Pub Date : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1619-1627
Anahita Sabagh Nejad, G. Fazekas
In this study, we compare a cluster-based whale optimization algorithm (WOA) with an uncombined method to find a more optimized solution for a traveling salesman problem (TSP). The main goal is to reduce the time of solving a TSP. First, we solve the TSP with the Whale optimization algorithm, later we solve it with the combined method of solving TSP which uses the clustering method, called BIRCH (balanced iterative reducing and clustering using hierarchies). Birch builds a clustering feature (CF) tree and then applies one of the clustering methods (for ex. K-means) to cluster data. Experiments performed on three datasets show that the convergence time improves by using the combined algorithm.
在这项研究中，我们比较了基于集群的鲸鱼优化算法(WOA)和非组合方法，以找到一个更优化的旅行推销员问题(TSP)的解决方案。主要目标是减少求解TSP的时间。首先，我们使用Whale优化算法求解TSP，然后我们使用聚类方法求解TSP的组合方法，称为BIRCH (balanced iterative reduction and clustering using hierarchies)。Birch构建了一个聚类特征(CF)树，然后应用其中一种聚类方法(例如K-means)来聚类数据。在三个数据集上进行的实验表明，该组合算法提高了收敛时间。
{"title":"Reducing the time needed to solve a traveling salesman problem by clustering with a Hierarchy-based algorithm","authors":"Anahita Sabagh Nejad, G. Fazekas","doi":"10.11591/ijai.v12.i4.pp1619-1627","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1619-1627","url":null,"abstract":"<div class=\"page\" title=\"Page 1\"><div class=\"layoutArea\"><div class=\"column\"><p>In this study, we compare a cluster-based whale optimization algorithm (WOA) with an uncombined method to find a more optimized solution for a traveling salesman problem (TSP). The main goal is to reduce the time of solving a TSP. First, we solve the TSP with the Whale optimization algorithm, later we solve it with the combined method of solving TSP which uses the clustering method, called BIRCH (balanced iterative reducing and clustering using hierarchies). Birch builds a clustering feature (CF) tree and then applies one of the clustering methods (for ex. K-means) to cluster data. Experiments performed on three datasets show that the convergence time improves by using the combined algorithm.</p></div></div></div>","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65353588","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1960-1973
S. Fuada, T. Adiono
This paper presents a webserver for Indonesian fishermen, to support fishing activities. This is one of the sub-systems of e-Nelayan (in English: eFisherman) architecture, which was connected to e-Nelayan Apps; it helps to provide interaction between two users, including the administrators and fishermen. Using hypertext preprocessor (PHP) language, the website was developed to function on an Apache web server, with the adaptation of my structured query language (MySQL) framework for the database. This system was subsequently divided into two parts: (1) the front-end, which is responsible for the accessibility of data collection and (2) the back-end, where administrators update or modify crucial information: price, fishing result, illegal activity report, save our ship! (SOS) potential fish zone, and ship tracking. The administrators are unable to update the real-time weather information for the front-end part. The application was found to record the information obtained from the fishermen through the e-Nelayan apps and meteorology, climatology, and geophysical agency (BMKG in Indonesian). This web system is expected to carry out the following functions: to ensure easier interactions between fishermen and administrators, to enable easy update of information, to promote monitoring and recording of results, and to ensure fishermen’s safety.
