Pub Date : 2019-09-01DOI: 10.1109/aidas47888.2019.8970781
{"title":"[AiDAS 2019 Title Page]","authors":"","doi":"10.1109/aidas47888.2019.8970781","DOIUrl":"https://doi.org/10.1109/aidas47888.2019.8970781","url":null,"abstract":"","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125088420","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8970983
M. F. Misman, A. A. Samah, N. Aziz, H. Majid, Z. A. Shah, H. Hashim, Muhamad Farhin Harun
Artificial neural networks (ANN) has been widely used to speed up data prediction operations with over thousands of features available. In this paper, we propose a regression-based ANN model with three hidden layers to predict the age of abalones. It is salient to predict abalone age as it helps farmers and sellers to determine the market price of abalones. The economic value of abalone is positively correlated with their respective ages. The age of the abalone can be estimated by measuring the number of layers of shell rings The model was built based on a dataset obtained from the UCI Machine Learning Repository. Before developing and training the model, a pre-processing methodology was applied to the dataset. Parameters tuning, which involves modifications in the number of hidden layers as well as the number of epochs, were done to obtain the best result. The finalised results were analysed and the results show that physical measurements of abalone can predict its respective age with less time consumption. This study has shown a result of low root mean-squared error, obtained from the proposed model in comparison with other methods stated in this study. Finally, the proposed model was validated using test dataset, and the results reveal a lower root-mean-squared error value in contrast to the value obtained during model training.
{"title":"Prediction of Abalone Age Using Regression-Based Neural Network","authors":"M. F. Misman, A. A. Samah, N. Aziz, H. Majid, Z. A. Shah, H. Hashim, Muhamad Farhin Harun","doi":"10.1109/AiDAS47888.2019.8970983","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8970983","url":null,"abstract":"Artificial neural networks (ANN) has been widely used to speed up data prediction operations with over thousands of features available. In this paper, we propose a regression-based ANN model with three hidden layers to predict the age of abalones. It is salient to predict abalone age as it helps farmers and sellers to determine the market price of abalones. The economic value of abalone is positively correlated with their respective ages. The age of the abalone can be estimated by measuring the number of layers of shell rings The model was built based on a dataset obtained from the UCI Machine Learning Repository. Before developing and training the model, a pre-processing methodology was applied to the dataset. Parameters tuning, which involves modifications in the number of hidden layers as well as the number of epochs, were done to obtain the best result. The finalised results were analysed and the results show that physical measurements of abalone can predict its respective age with less time consumption. This study has shown a result of low root mean-squared error, obtained from the proposed model in comparison with other methods stated in this study. Finally, the proposed model was validated using test dataset, and the results reveal a lower root-mean-squared error value in contrast to the value obtained during model training.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124519945","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8971016
Faisal Baseer, J. Jaafar, Asad Habib
Urdu ranks very high among languages used for communication in the Southern Asia. Even though with great following, it clearly lack computational support that is why it is written in Romanized Urdu script. There has been a lot of research done on the gender and age identification of author through written text but not ample have been done using Romanized Urdu dataset. In our research, we have proposed a model for the said purpose by identifying key parameter (defined attributes) of an author. These parameters were measured for both the genders and three categories of age. Weight assignment technique was used to plot graphs which help in computation of the desired results.
