Abstract In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.
{"title":"A Novel Method for Automatic Detection of Arrhythmias Using the Unsupervised Convolutional Neural Network","authors":"Junming Zhang, Ruxian Yao, Jinfeng Gao, Gangqiang Li, Haitao Wu","doi":"10.2478/jaiscr-2023-0014","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0014","url":null,"abstract":"Abstract In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"181 - 196"},"PeriodicalIF":2.8,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49244097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.2478/jaiscr-2023-0011
Fuyun Jia, Sheng Luo, Guan Yin, Yin Ye
Abstract There are many design problems need to be optimized in various fields of engineering, and most of them belong to the NP-hard problem. The meta-heuristic algorithm is one kind of optimization method and provides an effective way to solve the NP-hard problem. Salp swarm algorithm (SSA) is a nature-inspired algorithm that mimics and mathematically models the behavior of slap swarm in nature. However, similar to most of the meta-heuristic algorithms, the traditional SSA has some shortcomings, such as entrapment in local optima. In this paper, the three main strategies are adopted to strengthen the basic SSA, including chaos theory, sine-cosine mechanism and the principle of quantum computation. Therefore, the SSA variant is proposed in this research, namely SCQ-SSA. The representative benchmark functions are employed to test the performances of the algorithms. The SCQ-SSA are compared with the seven algorithms in high-dimensional functions (1000 dimensions), seven SSA variants and six advanced variants on benchmark functions, the experiment reveals that the SCQ-SSA enhances resulting precision and alleviates local optimal problems. Besides, the SCQ-SSA is applied to resolve three classical engineering problems: tubular column design problem, tension/compression spring design problem and pressure vessel design problem. The design results indicate that these engineering problems are optimized with high accuracy and superiority by the improved SSA. The source code is available in the URL: https://github.com/ye-zero/SCQSSA/tree/main/SCQ-SSA.
{"title":"A Novel Variant of the Salp Swarm Algorithm for Engineering Optimization","authors":"Fuyun Jia, Sheng Luo, Guan Yin, Yin Ye","doi":"10.2478/jaiscr-2023-0011","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0011","url":null,"abstract":"Abstract There are many design problems need to be optimized in various fields of engineering, and most of them belong to the NP-hard problem. The meta-heuristic algorithm is one kind of optimization method and provides an effective way to solve the NP-hard problem. Salp swarm algorithm (SSA) is a nature-inspired algorithm that mimics and mathematically models the behavior of slap swarm in nature. However, similar to most of the meta-heuristic algorithms, the traditional SSA has some shortcomings, such as entrapment in local optima. In this paper, the three main strategies are adopted to strengthen the basic SSA, including chaos theory, sine-cosine mechanism and the principle of quantum computation. Therefore, the SSA variant is proposed in this research, namely SCQ-SSA. The representative benchmark functions are employed to test the performances of the algorithms. The SCQ-SSA are compared with the seven algorithms in high-dimensional functions (1000 dimensions), seven SSA variants and six advanced variants on benchmark functions, the experiment reveals that the SCQ-SSA enhances resulting precision and alleviates local optimal problems. Besides, the SCQ-SSA is applied to resolve three classical engineering problems: tubular column design problem, tension/compression spring design problem and pressure vessel design problem. The design results indicate that these engineering problems are optimized with high accuracy and superiority by the improved SSA. The source code is available in the URL: https://github.com/ye-zero/SCQSSA/tree/main/SCQ-SSA.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"131 - 149"},"PeriodicalIF":2.8,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48018350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In recent years, many studies have attempted to use deep learning for moving object detection. Some research also combines object detection methods with traditional background modeling. However, this approach may run into some problems with parameter settings and weight imbalances. In order to solve the aforementioned problems, this paper proposes a new way to combine ViBe and Faster-RCNN for moving object detection. To be more specific, our approach is to confine the candidate boxes to only retain the area containing moving objects through traditional background modeling. Furthermore, in order to make the detection able to more accurately filter out the static object, the probability of each region proposal then being retained. In this paper, we compare four famous methods, namely GMM and ViBe for the traditional methods, and DeepBS and SFEN for the deep learning-based methods. The result of the experiment shows that the proposed method has the best overall performance score among all methods. The proposed method is also robust to the dynamic background and environmental changes and is able to separate stationary objects from moving objects. Especially the overall F-measure with the CDNET 2014 dataset (like in the dynamic background and intermittent object motion cases) was 0,8572.
