Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2027-2035
Andre Citro Febriliyan Lanyak, Agi Prasetiadi, Haris Budi Widodo, Muhammad Hisyam Ghani, Abiyan Athallah
Dental caries is the highest prevalent dental disease in the world by 2022. Caries can be stopped by early detection of patients through efficient screening. Previously, there have been several methods used to detect caries such as single shot multibox detector (SSD), faster region-based convolutional neural network (Faster R-CNN) and you only look once (YOLO). This research aims to develop accurate dental caries detection using Faster R-CNN. Using a dataset collected from scraping on the internet, this research is started by creating an original dataset consisting of 81 base images which are then augmented to a total of 486 images and annotated by dental health experts from Jenderal Soedirman University. Transfer learning using pre-trained Faster R-CNN residual network (ResNet)-50 and ResNet-101 model is utilized to detect and localise dental caries. The Faster R-CNN ResNet-50 model trained using the Adam optimizer produces a mean average precision (mAP) of 0.213, and those using the momentum optimizer produce a mAP of 0.177. While the Faster R-CNN ResNet-101 model trained using the Adam optimizer produces a mAP of 0.192, and those using the momentum optimizer produce a mAP of 0.004. The model trained on the dataset showed satisfactory results in detecting dental caries, especially ResNet-50 with Adam optimizer.
{"title":"Dental caries detection using faster region-based convolutional neural network with residual network","authors":"Andre Citro Febriliyan Lanyak, Agi Prasetiadi, Haris Budi Widodo, Muhammad Hisyam Ghani, Abiyan Athallah","doi":"10.11591/ijai.v13.i2.pp2027-2035","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2027-2035","url":null,"abstract":"Dental caries is the highest prevalent dental disease in the world by 2022. Caries can be stopped by early detection of patients through efficient screening. Previously, there have been several methods used to detect caries such as single shot multibox detector (SSD), faster region-based convolutional neural network (Faster R-CNN) and you only look once (YOLO). This research aims to develop accurate dental caries detection using Faster R-CNN. Using a dataset collected from scraping on the internet, this research is started by creating an original dataset consisting of 81 base images which are then augmented to a total of 486 images and annotated by dental health experts from Jenderal Soedirman University. Transfer learning using pre-trained Faster R-CNN residual network (ResNet)-50 and ResNet-101 model is utilized to detect and localise dental caries. The Faster R-CNN ResNet-50 model trained using the Adam optimizer produces a mean average precision (mAP) of 0.213, and those using the momentum optimizer produce a mAP of 0.177. While the Faster R-CNN ResNet-101 model trained using the Adam optimizer produces a mAP of 0.192, and those using the momentum optimizer produce a mAP of 0.004. The model trained on the dataset showed satisfactory results in detecting dental caries, especially ResNet-50 with Adam optimizer.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"7 34","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229340","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1526-1534
Agus Tedyyana, Osman Ghazali, Onno W. Purbo, M. A. A. Seman
The increasing rate of cybercrime in the digital world highlights the importance of having a reliable intrusion detection system (IDS) to detect unauthorized attacks and notify administrators. IDS can leverage machine learning techniques to identify patterns of attacks and provide real-time notifications. In building a successful IDS, selecting the right features is crucial as it determines the accuracy of the predictions made by the model. This paper presents a new IDS algorithm that combines the rectified linear unit (ReLU) activation function with a pigeon-inspired optimizer in feature selection. The proposed algorithm was evaluated on network security layer - knowledge discovery in databases (NSL-KDD) datasets and demonstrated improved performance in terms of training speed and accuracy compared to previous IDS models. Thus, the use of the ReLU activation function and a pigeon-inspired optimizer in feature selection can significantly enhance the effectiveness of an IDS in detecting unauthorized attacks.
