Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068456
H. Nguyen, H.C. Warrier, Yogesh Gupta
Federated learning (FL) is an emerging technique used to collaboratively train a global machine learning model while keeping the data localized on the user devices. The main obstacle to FL's practical implementation is the Non-Independent and Identical (Non-IID) data distribution across users, which slows convergence and degrades performance. To tackle this fundamental issue, we propose a method (called ComFed) that enhances the whole training process on both the client and server sides. The key idea of ComFed is to simultaneously utilize client-variance reduction techniques to facilitate server aggregation and global adaptive update techniques to accelerate learning. Our experiments show that ComFed can improve state-of-the-art algorithms dedicated to Non-IID data.
{"title":"A Novel Approach for Federated Learning with Non-IID Data","authors":"H. Nguyen, H.C. Warrier, Yogesh Gupta","doi":"10.1109/ISCMI56532.2022.10068456","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068456","url":null,"abstract":"Federated learning (FL) is an emerging technique used to collaboratively train a global machine learning model while keeping the data localized on the user devices. The main obstacle to FL's practical implementation is the Non-Independent and Identical (Non-IID) data distribution across users, which slows convergence and degrades performance. To tackle this fundamental issue, we propose a method (called ComFed) that enhances the whole training process on both the client and server sides. The key idea of ComFed is to simultaneously utilize client-variance reduction techniques to facilitate server aggregation and global adaptive update techniques to accelerate learning. Our experiments show that ComFed can improve state-of-the-art algorithms dedicated to Non-IID data.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114962846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068443
You-Xuan Huang, N. Huang, J. Tzeng, James Liang, Ching-Wei Su, Yao-Ting Li
In recent years, online learning systems have become increasingly popular among students and teachers because they are unlimited by time and space. A brand-new online learning system called QSticker, which is based on a line bot, has also been proposed to improve the online learning environment. However, there is still a problem in the online learning system that teachers and students cannot communicate face-to-face in time and care about students' learning status, so if there is not a proper analysis of students' performance, it will lead to poor learning conditions. There have been many pieces of research about knowledge tracing in the past. Nonetheless, we found that the knowledge tracing models cannot optimally predict students' proficiency in knowledge concepts in some online learning environments such as QSticker. Therefore, we proposed a Proficiency Prediction System based on Gated Recurrent Unit (GRU). Since many students have similar trajectories in learning, the system uses the most straightforward exercise answering behavior data, including the correctness of his answer and the knowledge concept correlations. It then calculates other characteristics, such as the difficulty of each knowledge concept, to predict students' proficiency in all knowledge concepts in the course. The accomplished experiments show that our model can achieve 71% accuracy on the collected dataset. With the help of this system, we can predict the difficulties students may encounter in the learning process. In addition, to be practically used in teaching scenarios, we also designed an analysis platform for this system.
{"title":"Proficiency Prediction System for Online Learning Based on Recurrent Neural Networks","authors":"You-Xuan Huang, N. Huang, J. Tzeng, James Liang, Ching-Wei Su, Yao-Ting Li","doi":"10.1109/ISCMI56532.2022.10068443","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068443","url":null,"abstract":"In recent years, online learning systems have become increasingly popular among students and teachers because they are unlimited by time and space. A brand-new online learning system called QSticker, which is based on a line bot, has also been proposed to improve the online learning environment. However, there is still a problem in the online learning system that teachers and students cannot communicate face-to-face in time and care about students' learning status, so if there is not a proper analysis of students' performance, it will lead to poor learning conditions. There have been many pieces of research about knowledge tracing in the past. Nonetheless, we found that the knowledge tracing models cannot optimally predict students' proficiency in knowledge concepts in some online learning environments such as QSticker. Therefore, we proposed a Proficiency Prediction System based on Gated Recurrent Unit (GRU). Since many students have similar trajectories in learning, the system uses the most straightforward exercise answering behavior data, including the correctness of his answer and the knowledge concept correlations. It then calculates other characteristics, such as the difficulty of each knowledge concept, to predict students' proficiency in all knowledge concepts in the course. The accomplished experiments show that our model can achieve 71% accuracy on the collected dataset. With the help of this system, we can predict the difficulties students may encounter in the learning process. In addition, to be practically used in teaching scenarios, we also designed an analysis platform for this system.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115707144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068467
L. Anbarasi, M. Jawahar, Bipasa Mukherjee, Modigari Narendra, Masoume Rahimi, A. Gandomi
Air travel has become one of the most popular forms of transportation around the globe because of its easy access, quick commute, and low cost. Due to rising demand, it is now feasible to connect to almost every area of the globe, with an increasing number of direct flights to key cities. Examining the Air routes through social network analysis (SNA) helps us determine the terminals that are significant actors in the business. Analysis can be performed to identify which airports are the main players in the sector by studying the network of flight routes. The proposed work helps to know the features and patterns of air transport and identifies the busiest flight route in different cities using social network analysis. For this purpose, data of all Brazilian flights in 2019, 2020, and 2021 from the Nation Civil Aviation Agency Brazil are considered. The network pattern, along with its characteristics, are analyzed in this study.