{"title":"Moving Object Detection for Complex Scenes by Merging BG Modeling and Deep Learning Method","authors":"Chih-Yang Lin, Han-Yi Huang, Wei-Yang Lin, Hui-Fuang Ng, K. Muchtar, Nadhila Nurdin","doi":"10.2478/jaiscr-2023-0012","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0012","url":null,"abstract":"Abstract In recent years, many studies have attempted to use deep learning for moving object detection. Some research also combines object detection methods with traditional background modeling. However, this approach may run into some problems with parameter settings and weight imbalances. In order to solve the aforementioned problems, this paper proposes a new way to combine ViBe and Faster-RCNN for moving object detection. To be more specific, our approach is to confine the candidate boxes to only retain the area containing moving objects through traditional background modeling. Furthermore, in order to make the detection able to more accurately filter out the static object, the probability of each region proposal then being retained. In this paper, we compare four famous methods, namely GMM and ViBe for the traditional methods, and DeepBS and SFEN for the deep learning-based methods. The result of the experiment shows that the proposed method has the best overall performance score among all methods. The proposed method is also robust to the dynamic background and environmental changes and is able to separate stationary objects from moving objects. Especially the overall F-measure with the CDNET 2014 dataset (like in the dynamic background and intermittent object motion cases) was 0,8572.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"151 - 163"},"PeriodicalIF":2.8,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47758457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.2478/jaiscr-2023-0015
Tacjana Niksa-Rynkiewicz, Piotr Stomma, A. Witkowska, D. Rutkowska, Adam Słowik, K. Cpałka, J. Jaworek-Korjakowska, P. Kolendo
Abstract In this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with the use of various types of Deep Neural Networks (DNNs). The impact of the prediction time horizon length on accuracy, and the influence of temperature on prediction effectiveness have been analyzed. Three types of DNNs have been implemented and tested, including: CNN (Convolutional Neural Networks), GRU (Gated Recurrent Unit), and H-MLP (Hierarchical Multilayer Perceptron). The DNN architectures are part of the Deep Learning Prediction (DLP) framework that is applied in the Deep Learning Power Prediction System (DLPPS). The system is trained based on data that comes from a real wind farm. This is significant because the prediction results strongly depend on weather conditions in specific locations. The results obtained from the proposed system, for the real data, are presented and compared. The best result has been achieved for the GRU network. The key advantage of the system is a high effectiveness prediction using a minimal subset of parameters. The prediction of wind power in wind farms is very important as wind power capacity has shown a rapid increase, and has become a promising source of renewable energies.
{"title":"An Intelligent Approach to Short-Term Wind Power Prediction Using Deep Neural Networks","authors":"Tacjana Niksa-Rynkiewicz, Piotr Stomma, A. Witkowska, D. Rutkowska, Adam Słowik, K. Cpałka, J. Jaworek-Korjakowska, P. Kolendo","doi":"10.2478/jaiscr-2023-0015","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0015","url":null,"abstract":"Abstract In this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with the use of various types of Deep Neural Networks (DNNs). The impact of the prediction time horizon length on accuracy, and the influence of temperature on prediction effectiveness have been analyzed. Three types of DNNs have been implemented and tested, including: CNN (Convolutional Neural Networks), GRU (Gated Recurrent Unit), and H-MLP (Hierarchical Multilayer Perceptron). The DNN architectures are part of the Deep Learning Prediction (DLP) framework that is applied in the Deep Learning Power Prediction System (DLPPS). The system is trained based on data that comes from a real wind farm. This is significant because the prediction results strongly depend on weather conditions in specific locations. The results obtained from the proposed system, for the real data, are presented and compared. The best result has been achieved for the GRU network. The key advantage of the system is a high effectiveness prediction using a minimal subset of parameters. The prediction of wind power in wind farms is very important as wind power capacity has shown a rapid increase, and has become a promising source of renewable energies.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"197 - 210"},"PeriodicalIF":2.8,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43807750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yasin Görmez, Halil Arslan, Y. Işık, İbrahim Ethem Dadaş
A lot of work has been done to prevent attacks from external sources and a great deal of success has been achieved. However, studies to detect internal attacks aren’t sufficient today. One of the most important studies for the detection of insider attacks is User and Entity Behavior Analysis (UEBA). In this letter, UEBA studies in the literature were reviewed and The Computer Emergency and Response Team Dataset was analyzed (CERT). For this purpose, preprocessing and feature extraction steps were applied on CERT datasets. Several log files combined with respect to user and for each user the number of activities in the specified time interval were obtained. The python code of these preprocessing and feature extraction steps were shared as open source in GitHub platform. In the final phase, future analysis was described and UEBA system planned to be designed was explained.