{"title":"Enhancing intrusion detection system using rectified linear unit function in pigeon inspired optimization algorithm","authors":"Agus Tedyyana, Osman Ghazali, Onno W. Purbo, M. A. A. Seman","doi":"10.11591/ijai.v13.i2.pp1526-1534","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1526-1534","url":null,"abstract":"The increasing rate of cybercrime in the digital world highlights the importance of having a reliable intrusion detection system (IDS) to detect unauthorized attacks and notify administrators. IDS can leverage machine learning techniques to identify patterns of attacks and provide real-time notifications. In building a successful IDS, selecting the right features is crucial as it determines the accuracy of the predictions made by the model. This paper presents a new IDS algorithm that combines the rectified linear unit (ReLU) activation function with a pigeon-inspired optimizer in feature selection. The proposed algorithm was evaluated on network security layer - knowledge discovery in databases (NSL-KDD) datasets and demonstrated improved performance in terms of training speed and accuracy compared to previous IDS models. Thus, the use of the ReLU activation function and a pigeon-inspired optimizer in feature selection can significantly enhance the effectiveness of an IDS in detecting unauthorized attacks.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"9 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230178","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1262-1271
Archana Bhaskar, Rajeev Ranjan
Distributed data processing model has been one of the primary components in the case of data-intensive applications; furthermore, due to advancements in technologies, there has been a huge volume of data generation of diverse nature. Hadoop map reduce framework is responsible for adopting the ease of deployment mechanism in an open-source framework. The existing Hadoop MapReduce framework possesses high makespan time and high Input/Output overhead and it mainly affects the cost of a model. Thus, this research work presents an optimized cost aware resource provisioning MapReduce model also known as the cost-effective resource provisioning MapReduce (CRP-MR) model. CRP-MR model introduces the two integrated approaches to minimize the cost; at first, this model presents the optimal resource optimization and optimal Input/Output optimization cleansing in the Hadoop MapReduce (HMR) scheduler. CRP-MR is evaluated considering the bioinformatics dataset and CRP-MR performs better than the existing model.
{"title":"Cost-aware optimal resource provisioning Map-Reduce scheduler for hadoop framework","authors":"Archana Bhaskar, Rajeev Ranjan","doi":"10.11591/ijai.v13.i2.pp1262-1271","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1262-1271","url":null,"abstract":"Distributed data processing model has been one of the primary components in the case of data-intensive applications; furthermore, due to advancements in technologies, there has been a huge volume of data generation of diverse nature. Hadoop map reduce framework is responsible for adopting the ease of deployment mechanism in an open-source framework. The existing Hadoop MapReduce framework possesses high makespan time and high Input/Output overhead and it mainly affects the cost of a model. Thus, this research work presents an optimized cost aware resource provisioning MapReduce model also known as the cost-effective resource provisioning MapReduce (CRP-MR) model. CRP-MR model introduces the two integrated approaches to minimize the cost; at first, this model presents the optimal resource optimization and optimal Input/Output optimization cleansing in the Hadoop MapReduce (HMR) scheduler. CRP-MR is evaluated considering the bioinformatics dataset and CRP-MR performs better than the existing model. ","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"29 47","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233061","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1741-1752
Herry Sujaini, Arif Bijaksana Putra
Detecting local languages in Indonesia is essential for recognizing linguistic diversity, promoting intercultural understanding, preserving endangered languages, and improving access to education and services. By identifying and documenting these languages, we can support language preservation efforts, provide tailored resources for communities, and celebrate the unique cultural heritage of different ethnic groups. Ultimately, this encourages a more accepting and open-minded society, prioritizing various languages and cultural customs. This research aims to identify the most suitable algorithm for language detection in Indonesian regional languages and gain insights into their unique characteristics through n-gram analysis. By understanding language diversity, the study contributes to preserving Indonesia's cultural and linguistic heritage and improving language detection techniques. This study compares the performance of five algorithms (Naïve Bayes, K-nearest neighbors (KNN), least-squares, Kullback Leibler divergence, and Kolmogorov Smirnov test) to determine the most accurate and efficient method for language identification. Incorporating trigram features alongside unigrams and bigrams significantly improved the model's performance, with F1 scores increasing from 0.923 to 0.959. The study found that using more features leads to better accuracy, with Naïve Bayes and KNN emerging as the top-performing algorithms for language identification.