{"title":"Prototyping of e-fisherman web server to support Indonesian fishermen’s activities","authors":"S. Fuada, T. Adiono","doi":"10.11591/ijai.v12.i4.pp1960-1973","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1960-1973","url":null,"abstract":"This paper presents a webserver for Indonesian fishermen, to support fishing activities. This is one of the sub-systems of e-Nelayan (in English: eFisherman) architecture, which was connected to e-Nelayan Apps; it helps to provide interaction between two users, including the administrators and fishermen. Using hypertext preprocessor (PHP) language, the website was developed to function on an Apache web server, with the adaptation of my structured query language (MySQL) framework for the database. This system was subsequently divided into two parts: (1) the front-end, which is responsible for the accessibility of data collection and (2) the back-end, where administrators update or modify crucial information: price, fishing result, illegal activity report, save our ship! (SOS) potential fish zone, and ship tracking. The administrators are unable to update the real-time weather information for the front-end part. The application was found to record the information obtained from the fishermen through the e-Nelayan apps and meteorology, climatology, and geophysical agency (BMKG in Indonesian). This web system is expected to carry out the following functions: to ensure easier interactions between fishermen and administrators, to enable easy update of information, to promote monitoring and recording of results, and to ensure fishermen’s safety.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65356152","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1585-1592
Hamzah Abdulmalek Al-Haimi, Z. Sani, Tarmizi Ahmad Izzudin, Hadhrami Abdul Ghani, A. Azizan, Samsul Ariffin Abdul Karim
This project aims to develop a vision system that can detect traffic lightcounter and to recognise the numbers shown on it. The system used you onlylook once version 3 (YOLOv3) algorithm because of its robust performanceand reliability and able to be implemented in Nvidia Jetson nano kit. A totalof 2204 images consisting of numbers from 0-9 green and 0-9 red. Another80% (1764) from the images are used for training and 20% (440) are used fortesting. The results obtained from the training demonstrated Totalprecision=89%, Recall=99.2%, F1 score=70%, intersection over union(IoU)=70.49%, mean average precision (mAp)=87.89%, Accuracy=99.2%and the estimate total confidence rate for red and green are 98.4% and 99.3%respectively. The results were compared with the previous YOLOv5algorithm, and the results are substantially close to each other as the YOLOv5accuracy and recall at 97.5% and 97.5% respectively.
该项目旨在开发一种视觉系统，可以检测交通灯计数器并识别其上显示的数字。该系统使用了你只看一次版本3 (YOLOv3)算法，因为它具有强大的性能和可靠性，并且能够在Nvidia Jetson纳米套件中实现。总共2204张图像，由0-9绿色和0-9红色的数字组成。另外80%(1764)的图像用于训练，20%(440)用于测试。训练结果表明:Totalprecision=89%， Recall=99.2%， F1得分=70%，intersection over union(IoU)=70.49%， mean average precision (mAp)=87.89%，准确率=99.2%，对红色和绿色的估计总置信度分别为98.4%和99.3%。将结果与之前的yolov5算法进行比较，结果基本接近，yolov5的准确率和召回率分别为97.5%和97.5%。
{"title":"Traffic light counter detection comparison using you only look oncev3 and you only look oncev5 for version 3 and 5","authors":"Hamzah Abdulmalek Al-Haimi, Z. Sani, Tarmizi Ahmad Izzudin, Hadhrami Abdul Ghani, A. Azizan, Samsul Ariffin Abdul Karim","doi":"10.11591/ijai.v12.i4.pp1585-1592","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1585-1592","url":null,"abstract":"This project aims to develop a vision system that can detect traffic lightcounter and to recognise the numbers shown on it. The system used you onlylook once version 3 (YOLOv3) algorithm because of its robust performanceand reliability and able to be implemented in Nvidia Jetson nano kit. A totalof 2204 images consisting of numbers from 0-9 green and 0-9 red. Another80% (1764) from the images are used for training and 20% (440) are used fortesting. The results obtained from the training demonstrated Totalprecision=89%, Recall=99.2%, F1 score=70%, intersection over union(IoU)=70.49%, mean average precision (mAp)=87.89%, Accuracy=99.2%and the estimate total confidence rate for red and green are 98.4% and 99.3%respectively. The results were compared with the previous YOLOv5algorithm, and the results are substantially close to each other as the YOLOv5accuracy and recall at 97.5% and 97.5% respectively.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65353100","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1883-1891
Nha Tran, Toan Nguyen, Minh Nguyen, Khiet Luong, Tai Lam
Person re-identification (Person Re-ID) is a research direction on tracking and identifying people in surveillance camera systems with non-overlapping camera perspectives. Despite much research on this topic, there are still some practical problems that Person Re-ID has not yet solved, in reality, human objects can easily be obscured by obstructions such as other people, trees, luggage, umbrellas, signs, cars, motorbikes. In this paper, we propose a multibranch deep learning network architecture. In which one branch is for the representation of global features and two branches are for the representation of local features. Dividing the input image into small parts and changing the number of parts between the two branches helps the model to represent the features better. In addition, we add an attention module to the ResNet50 backbone that enhances important human characteristics and eliminates irrelevant information. To improve robustness, the model is trained by combining triplet loss and label smoothing cross-entropy loss (LSCE). Experiments are carried out on datasets Market1501, and duke multi-target multi-camera (DukeMTMC) datasets, our method achieved 96.04% rank-1, 88,11% mean average precision (mAP) on the Market1501 dataset, and 88.78% rank-1, 78,6% mAP on the DukeMTMC dataset. This method achieves performance better than some state-of-the-art methods.
