Chandadevi Giri, S. Thomassey, Jenny Balkow, Xianyi Zeng
{"title":"Forecasting New Apparel Sales Using Deep Learning and Nonlinear Neural Network Regression","authors":"Chandadevi Giri, S. Thomassey, Jenny Balkow, Xianyi Zeng","doi":"10.1109/ICESI.2019.8863024","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863024","url":null,"abstract":"Compared to other retail industries, fashion retail industry faces many challenges to foresee future demand of its products. This is due to ever-changing choices of their consumers, who get influenced by rapidly changing market trends and it leads to the short life cycle of a fashion product. Due to the advent of e-commerce business models, fashion retailers have to put a multitude of virtual product images along with their feature information on their websites in order for their customers to know the fashion products and improve their purchasing experience. It is imperative for fashion retailers to predict future consumer preferences in advance; however, they lack advanced tools to achieve this goal. To overcome this problem, this research work combines the historical information of products with their image features using deep learning and predicts future sales. Apparel images are converted into feature vectors and then are merged with historical sales data. We applied backward propagation neural network model to predict the sales of a new product. It is found that the model performs quite well despite the small size of the dataset. This approach could be promising for forecasting the new arrivals of apparels in the market, and fashion retailers could improve their efficiency and growth.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114625454","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}
Muhammad Murtadha Othman, Muhamad Hafizuddin Idris Ramlee, M. H. Harun, I. Musirin
{"title":"Short-Term Photovoltaic Power Forecasting Using Artificial Neural Network Considering Multiple Time Lags","authors":"Muhammad Murtadha Othman, Muhamad Hafizuddin Idris Ramlee, M. H. Harun, I. Musirin","doi":"10.1109/ICESI.2019.8862996","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8862996","url":null,"abstract":"This paper presents the artificial neural network (ANN) used to perform the short-term photovoltaic power forecasting (STPPF) for the next 24 hours. The input data of ANN is comprising with the multiple time lags of hourly data of power, current, temperature, solar irradiance and hour that have been denoised by using the wavelet decomposition. The multiple time lags are used to improve the input data while wavelet decomposition removes the noises available in the data which will then significantly improve the STPPF results. The data of a solar photovoltaic (PV) system in the year 2015 and 2016 obtained from the Green Energy Research (GERC), UiTM, Shah Alam, Malaysia. The results have shown that the ANN provides relatively accurate results of STPPF and able to forecast the PV output power for the next 24 hours with less error.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126461152","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":"Time series prediction for EMS with machine learning","authors":"M. Bizjak, G. Štumberger, B. Žalik, N. Lukač","doi":"10.1109/ICESI.2019.8863006","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863006","url":null,"abstract":"One of the key purposes of an Energy Management System (EMS) is the optimisation of energy costs, which relies on accurate prediction of their components' behaviour in the short-term future. EMS operates various types of devices that consume energy. For each device, the short-term prediction of its parameters is required for effective EMS. A machine learning approach is proposed for predicting the behaviour of EMS devices. For this purpose, a Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) is used, where multivariate time-series data serve as input. For each device, a new model is trained with the corresponding measurements of the devices' parameters and local environment variables, which are provided as time-series with the same time-step. One of the time series is selected as the predicted output. In the experiments, the proposed approach was applied to train a model for predicting the temperature in a water heater, based on the time-series of water temperature and heater power consumption. The water temperature was estimated successfully for the short-term future, based on the input temperature and planned heater action. For the two-step prediction, the RMSE of 0.006 K was calculated between the predicted and measured temperatures.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114510348","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":"Visualization of the Inventive Principle of TRIZ to Improve Problem-Solving Ability in Design Processs","authors":"N. Faria","doi":"10.1109/ICESI.2019.8863011","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863011","url":null,"abstract":"TRIZ as a problem-solving method has been widely used in the 21st century. This study aims to obtain a new method that can be used as a supplementary of the TRIZ learning process. The new method will be developed by visualizing the 40 Inventive principles of TRIZ in the form of symbols. The symbol is developed as an image to describe the inventive principle clearly, so the users can distinguish one principle from another. The symbol is equipped with examples of the use of principles in the design process. The symbol had been evaluated by professionals who have known and used TRIZ to solve problems in the design field.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122631821","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":"Value Chain and Customer's Perception towards Organic Livestock Foods","authors":"Suchawadee Sarunyut, A. Kessuvan","doi":"10.1109/ICESI.2019.8863002","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863002","url":null,"abstract":"Due to food safety and environmentally conscious, many people prefer organic consumption which affects the increase in its demand. In Thailand, the growth rate of organic land, as well as organic livestock, has continuously increased. Organic livestock becomes more important since consumers tend to be aware of food safety. This research aims to study the business processes of organic livestock food supply chain, specifically a case of organic poultry and egg by using Integration Definition for Function Modeling (IDEF0), to examine the expert's opinion on motivation and value proposition toward organic livestock foods from the food service business's viewpoint, and to survey the knowledge and value perception toward organic livestock foods from the consumer's viewpoint. The result shows that the food service's motivation to adopt organic livestock and value proposition which are food safety and high quality including nutrition, texture, and taste. In addition, the knowledge and value perception of organic livestock foods has been indicated by the end consumer. The information from food service business and end consumer's viewpoint will become a guideline to stimulate the organic livestock consumptions","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122829515","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":"Detection of snow levels in the Slovenian Alps at different seasons using Sentinel-1","authors":"David Jesenko, D. Mongus, Shuang Liu, M. Čekada","doi":"10.1109/ICESI.2019.8863012","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863012","url":null,"abstract":"The Sentinel satellite constellation series, developed and operated by the European Space Agency, represents a dedicated space component of the European Copernicus Programme, committed to long-term operational services in the environment, climate and security. A huge amount of obtained data allows us different surveys. We decided to detect changes in the snow cover in the Julian Alps at the different seasons. The differences have been calculated using Sentinel-1 images from each season period. The presented methodology consist of five main steps, where the most important step is the calculation of Differential SAR Interferometry (DInSAR). By doing this, we found out how the thickness of the snow changes during the seasons. As demonstrated by the results, the presented approach is suitable for detection of snow level changes.