Pub Date : 2021-12-05DOI: 10.1109/SSCI50451.2021.9659926
Fred D. Foss, Truls Stenrud, P. Haddow
Genetic Network Programming is a relatively unexplored evolutionary algorithm, particularly for more advanced tasks. Foraging is a challenging domain within swarm robotics, since it requires an aptitude for multiple rudimentary behaviours. The work herein thus investigates the application of Genetic Network Programming for multiple nest foraging. Further, a variant of Genetic Network Programming, which incorporates neural network benefits is proposed and evaluated. The results are compared to state-of-the-art foraging algorithms including the generic Neuro-evolution of Augmented Technologies and Novelty Search algorithms and the more application specific Multiple-Place Foraging Algorithm. Results indicate that Genetic Network Programming shows promise.
{"title":"Investigating Genetic Network Programming for Multiple Nest Foraging","authors":"Fred D. Foss, Truls Stenrud, P. Haddow","doi":"10.1109/SSCI50451.2021.9659926","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9659926","url":null,"abstract":"Genetic Network Programming is a relatively unexplored evolutionary algorithm, particularly for more advanced tasks. Foraging is a challenging domain within swarm robotics, since it requires an aptitude for multiple rudimentary behaviours. The work herein thus investigates the application of Genetic Network Programming for multiple nest foraging. Further, a variant of Genetic Network Programming, which incorporates neural network benefits is proposed and evaluated. The results are compared to state-of-the-art foraging algorithms including the generic Neuro-evolution of Augmented Technologies and Novelty Search algorithms and the more application specific Multiple-Place Foraging Algorithm. Results indicate that Genetic Network Programming shows promise.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131642230","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9659848
Shuo Yang, M. Barlow, E. Lakshika, Kathryn E. Kasmarik
Trust has been widely recognized as one of the most important factors influencing team performance. The ability to accurately evaluate the trustworthiness of team members (agents) is crucial for effective team performance. Interaction data among agents are suitable sources of information determining each agent's trustworthiness. However, the existing interaction-based trust models are usually task specific and are only applicable to some well-defined domains (tasks). This paper addresses the problem of accurate trust evaluation in a team of agents by proposing an interaction-based trust evaluation model - the Determination of Trust Model (DoTM), which is applicable to various team tasks. The DoTM maps the relationships between interaction records and the trustworthiness of an agent through a supervised learning algorithm. To take full advantage of the interaction data, before being fed into the machine learner, interaction data are pre-processed by three data processing methods, i.e., combining data from multiple runs, involving indirect interaction records and calculating relative data across agents. A series of experiments are conducted on a simulation platform which performs a cooperative food foraging task. Different types of flawed agents are introduced to distinguish between agents with different trustworthiness. The experimental results demonstrate that the DoTM achieves high accuracy and consistency in scenarios involving different types of flawed agents. The DoTM is compared with an existing interaction-based trust model - LogitTrust and achieved significantly better evaluation accuracy in all considered scenarios. Moreover, the impact of each data processing method is demonstrated through experimental investigations.
信任已被广泛认为是影响团队绩效的最重要因素之一。准确评估团队成员(代理)可信度的能力对于有效的团队绩效至关重要。智能体之间的交互数据是决定每个智能体可信度的合适信息源。然而，现有的基于交互的信任模型通常是特定于任务的，并且只适用于一些定义良好的领域(任务)。本文提出了一种基于交互的信任评估模型——确定信任模型(Determination of trust model, DoTM)，该模型适用于各种团队任务，解决了智能体团队中准确的信任评估问题。DoTM通过监督学习算法映射交互记录与代理可信度之间的关系。为了充分利用交互数据，在将交互数据输入机器学习之前，对交互数据进行了三种数据处理方法的预处理，即合并多次运行的数据、涉及间接交互记录和计算跨agent的相对数据。在一个执行合作觅食任务的仿真平台上进行了一系列的实验。引入不同类型的缺陷代理来区分具有不同可信度的代理。实验结果表明，DoTM在不同类型的有缺陷智能体的场景下具有较高的准确率和一致性。DoTM与现有的基于交互的信任模型LogitTrust进行了比较，在所有考虑的场景中都取得了更好的评估准确性。此外，通过实验研究证明了每种数据处理方法的影响。
{"title":"Interaction-Based Trust Evaluation in a Team of Agents Using a Determination of Trust Model","authors":"Shuo Yang, M. Barlow, E. Lakshika, Kathryn E. Kasmarik","doi":"10.1109/SSCI50451.2021.9659848","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9659848","url":null,"abstract":"Trust has been widely recognized as one of the most important factors influencing team performance. The ability to accurately evaluate the trustworthiness of team members (agents) is crucial for effective team performance. Interaction data among agents are suitable sources of information determining each agent's trustworthiness. However, the existing interaction-based trust models are usually task specific and are only applicable to some well-defined domains (tasks). This paper addresses the problem of accurate trust evaluation in a team of agents by proposing an interaction-based trust evaluation model - the Determination of Trust Model (DoTM), which is applicable to various team tasks. The DoTM maps the relationships between interaction records and the trustworthiness of an agent through a supervised learning algorithm. To take full advantage of the interaction data, before being fed into the machine learner, interaction data are pre-processed by three data processing methods, i.e., combining data from multiple runs, involving indirect interaction records and calculating relative data across agents. A series of experiments are conducted on a simulation platform which performs a cooperative food foraging task. Different types of flawed agents are introduced to distinguish between agents with different trustworthiness. The experimental results demonstrate that the DoTM achieves high accuracy and consistency in scenarios involving different types of flawed agents. The DoTM is compared with an existing interaction-based trust model - LogitTrust and achieved significantly better evaluation accuracy in all considered scenarios. Moreover, the impact of each data processing method is demonstrated through experimental investigations.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"47 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132643851","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9659876
Michal Bidlo
This paper investigates the utilisation of approximate addition and multiplication for designing image thresholding functions. Cartesian Genetic Programming is applied for the evolutionary design of circuits using various implementations of the approximate operations. The results are presented for various experimental setups and compared with the case when only exact addition and multiplication is considered. It will be shown that for some range of error metrics of the approximate operations the evolution provides solutions that are better than those provided by the exact operations. Moreover, the utilisation of approximate components allows reducing the implementation area of the resulting functions.