{"title":"Gender and Age Identification Through Romanized Urdu Dataset","authors":"Faisal Baseer, J. Jaafar, Asad Habib","doi":"10.1109/AiDAS47888.2019.8971016","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8971016","url":null,"abstract":"Urdu ranks very high among languages used for communication in the Southern Asia. Even though with great following, it clearly lack computational support that is why it is written in Romanized Urdu script. There has been a lot of research done on the gender and age identification of author through written text but not ample have been done using Romanized Urdu dataset. In our research, we have proposed a model for the said purpose by identifying key parameter (defined attributes) of an author. These parameters were measured for both the genders and three categories of age. Weight assignment technique was used to plot graphs which help in computation of the desired results.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134457790","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 : 2019-09-01DOI: 10.1109/aidas47888.2019.8970966
{"title":"[AiDAS 2019 Blank page]","authors":"","doi":"10.1109/aidas47888.2019.8970966","DOIUrl":"https://doi.org/10.1109/aidas47888.2019.8970966","url":null,"abstract":"","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131606574","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8970957
C. Fatichah, Sirria Panah Alam, D. A. Navastara
A fire detection on video data using optical flow feature is presented to improve the performance of detection when using only texture or color feature. We compare two kinds of optical flow that are dense optical flow using Farneback algorithm and sparse optical flow using the Lucas Kanade algorithm. The fusion of optical flow feature and Local Binary Pattern (LBP) as a texture feature is used to classify the video frame as fire or not fire using Support Vector Machine (SVM). There are three phases for fire detection in our framework. First, segmentation on each video frames based on Hue, Saturation, Value (HSV) color space is done to obtain the candidate of the fire area. Second, feature extraction using optical flow and LBP method is done to achieve the movement and texture features of the fire. Finally, the extracted features are classified to fire or not fire using the SVM method. The model is evaluated using stratified 10-folds cross-validation to be separated into learning process data and validation data. The best result is obtained using the Lucas Kanade optical flow feature and using a linear kernel SVM with 96.21% in accuracy.
为了提高仅使用纹理或颜色特征时的检测性能，提出了一种利用光流特征对视频数据进行火灾检测的方法。比较了采用Farneback算法的密集光流和采用Lucas Kanade算法的稀疏光流两种光流。将光流特征与局部二值模式(LBP)融合为纹理特征，利用支持向量机(SVM)对视频帧进行火与不火的分类。在我们的框架中，火灾探测分为三个阶段。首先，对每个视频帧进行基于Hue, Saturation, Value (HSV)色彩空间的分割，得到候选火焰区域;其次，利用光流和LBP方法进行特征提取，得到火焰的运动特征和纹理特征;最后，利用支持向量机方法对提取的特征进行火灾和非火灾分类。模型使用分层10倍交叉验证进行评估，将其分为学习过程数据和验证数据。使用Lucas Kanade光流特征和线性核支持向量机获得了最好的结果，准确率为96.21%。
{"title":"Optical Flow Feature Based for Fire Detection on Video Data","authors":"C. Fatichah, Sirria Panah Alam, D. A. Navastara","doi":"10.1109/AiDAS47888.2019.8970957","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8970957","url":null,"abstract":"A fire detection on video data using optical flow feature is presented to improve the performance of detection when using only texture or color feature. We compare two kinds of optical flow that are dense optical flow using Farneback algorithm and sparse optical flow using the Lucas Kanade algorithm. The fusion of optical flow feature and Local Binary Pattern (LBP) as a texture feature is used to classify the video frame as fire or not fire using Support Vector Machine (SVM). There are three phases for fire detection in our framework. First, segmentation on each video frames based on Hue, Saturation, Value (HSV) color space is done to obtain the candidate of the fire area. Second, feature extraction using optical flow and LBP method is done to achieve the movement and texture features of the fire. Finally, the extracted features are classified to fire or not fire using the SVM method. The model is evaluated using stratified 10-folds cross-validation to be separated into learning process data and validation data. The best result is obtained using the Lucas Kanade optical flow feature and using a linear kernel SVM with 96.21% in accuracy.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121795653","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8970778
N. Hila, Muhamad Safiih L, S. M. Shaharudin, N. Mohamed
Improving the forecasting estimation is significantly contributes to the growth of time series estimation. In this paper, based on the set of integrating data from autoregressive integrated moving average (SARIMA) model, we hybrid it in artificial neural network (ANN) algorithm to quantify nonlinearity part of SARIMA model and improve the forecasting estimation. This hybrid methodology is apply to Malaysia arrival guest historical data. The forecasting performance of the hybrid approach is compared to individual model of SARIMA and ANN. We found that the hybrid approach results are remarkably improved the correlation and error estimation. Thus, this improvement shows that the forecasting is improved with the hybrid SARIMA-ANN model.