{"title":"Global-local attention with triplet loss and label smoothed crossentropy for person re-identification","authors":"Nha Tran, Toan Nguyen, Minh Nguyen, Khiet Luong, Tai Lam","doi":"10.11591/ijai.v12.i4.pp1883-1891","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1883-1891","url":null,"abstract":"Person re-identification (Person Re-ID) is a research direction on tracking and identifying people in surveillance camera systems with non-overlapping camera perspectives. Despite much research on this topic, there are still some practical problems that Person Re-ID has not yet solved, in reality, human objects can easily be obscured by obstructions such as other people, trees, luggage, umbrellas, signs, cars, motorbikes. In this paper, we propose a multibranch deep learning network architecture. In which one branch is for the representation of global features and two branches are for the representation of local features. Dividing the input image into small parts and changing the number of parts between the two branches helps the model to represent the features better. In addition, we add an attention module to the ResNet50 backbone that enhances important human characteristics and eliminates irrelevant information. To improve robustness, the model is trained by combining triplet loss and label smoothing cross-entropy loss (LSCE). Experiments are carried out on datasets Market1501, and duke multi-target multi-camera (DukeMTMC) datasets, our method achieved 96.04% rank-1, 88,11% mean average precision (mAP) on the Market1501 dataset, and 88.78% rank-1, 78,6% mAP on the DukeMTMC dataset. This method achieves performance better than some state-of-the-art methods.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65355319","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1920-1927
Asad Abdo, S. M. Yusof
Over the past decade, chatbots have experienced a significant increase inpopularity, especially since the outbreak of COVID-19. In the United ArabEmirates, most businesses have accelerated their digital transformation andare relying on chatbots as a primary way to interact with customers. However,many of these chatbots lack a voice input option for customers. This studyinvestigates the benefits and challenges of incorporating artificial intelligence(AI) voice-enabled chatbots into United Arab Emirates (UAE) businesses andhow this impacts customer experience. Qualitative research techniques wereused to gather information, and the results demonstrate that implementing AIchatbots with voice input and sentiment analysis features can enhance thecustomer experience by making it more efficient and convenient.Additionally, the study found that AI chatbots can ultimately save businessestime and money, and while they may reduce the need for human agents, theywill not replace them entirely. Finally, an implementation framework andsuggestions are provided for businesses that are interested in adopting AIvoice-enabled chatbots for customer interactions.
