Pub Date : 2022-07-31DOI: 10.5121/ijaia.2022.13405
C. Atheeq, Mohammad Mohammad, Aleem Mohammed
Besides causing awful fatalities resulting in deaths and significant resources like many acres of timberland and dwelling places, forest fires are a significant threat to sound enormous wilderness biologically and environmentally. Consistently, a considerable number of fires around the globe reason debacles to different habitats and layouts. The stated matter has been the investigation premium for a significant length of time; there is a considerable amount of good concentrated on arrangements available for testing or perhaps ready to be utilized to determine this disadvantage. Woods and actual flames have been severe issues for quite some time. Presently, there is a wide range of answers for distinguishing woods fires. Individuals are utilizing sensors to determine the fire. However, this case isn't workable for vast sections of land woods. This paper discusses another fire-recognition methodology with incremental advancements. Specifically, we put forward a stage-Artificial Intelligence. The PC innovation strategies for acknowledgment and whereabouts of smog and fires, in light of the inert photographs or the graphics captured by the cameras. AI for tracing down the fires. The accuracy relies on the calculations that use dataset values later divided in various test and train sets, respectively.
{"title":"Prior Bush Fire Identification Mechanism based on Machine Learning Algorithms","authors":"C. Atheeq, Mohammad Mohammad, Aleem Mohammed","doi":"10.5121/ijaia.2022.13405","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13405","url":null,"abstract":"Besides causing awful fatalities resulting in deaths and significant resources like many acres of timberland and dwelling places, forest fires are a significant threat to sound enormous wilderness biologically and environmentally. Consistently, a considerable number of fires around the globe reason debacles to different habitats and layouts. The stated matter has been the investigation premium for a significant length of time; there is a considerable amount of good concentrated on arrangements available for testing or perhaps ready to be utilized to determine this disadvantage. Woods and actual flames have been severe issues for quite some time. Presently, there is a wide range of answers for distinguishing woods fires. Individuals are utilizing sensors to determine the fire. However, this case isn't workable for vast sections of land woods. This paper discusses another fire-recognition methodology with incremental advancements. Specifically, we put forward a stage-Artificial Intelligence. The PC innovation strategies for acknowledgment and whereabouts of smog and fires, in light of the inert photographs or the graphics captured by the cameras. AI for tracing down the fires. The accuracy relies on the calculations that use dataset values later divided in various test and train sets, respectively.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124307373","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 : 2022-07-31DOI: 10.5121/ijaia.2022.13402
Yiqi Deng, Siu Ming Yiu
A major source of information can be taken from financial news articles, which have some correlations about the fluctuation of stock trends. In this paper, we investigate the influences of financial news on the stock trends, from a multi-instance view. The intuition behind this is based on the news uncertainty in random news occurrences and the lack of annotation for every single financial news. Under the scenario of Multiple Instance Learning (MIL) where training instances are arranged in bags, and a label is assigned for the entire bag instead of instances, we develop a flexible and adaptive multi-instance learning model and evaluate its ability in directional movement forecast of Standard & Poor’s 500 index on financial news dataset. Specifically, we treat each trading day as one bag, with certain amounts of news happening on each trading day as instances in each bag. Experiment results demonstrate that our proposed multiinstance-based framework gains outstanding results in terms of the accuracy of trend prediction, compared with other state-of-art approaches and baselines.
{"title":"Multiple Instance Learning Networks for Stock Movements Prediction with Financial News","authors":"Yiqi Deng, Siu Ming Yiu","doi":"10.5121/ijaia.2022.13402","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13402","url":null,"abstract":"A major source of information can be taken from financial news articles, which have some correlations about the fluctuation of stock trends. In this paper, we investigate the influences of financial news on the stock trends, from a multi-instance view. The intuition behind this is based on the news uncertainty in random news occurrences and the lack of annotation for every single financial news. Under the scenario of Multiple Instance Learning (MIL) where training instances are arranged in bags, and a label is assigned for the entire bag instead of instances, we develop a flexible and adaptive multi-instance learning model and evaluate its ability in directional movement forecast of Standard & Poor’s 500 index on financial news dataset. Specifically, we treat each trading day as one bag, with certain amounts of news happening on each trading day as instances in each bag. Experiment results demonstrate that our proposed multiinstance-based framework gains outstanding results in terms of the accuracy of trend prediction, compared with other state-of-art approaches and baselines.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125892548","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 : 2022-03-31DOI: 10.5121/ijaia.2022.13201
Sajedul Talukder, F. Hossen
Early identification of COVID-19 is critical for preventing death and significant illness. People living in remote parts of resource-constrained countries find it more difficult to get tested due to a lack of adequate testing. As a result, having a primary filtering tool that can assist us in simplifying bulk COVID testing to prevent community spread is vital. In this paper, we introduce CovFilter, a low-cost portable device for COVID-19 prediction for resource-constrained rural communities, with the goal of encouraging people to be tested for COVID-19 in a more informed manner. CovFilter Hardware Module collects health parameters from three sensors while the CovFilter Prediction Module predicts COVID-19 status using the health data. We train supervised learning algorithms and an artificial neural network to predict COVID-19 from vital sign readings where MultilayerPerceptron outperformed ANN, NaiveBayes, Logistic, SGD, DecisionStump, and SVM with an F1 of 93.22%. We further show that a weighted majority voting ensemble classifier can outperform all single classifiers achieving an F1 of over 94%.