{"title":"A User and Entity Behavior Analysis for SIEM Systems: Preprocessing of The Computer Emergency and Response Team Dataset","authors":"Yasin Görmez, Halil Arslan, Y. Işık, İbrahim Ethem Dadaş","doi":"10.55195/jscai.1213782","DOIUrl":"https://doi.org/10.55195/jscai.1213782","url":null,"abstract":"A lot of work has been done to prevent attacks from external sources and a great deal of success has been achieved. However, studies to detect internal attacks aren’t sufficient today. One of the most important studies for the detection of insider attacks is User and Entity Behavior Analysis (UEBA). In this letter, UEBA studies in the literature were reviewed and The Computer Emergency and Response Team Dataset was analyzed (CERT). For this purpose, preprocessing and feature extraction steps were applied on CERT datasets. Several log files combined with respect to user and for each user the number of activities in the specified time interval were obtained. The python code of these preprocessing and feature extraction steps were shared as open source in GitHub platform. In the final phase, future analysis was described and UEBA system planned to be designed was explained.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"18 70 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83236721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.2478/jaiscr-2023-0007
Piotr Woldan, P. Duda, A. Cader, Ivan Laktionov
Abstract One of the fundamental issues of modern society is access to interesting and useful content. As the amount of available content increases, this task becomes more and more challenging. Our needs are not always formulated in words; sometimes we have to use complex data types like images. In this paper, we consider the three approaches to creating recommender systems based on image data. The proposed systems are evaluated on a real-world dataset. Two case studies are presented. The first one presents the case of an item with many similar objects in a database, and the second one with only a few similar items.
{"title":"A New Approach to Image-Based Recommender Systems with the Application of Heatmaps Maps","authors":"Piotr Woldan, P. Duda, A. Cader, Ivan Laktionov","doi":"10.2478/jaiscr-2023-0007","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0007","url":null,"abstract":"Abstract One of the fundamental issues of modern society is access to interesting and useful content. As the amount of available content increases, this task becomes more and more challenging. Our needs are not always formulated in words; sometimes we have to use complex data types like images. In this paper, we consider the three approaches to creating recommender systems based on image data. The proposed systems are evaluated on a real-world dataset. Two case studies are presented. The first one presents the case of an item with many similar objects in a database, and the second one with only a few similar items.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"16 13","pages":"63 - 72"},"PeriodicalIF":2.8,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41279434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.2478/jaiscr-2023-0008
Justyna Pawłowska, Klara Rydzewska, A. Wierzbicki
Abstract Recommendation algorithms trained on a training set containing sub-optimal decisions may increase the likelihood of making more bad decisions in the future. We call this harmful effect self-induced bias, to emphasize that the bias is driven directly by the user’s past choices. In order to better understand the nature of self-induced bias of recommendation algorithms that are used by older adults with cognitive limitations, we have used agent-based simulation. Based on state-of-the-art results in psychology of aging and cognitive science, as well as our own empirical results, we have developed a cognitive model of an e-commerce client that incorporates cognitive decision-making abilities. We have evaluated the magnitude of self-induced bias by comparing results achieved by simulated agents with and without cognitive limitations due to age. We have also proposed new recommendation algorithms designed to counteract self-induced bias. The algorithms take into account user preferences and cognitive abilities relevant to decision making. To evaluate the algorithms, we have introduced 3 benchmarks: a simple product filtering method and two types of widely used recommendation algorithms: Content-Based and Collaborative filtering. Results indicate that the new algorithms outperform benchmarks both in terms of increasing the utility of simulated agents (both old and young), and in reducing self-induced bias.