{"title":"Exploring the impacts of using the artificial intelligence voice-enabled chatbots on customers interactions in the United Arab Emirates","authors":"Asad Abdo, S. M. Yusof","doi":"10.11591/ijai.v12.i4.pp1920-1927","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1920-1927","url":null,"abstract":"Over the past decade, chatbots have experienced a significant increase inpopularity, especially since the outbreak of COVID-19. In the United ArabEmirates, most businesses have accelerated their digital transformation andare relying on chatbots as a primary way to interact with customers. However,many of these chatbots lack a voice input option for customers. This studyinvestigates the benefits and challenges of incorporating artificial intelligence(AI) voice-enabled chatbots into United Arab Emirates (UAE) businesses andhow this impacts customer experience. Qualitative research techniques wereused to gather information, and the results demonstrate that implementing AIchatbots with voice input and sentiment analysis features can enhance thecustomer experience by making it more efficient and convenient.Additionally, the study found that AI chatbots can ultimately save businessestime and money, and while they may reduce the need for human agents, theywill not replace them entirely. Finally, an implementation framework andsuggestions are provided for businesses that are interested in adopting AIvoice-enabled chatbots for customer interactions.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65355354","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1974-1984
Muhammad Abizar, Muhammad Ferry Septian Ihzanor Syahputra, Ahmad Rizky Habibullah, Christian Sri Kusuma Aditya, Fauzi Dwi Setiawan Sumadi
One of the main challenges in developing the internet of things (IoT) is the existence of availability problems originated from the low-rate distributed denial of service attacks (LRDDoS). The complexity of IoT makes the LRDDoS hard to detect because the attack flow is performed similarly to the regular traffic. Integration of software defined IoT (SDN-Enabled IoT) is considered an alternative solution for overcoming the specified problem through a single detection point using machine learning approaches. The controller has a resource limitation for implementing the classification process. Therefore, this paper extends the usage of Feature Importance to reduce the data complexity during the model generation process and choose an appropriate feature for generating an efficient classification model. The research results show that the Gaussian Naïve Bayes (GNB) produced the most effective outcome. GNB performed better than the other algorithms because the feature reduction only selected the independent feature, which had no relation to the other features.
{"title":"Low-rate distributed denial of service attacks detection in software defined network-enabled internet of things using machine learning combined with feature importance","authors":"Muhammad Abizar, Muhammad Ferry Septian Ihzanor Syahputra, Ahmad Rizky Habibullah, Christian Sri Kusuma Aditya, Fauzi Dwi Setiawan Sumadi","doi":"10.11591/ijai.v12.i4.pp1974-1984","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1974-1984","url":null,"abstract":"One of the main challenges in developing the internet of things (IoT) is the existence of availability problems originated from the low-rate distributed denial of service attacks (LRDDoS). The complexity of IoT makes the LRDDoS hard to detect because the attack flow is performed similarly to the regular traffic. Integration of software defined IoT (SDN-Enabled IoT) is considered an alternative solution for overcoming the specified problem through a single detection point using machine learning approaches. The controller has a resource limitation for implementing the classification process. Therefore, this paper extends the usage of Feature Importance to reduce the data complexity during the model generation process and choose an appropriate feature for generating an efficient classification model. The research results show that the Gaussian Naïve Bayes (GNB) produced the most effective outcome. GNB performed better than the other algorithms because the feature reduction only selected the independent feature, which had no relation to the other features.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65355749","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1755-1764
A. Prakash, R. Sumathi, Honnudike Satyanarayana Sudhira
A reliable transit service can motivate commuters to switch their travelingmode from private to public. Providing necessary information to passengerswill reduce the uncertainties encountered during their travel and improveservice reliability. This article addresses the challenge of predicting dynamictravel times in urban areas where real-time traffic flow information isunavailable. In this perspective, a hybrid travel time estimation model(HTTEM) is proposed to predict the dynamic travel time using the predictedtravel times of the machine learning model and the preceding trip details. Theproposed model is validated using the location data of public transit buses of,Tumakuru, India. From the numerical results through error metrics, it is foundthat HTTEM improves the prediction accuracy, finally, it is concluded that theproposed model is suitable for estimating travel time in urban areas withheterogeneous traffic and limited traffic infrastructure.