{"title":"A Hybrid Neural Network Model to Forecast Arrival Guest in Malaysia","authors":"N. Hila, Muhamad Safiih L, S. M. Shaharudin, N. Mohamed","doi":"10.1109/AiDAS47888.2019.8970778","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8970778","url":null,"abstract":"Improving the forecasting estimation is significantly contributes to the growth of time series estimation. In this paper, based on the set of integrating data from autoregressive integrated moving average (SARIMA) model, we hybrid it in artificial neural network (ANN) algorithm to quantify nonlinearity part of SARIMA model and improve the forecasting estimation. This hybrid methodology is apply to Malaysia arrival guest historical data. The forecasting performance of the hybrid approach is compared to individual model of SARIMA and ANN. We found that the hybrid approach results are remarkably improved the correlation and error estimation. Thus, this improvement shows that the forecasting is improved with the hybrid SARIMA-ANN model.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125294289","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8971014
Syazwani Yahya, M. Kamalrudin, Safiah Sidek, Munaliza Jaimun, Junaidah Yusof, A. Hua, P. Gani
Security requirements are the major reasons for secure software developments. Many methods, model and approaches have been designed by many researchers to ensure a correct built of security requirement. The security patterns approach aims to benefit security requirements by allowing requirement engineers who are not security experts to better identifying and understanding security concerns and leads to a correct implementation. In this study, we evaluate various security patterns that existed in Software Requirements Engineering. Based on a literature search conducted traditionally, we report our findings on classifying and structuring this security requirements patterns. Derived from this study, a future direction for our research is clarified.
{"title":"A Review Paper: Security Requirement Patterns for a Secure Software Development","authors":"Syazwani Yahya, M. Kamalrudin, Safiah Sidek, Munaliza Jaimun, Junaidah Yusof, A. Hua, P. Gani","doi":"10.1109/AiDAS47888.2019.8971014","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8971014","url":null,"abstract":"Security requirements are the major reasons for secure software developments. Many methods, model and approaches have been designed by many researchers to ensure a correct built of security requirement. The security patterns approach aims to benefit security requirements by allowing requirement engineers who are not security experts to better identifying and understanding security concerns and leads to a correct implementation. In this study, we evaluate various security patterns that existed in Software Requirements Engineering. Based on a literature search conducted traditionally, we report our findings on classifying and structuring this security requirements patterns. Derived from this study, a future direction for our research is clarified.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126736706","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8970953
Jasy Liew Suet Yan, Howard R. Turtle
This study investigates the effect of diverse training samples on machine learning model performance for fine-grained emotion classification. Using four different sampling strategies (random sampling, sampling by topic and two variations of sampling by user), we found the class distribution of28 emotion categories to differ across the samples produced by each sampling strategy. However, combining different sampling strategies is complementary in generating sufficiently diverse training examples for the emotion classifiers. Based on support vector machine (SVM) and Bayesian network learning algorithms, our findings show that a classifier trained on combined data from the four sampling strategies performs better and is more generalizable than a classifier trained only on data from a single sampling strategy. Demonstrating how the diversity of the training samples affect the performance of emotion classifiers is the main contribution of this study.
