2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)最新文献

{"title":"Reliable of traditional cloth pattern Classification Using Convolutional Neural Network","authors":"A. H. Rangkuti, Varyl Hasbi Athala, Naufal Fauzi Luthfi, Syaugi Vikri Aditama, Johan Muliadi Kerta","doi":"10.1109/AiDAS53897.2021.9574402","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574402","url":null,"abstract":"Basically the traditional cloth pattern varieties increase every year so that they become more difficult to identify. Based on that fact, automatic traditional cloth patterns has become more important to help people recognize their patterns. This research can improve reliability in recognizing and understanding traditional cloth patterns originating from several regions in Indonesia by using a Deep Convolution neural network. In this study, several conditions were carried out, namely, the amount of training image data was more than the number of test images (3 conditions) and vice versa where the number of training images was much less but could recognize more test images (2 conditions). To support classification reliability, data processing is carried out starting from preprocessing with grayscale, resizing, noise reduction, and continued with image segmentation, and feature extraction and classification using the CNN Algorithm. After We do experiment with 42 classes of traditional cloth patterns from 22 provinces on collecting images that can be found in various scales and degrees than the average classification accuracy using Inception V3 3.0 is 83.9% with condition 1, but the highest is between 98.1 %–99.7%. Meanwhile, if using resnetV2 50 the average classification accuracy is between 78.3% for the highest between 93.7%–94.3%. This Research can be continued using antoher Deep CNN algorithm to get the optimal of classification accuracy.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134525654","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":"Agarwood Oil Quality Grading using OVO Multiclass Support Vector Machine","authors":"A. F. M. Amidon, N. Z. Mahabob, M. H. Haron, N. Ismail, Z. Yusoff, M. Taib, S. N. Tajuddin, N. M. Ali","doi":"10.1109/AiDAS53897.2021.9574320","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574320","url":null,"abstract":"When heard about agarwood oil, it is very familiar with world community because of its beneficial. Unfortunately, there is no any standard grading model of agarwood oil was implemented. As a solution forms, it is very important to come out with a standard of quality classification model for agarwood oil grading's. By continuing of the research for the development of this standard, specific algorithm function has been used to make sure the ability of this model is totally not in doubt. Support vector machine (SVM) has been chosen as a main model and for the specific algorithm function that has been chosen was multiclass function. Then, in the function, the one versus one (OVO) strategy has been used to make multiclass work and can be applied on SVM. The analysis work has involving the data taken from the previous researcher that consists of four classes of agarwood oil quality's samples which are low, medium low, medium high and high quality. So, the output was the classification of quality between low, medium low, medium high or high quality while the input was the abundances (%) of compounds. The desk research has been conducted by using MATLAB software version r2020a for the simulation platform. The result showed that the model by using multiclass function has pass the performance criteria standard. The verdict in this research for sure will be valuable for the future research works of agarwood oil areas, especially quality classification part.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124960419","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":"Role of Artificial Intelligence in the Management of Food Waste","authors":"Maria Cecilia Anggraeni, Chrysanti Anastasya Silaban, Maria Susan Anggreainy, Ervan Cahyadi","doi":"10.1109/AiDAS53897.2021.9574167","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574167","url":null,"abstract":"Food waste is caused by a complex collection of interconnected behavior at both the supplier and customer levels. Computational and mathematical models provide various methods for simulating, diagnosing, and predicting various aspects of the dynamic food waste generation and prevention system. This paper describes three modeling methods that have been used to analyze food waste in the past. Bayesian networks and machine learning algorithms are applied to help determine how much food is discarded at the household level. Agent-Based Simulation was used to gain insight into how innovation and adoption of a particular technology can help minimize retail food waste. The first BN-ABM integrated model assesses consumer food waste levels affected by particular features and aspects, resulting in the model reaching equilibrium. Proofing that there is a need for policy interventions, including training, economic incentives, and campaigns, to obtain the resulting model transformation. These interventions are ready to be assessed by the model, but further study is needed to understand the effects of enforcing these structures on the accuracy of the BN-ABM predictive model. The second ABM model aims to determine the factors that establish the adoption of food waste reduction technology at the retail level, which is influenced by particular but not limited to economic factors, including a strong network between retailers and consumer's awareness regarding food waste reduction technology. These findings can study the effects of policy intervention regarding food waste reduction at the retail and consumer level. The third ABM model employed a general food chain network model consisting of consumers, traders, and producers to simulate the dynamic change of product flow between agents and to be able to assess the effect of agent's behavioral contrast. Resilience