{"title":"Hybrid travel time estimation model for public transit buses using limited datasets","authors":"A. Prakash, R. Sumathi, Honnudike Satyanarayana Sudhira","doi":"10.11591/ijai.v12.i4.pp1755-1764","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1755-1764","url":null,"abstract":"A reliable transit service can motivate commuters to switch their travelingmode from private to public. Providing necessary information to passengerswill reduce the uncertainties encountered during their travel and improveservice reliability. This article addresses the challenge of predicting dynamictravel times in urban areas where real-time traffic flow information isunavailable. In this perspective, a hybrid travel time estimation model(HTTEM) is proposed to predict the dynamic travel time using the predictedtravel times of the machine learning model and the preceding trip details. Theproposed model is validated using the location data of public transit buses of,Tumakuru, India. From the numerical results through error metrics, it is foundthat HTTEM improves the prediction accuracy, finally, it is concluded that theproposed model is suitable for estimating travel time in urban areas withheterogeneous traffic and limited traffic infrastructure.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65354373","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1666-1676
Soly Mathew Biju, Obada Al-Khatib, H. Sheikh, F. Oroumchian
Loss of the capability to talk or hear has psychological and social effects onthe affected individuals due to the absence of appropriate interaction. SignLanguage is used by such individuals to assist them in communicating witheach other. This paper proposes a glove called GloSign that can convertAmerican sign language to characters. This glove consists of flex and inertialmeasurement unit (IMU) sensors to identify gestures. The data from glove isuploaded on IoT platform, which makes the glove portable and wireless. Thedata from gloves is passed through a k-nearest neighbors (KNN) Algorithmmachine learning algorithm to improve the accuracy of the system. Thesystem was able to achieve an accuracy of 96.8%. The glove can also be usedto form sentences. The output is displayed on the screen or is converted tospeech. This glove can be used in communicating with people who don’t knowsign language.
{"title":"Glove based wearable devices for sign language-GloSign","authors":"Soly Mathew Biju, Obada Al-Khatib, H. Sheikh, F. Oroumchian","doi":"10.11591/ijai.v12.i4.pp1666-1676","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1666-1676","url":null,"abstract":"Loss of the capability to talk or hear has psychological and social effects onthe affected individuals due to the absence of appropriate interaction. SignLanguage is used by such individuals to assist them in communicating witheach other. This paper proposes a glove called GloSign that can convertAmerican sign language to characters. This glove consists of flex and inertialmeasurement unit (IMU) sensors to identify gestures. The data from glove isuploaded on IoT platform, which makes the glove portable and wireless. Thedata from gloves is passed through a k-nearest neighbors (KNN) Algorithmmachine learning algorithm to improve the accuracy of the system. Thesystem was able to achieve an accuracy of 96.8%. The glove can also be usedto form sentences. The output is displayed on the screen or is converted tospeech. This glove can be used in communicating with people who don’t knowsign language.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65354173","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp2048-2054
S. A. Ahmed, H. Desa, A. T. T. Hussain
Time restrictions and lack of precision demand that the initial technique be abandoned. Even though the remaining datasets had fewer identified classes than initially planned for the study, the labels were more accurate. Because of the need for additional data, a single network cannot categorize all the essential elements in a picture, including bodies of water, roads, trees, buildings, and crops. However, the final network gains some invariance in detecting these classes with environmental changes due to the different geographic positions of roads and buildings discovered in the final datasets, which could be valuable in future navigation research. At the moment, binary classifications of a single class are the only datasets that can be used for the semantic segmentation of aerial images. Even though some pictures have more than one classification, images of roads and buildings were only found in a significant number of samples. Then, the building datasets were pooled to produce a larger dataset and for the constructed models to gain some invariance on image location. Because of the massive disparity in sample size, road datasets needed to be integrated.