{"title":"COVFILTER: A Low-cost Portable Device for the Prediction of Covid-19 for Resource-Constrained Rural Communities","authors":"Sajedul Talukder, F. Hossen","doi":"10.5121/ijaia.2022.13201","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13201","url":null,"abstract":"Early identification of COVID-19 is critical for preventing death and significant illness. People living in remote parts of resource-constrained countries find it more difficult to get tested due to a lack of adequate testing. As a result, having a primary filtering tool that can assist us in simplifying bulk COVID testing to prevent community spread is vital. In this paper, we introduce CovFilter, a low-cost portable device for COVID-19 prediction for resource-constrained rural communities, with the goal of encouraging people to be tested for COVID-19 in a more informed manner. CovFilter Hardware Module collects health parameters from three sensors while the CovFilter Prediction Module predicts COVID-19 status using the health data. We train supervised learning algorithms and an artificial neural network to predict COVID-19 from vital sign readings where MultilayerPerceptron outperformed ANN, NaiveBayes, Logistic, SGD, DecisionStump, and SVM with an F1 of 93.22%. We further show that a weighted majority voting ensemble classifier can outperform all single classifiers achieving an F1 of over 94%.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122898768","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 : 2022-03-31DOI: 10.5121/ijaia.2022.13203
A. Alzayed, Waheeda Almayyan, A. Al-Hunaiyyan
In the current era, the amount of data generated from various device sources and business transactions is rising exponentially, and the current machine learning techniques are not feasible for handling the massive volume of data. Two commonly adopted schemes exist to solve such issues scaling up the data mining algorithms and data reduction. Scaling the data mining algorithms is not the best way, but data reduction is feasible. There are two approaches to reducing datasets selecting an optimal subset of features from the initial dataset or eliminating those that contribute less information. Overweight and obesity are increasing worldwide, and forecasting future overweight or obesity could help intervention. Our primary objective is to find the optimal subset of features to diagnose obesity. This article proposes adapting a bagging algorithm based on filter-based feature selection to improve the prediction accuracy of obesity with a minimal number of feature subsets. We utilized several machine learning algorithms for classifying the obesity classes and several filter feature selection methods to maximize the classifier accuracy. Based on the results of experiments, Pairwise Consistency and Pairwise Correlation techniques are shown to be promising tools for feature selection in respect of the quality of obtained feature subset and computation efficiency. Analyzing the results obtained from the original and modified datasets has improved the classification accuracy and established a relationship between obesity/overweight and common risk factors such as weight, age, and physical activity patterns.