{"title":"Effect of Sampling Strategies on Fine-grained Emotion Classification in Microblog Text","authors":"Jasy Liew Suet Yan, Howard R. Turtle","doi":"10.1109/AiDAS47888.2019.8970953","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8970953","url":null,"abstract":"This study investigates the effect of diverse training samples on machine learning model performance for fine-grained emotion classification. Using four different sampling strategies (random sampling, sampling by topic and two variations of sampling by user), we found the class distribution of28 emotion categories to differ across the samples produced by each sampling strategy. However, combining different sampling strategies is complementary in generating sufficiently diverse training examples for the emotion classifiers. Based on support vector machine (SVM) and Bayesian network learning algorithms, our findings show that a classifier trained on combined data from the four sampling strategies performs better and is more generalizable than a classifier trained only on data from a single sampling strategy. Demonstrating how the diversity of the training samples affect the performance of emotion classifiers is the main contribution of this study.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134485563","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8970976
S. M. Asiful Huda, M. Shoikot, M. A. Hossain, Ishrat Jahan Ila
Sentiment analysis or text mining is making a huge field of research in this cutting-edge period of social media. Different web journals and Social Media (Facebook, Twitter, Instagram) are the most prevalent stage for the consumers and users where most of the time they express their judgement about trending topics, different brands, restaurant, films, books and so on. Analyzing sentiment is an exceptionally brilliant and viable way to discover people views about news, place, restaurant, film, book, brand. It is helpful for both the owners and sellers. In this study, we built a model using natural language processing techniques and machine learning algorithms to automate the approach of classifying a review on around 200 popular restaurants of Bangladesh as Satisfactory or Poor. This would greatly help the owners to gather a view about the consumers on their restaurant. In this paper, we developed an effective machine learning approach to build a model that can predict the sentiment by analyzing the customer’s review of a restaurant. Our model achieved an accuracy of 95% using Support Vector Machine Classifier besides other classification models.
{"title":"An Effective Machine Learning Approach for Sentiment Analysis on Popular Restaurant Reviews in Bangladesh","authors":"S. M. Asiful Huda, M. Shoikot, M. A. Hossain, Ishrat Jahan Ila","doi":"10.1109/AiDAS47888.2019.8970976","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8970976","url":null,"abstract":"Sentiment analysis or text mining is making a huge field of research in this cutting-edge period of social media. Different web journals and Social Media (Facebook, Twitter, Instagram) are the most prevalent stage for the consumers and users where most of the time they express their judgement about trending topics, different brands, restaurant, films, books and so on. Analyzing sentiment is an exceptionally brilliant and viable way to discover people views about news, place, restaurant, film, book, brand. It is helpful for both the owners and sellers. In this study, we built a model using natural language processing techniques and machine learning algorithms to automate the approach of classifying a review on around 200 popular restaurants of Bangladesh as Satisfactory or Poor. This would greatly help the owners to gather a view about the consumers on their restaurant. In this paper, we developed an effective machine learning approach to build a model that can predict the sentiment by analyzing the customer’s review of a restaurant. Our model achieved an accuracy of 95% using Support Vector Machine Classifier besides other classification models.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130931323","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 : 2019-09-01DOI: 10.1109/AiDAS47888.2019.8970972
Olalekan Agbolade, Azree Nazri, R. Yaakob, Abdul Azim Abdul Ghani, Y. Cheah
Expression in H-sapiens plays a remarkable role when it comes to social communication. The identification of this expression by human beings is relatively easy and accurate. However, achieving the same result in 3D by machine remains a challenge in computer vision. This is due to the current challenges facing facial data acquisition in 3D: such as lack of homology and complex mathematical analysis for facial point digitization. This study proposes facial expression recognition in human with the application of Multi-points Warping for 3D facial landmark. The results indicate that Fear expression has the lowest recognition accuracy while Surprise expression has the highest recognition accuracy. The classifier achieved a recognition accuracy of 99.58%.
{"title":"Landmark-based Multi-Points Warping Approach to 3D Facial Expression Recognition in Human","authors":"Olalekan Agbolade, Azree Nazri, R. Yaakob, Abdul Azim Abdul Ghani, Y. Cheah","doi":"10.1109/AiDAS47888.2019.8970972","DOIUrl":"https://doi.org/10.1109/AiDAS47888.2019.8970972","url":null,"abstract":"Expression in H-sapiens plays a remarkable role when it comes to social communication. The identification of this expression by human beings is relatively easy and accurate. However, achieving the same result in 3D by machine remains a challenge in computer vision. This is due to the current challenges facing facial data acquisition in 3D: such as lack of homology and complex mathematical analysis for facial point digitization. This study proposes facial expression recognition in human with the application of Multi-points Warping for 3D facial landmark. The results indicate that Fear expression has the lowest recognition accuracy while Surprise expression has the highest recognition accuracy. The classifier achieved a recognition accuracy of 99.58%.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124759266","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：