{"title":"Aerial image semantic segmentation based on 3D fits a small dataset of 1D","authors":"S. A. Ahmed, H. Desa, A. T. T. Hussain","doi":"10.11591/ijai.v12.i4.pp2048-2054","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp2048-2054","url":null,"abstract":"Time restrictions and lack of precision demand that the initial technique be abandoned. Even though the remaining datasets had fewer identified classes than initially planned for the study, the labels were more accurate. Because of the need for additional data, a single network cannot categorize all the essential elements in a picture, including bodies of water, roads, trees, buildings, and crops. However, the final network gains some invariance in detecting these classes with environmental changes due to the different geographic positions of roads and buildings discovered in the final datasets, which could be valuable in future navigation research. At the moment, binary classifications of a single class are the only datasets that can be used for the semantic segmentation of aerial images. Even though some pictures have more than one classification, images of roads and buildings were only found in a significant number of samples. Then, the building datasets were pooled to produce a larger dataset and for the constructed models to gain some invariance on image location. Because of the massive disparity in sample size, road datasets needed to be integrated.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65356575","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 : 2023-12-01DOI: 10.11591/ijai.v12.i4.pp1611-1618
Dwi Marisa Midyanti, Syamsul Bahri, S. Suhardi, H. I. Midyanti
Bantuan Langsung Tunai Dana Desa (BLT-DD), or known as Village Fund Direct Cash Assistance is assistance from the Indonesian government which causes problems and conflicts in the community when the assistance is not on target. The classification algorithm is proven to use in determining BLT-DD recipients. In this study, the radial basis function (RBF) and elman recurrent neural network (ERNN) models compare to classify the eligibility of BLTDD recipients. In the experiment, the optimal performance of the RBF and ERNN compare in determining the eligibility of BLT-DD recipients. Also, it’s compared with the classification algorithm that implements the same data, namely BLT-DD data for Kubu Raya District. The experimental results show the effectiveness of the RBF model in recognizing test data, while the ERNN model is effective in identifying test data. The RBF and ERNN models can achieve the same total accuracy of 98.10%.
Bantuan Langsung Tunai Dana Desa (BLT-DD)，或称为村庄基金直接现金援助，是印度尼西亚政府的援助，当援助没有达到目标时，会在社区中引起问题和冲突。该分类算法已被证明可用于确定BLT-DD接收者。本研究比较了径向基函数(RBF)和elman递归神经网络(ERNN)模型对BLTDD受者资格的分类。在实验中，比较了RBF和ERNN在确定BLT-DD接受者资格方面的最优性能。并与实现相同数据的分类算法，即Kubu Raya区的BLT-DD数据进行了比较。实验结果表明，RBF模型在识别测试数据方面是有效的，而ERNN模型在识别测试数据方面是有效的。RBF和ERNN模型的总准确率均为98.10%。
{"title":"Eligibility of village fund direct cash assistance recipients using artificial neural network","authors":"Dwi Marisa Midyanti, Syamsul Bahri, S. Suhardi, H. I. Midyanti","doi":"10.11591/ijai.v12.i4.pp1611-1618","DOIUrl":"https://doi.org/10.11591/ijai.v12.i4.pp1611-1618","url":null,"abstract":"Bantuan Langsung Tunai Dana Desa (BLT-DD), or known as Village Fund Direct Cash Assistance is assistance from the Indonesian government which causes problems and conflicts in the community when the assistance is not on target. The classification algorithm is proven to use in determining BLT-DD recipients. In this study, the radial basis function (RBF) and elman recurrent neural network (ERNN) models compare to classify the eligibility of BLTDD recipients. In the experiment, the optimal performance of the RBF and ERNN compare in determining the eligibility of BLT-DD recipients. Also, it’s compared with the classification algorithm that implements the same data, namely BLT-DD data for Kubu Raya District. The experimental results show the effectiveness of the RBF model in recognizing test data, while the ERNN model is effective in identifying test data. The RBF and ERNN models can achieve the same total accuracy of 98.10%.","PeriodicalId":52221,"journal":{"name":"IAES International Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65353499","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号