{"title":"Analysis of language identification algorithms for regional Indonesian languages","authors":"Herry Sujaini, Arif Bijaksana Putra","doi":"10.11591/ijai.v13.i2.pp1741-1752","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1741-1752","url":null,"abstract":"Detecting local languages in Indonesia is essential for recognizing linguistic diversity, promoting intercultural understanding, preserving endangered languages, and improving access to education and services. By identifying and documenting these languages, we can support language preservation efforts, provide tailored resources for communities, and celebrate the unique cultural heritage of different ethnic groups. Ultimately, this encourages a more accepting and open-minded society, prioritizing various languages and cultural customs. This research aims to identify the most suitable algorithm for language detection in Indonesian regional languages and gain insights into their unique characteristics through n-gram analysis. By understanding language diversity, the study contributes to preserving Indonesia's cultural and linguistic heritage and improving language detection techniques. This study compares the performance of five algorithms (Naïve Bayes, K-nearest neighbors (KNN), least-squares, Kullback Leibler divergence, and Kolmogorov Smirnov test) to determine the most accurate and efficient method for language identification. Incorporating trigram features alongside unigrams and bigrams significantly improved the model's performance, with F1 scores increasing from 0.923 to 0.959. The study found that using more features leads to better accuracy, with Naïve Bayes and KNN emerging as the top-performing algorithms for language identification.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"45 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141277856","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}
The sea brings many benefits for society, especially for a maritime country such as Indonesia. The potential in various sectors is limited only by the willingness of a party to invest in it. One such investment is in learning the knowledge and information that can be gathered from the sea, and even predicting its behavior with enough data. Using a residual LSTM algorithm, we will predict the tidal level in eastern Bintan island, a tropical island on the tip of Malay peninsula. The dataset is acquired from two sensor points in eastern Bintan coast from July 2018 to June 2019 for a span of one year, giving a total of 7,961 data points. The residual LSTM model consists of a residual wrapper with two consecutive LSTM layers and one dense layer. The model is also compared with variations of LSTM and RNN models. The result of the residual LSTM model has an MAE value of 0.1495 cm and an RMSE value of 0.3353 cm, compared to the baseline model’s 1.1148 cm and 1.4107 cm respectively. The model also has an RMSE value improvement of 76.23% compared to the base model.
{"title":"Predicting tidal level in tropical Eastern Bintan waters using residual long short-term memory","authors":"Agsanshina Raka Syakti, Syahri Rhamadhan, Ghora Laziola, Pahrizal Pahrizal, Dony Apdillah, Nola Ritha","doi":"10.11591/ijai.v13.i2.pp2003-2010","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2003-2010","url":null,"abstract":"The sea brings many benefits for society, especially for a maritime country such as Indonesia. The potential in various sectors is limited only by the willingness of a party to invest in it. One such investment is in learning the knowledge and information that can be gathered from the sea, and even predicting its behavior with enough data. Using a residual LSTM algorithm, we will predict the tidal level in eastern Bintan island, a tropical island on the tip of Malay peninsula. The dataset is acquired from two sensor points in eastern Bintan coast from July 2018 to June 2019 for a span of one year, giving a total of 7,961 data points. The residual LSTM model consists of a residual wrapper with two consecutive LSTM layers and one dense layer. The model is also compared with variations of LSTM and RNN models. The result of the residual LSTM model has an MAE value of 0.1495 cm and an RMSE value of 0.3353 cm, compared to the baseline model’s 1.1148 cm and 1.4107 cm respectively. The model also has an RMSE value improvement of 76.23% compared to the base model.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"7 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229093","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1339-1347
N. Rahayu, R. Ferdiana, S. Kusumawardani
The ACM/IEEE Computing Curricula 2020 includes the study of relational databases in four of its six disciplines. However, a domain ontology model of multidisciplinary database course does not exist. Therefore, the current study aims to build a domain ontology model for the multidisciplinary database course. The research process comprises three phases: a review of database course contents based on the ACM/IEEE Computing Curricula 2020, a literature review of relevant domain ontology models, and a design research phase using the NeOn methodology framework. The ontology building involves the ontology reuse and reengineering of existing models, along with the construction of some classes from a non-ontological resource. The approach to ontology reuse and reengineering demonstrates ontology reusability. The final domain ontology model is then evaluated using two ontology syntactic metrics: Relationship Richness and Information Richness. These metrics reflect the diversity of relationships and the breadth of knowledge in the model, respectively. In conclusion, the current research contributes to the Computing Curricula by providing an ontology model for a multidisciplinary database course. The model, developed through ontology reuse and reengineering and the integration of non-ontological resources, exhibits more diverse relationships and represents a broader range of knowledge.