{"title":"Brazilian Air Traffic Network Analysis Using Social Network Metrics","authors":"L. Anbarasi, M. Jawahar, Bipasa Mukherjee, Modigari Narendra, Masoume Rahimi, A. Gandomi","doi":"10.1109/ISCMI56532.2022.10068467","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068467","url":null,"abstract":"Air travel has become one of the most popular forms of transportation around the globe because of its easy access, quick commute, and low cost. Due to rising demand, it is now feasible to connect to almost every area of the globe, with an increasing number of direct flights to key cities. Examining the Air routes through social network analysis (SNA) helps us determine the terminals that are significant actors in the business. Analysis can be performed to identify which airports are the main players in the sector by studying the network of flight routes. The proposed work helps to know the features and patterns of air transport and identifies the busiest flight route in different cities using social network analysis. For this purpose, data of all Brazilian flights in 2019, 2020, and 2021 from the Nation Civil Aviation Agency Brazil are considered. The network pattern, along with its characteristics, are analyzed in this study.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129006924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068441
R.-Q. Tian, L. Liboni, M. Capretz
Predictive maintenance is set to prevent downtime and failures of equipment and processes to meet the quality and availability requirements of several industrial, commercial, and even residential activities. This paper proposes CAE-AD, a novel convolutional autoencoder anomaly detection method that relies only on normal operation data for training the intelligent classi-fier. The method also accommodates a sliding window algorithm for generating the input from sensor readings, which accounts for the dynamic characteristics of the data. The anomaly detection is accomplished by comparing the convolutional autoencoder reconstruction error to a threshold value to segregate between normal and anomalous predictions. The threshold value is found by minimizing the False Positive Rates and False Negative Rates. Using a benchmark water pump sensor time-series data, the model successfully classified all water pump breakdowns and correctly identified 98.8% of anomalous data and 94.8 % of normal data using a chosen best window length of the past 37 sensor readings.
{"title":"Anomaly Detection with Convolutional Autoencoder for Predictive Maintenance","authors":"R.-Q. Tian, L. Liboni, M. Capretz","doi":"10.1109/ISCMI56532.2022.10068441","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068441","url":null,"abstract":"Predictive maintenance is set to prevent downtime and failures of equipment and processes to meet the quality and availability requirements of several industrial, commercial, and even residential activities. This paper proposes CAE-AD, a novel convolutional autoencoder anomaly detection method that relies only on normal operation data for training the intelligent classi-fier. The method also accommodates a sliding window algorithm for generating the input from sensor readings, which accounts for the dynamic characteristics of the data. The anomaly detection is accomplished by comparing the convolutional autoencoder reconstruction error to a threshold value to segregate between normal and anomalous predictions. The threshold value is found by minimizing the False Positive Rates and False Negative Rates. Using a benchmark water pump sensor time-series data, the model successfully classified all water pump breakdowns and correctly identified 98.8% of anomalous data and 94.8 % of normal data using a chosen best window length of the past 37 sensor readings.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129968382","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 advancement of Artificial Intelligence has led to a surge in its application in Information Technology (IT) Operations, often termed Artificial Intelligence for IT Operations (AIOPS). One of the most challenging problems in AIOPS is IT Service Management (ITSM), which deals with incidents and anomalies of users, often referred to as tickets. These tickets are resolved by the IT firm support system, which plays a significant role in the company's user experiences, productivity, and profit. Recent advances have been made to automate the prediction of IT incidents and resolve them in a minimal time, utilizing AI models. In this paper, we take stock of the work in this domain and review the challenges. We also highlight the open topics that require further investigation for the advancement of the field.
