IAES International Journal of Artificial Intelligence (IJ-AI)
IAES International Journal of Artificial Intelligence (IJ-AI) publishes articles in the field of artificial intelligence (AI). The scope covers all artificial intelligence area and its application in the following topics: neural networks; fuzzy logic; simulated biological evolution algorithms (like genetic algorithm, ant colony optimization, etc); reasoning and evolution; intelligence applications; computer vision and speech understanding; multimedia and cognitive informatics, data mining and machine learning tools, heuristic and AI planning strategies and tools, computational theories of learning; technology and computing (like particle swarm optimization); intelligent system architectures; knowledge representation; bioinformatics; natural language processing; multiagent systems; etc.
Articles
43 Documents
Search results for
, issue
"Vol 11, No 4: December 2022"
:
43 Documents
clear
<![CDATA[Weather prediction performance evaluation on selected machine learning algorithms ]]>
<![CDATA[Muyideen Abdulraheem]]>;
<![CDATA[Joseph Bamidele Awotunde]]>;
<![CDATA[Abidemi Emmanuel Adeniyi]]>;
<![CDATA[Idowu Dauda Oladipo]]>;
<![CDATA[Sekinat Olaide Adekola]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[Prediction of weather has been proved useful in the early warning on the impacts of weather on several areas of human livelihood. For example, the provision of decisions for autonomous transportation to reduce traffic congestion and accidents during the rainy season. However, providing the most accurate and effective forecasting model for weather forecasts has been a challenge. Hence, machine learning (ML) techniques and factors influencing weather prediction need to be investigated. Data scientists are yet to discover the best models for weather prediction. Therefore, this study compares three ML classification techniques for weather prediction. A web-based software application was developed using Flask App to demonstrate weather modeling using three ML models, and the data used for the study was obtained from Kaggle. For the weather prediction; a decision tree (DT), K-nearest neighbor (K-NN), and logistic regression (LR) classifier method were suggested, and comparisons were made between the three classifications techniques. The accuracy results show that with a 100% accuracy rate, the DL classifier outperforms the K-NN with a 78% accuracy rate and LR with a 93% accuracy rate. The results show that the application of ML models gives accurate results on weather prediction.]]>
<![CDATA[Pneumonia binary classification using multi-scale feature classification network on chest x-ray images ]]>
<![CDATA[Thulfiqar H. Mandeel]]>;
<![CDATA[Salah M. Awad]]>;
<![CDATA[Shama Naji]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[According to the world health organization, pneumonia was the cause for 14% of all deaths of children under 5 years old. A computer-aided diagnosis (CADx) system can help the radiologist in the detection of pneumonia in chest radiographs by serving as a second opinion. The typical CADx is based on transfer learning which is done by transferring the learning of feature extraction from one task with plenty of available data to a related task with a scarcity of data. This approach has two limitations which are first, blocking the transferred model from extracting the features that are singular to the new dataset as well as the inability to reduce the complexity of the original model. To address these drawbacks, we proposed a convolutional neural network (CNN) model with low complexity and three paths for feature extraction. The proposed model extracts three different types of features and concatenates them into one feature that provides a good representation for the classes. The proposed model was evaluated on a publicly available dataset. The results showed outperformance by the proposed model compared to the transfer learning models with recall 0.912±0.039, precision 0.942±0.029, F-beta score 0.93, and Cohen’s kappa score 0.740±0.008. ]]>
<![CDATA[Coronavirus disease 2019; pandemic; Data analysis; Energy demand; Neural network; Self-organizing mapping; ]]>
<![CDATA[Mohamad Fani Sulaima]]>;
<![CDATA[Sharizad Saharani]]>;
<![CDATA[Arfah Ahmad]]>;
<![CDATA[Elia Erwani Hassan]]>;
<![CDATA[Zul Hasrizal Bohari]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[The world faces a significant impact from the coronavirus disease 2019 (Covid-19) pandemic, which also influences energy consumption. This study investigates the substantial connection of the classified data between power consumption, cooling degree days, average temperature, and covid-19 cases information using mathematical and neural network approaches regression analysis, and self-organizing maps. It is well established that various data mining methods have revamped the classification process of data analytics. Specifically, this study investigates the correlation between the collected variables using regression analysis and selecting the best-matching unit under the normalization method using self-organizing maps. The selforganizing maps become better when the datasets have variations; the result denotes that this method produced high mapping quality based on the map size and normalization method. Furthermore, the data crossing connection is indicated using the regression analysis method. Finally, the classified data results during the movement control order are validated in self-organizing maps to achieve the study objective. By performing these methods, this study established that the correlation between the energy demand towards cooling degree days, average temperature, and covid-19 cases is very weak. The verification has been made where the ‘logistic’ normalization method has produced the best classification result.]]>
