Today, with technological advancement, acquiring knowledge and its application is regarded as the only effective way to prevent disasters or reducing its effects. The research also aimed to review the importance of gamification integration to support the existing education and the effect of different methods of education on disaster mitigation among Indonesia community. In this regard, having the gamification to disaster educational is possible for people to acquire and increase the level of knowledge, which in return, increases the motivation and engagement of the learner. The results showed that gamification integration positively affects learner’ learning compare to existing traditional classroom method.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125654213","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497157
Muhammad Zahid bin Hilmi, A. Mahmood, A. Moin, Toni Anwar, S. Sutrisno
Share buyback is a strategy for companies to repurchase their outstanding shares to reduce the number of shares from the open markets. With buyback, it indirectly increases the shares proportion and earning per shares (EPS) of a company. The aim of this study is to investigate the trend of share buyback strategy, and to design a simple prediction model for stock market price movement before initiating any buyback action. This study finds the use of Long Short-Term Memory (LSTM) as prediction algorithm has demonstrated that stock market price movement can be predicted using associated stock indicators, namely MACD and RSI which have an impact to the stock market price movement. The study also finds that the "Open" parameter based on the MAE, MSE and RMSE have been found to be the lowest value as compared to "High", "Low" and "Close" parameters.
{"title":"Share Buyback Prediction using LSTM on Malaysian Stock Market","authors":"Muhammad Zahid bin Hilmi, A. Mahmood, A. Moin, Toni Anwar, S. Sutrisno","doi":"10.1109/ICCOINS49721.2021.9497157","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497157","url":null,"abstract":"Share buyback is a strategy for companies to repurchase their outstanding shares to reduce the number of shares from the open markets. With buyback, it indirectly increases the shares proportion and earning per shares (EPS) of a company. The aim of this study is to investigate the trend of share buyback strategy, and to design a simple prediction model for stock market price movement before initiating any buyback action. This study finds the use of Long Short-Term Memory (LSTM) as prediction algorithm has demonstrated that stock market price movement can be predicted using associated stock indicators, namely MACD and RSI which have an impact to the stock market price movement. The study also finds that the \"Open\" parameter based on the MAE, MSE and RMSE have been found to be the lowest value as compared to \"High\", \"Low\" and \"Close\" parameters.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115462436","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497152
Ibrahim Khan, R. Hussain, M. Sikander, Sheeraz Arif, Muhammad Umair
The world ever increasing energy needs are deeply intervenes with demand appetite and depleting fuels sources. Traditional energy sources are the major cause of the pollution which adversely affects ecology. The global impetus towards alternate is now gaining momentum for eco-friendly energy needs. This research focuses on the performance optimization of solar wind hybrid generation system. In the wake of plethora of research techniques, the challenge of extracting maximum power from photovoltaic panel and wind generated power is yet to be address. Solar power varies due to sporadic environmental conditions so does the output power. In this research, we have investigated the Perturb and Observe (P&O) algorithm for IV and PV curves of photovoltaic cell. Perturb and Observe (P&O) algorithm is the industry de facto standard for optimization of PV panel power. The results demonstrated efficient battery charging by extracting maximum power point form photovoltaic cell.
世界日益增长的能源需求严重影响了需求需求和燃料来源的消耗。传统能源是造成生态环境污染的主要原因。全球对可替代能源的推动正在获得环保能源需求的动力。本文主要研究了太阳风混合发电系统的性能优化问题。在大量的研究技术之后，从光伏板和风力发电中提取最大功率的挑战尚未得到解决。太阳能的功率随零星的环境条件而变化，输出功率也是如此。在本研究中，我们研究了光伏电池IV和PV曲线的Perturb and Observe (P&O)算法。扰动和观察(P&O)算法是光伏电池板功率优化的行业事实上的标准。结果表明，通过提取光伏电池的最大功率点，可以实现高效充电。
{"title":"Solar-Wind Hybrid Energy Generation System Maximum Power Point Tracking using Perturb and Observe (P&O) Algorithm*","authors":"Ibrahim Khan, R. Hussain, M. Sikander, Sheeraz Arif, Muhammad Umair","doi":"10.1109/ICCOINS49721.2021.9497152","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497152","url":null,"abstract":"The world ever increasing energy needs are deeply intervenes with demand appetite and depleting fuels sources. Traditional energy sources are the major cause of the pollution which adversely affects ecology. The global impetus towards alternate is now gaining momentum for eco-friendly energy needs. This research focuses on the performance optimization of solar wind hybrid generation system. In the wake of plethora of research techniques, the challenge of extracting maximum power from photovoltaic panel and wind generated power is yet to be address. Solar power varies due to sporadic environmental conditions so does the output power. In this research, we have investigated the Perturb and Observe (P&O) algorithm for IV and PV curves of photovoltaic cell. Perturb and Observe (P&O) algorithm is the industry de facto standard for optimization of PV panel power. The results demonstrated efficient battery charging by extracting maximum power point form photovoltaic cell.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123607861","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497225
H. Lee, W. Beh, K. Lem
Financial time series analysis often requires both temporal and spectral information. Wavelet transform, which shares fundamental concepts with windowed Fourier transform, introduces the notion of scale to enable simultaneous time-frequency analysis. Continuous Wavelet Transform (CWT), coupling with Morse analytic wavelet function have been chosen to extract frequency information from the residual of ARIMA fitted financial time series. The extracted frequency information was then utilized to perform in-sample forecasting. The hybrid ARIMA+CWT forecasting results were then compared with pure ARIMA forecasting results. Results showed that hybrid ARIMA+CWT forecasting performed better than pure ARIMA forecasting. A conclusion has thus been drawn that additional data can be extracted from the residual of ARIMA using CWT and turned into useful information.