{"title":"Using Cognitive Models to Understand and Counteract the Effect of Self-Induced Bias on Recommendation Algorithms","authors":"Justyna Pawłowska, Klara Rydzewska, A. Wierzbicki","doi":"10.2478/jaiscr-2023-0008","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0008","url":null,"abstract":"Abstract Recommendation algorithms trained on a training set containing sub-optimal decisions may increase the likelihood of making more bad decisions in the future. We call this harmful effect self-induced bias, to emphasize that the bias is driven directly by the user’s past choices. In order to better understand the nature of self-induced bias of recommendation algorithms that are used by older adults with cognitive limitations, we have used agent-based simulation. Based on state-of-the-art results in psychology of aging and cognitive science, as well as our own empirical results, we have developed a cognitive model of an e-commerce client that incorporates cognitive decision-making abilities. We have evaluated the magnitude of self-induced bias by comparing results achieved by simulated agents with and without cognitive limitations due to age. We have also proposed new recommendation algorithms designed to counteract self-induced bias. The algorithms take into account user preferences and cognitive abilities relevant to decision making. To evaluate the algorithms, we have introduced 3 benchmarks: a simple product filtering method and two types of widely used recommendation algorithms: Content-Based and Collaborative filtering. Results indicate that the new algorithms outperform benchmarks both in terms of increasing the utility of simulated agents (both old and young), and in reducing self-induced bias.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"73 - 94"},"PeriodicalIF":2.8,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46907173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.2478/jaiscr-2023-0010
T. Praczyk
Abstract Modularity is a feature of most small, medium and large–scale living organisms that has evolved over many years of evolution. A lot of artificial systems are also modular, however, in this case, the modularity is the most frequently a consequence of a handmade design process. Modular systems that emerge automatically, as a result of a learning process, are very rare. What is more, we do not know mechanisms which result in modularity. The main goal of the paper is to continue the work of other researchers on the origins of modularity, which is a form of optimal organization of matter, and the mechanisms that led to the spontaneous formation of modular living forms in the process of evolution in response to limited resources and environmental variability. The paper focuses on artificial neural networks and proposes a number of mechanisms operating at the genetic level, both those borrowed from the natural world and those designed by hand, the use of which may lead to network modularity and hopefully to an increase in their effectiveness. In addition, the influence of external factors on the shape of the networks, such as the variability of tasks and the conditions in which these tasks are performed, is also analyzed. The analysis is performed using the Hill Climb Assembler Encoding constructive neuro-evolutionary algorithm. The algorithm was extended with various module-oriented mechanisms and tested under various conditions. The aim of the tests was to investigate how individual mechanisms involved in the evolutionary process and factors external to this process affect modularity and efficiency of neural networks.
{"title":"Emerging Modularity During the Evolution of Neural Networks","authors":"T. Praczyk","doi":"10.2478/jaiscr-2023-0010","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0010","url":null,"abstract":"Abstract Modularity is a feature of most small, medium and large–scale living organisms that has evolved over many years of evolution. A lot of artificial systems are also modular, however, in this case, the modularity is the most frequently a consequence of a handmade design process. Modular systems that emerge automatically, as a result of a learning process, are very rare. What is more, we do not know mechanisms which result in modularity. The main goal of the paper is to continue the work of other researchers on the origins of modularity, which is a form of optimal organization of matter, and the mechanisms that led to the spontaneous formation of modular living forms in the process of evolution in response to limited resources and environmental variability. The paper focuses on artificial neural networks and proposes a number of mechanisms operating at the genetic level, both those borrowed from the natural world and those designed by hand, the use of which may lead to network modularity and hopefully to an increase in their effectiveness. In addition, the influence of external factors on the shape of the networks, such as the variability of tasks and the conditions in which these tasks are performed, is also analyzed. The analysis is performed using the Hill Climb Assembler Encoding constructive neuro-evolutionary algorithm. The algorithm was extended with various module-oriented mechanisms and tested under various conditions. The aim of the tests was to investigate how individual mechanisms involved in the evolutionary process and factors external to this process affect modularity and efficiency of neural networks.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"107 - 126"},"PeriodicalIF":2.8,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47811291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.2478/jaiscr-2023-0009
T. Szmuc, Rafał Mrówka, Marek Brańka, Jakub Ficoń, Piotr Pięta
Abstract Scanning real 3D objects face many technical challenges. Stationary solutions allow for accurate scanning. However, they usually require special and expensive equipment. Competitive mobile solutions (handheld scanners, LiDARs on vehicles, etc.) do not allow for an accurate and fast mapping of the surface of the scanned object. The article proposes an end-to-end automated solution that enables the use of widely available mobile and stationary scanners. The related system generates a full 3D model of the object based on multiple depth sensors. For this purpose, the scanned object is marked with markers. Markers type and positions are automatically detected and mapped to a template mesh. The reference template is automatically selected for the scanned object, which is then transformed according to the data from the scanners with non-rigid transformation. The solution allows for the fast scanning of complex and varied size objects, constituting a set of training data for segmentation and classification systems of 3D scenes. The main advantage of the proposed solution is its efficiency, which enables real-time scanning and the ability to generate a mesh with a regular structure. It is critical for training data for machine learning algorithms. The source code is available at https://github.com/SATOffice/improved_scanner3D.