{"title":"An enhanced domain ontology model of database course in computing curricula","authors":"N. Rahayu, R. Ferdiana, S. Kusumawardani","doi":"10.11591/ijai.v13.i2.pp1339-1347","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1339-1347","url":null,"abstract":"The ACM/IEEE Computing Curricula 2020 includes the study of relational databases in four of its six disciplines. However, a domain ontology model of multidisciplinary database course does not exist. Therefore, the current study aims to build a domain ontology model for the multidisciplinary database course. The research process comprises three phases: a review of database course contents based on the ACM/IEEE Computing Curricula 2020, a literature review of relevant domain ontology models, and a design research phase using the NeOn methodology framework. The ontology building involves the ontology reuse and reengineering of existing models, along with the construction of some classes from a non-ontological resource. The approach to ontology reuse and reengineering demonstrates ontology reusability. The final domain ontology model is then evaluated using two ontology syntactic metrics: Relationship Richness and Information Richness. These metrics reflect the diversity of relationships and the breadth of knowledge in the model, respectively. In conclusion, the current research contributes to the Computing Curricula by providing an ontology model for a multidisciplinary database course. The model, developed through ontology reuse and reengineering and the integration of non-ontological resources, exhibits more diverse relationships and represents a broader range of knowledge.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230771","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2433-2440
Ku Muhammad Naim Ku Khalif, Noryanti Muhammad, Mohd Khairul Bazli Mohd Aziz, Mohammad Isa Irawan, Mohammad Iqbal, Muhammad Nanda Setiawan
Machine learning in cardiovascular disease has broad applications in healthcare, automatically identifying hidden patterns in vast data without human intervention. Early-stage cardiovascular illness can benefit from machine learning models in drug selection. The integration of granular computing, specifically z-numbers, with machine learning algorithms, is suggested for cardiovascular disease identification. Granular computing enables handling unpredictable and imprecise situations, akin to human cognitive abilities. Machine learning algorithms such as Naïve Bayes, K-Nearest Neighbor (KNN), Random Forest, and Gradient Boosting are commonly used in constructing these models. Experimental findings indicate that incorporating granular computing into machine learning models enhances the ability to represent uncertainty and improves accuracy in cardiovascular disease detection.
{"title":"Advancing machine learning for identifying cardiovascular disease via granular computing","authors":"Ku Muhammad Naim Ku Khalif, Noryanti Muhammad, Mohd Khairul Bazli Mohd Aziz, Mohammad Isa Irawan, Mohammad Iqbal, Muhammad Nanda Setiawan","doi":"10.11591/ijai.v13.i2.pp2433-2440","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2433-2440","url":null,"abstract":"Machine learning in cardiovascular disease has broad applications in healthcare, automatically identifying hidden patterns in vast data without human intervention. Early-stage cardiovascular illness can benefit from machine learning models in drug selection. The integration of granular computing, specifically z-numbers, with machine learning algorithms, is suggested for cardiovascular disease identification. Granular computing enables handling unpredictable and imprecise situations, akin to human cognitive abilities. Machine learning algorithms such as Naïve Bayes, K-Nearest Neighbor (KNN), Random Forest, and Gradient Boosting are commonly used in constructing these models. Experimental findings indicate that incorporating granular computing into machine learning models enhances the ability to represent uncertainty and improves accuracy in cardiovascular disease detection.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"36 43","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232822","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1585-1595
Aris Tjahyanto, Rivanda Putra Pratama, A. M. Shiddiqi
Feature selection plays a crucial role in the development of high-performance classification models. We propose an innovative method for detecting fake accounts. This method leverages the percentage overlap technique to refine feature selection. We introduce our technique upon earlier work that showcased the enhanced efficacy of the Naïve Bayesian classifier through dataset normalization. Our study employs a dataset of account profiles sourced from Twitter, which we normalize using the Min-Max method. We analyze the results through a series of comprehensive experiments involving diverse classification algorithms—such as Naïve Bayes, decision tree, k-nearest neighbors (KNN), deep learning, and support vector machines (SVM). Our experimental results demonstrate a 100% accuracy achieved by the SVM and deep learning classifiers. The results are attributed to the percentage overlap technique, which facilitates the identification of four highly informative features. These findings outperform models with more extensive feature sets, underscoring the efficacy of our approach.