<![CDATA[The impact of weather data on traffic flow prediction models ]]>
<![CDATA[Hatem Fahd Al-Selwi]]>;
<![CDATA[Azlan Bin Abd Aziz]]>;
<![CDATA[Fazly Salleh Abas]]>;
<![CDATA[Nur Asyiqin Amir Hamzah]]>;
<![CDATA[Azwan Bin Mahmud]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[Traffic flow prediction is an integral part of the intelligent transportation system (ITS) that helps in making well-informed decisions. Traffic flow prediction helps in alleviating traffic congestion as well as in some connected vehicles applications such as resources allocation. However, most of the existing models do not consider external factors such as weather data. Traffic flow in road networks is affected by weather conditions which affects the periodicity of traffic. These effects introduce some irregularity to the traffic pattern, making traffic flow prediction a challenging issue. In this paper, we present a detailed investigation on the impact of weather data on different traffic flow prediction models. The investigation presented in this paper demonstrates how adding weather data could improve the models’ prediction accuracy and efficiency.]]>
<![CDATA[Correlation between nicotine dependence and inflammatory biomarkers in Thai smokers: eight weeks of synbiotic intervention ]]>
<![CDATA[Ekasit Lalitsuradej]]>;
<![CDATA[Parama Pratummas]]>;
<![CDATA[Phakkharawat Sittiprapaporn]]>;
<![CDATA[Chaiyavat Chaiyasut]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp1414-1425
<![CDATA[Cigarette smoke contains thousands of man-made substances, and many may contribute to addiction and inflammation. This study examined the effect of synbiotics on the Fagerstrom test for nicotine dependence (FTND) and inflammatory markers in Thai smokers. 14 smokers with a Nicotine Dependence Fagerstrom Test scores of 4 or higher and no pregnancy or lactation history participated in this study. We gave them surveys about the FTND and continued blood tests for Lipopolysaccharide (LPS), lactulose and mannitol ratios (LMR), Quinolinic acid (QA), and 5-hydroindoleacetic acid (5-HIAA) to record inflammatory marker levels and leaky gut information. Pearson's R-values for LPS and LMR were 0.444 and -0.465. FTND showed a positive correlation with LPS and a negative correlation with leaky gut, but both relationships were weak due to no correlation for LPS but leaky gut. The R2 of the LPS correlation coefficient was 0.197, p = 0.112, and the R2 of the leaky gut correlation was 0.217, p 0.001. FTND, LMR, and QA were significantly reduced, while 5-HIAA was elevated. Further investigation is needed to determine the association between smoking and inflammation. In conclusion, synbiotics improved FTND, gut permeability, and inflammation. ]]>
<![CDATA[Novel approach for pedestrian unusual activity detection in academic environment ]]>
<![CDATA[Kamal Omprakash Hajari]]>;
<![CDATA[Ujwalla Haridas Gawande]]>;
<![CDATA[Yogesh Golhar]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[In this paper, we propose an efficient method for the detection of student unusual activity in the academic environment. The proposed method extracts motion features that accurately describe the motion characteristics of the pedestrian's movement, velocity, and direction, as well as their intercommunication within a frame. We also use these motion features to detect both global and local anomalous behaviors within the frame. The proposed approach is validated on a newly built proposed student behavior database and three additional publicly available benchmark datasets. When compared to state-of-the-art techniques, the experimental results reveal a considerable performance improvement in anomalous activity recognition. Finally, we summarize and discuss future research directions.]]>
<![CDATA[Data augmentation for stock return prediction ]]>
<![CDATA[Tanapong Potipiti]]>;
<![CDATA[Win Supanwanid]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[In the last decade, there have been advances in machine learning performance in various domains, including image classification, natural language processing, and speech recognition. The increase in the size of training data is essential for the improvement in these domains. The two ways to have larger training sets are acquiring more original data and employing effective data augmentation techniques. However, in stock prediction studies, the sizes of datasets have not changed much and there is no accepted data augmentation technique. Consequently, there has been no similar progress in stock prediction. This paper proposes an intuitive and effective data augmentation technique for stock return prediction. New synthetic stocks are generated from linear combinations of original stocks. Unlike previous studies, our augmentation mimics actual financial asset creation processes. Our data augmentation significantly improves prediction accuracy. Moreover, we investigate how the characteristics of original data affect the data augmentation performance. We find a U-shape relationship between accuracy improved from the augmentation and return correlation in original data.]]>