{"title":"Diagnosis of Obesity Level based on Bagging Ensemble Classifier and Feature Selection Methods","authors":"A. Alzayed, Waheeda Almayyan, A. Al-Hunaiyyan","doi":"10.5121/ijaia.2022.13203","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13203","url":null,"abstract":"In the current era, the amount of data generated from various device sources and business transactions is rising exponentially, and the current machine learning techniques are not feasible for handling the massive volume of data. Two commonly adopted schemes exist to solve such issues scaling up the data mining algorithms and data reduction. Scaling the data mining algorithms is not the best way, but data reduction is feasible. There are two approaches to reducing datasets selecting an optimal subset of features from the initial dataset or eliminating those that contribute less information. Overweight and obesity are increasing worldwide, and forecasting future overweight or obesity could help intervention. Our primary objective is to find the optimal subset of features to diagnose obesity. This article proposes adapting a bagging algorithm based on filter-based feature selection to improve the prediction accuracy of obesity with a minimal number of feature subsets. We utilized several machine learning algorithms for classifying the obesity classes and several filter feature selection methods to maximize the classifier accuracy. Based on the results of experiments, Pairwise Consistency and Pairwise Correlation techniques are shown to be promising tools for feature selection in respect of the quality of obtained feature subset and computation efficiency. Analyzing the results obtained from the original and modified datasets has improved the classification accuracy and established a relationship between obesity/overweight and common risk factors such as weight, age, and physical activity patterns.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127100713","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 : 2022-03-31DOI: 10.5121/ijaia.2022.13205
Karim Amzile, Rajaa Amzile
Artificial intelligence techniques are still revealing their pros; however, several fields have benefited from these techniques. In this study we applied the Decision Tree (DT-CART) method derived from artificial intelligence techniques to the prediction of the creditworthy of bank customers, for this we used historical data of bank customers. However we have adopted the flowing process, for this purpose we started with a data preprocessing in which we clean the data and we deleted all rows with outliers or missing values, then we fixed the variable to be explained (dependent or Target) and we also thought to eliminate all explanatory (independent) variables that are not significant using univariate analysis as well as the correlation matrix, then we applied our CART decision tree method using the SPSS tool. After completing our process of building our model (DT-CART), we started the process of evaluating and testing the performance of our model, by which we found that the accuracy and precision of our model is 71%, so we calculated the error ratios, and we found that the error rate equal to 29%, this allowed us to conclude that our model at a fairly good level in terms of precision, predictability and very precisely in predicting the solvency of our banking customers.
{"title":"Credit Risk Management using Artificial Intelligence Techniques","authors":"Karim Amzile, Rajaa Amzile","doi":"10.5121/ijaia.2022.13205","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13205","url":null,"abstract":"Artificial intelligence techniques are still revealing their pros; however, several fields have benefited from these techniques. In this study we applied the Decision Tree (DT-CART) method derived from artificial intelligence techniques to the prediction of the creditworthy of bank customers, for this we used historical data of bank customers. However we have adopted the flowing process, for this purpose we started with a data preprocessing in which we clean the data and we deleted all rows with outliers or missing values, then we fixed the variable to be explained (dependent or Target) and we also thought to eliminate all explanatory (independent) variables that are not significant using univariate analysis as well as the correlation matrix, then we applied our CART decision tree method using the SPSS tool. After completing our process of building our model (DT-CART), we started the process of evaluating and testing the performance of our model, by which we found that the accuracy and precision of our model is 71%, so we calculated the error ratios, and we found that the error rate equal to 29%, this allowed us to conclude that our model at a fairly good level in terms of precision, predictability and very precisely in predicting the solvency of our banking customers.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133027325","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 : 2022-03-31DOI: 10.5121/ijaia.2022.13202
Teerath Kumar, Muhammad Turab, Shahnawaz Talpur, Rob Brennan, Malika Bendechache
Forged documents specifically passport, driving licence and VISA stickers are used for fraud purposes including robbery, theft and many more. So detecting forged characters from documents is a significantly important and challenging task in digital forensic imaging. Forged characters detection has two big challenges. First challenge is, data for forged characters detection is extremely difficult to get due to several reasons including limited access of data, unlabeled data or work is done on private data. Second challenge is, deep learning (DL) algorithms require labeled data, which poses a further challenge as getting labeled is tedious, time-consuming, expensive and requires domain expertise. To end these issues, in this paper we propose a novel algorithm, which generates the three datasets namely forged characters detection for passport (FCD-P), forged characters detection for driving licence (FCD-D) and forged characters detection for VISA stickers (FCD-V). To the best of our knowledge, we are the first to release these datasets. The proposed algorithm starts by reading plain document images, simulates forging simulation tasks on five different countries' passports, driving licences and VISA stickers. Then it keeps the bounding boxes as a track of the forged characters as a labeling process. Furthermore, considering the real world scenario, we performed the selected data augmentation accordingly. Regarding the stats of datasets, each dataset consists of 15000 images having size of 950 x 550 of each. For further research purpose we release our algorithm code 1 and, datasets i.e. FCD-P 2 , FCD-D 3 and FCD-V 4.