{"title":"A Novel Method for Fast Generation of 3D Objects from Multiple Depth Sensors","authors":"T. Szmuc, Rafał Mrówka, Marek Brańka, Jakub Ficoń, Piotr Pięta","doi":"10.2478/jaiscr-2023-0009","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0009","url":null,"abstract":"Abstract Scanning real 3D objects face many technical challenges. Stationary solutions allow for accurate scanning. However, they usually require special and expensive equipment. Competitive mobile solutions (handheld scanners, LiDARs on vehicles, etc.) do not allow for an accurate and fast mapping of the surface of the scanned object. The article proposes an end-to-end automated solution that enables the use of widely available mobile and stationary scanners. The related system generates a full 3D model of the object based on multiple depth sensors. For this purpose, the scanned object is marked with markers. Markers type and positions are automatically detected and mapped to a template mesh. The reference template is automatically selected for the scanned object, which is then transformed according to the data from the scanners with non-rigid transformation. The solution allows for the fast scanning of complex and varied size objects, constituting a set of training data for segmentation and classification systems of 3D scenes. The main advantage of the proposed solution is its efficiency, which enables real-time scanning and the ability to generate a mesh with a regular structure. It is critical for training data for machine learning algorithms. The source code is available at https://github.com/SATOffice/improved_scanner3D.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"95 - 105"},"PeriodicalIF":2.8,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45183656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.2478/jaiscr-2023-0006
J. Bilski, Jacek Smoląg, Bartosz Kowalczyk, K. Grzanek, I. Izonin
Abstract This paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is associated with significant computational complexity, and thus computation time. As a result, when the neural network has a big number of weights, the algorithm becomes practically ineffective. This article presents a new parallel approach to the computations in Levenberg-Marquardt neural network learning algorithm. The proposed solution is based on vector instructions to effectively reduce the high computational time of this algorithm. The new approach was tested on several examples involving the problems of classification and function approximation, and next it was compared with a classical computational method. The article presents in detail the idea of parallel neural network computations and shows the obtained acceleration for different problems.
{"title":"Fast Computational Approach to the Levenberg-Marquardt Algorithm for Training Feedforward Neural Networks","authors":"J. Bilski, Jacek Smoląg, Bartosz Kowalczyk, K. Grzanek, I. Izonin","doi":"10.2478/jaiscr-2023-0006","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0006","url":null,"abstract":"Abstract This paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is associated with significant computational complexity, and thus computation time. As a result, when the neural network has a big number of weights, the algorithm becomes practically ineffective. This article presents a new parallel approach to the computations in Levenberg-Marquardt neural network learning algorithm. The proposed solution is based on vector instructions to effectively reduce the high computational time of this algorithm. The new approach was tested on several examples involving the problems of classification and function approximation, and next it was compared with a classical computational method. The article presents in detail the idea of parallel neural network computations and shows the obtained acceleration for different problems.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"45 - 61"},"PeriodicalIF":2.8,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45531702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：