{"title":"Financial Time Series Forecasting with Hybrid ARIMA-Continuous Wavelet Transform","authors":"H. Lee, W. Beh, K. Lem","doi":"10.1109/ICCOINS49721.2021.9497225","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497225","url":null,"abstract":"Financial time series analysis often requires both temporal and spectral information. Wavelet transform, which shares fundamental concepts with windowed Fourier transform, introduces the notion of scale to enable simultaneous time-frequency analysis. Continuous Wavelet Transform (CWT), coupling with Morse analytic wavelet function have been chosen to extract frequency information from the residual of ARIMA fitted financial time series. The extracted frequency information was then utilized to perform in-sample forecasting. The hybrid ARIMA+CWT forecasting results were then compared with pure ARIMA forecasting results. Results showed that hybrid ARIMA+CWT forecasting performed better than pure ARIMA forecasting. A conclusion has thus been drawn that additional data can be extracted from the residual of ARIMA using CWT and turned into useful information.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127185407","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}
Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497231
Elizabeth Lucky Maretha Sitinjak, K. Haryanti, Yohanes Wisnu Djati Sasmito, Widuri Kurniasari
Every investor has different investment behavior. These differences are called investor style. Investor style can be different because of demography, personality, and different transaction times. The purpose of this study is to reduce the mistakes made by individual investors style. Some of the methods used in this research are Analytical Hierarchy Process (AHP), secondary data, Focus Group Discussion (FGD), and stock simulation with algorithm. All of these methods emphasize the decision making process when buying and selling stocks. The results provide a set of price targets and types of stocks purchased. Accounting information remains the main ingredient for making these decisions. Accounting information that is often used is Price Book Value (PBV) to select undervalued stocks. Additional results from depth interviews, average return obtained based on the time horizon, the beginning of the transaction up to 1 year has a stock return of around 2-4 percent. A time horizon of 1-3 years will get a return of around 10 percent. Time horizon of more than 3 years, stock returns will rise again. The average long-term stock investment is around 20 percent. Personalities based on Dominance, influence, Steadiness, Conscientiousness (DISC) that fit the stock investment style tend to be a precisionist personality, a style of investor that systematically follows existing trading orders. The stock simulation method also uses a trading algorithm with stages according to the AHP results, in order to be able to see the investment style of stocks in the Indonesian capital market.
每个投资者都有不同的投资行为。这些差异被称为投资者风格。由于人口、个性和交易时间的不同，投资者的风格可能会有所不同。本研究的目的是为了减少个人投资者在风格上的错误。本文采用了层次分析法(AHP)、二次数据法(secondary data)、焦点小组讨论法(Focus Group Discussion, FGD)和基于算法的股票模拟等方法。所有这些方法都强调买卖股票时的决策过程。结果提供了一组价格目标和购买的股票类型。会计信息仍然是做出这些决策的主要因素。通常使用的会计信息是价格账面价值(PBV)来选择被低估的股票。深度访谈的其他结果，基于时间范围获得的平均回报，交易开始至1年的股票回报率约为2- 4%。1-3年的时间跨度将获得10%左右的回报。时间跨度超过3年，股票回报率将再次上升。平均长期股票投资在20%左右。以“支配型”、“影响力型”、“稳定型”、“尽责型”(DISC)为基础的性格符合股票投资风格，往往是精确主义人格，即系统地遵循现有交易指令的投资者风格。股票模拟方法还根据AHP结果采用了分阶段的交易算法，以便能够看到印尼资本市场股票的投资风格。
{"title":"Investor Style in Stock Investment Decisions","authors":"Elizabeth Lucky Maretha Sitinjak, K. Haryanti, Yohanes Wisnu Djati Sasmito, Widuri Kurniasari","doi":"10.1109/ICCOINS49721.2021.9497231","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497231","url":null,"abstract":"Every investor has different investment behavior. These differences are called investor style. Investor style can be different because of demography, personality, and different transaction times. The purpose of this study is to reduce the mistakes made by individual investors style. Some of the methods used in this research are Analytical Hierarchy Process (AHP), secondary data, Focus Group Discussion (FGD), and stock simulation with algorithm. All of these methods emphasize the decision making process when buying and selling stocks. The results provide a set of price targets and types of stocks purchased. Accounting information remains the main ingredient for making these decisions. Accounting information that is often used is Price Book Value (PBV) to select undervalued stocks. Additional results from depth interviews, average return obtained based on the time horizon, the beginning of the transaction up to 1 year has a stock return of around 2-4 percent. A time horizon of 1-3 years will get a return of around 10 percent. Time horizon of more than 3 years, stock returns will rise again. The average long-term stock investment is around 20 percent. Personalities based on Dominance, influence, Steadiness, Conscientiousness (DISC) that fit the stock investment style tend to be a precisionist personality, a style of investor that systematically follows existing trading orders. The stock simulation method also uses a trading algorithm with stages according to the AHP results, in order to be able to see the investment style of stocks in the Indonesian capital market.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126606662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：