{"title":"Improved performance of fake account classifiers with percentage overlap features selection","authors":"Aris Tjahyanto, Rivanda Putra Pratama, A. M. Shiddiqi","doi":"10.11591/ijai.v13.i2.pp1585-1595","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1585-1595","url":null,"abstract":"Feature selection plays a crucial role in the development of high-performance classification models. We propose an innovative method for detecting fake accounts. This method leverages the percentage overlap technique to refine feature selection. We introduce our technique upon earlier work that showcased the enhanced efficacy of the Naïve Bayesian classifier through dataset normalization. Our study employs a dataset of account profiles sourced from Twitter, which we normalize using the Min-Max method. We analyze the results through a series of comprehensive experiments involving diverse classification algorithms—such as Naïve Bayes, decision tree, k-nearest neighbors (KNN), deep learning, and support vector machines (SVM). Our experimental results demonstrate a 100% accuracy achieved by the SVM and deep learning classifiers. The results are attributed to the percentage overlap technique, which facilitates the identification of four highly informative features. These findings outperform models with more extensive feature sets, underscoring the efficacy of our approach.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"10 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234188","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1838-1844
Aicha Khalfaoui, Abdelmajid Badri, Ilham El Mourabit
Deep neural networks are currently employed to detect weapons, and although these techniques provide a high level of accuracy, it still suffers from large weight parameters and a slow inference speed. When it comes to real-world applications, such as weapon detection, these methods are often not suitable for deployment on embedded devices. Because of the huge number of parameters and poor efficiency. The most recent object detection technique, which belongs to the YOLOv5 class, is commonly used for detecting weapons. However, it faces some difficulties such as high computational parameters and an unfavorable detection rate. to solve these shortcomings. an enhanced lightweight Yolov5s approach is suggested. Which consists of a combination of YOLOv5 and GhostNet modules. To evaluate the efficacy of the suggested technique, a set of experiments was performed on the Sohas weapon dataset., which is commonly used as a reference dataset in the field. Compared to the original YOLOv5, the results indicate a slight increase in the proposed model's mean Average Precision (mAP). Furthermore, there has been a reduction of 2.7 in GFLOPs and weights, and the number of model parameters has decreased by 1.42.