<![CDATA[Classification of jackfruit and cempedak using convolutional neural network and transfer learning ]]>
<![CDATA[Putra Sumari]]>;
<![CDATA[Azleena Mohd Kassim]]>;
<![CDATA[Song-Quan Ong]]>;
<![CDATA[Gomesh Nair]]>;
<![CDATA[Al Dabbagh Ragheed]]>;
<![CDATA[Nur Farihah Aminuddin]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[Jackfruit (Artocarpus integer) and Cempedak (Artocarpus heterophyllus) are two different Southeast Asian fruit species from the same genus that are quite similar in their external appearance, therefore, sometimes difficult to be recognized visually by humans, especially in the form of pictures. Convolutional neural networks (CNN) and transfer learning can provide an excellent solution to recognize fruits, where the methods are known to be able to classify objects with high accuracy. In this study, several models were proposed and constructed to recognize the Jackfruit and Cempedak using a deep convolutional neural network (DCNN). We proposed our custom-made own CNN model and modify five transfer learning models on pre-trained VGG16, VGG19, Xception, ResNet50, and InceptionV3. The experiment used our own dataset and the result showed that the proposed CNN architecture was able to provide an accuracy between 89% to 93.67% compared to the other CNN transfer learning.]]>
<![CDATA[Cognitive and academic-based probability models for predicting campus placements ]]>
<![CDATA[Shaik Alfana]]>;
<![CDATA[Sastry Kodanda Rama Jammalamadaka]]>;
<![CDATA[Vudatha Chandra Prakash]]>;
<![CDATA[Burramukku Tirapathi Reddy]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[Industrial organizations select the students for placement by conducting tests based on the academic content and targeting students' cognitive levels, such as the problem-solving ability. Educational institutes are mostly dependent on the students' academic performance to judge the likelihood of Employing the students. Cognitive and academic-based models are required to accurately predict the students' employment and assess the areas of improvement required. The interrelationships must be established to achieve coherence between the models. In this paper, three predictive models have been presented, which are based on: cognitive factors, Academic factors with and without anomaly correction. The models will help the educational institutions prepare the students for the highest number of placements. The models provide the basis for prediction on the individual subject/factor basis and the overall prediction considering all the subjects/cognitive factors. 98% accuracy in predicting the placement of the students has been achieved considering both the cognitive and Academic models with a built-in anomaly correction mechanism. The anomaly correction mechanism presented in the paper improved the accuracy of prediction from 92% to 98%. The positive correlation between the cognitive and Academic model helps inferencing one model from the other.]]>
<![CDATA[CekUmpanKlik: an artificial intelligence-based application to detect Indonesian clickbait ]]>
<![CDATA[Muhammad Noor Fakhruzzaman]]>;
<![CDATA[Sie Wildan Gunawan]]>
<![CDATA[ IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 4: December 2022 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijai.v11.i4.pp%p
<![CDATA[This study attempted to deploy a high performing natural language processing model which specifically trained on flagging clickbait Indonesian news headline. The deployed model is accessible from any internet-connected device because it implements representational state transfer application programming interface (RESTful API). The application is useful to avoid clickbait news which often solely purposed to rack money but not delivering trustworthy news. With many online news outlets adopting the click-based advertising, clickbait headline become ubiquitous. Thus, newsworthy articles often cluttered with clickbait news. Leveraging state-of-the-art bidirectional encoder representation from transformers (BERT), a lightweight web application is developed. This study offloaded the computing resources needed to train the model on a separate instance of virtual server and then deployed the trained model on the cloud, while the client-side application only needs to send a request to the API and the cloud server will handle the rest, often known as three-layer architecture. This study designed and developed a web-based application to detect clickbait in Indonesian using IndoBERT as its language model. The application usage and potentials were discussed. The source code and running application are available for public with a performance of mean receiver operating characteristic-area under the curve (ROC-AUC) of 89%.]]>