伪造的文件，特别是护照、驾驶执照和VISA贴纸，被用于欺诈目的，包括抢劫、盗窃等等。因此，文件伪造字符的检测是数字法医成像中十分重要和具有挑战性的课题。伪造字符检测面临两大挑战。第一个挑战是，伪造字符检测的数据非常难以获得，原因包括数据访问受限，未标记数据或对私人数据进行的工作。第二个挑战是，深度学习(DL)算法需要标记数据，这带来了进一步的挑战，因为标记是乏味、耗时、昂贵的，并且需要领域的专业知识。为了解决这些问题，本文提出了一种新的算法，该算法生成了护照伪造字符检测(FCD-P)、驾照伪造字符检测(FCD-D)和VISA贴纸伪造字符检测(FCD-V)三个数据集。据我们所知，我们是第一个发布这些数据集的。该算法首先读取普通文件图像，在五个不同国家的护照、驾照和VISA贴纸上模拟伪造模拟任务。然后，它将边界框作为伪造字符的跟踪，作为标记过程。此外，考虑到现实场景，我们相应地执行了所选的数据增强。关于数据集的统计，每个数据集由15000张图像组成，每张图像的大小为950 x 550。为了进一步的研究目的，我们发布了我们的算法代码1和数据集，即fcd - p2, fcd - d3和fcd - v4。
{"title":"Forged Character Detection Datasets: Passports, Driving Licences and Visa Stickers","authors":"Teerath Kumar, Muhammad Turab, Shahnawaz Talpur, Rob Brennan, Malika Bendechache","doi":"10.5121/ijaia.2022.13202","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13202","url":null,"abstract":"Forged documents specifically passport, driving licence and VISA stickers are used for fraud purposes including robbery, theft and many more. So detecting forged characters from documents is a significantly important and challenging task in digital forensic imaging. Forged characters detection has two big challenges. First challenge is, data for forged characters detection is extremely difficult to get due to several reasons including limited access of data, unlabeled data or work is done on private data. Second challenge is, deep learning (DL) algorithms require labeled data, which poses a further challenge as getting labeled is tedious, time-consuming, expensive and requires domain expertise. To end these issues, in this paper we propose a novel algorithm, which generates the three datasets namely forged characters detection for passport (FCD-P), forged characters detection for driving licence (FCD-D) and forged characters detection for VISA stickers (FCD-V). To the best of our knowledge, we are the first to release these datasets. The proposed algorithm starts by reading plain document images, simulates forging simulation tasks on five different countries' passports, driving licences and VISA stickers. Then it keeps the bounding boxes as a track of the forged characters as a labeling process. Furthermore, considering the real world scenario, we performed the selected data augmentation accordingly. Regarding the stats of datasets, each dataset consists of 15000 images having size of 950 x 550 of each. For further research purpose we release our algorithm code 1 and, datasets i.e. FCD-P 2 , FCD-D 3 and FCD-V 4.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134280563","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 : 2022-03-31DOI: 10.5121/ijaia.2022.13204
F. Hossen, Sajedul Talukder, Refatul Fahad
COVID-19’s outbreak affected and compelled people from all walks of life to self-quarantine in their houses in order to prevent the virus from spreading. As a result of adhering to the exceedingly strict guideline, many people developed mental illnesses. Because the educational institution was closed at the time, students remained at home and practiced self-quarantine. As a result, it is necessary to identify the students who developed mental illnesses at that time. To develop AiPsych, a mobile application-based artificial psychiatrist, we train supervised and deep learning algorithms to predict the mental illness of students during the COVID-19 situation. Our experiment reveals that supervised learning outperforms deep learning, with a 97% accuracy of the Support Vector Machine (SVM) for mental illness prediction. Random Forest (RF) achieves the best accuracy of 91% for the recovery suggestion prediction. Our android application can be used by parents, educational institutes, or the government to get the predicted result of a student’s mental illness status and take proper measures to overcome the situation.
{"title":"AIPSYCH: A Mobile Application-based Artificial Psychiatrist for Predicting Mental Illness and Recovery Suggestions among Students","authors":"F. Hossen, Sajedul Talukder, Refatul Fahad","doi":"10.5121/ijaia.2022.13204","DOIUrl":"https://doi.org/10.5121/ijaia.2022.13204","url":null,"abstract":"COVID-19’s outbreak affected and compelled people from all walks of life to self-quarantine in their houses in order to prevent the virus from spreading. As a result of adhering to the exceedingly strict guideline, many people developed mental illnesses. Because the educational institution was closed at the time, students remained at home and practiced self-quarantine. As a result, it is necessary to identify the students who developed mental illnesses at that time. To develop AiPsych, a mobile application-based artificial psychiatrist, we train supervised and deep learning algorithms to predict the mental illness of students during the COVID-19 situation. Our experiment reveals that supervised learning outperforms deep learning, with a 97% accuracy of the Support Vector Machine (SVM) for mental illness prediction. Random Forest (RF) achieves the best accuracy of 91% for the recovery suggestion prediction. Our android application can be used by parents, educational institutes, or the government to get the predicted result of a student’s mental illness status and take proper measures to overcome the situation.","PeriodicalId":391502,"journal":{"name":"International Journal of Artificial Intelligence & Applications","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121514431","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：