is measured by the ability to deal with shocks, and efficiency is the share of total food manages to be dispatched to consumers. At first glance, the simulation results seem to show a system trade-off between efficiency and resilience. Network chain structures with higher efficiency displayed more sensitivity to shocks, while networks with less efficiency show more resilience. However, there seem to be modifications in the results when applying several trading interactions and shock types. Resiliency and efficiency are affected by social aspects (trust and preference) in trading interaction between agents. An essential aspect of resilience is the agent's ability to switch links (trading partners) which shows the capability of reorganization. Insights regarding the research can be applicable when considering real-life food chain and structural reorganization to increase resilience and efficiency in meeting national food security goals.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122777409","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":"Phishing Website Detection Using Random Forest and Support Vector Machine: A Comparison","authors":"Norzaidah Binti Md Noh, M. N. Bin M. Basri","doi":"10.1109/AiDAS53897.2021.9574282","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574282","url":null,"abstract":"As the Internet usage is growing rapidly, people are changing their choice from traditional shopping to electronic commerce. However, instead of robbery at banks and stores, criminals now locate their victims with some tricks in cyber world by applying the anonymous internet framework. Hackers are using new tactics, including phishing, to mislead the victims by using fake websites to gather sensitive information, including account ids, usernames, and password. Understanding whether a website is legitimate or phishing is an incredibly difficult problem because of its phishing attack structure, which primarily targets the vulnerabilities of web users. This work was proposed to solve these issues by using machine learning technology to detect the phishing websites. The system analyzed the HTML code structure that include in the hyperlink of the websites. Two machine learning techniques, namely Random Forest and Support Vector Machine are tested to identify the best machine learning algorithm in detecting phishing website. The performance metric for each algorithm was used as measured. The result average of accuracy for Random Forest is 99.98 percent and Support Vector Machine is 84.73 percent. This study aims to detect phishing websites hyperlink and produces the best algorithm which is Random Forest that achieved the highest accuracy to be used for the system.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127760038","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":"Evaluation of Deep Learning for Image-based Black Pepper Disease and Nutrient Deficiency Classification","authors":"C. Khew, Yi Qin Teow, Ee-Tiing Lau, S. Hwang, Chih How Bong, Nung Kion Lee","doi":"10.1109/AiDAS53897.2021.9574346","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574346","url":null,"abstract":"Black pepper (Piper nigrum) diseases and nutrient deficiency can often be observed based on the symptoms exerted on its leaves. This paper aimed to investigate the effectiveness of employing a deep learning approach to classify black pepper disease and nutrient deficiency based on leaf images. We constructed a customized convolutionary neural network to determine how its training parameters would affect the prediction performances. Another two deep learning neural networks VGG16 and Inception V3, are also employed for comparisons. We have sampled 947 images from farms in Sarawak consisted of 8 classes in total. Image augmentation is performed on the images to produce a total of 9532 images. The result shows that the customized CNN performed slightly better than the other two deep learning approaches at a 0.98 sensitivity rate. Furthermore, image augmentation contributed to improving prediction performance for all the deep learning models. This study has demonstrated that deep learning is a feasible approach for classifying black pepper diseases and nutrient deficiency based on leaf images.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130879650","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":"Mathematics Performance Monitoring System Using Data Analytics","authors":"M. S. A. Razak, S. Abdul-Rahman, Yuzi Mahmud","doi":"10.1109/AiDAS53897.2021.9574210","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574210","url":null,"abstract":"In recent years, technology has advanced so rapidly to the point where core elements such as Artificial Intelligence (AI), Big Data, Data Analytics, and the Internet of Things (IoT) are becoming trends for Industrial Revolution 4.0 (IR 4.0). The core elements for IR 4.0 have been extensively applied to various major sectors such as Transportation, Retail, Communications, and Education to provide better services while being as efficient as possible. Hence, a system is needed to tackle many students, which has been a limiting factor for teachers to track students' progress efficiently. This research highlights the application of data analytics in mathematics due to its importance in IR 4.0. Predictive analytics has been specifically chosen to help educators gain valuable insight into their students' strengths and weaknesses in each subtopic in Mathematics. Several machine learning algorithms have been used, such as Multiclass Decision Forest, Multiclass Decision Tree, Multiclass Logistic Regression and Multiclass Neural Network. The best model was trained with Multiclass Decision Forest with an accuracy of 95.16%. Several future improvements have been mentioned, such as increasing the number of instances, adding more significant variables, and deploying the system into mobile platforms.