{"title":"AI for Information Tecchnology Operation (AIOps): A Review of IT Incident Risk Prediction","authors":"Salman Ahmed, Muskaan Singh, Brendan Doherty, E. Ramlan, Kathryn Harkin, Damien Coyle","doi":"10.1109/ISCMI56532.2022.10068482","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068482","url":null,"abstract":"The advancement of Artificial Intelligence has led to a surge in its application in Information Technology (IT) Operations, often termed Artificial Intelligence for IT Operations (AIOPS). One of the most challenging problems in AIOPS is IT Service Management (ITSM), which deals with incidents and anomalies of users, often referred to as tickets. These tickets are resolved by the IT firm support system, which plays a significant role in the company's user experiences, productivity, and profit. Recent advances have been made to automate the prediction of IT incidents and resolve them in a minimal time, utilizing AI models. In this paper, we take stock of the work in this domain and review the challenges. We also highlight the open topics that require further investigation for the advancement of the field.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125443202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068480
A. Vakil, E. Blasch, Robert Ewing, Jia Li
As technology trends towards automation, deep neural network (DNN) based methods become more and more desirable from a technological, economical, and societal standpoint. However, owing to the way that these black box technologies operate, it can be difficult to troubleshoot potential errors, especially when dealing with data that the human mind cannot intuitively understand. For this reason, the use of explainable artificial intelligence (XAI) is integral to obtaining interpretability and understanding of these systems' techniques. The paper explores some of the known uses of XAI in Generative Adversarial Networks (GANs); i.e., in processing electro-optical (EO) and passive radiofrequency (Passive RF) data to achieve heterogenous sensor fusion. GANs are capable of generating realistic images, music text, and other forms of data, and the use of deep convolutional generative adversarial networks (DCGANs) to process such information provides “richer” corrective feedback from which the model can train from. Using the DCGAN approach, tone can provide visualizations from different types of neural networks and use them as a training source for the multiple visualizations input (MVI) DCGAN. The MVI-DCGAN uses these visualizations in order to track the vehicle target and further differentiate between other overlay visualization data and the generated overlay input visualizations. The paper demonstrates multiple sources of visualization input from different neural networks for the training of the MVI-DCGAN for a more robust training and directing the discriminator towards focusing on the P-RF aspects of the visualizations.
{"title":"MVI-DCGAN Insights into Heterogenous EO and Passive RF Fusion","authors":"A. Vakil, E. Blasch, Robert Ewing, Jia Li","doi":"10.1109/ISCMI56532.2022.10068480","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068480","url":null,"abstract":"As technology trends towards automation, deep neural network (DNN) based methods become more and more desirable from a technological, economical, and societal standpoint. However, owing to the way that these black box technologies operate, it can be difficult to troubleshoot potential errors, especially when dealing with data that the human mind cannot intuitively understand. For this reason, the use of explainable artificial intelligence (XAI) is integral to obtaining interpretability and understanding of these systems' techniques. The paper explores some of the known uses of XAI in Generative Adversarial Networks (GANs); i.e., in processing electro-optical (EO) and passive radiofrequency (Passive RF) data to achieve heterogenous sensor fusion. GANs are capable of generating realistic images, music text, and other forms of data, and the use of deep convolutional generative adversarial networks (DCGANs) to process such information provides “richer” corrective feedback from which the model can train from. Using the DCGAN approach, tone can provide visualizations from different types of neural networks and use them as a training source for the multiple visualizations input (MVI) DCGAN. The MVI-DCGAN uses these visualizations in order to track the vehicle target and further differentiate between other overlay visualization data and the generated overlay input visualizations. The paper demonstrates multiple sources of visualization input from different neural networks for the training of the MVI-DCGAN for a more robust training and directing the discriminator towards focusing on the P-RF aspects of the visualizations.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125605272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068479