{"title":"A lightweight YOLOv5 for real-time dangerous weapons detection","authors":"Aicha Khalfaoui, Abdelmajid Badri, Ilham El Mourabit","doi":"10.11591/ijai.v13.i2.pp1838-1844","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1838-1844","url":null,"abstract":"Deep neural networks are currently employed to detect weapons, and although these techniques provide a high level of accuracy, it still suffers from large weight parameters and a slow inference speed. When it comes to real-world applications, such as weapon detection, these methods are often not suitable for deployment on embedded devices. Because of the huge number of parameters and poor efficiency. The most recent object detection technique, which belongs to the YOLOv5 class, is commonly used for detecting weapons. However, it faces some difficulties such as high computational parameters and an unfavorable detection rate. to solve these shortcomings. an enhanced lightweight Yolov5s approach is suggested. Which consists of a combination of YOLOv5 and GhostNet modules. To evaluate the efficacy of the suggested technique, a set of experiments was performed on the Sohas weapon dataset., which is commonly used as a reference dataset in the field. Compared to the original YOLOv5, the results indicate a slight increase in the proposed model's mean Average Precision (mAP). Furthermore, there has been a reduction of 2.7 in GFLOPs and weights, and the number of model parameters has decreased by 1.42.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"34 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233019","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1535-1546
Sri Yulianto Joko Prasetyo, Wiwin Sulistyo, Erwien Christanto, Bistok Hasiholan Simanjuntak
The aim of this research is to compile a tsunami wave hazard scale based on built-up land density extracted and classified by machine learning from Sentinel 2A satellite and digital elevation model (DEM) imageries. This research was carried out in 5 stages, namely: (i) pre-processing of Sentinel 2A and DEM images, (ii) Classification of VI data using the machine learning algorithms, (iii) Spatial prediction using the ordinary kriging method, (iv) Field testing using the confusion matrix method, (v) Preparation of decision matrix for tsunami wave hazard. The results of the study show that the most accurate classification algorithm for classifying built-up indices data is the k-nearest neighbor (k-NN) algorithm. The results of the statistical accuracy test show that the most accurate is normalized difference built-up index (NDBI) with a mean of square error (MSE) value of 0.073 and a mean of absolute error (MAE) of 0.003. DEM analysis shows that the research area is at an altitude of 0–15 meters above sea level so it is in the high vulnerability to medium vulnerability category. Field testing showed user accuracy of 91.11%, manufacturer accuracy of 92.16%, and overall average accuracy of 91%.
本研究的目的是从哨兵 2A 卫星和数字高程模型（DEM）图像中通过机器学习提取并分类的建筑密集度为基础，编制海啸波浪危害等级表。这项研究分五个阶段进行，即：(i) 对 Sentinel 2A 和 DEM 图像进行预处理；(ii) 利用机器学习算法对 VI 数据进行分类；(iii) 利用普通克里金法进行空间预测；(iv) 利用混淆矩阵法进行实地测试；(v) 编制海啸波浪危害决策矩阵。研究结果表明，对已建指数数据进行分类的最准确分类算法是 k 近邻（k-NN）算法。统计准确性测试结果表明，最准确的是归一化差异建成指数（NDBI），其平均平方误差（MSE）值为 0.073，平均绝对误差（MAE）为 0.003。DEM 分析表明，研究区域的海拔高度为 0-15 米，因此属于高脆弱度到中等脆弱度类别。实地测试显示，用户准确率为 91.11%，制造商准确率为 92.16%，总体平均准确率为 91%。
{"title":"Computer model for detecting tsunami wave hazard on built-up land using machine learning and sentinel 2A satellite imagery","authors":"Sri Yulianto Joko Prasetyo, Wiwin Sulistyo, Erwien Christanto, Bistok Hasiholan Simanjuntak","doi":"10.11591/ijai.v13.i2.pp1535-1546","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1535-1546","url":null,"abstract":"The aim of this research is to compile a tsunami wave hazard scale based on built-up land density extracted and classified by machine learning from Sentinel 2A satellite and digital elevation model (DEM) imageries. This research was carried out in 5 stages, namely: (i) pre-processing of Sentinel 2A and DEM images, (ii) Classification of VI data using the machine learning algorithms, (iii) Spatial prediction using the ordinary kriging method, (iv) Field testing using the confusion matrix method, (v) Preparation of decision matrix for tsunami wave hazard. The results of the study show that the most accurate classification algorithm for classifying built-up indices data is the k-nearest neighbor (k-NN) algorithm. The results of the statistical accuracy test show that the most accurate is normalized difference built-up index (NDBI) with a mean of square error (MSE) value of 0.073 and a mean of absolute error (MAE) of 0.003. DEM analysis shows that the research area is at an altitude of 0–15 meters above sea level so it is in the high vulnerability to medium vulnerability category. Field testing showed user accuracy of 91.11%, manufacturer accuracy of 92.16%, and overall average accuracy of 91%.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"49 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232372","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：