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132825600","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":"Process Mining of Cardiovascular Diseases Trajectories in Malaysia Public Hospital: A Feasibility Study","authors":"N. Ahmad, Hamidah Mat, A. Z. Shahuddin, Z. Shaffiei, S. J. Elias, S. Hatim, Samsiah Ahmad","doi":"10.1109/AiDAS53897.2021.9574146","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574146","url":null,"abstract":"The Electronic Health Record (EHR) consists of information captured in various data types, for example, radiological images, textual documents, structured values, or graphs. These data show the history of treatment received and the types of diseases faced by patients. This becomes an issue for medical practitioners where they are required to read this complex data describing the diverse patient history and must decide what treatment is needed for each of these patients. Process mining gives a bunch of grounded apparatuses and techniques that have been utilized to find health record data to comprehend healthcare pathways. In this paper, we conducted a feasibility study to identify suitable process mining techniques that can be applied to gain insights into patterns associated with patient diagnosis history and visualize cardiovascular cluster diseases pattern from patient diagnosis history. Visualizing patients' disease trajectories from real-life data seem to offer medical practitioners and medical researchers create a brighter insight into the advancement of diseases within target populaces. The limitations of the process mining activity and future research are finally discussed.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115043976","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":"Object Detection and Recognition for Visually Impaired Users: A Transfer Learning Approach","authors":"Wei-Cheng Won, Y. Yong, Kok-Chin Khor","doi":"10.1109/AiDAS53897.2021.9574220","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574220","url":null,"abstract":"Vision is one of the most important human senses, and it plays a critical role in understanding the surrounding environment. However, millions of people in the world are experiencing visual impairment. They are facing difficulties in their daily navigations since they cannot see the obstacles in their surroundings. In this paper, we applied transfer learning to two pre-trained models, Single Shot Detector Mobilenet V1 (SSD) and Faster Region-Convolutional Neural Network Inception V2 (Faster R-CNN), to detect and recognise 40 classes of common objects in surroundings. The performance of these two trained models was subsequently compared. The fine-tuned Faster R-CNN model was able to achieve an mAP (Mean Average Precision) score of 0.8961 with an inference time of 7.2 seconds. On the other hand, the SSd model achieved an mAP score of 0.5708 with an inference time of 1.8 seconds. In consludion, Faster R-CNN appears as the suitable model to be implemented in the mobile application to help visually impaired people as it produces a good mAP result.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129428380","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 Computational Method of Optimizing Chess Compositions to Enhance Aesthetic Appeal","authors":"Azlan Iqbal","doi":"10.1109/AiDAS53897.2021.9574145","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574145","url":null,"abstract":"Chess compositions are typically positions set up with a stipulation, e.g., ‘White to Play and Mate in 3’. They are also usually challenging, educational or possess some aesthetic appeal. In this article, a computational method of optimizing compositions is presented that can help improve them, primarily in terms of aesthetics as described by the conventions of problem composition. This is useful in automatic chess composition, which is fairly new in artificial intelligence (AI) and still a largely open area of research. The method involves seven aspects, namely 1) removing pieces, 2) swapping white pieces for weaker ones, 3) swapping black pieces for stronger ones, 4) moving the white king to avoid check, 5) looking for a shorter mate, 6) moving the white king closer to the other pieces, and 7) preventing major black pieces from being en prise (capturable). All of these are applied in order and together whilst preserving the original solution as much as possible. The effectiveness of the method is demonstrated using examples (before and after optimization) illustrating the positive changes to the positions. Human expert assessment is also shown to be comparable in outcome. This method can therefore be used to automatically improve, in general, the aesthetic appeal of compositions to a significant or noticeable degree.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130528976","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":"An Empirical Study on Sentiment Analysis of Student Happiness Index via Twitter","authors":"Samsiah Ahmad, Puteri Nur Sarah Nabila Mahdi, Zalikha Zulkifli, Lily Marlia Abdul Latif, M. Ariff","doi":"10.1109/AiDAS53897.2021.9574246","DOIUrl":"https://doi.org/10.1109/AiDAS53897.2021.9574246","url":null,"abstract":"The ubiquities of social media have changed the way how the general public consumes their daily news and information. This results in social media becoming an agent of influence in changing the public opinions towards an organization via social media. Thus, university institutions or organizations must perceive and monitor any issues regarding the university or organization on social media and the student's sentiment towards their university. This is because university reputation is one of the main aspects that heavily affected student enrollment decisions for universities This paper is an empirical study on sentiment analysis of student happiness. This project aims to investigate and analyze the sentiment classifier as the measurement in visualizing the student happiness index on Twitter.","PeriodicalId":152187,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116660869","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}