Kevin Fan, Mélanie Jouaiti, K. Dautenhahn, C. Nehaniv
Domestic service robots have the promising potential of bringing significant services to the general population, and more importantly, successful applications of universal domestic service robots can potentially help mitigate critical societal issues such as senior care. In order to do so, domestic service robots need to integrate seamlessly into home environments. However, home environments are dynamic, complex and filled with personal items. Therefore, ambiguity can quickly arise for robots operating in such rich environments. In this paper, we propose an object ambiguity determination system that can determine the level of ambiguity in robot object selection tasks with fuzzy logic data integration. Additionally, we propose a functional human attention assessment system with fuzzy logic that enables the robot to determine user attention before committing to general disambiguation processes. Our preliminary results show that the proposed fuzzy logic inference systems can reliably estimate the robot object selection task ambiguity from object confidence level and the number of potential target objects that satisfy the user's command. Furthermore, fuzzy inference is applied to decide human eye gaze direction robustly. These subsystems can be utilized in the context of human-robot interaction to guide the robot when to seek feedback from a human partner in order to disambiguate reference in domestic service tasks. The source code of all proposed systems is available publicly on GitHub.1
{"title":"Fuzzy Object Ambiguity Determination and Human Attention Assessment for Domestic Service Robots","authors":"Kevin Fan, Mélanie Jouaiti, K. Dautenhahn, C. Nehaniv","doi":"10.1109/ISCMI56532.2022.10068479","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068479","url":null,"abstract":"Domestic service robots have the promising potential of bringing significant services to the general population, and more importantly, successful applications of universal domestic service robots can potentially help mitigate critical societal issues such as senior care. In order to do so, domestic service robots need to integrate seamlessly into home environments. However, home environments are dynamic, complex and filled with personal items. Therefore, ambiguity can quickly arise for robots operating in such rich environments. In this paper, we propose an object ambiguity determination system that can determine the level of ambiguity in robot object selection tasks with fuzzy logic data integration. Additionally, we propose a functional human attention assessment system with fuzzy logic that enables the robot to determine user attention before committing to general disambiguation processes. Our preliminary results show that the proposed fuzzy logic inference systems can reliably estimate the robot object selection task ambiguity from object confidence level and the number of potential target objects that satisfy the user's command. Furthermore, fuzzy inference is applied to decide human eye gaze direction robustly. These subsystems can be utilized in the context of human-robot interaction to guide the robot when to seek feedback from a human partner in order to disambiguate reference in domestic service tasks. The source code of all proposed systems is available publicly on GitHub.1","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134424567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068461
Ravi Kansagara, Ank Zaman
The use of technology is one of the keys to combating the covid-19 pandemic. This paper proposes and demonstrates an implementation of a digital vaccine passport /certificate is, called VPass, for taking non-essential services. This passport will represent someone's vaccination status while preserving all personal data safe. The developed application is platform-independent and accessible using any device connected to the internet. This application also keeps an offline copy in a device or a printed copy of a vaccine passport for convenience. A quick response (QR) code will show the COVID-19 vaccination status. All data stored and transmitted between the front (to the end user) and backend (to and from the server) are fully encrypted. This paper presents the technical detail of implementing a digital vaccine passport for COVID-19. This application could also be used for keeping other vaccination records/certificates.