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127349029","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":"Stock Price Prediction based on Recurrent Neural Network with Long Short-Term Memory Units","authors":"Cheng Peng, Zhihong Yin, Xinxin Wei, Anqi Zhu","doi":"10.1109/ICESI.2019.8863005","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863005","url":null,"abstract":"Stock price prediction has been playing a very comprehensive impact on the financial industry. However, it has been considered as one of the most challenging tasks due to the financial time series data has some unpredictable and volatile characteristics. Conventional statistical models can only give a reasonable prediction for the next following one step. In this paper, we propose two novel prediction methods embedded with a deep learning framework using long short-term memory units, providing predictions for both short and long-term horizons. Comparison tests has been carried out between the two proposed methods, and the experiment results have shown that our methods have a significant performance in capturing both the trend and the exact value of the stock data.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130477143","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":"Wide Stopband Microstrip Diplexer Using a Novel Configuration for Frequency Division Duplex and GSM-4G Applications","authors":"S. Yahya, A. Rezaei, L. Noori, M. Jamaluddin","doi":"10.1109/ICESI.2019.8862988","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8862988","url":null,"abstract":"This paper presents a high performance microstrip diplexer based on a novel geometrical structure. The realized diplexer consists of coupled lines and semicircular structures. It operates at 2.58 GHz and 2.72 GHz, for GSM-4G and wireless applications. The diplexer channels are close to each other, which fulfill the frequency division duplex (FDD) application needs. The wide stopband rejections for both S21 and S31 are provided up to 15 GHz. Despite of quite close channels, the simulated and measured isolation between the two channels (S32) is better than −20 dB, from DC up to 20 GHz. The designing method is based on providing a theoretical approach to attenuate the harmonics and tuning the resonance frequency. Meanwhile, several transmission zeros are created after the passbands, which improve the stopband properties. The proposed diplexer provides sharp transition edges for both passbands. The high performance is obtained using a compact size of 0.047λ2. To verify the designing methodology, the proposed diplexer is fabricated and measured. Good agreement between simulation results and measurement results are observed.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134033233","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}
Merry Siska, Reski Mai Candra, Eki Saputra, M. Zein, A. Wenda, N. Yanti
{"title":"Application of Novel Ergonomic Postural Assessment Method in Indonesia Creative Industry Centers","authors":"Merry Siska, Reski Mai Candra, Eki Saputra, M. Zein, A. Wenda, N. Yanti","doi":"10.1109/ICESI.2019.8863008","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863008","url":null,"abstract":"An operator's productivity should be affected by the conditions of the work station where the operators are carrying out their activities. The conditions of the work station or good work environment for an operator are effective, comfortable, safe, healthy and efficient. This paper analyze the Novel Ergonomic Postural Assessment Method application in the Indonesia creative industry centers in Bandung. Bad operator work postures carried out every day cause a high risk of musculoskeletal disorders for the operators in the creative industry centers in Indonesia. Thus, the research problems can be formulated as: How is the application of the Novel Ergonomic Postural Assessment Method (NERPA) in the center of creative industries in Indonesia. Based on the constraints of the problem, each new design in four creative centers in Bandung was conducted. In the doll making, the first posture is designing doll pattern station which is a priority for improvement by designing a table to reduce the level of musculoskeletal risk for its workers. The fourth body posture in shoe-making is a priority to be improved by making a design tool to cut the footwear to reduce the level of musculoskeletal risk. Knitted clothing center having level of musculoskeletal risk are priority improvements, namely in the first posture because the operator works in long standing state. Tofu making center also has high level of musculoskeletal risk, namely in the molding tofu station in posture 5.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130919281","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}
E. Akinlabi, Y. Okamoto, M. Maina, S. Akinlabi, S. Pityana, M. Tlotleng, G. A. Soliu, Rasheedat Modupe Mahamood
{"title":"Laser Metal Deposition of Titanium Alloy (Ti6Al4V): A Review","authors":"E. Akinlabi, Y. Okamoto, M. Maina, S. Akinlabi, S. Pityana, M. Tlotleng, G. A. Soliu, Rasheedat Modupe Mahamood","doi":"10.1109/ICESI.2019.8863018","DOIUrl":"https://doi.org/10.1109/ICESI.2019.8863018","url":null,"abstract":"Laser metal deposition (LMD) is an additive manufacturing (AM) technologies in that belongs to the class of direct energy deposition which is suitable for manufacturing of alloys and composites materials. LMD is an efficient AM technique which is capable of producing end-use products starting from depositing the powder/wire material layer-by-layer. During LMD process, a laser beam is used as a heat source to generate a melt-pool on the substrate and melts the powder that is deposited through a co-axial nozzle and supported with a shielding gas that helps to prevent oxidation. LMD is capable of producing complex shaped and functionally graded parts which are useful in many industrial applications. This AM technology can also be used in repairing worn out parts that cannot be repaired by other manufacturing technology. In this paper, a review of laser metal deposition of titanium alloy is presented. This provides an overview of LMD of titanium alloys grade 5 (Ti6Al4V) and focuses on the effects of processing parameters on the overall evolving properties.","PeriodicalId":249316,"journal":{"name":"2019 International Conference on Engineering, Science, and Industrial Applications (ICESI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130696764","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}