{"title":"VPass: An Open-Source COVID-19 Vaccine Passport, and Vaccine Hesitancy","authors":"Ravi Kansagara, Ank Zaman","doi":"10.1109/ISCMI56532.2022.10068461","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068461","url":null,"abstract":"The use of technology is one of the keys to combating the covid-19 pandemic. This paper proposes and demonstrates an implementation of a digital vaccine passport /certificate is, called VPass, for taking non-essential services. This passport will represent someone's vaccination status while preserving all personal data safe. The developed application is platform-independent and accessible using any device connected to the internet. This application also keeps an offline copy in a device or a printed copy of a vaccine passport for convenience. A quick response (QR) code will show the COVID-19 vaccination status. All data stored and transmitted between the front (to the end user) and backend (to and from the server) are fully encrypted. This paper presents the technical detail of implementing a digital vaccine passport for COVID-19. This application could also be used for keeping other vaccination records/certificates.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121532738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068475
Cintia Lia Szucs, B. Kővári
Handwritten signatures are one of the most commonly used biometrics. Because signatures are widely accepted, their verification is a fundamental problem. The aim of signature verification is to decide about the origin of the signature so the ability to detect forgeries. Until offline signature verification is based on the scanned image of the signatures, online signature verification applies different electronic devices to capture the signatures. Online signatures also contain dynamic information such as the pressure or inclination angle of the pen, so it is much more challenging to forge online signatures than offline ones. In addition, it is possible to define and calculate further derived features based on the captured ones. The captured features are usually function features, which means they assign a value to each signature point or specified sets of signature points. This work aims to compare the usability of common derived function features using a dynamic time warping (DTW) based solution.
{"title":"The Usability of Derived Function Features in Online Signature Verification","authors":"Cintia Lia Szucs, B. Kővári","doi":"10.1109/ISCMI56532.2022.10068475","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068475","url":null,"abstract":"Handwritten signatures are one of the most commonly used biometrics. Because signatures are widely accepted, their verification is a fundamental problem. The aim of signature verification is to decide about the origin of the signature so the ability to detect forgeries. Until offline signature verification is based on the scanned image of the signatures, online signature verification applies different electronic devices to capture the signatures. Online signatures also contain dynamic information such as the pressure or inclination angle of the pen, so it is much more challenging to forge online signatures than offline ones. In addition, it is possible to define and calculate further derived features based on the captured ones. The captured features are usually function features, which means they assign a value to each signature point or specified sets of signature points. This work aims to compare the usability of common derived function features using a dynamic time warping (DTW) based solution.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121880927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-26DOI: 10.1109/ISCMI56532.2022.10068469
Rohit Salgotra, Seyedali Mirjalili, A. Gandomi
Differential evolution (DE) has proved its significance for optimizing various real-world applications and standard benchmarks. In this work, a self-adaptive version of DE is proposed namely LSHADESPA by employing three major modifications, i) proportional shrinking population mechanism for reducing computational burden, ii) simulated annealing-based scaling factor (F) for improving the exploration properties, and iii) oscillating inertia weight-based crossover rate (CR) for a balancing exploitation and exploration. The proposed algorithm has been experimentally tested on IEEE CEC 2017 and IEEE CEC 2021 benchmarks. For performance evaluation, a comparison with respect to JADE, SaDE, SHADE, LSHADE, MVMO, and others has been performed. Experimental and statistical results affirm the superior performance of the proposed LSHADESPA algorithms with respect to other algorithms.
{"title":"Enhancing Differential Evolution Algorithm: Adaptation for CEC 2017 and CEC 2021 Test Suites","authors":"Rohit Salgotra, Seyedali Mirjalili, A. Gandomi","doi":"10.1109/ISCMI56532.2022.10068469","DOIUrl":"https://doi.org/10.1109/ISCMI56532.2022.10068469","url":null,"abstract":"Differential evolution (DE) has proved its significance for optimizing various real-world applications and standard benchmarks. In this work, a self-adaptive version of DE is proposed namely LSHADESPA by employing three major modifications, i) proportional shrinking population mechanism for reducing computational burden, ii) simulated annealing-based scaling factor (F) for improving the exploration properties, and iii) oscillating inertia weight-based crossover rate (CR) for a balancing exploitation and exploration. The proposed algorithm has been experimentally tested on IEEE CEC 2017 and IEEE CEC 2021 benchmarks. For performance evaluation, a comparison with respect to JADE, SaDE, SHADE, LSHADE, MVMO, and others has been performed. Experimental and statistical results affirm the superior performance of the proposed LSHADESPA algorithms with respect to other algorithms.","PeriodicalId":340397,"journal":{"name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122325040","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：