{"title":"Evolution of Approximate Functions for Image Thresholding","authors":"Michal Bidlo","doi":"10.1109/SSCI50451.2021.9659876","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9659876","url":null,"abstract":"This paper investigates the utilisation of approximate addition and multiplication for designing image thresholding functions. Cartesian Genetic Programming is applied for the evolutionary design of circuits using various implementations of the approximate operations. The results are presented for various experimental setups and compared with the case when only exact addition and multiplication is considered. It will be shown that for some range of error metrics of the approximate operations the evolution provides solutions that are better than those provided by the exact operations. Moreover, the utilisation of approximate components allows reducing the implementation area of the resulting functions.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130697545","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9660120
Koen Ponse, Anna V. Kononova, Maria Loleyt, Bas van Stein
Automated symmetry detection is still a difficult task in 2021. However, it has applications in computer vision, and it also plays an important part in understanding art. This paper focuses on aiding the latter by comparing different state-of-the-art automated symmetry detection algorithms. For one of such algorithms aimed at reflectional symmetries, we propose postprocessing improvements to find localised symmetries in images, improve the selection of detected symmetries and identify another symmetry type (rotational). In order to detect rotational symmetries, we contribute a machine learning model which detects rotational symmetries based on provided reflection symmetry axis pairs. We demonstrate and analyze the performance of the extended algorithm to detect localised symmetries and the machine learning model to classify rotational symmetries.
{"title":"Using Machine Learning to Detect Rotational Symmetries from Reflectional Symmetries in 2D Images","authors":"Koen Ponse, Anna V. Kononova, Maria Loleyt, Bas van Stein","doi":"10.1109/SSCI50451.2021.9660120","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9660120","url":null,"abstract":"Automated symmetry detection is still a difficult task in 2021. However, it has applications in computer vision, and it also plays an important part in understanding art. This paper focuses on aiding the latter by comparing different state-of-the-art automated symmetry detection algorithms. For one of such algorithms aimed at reflectional symmetries, we propose postprocessing improvements to find localised symmetries in images, improve the selection of detected symmetries and identify another symmetry type (rotational). In order to detect rotational symmetries, we contribute a machine learning model which detects rotational symmetries based on provided reflection symmetry axis pairs. We demonstrate and analyze the performance of the extended algorithm to detect localised symmetries and the machine learning model to classify rotational symmetries.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130881001","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9660167
Junfeng Tang, Handing Wang
In the preference-based multi-objective optimization, decision makers may be interested in only a part of the representative solutions and hardly specify their preferences. In this case, knee points are considered as the naturally preferred trade-off solutions. Most research utilizes the trade-off information or certain properties to find knee points. However, little attention has been paid to combine them to further enhance the knee identification. This paper proposes a multi-objective evolutionary algorithm using a hybrid identification method and a bi-population structure to find knee points. The hybrid identification method is based on the localized α-dominance and the distance to the hyperplane. Firstly, two populations are partitioned by a set of predefined reference vectors and apply the localized α-dominance to guide the search towards potential knee regions. Then knee solutions are detected based on the distance to hyperplane constructed by the extreme points. Finally in the environmental selection, a niche-preserving operation is applied to take the knee solutions of all sub-populations into account. The first population is the main part of the search, and affects the offspring generation and environmental selection of the second population. The experiments demonstrate that the proposed method is effective and competitive in identifying knee solutions.
{"title":"A Bi-Population Based Multi-Objective Evolutionary Algorithm Using Hybrid Identification Method for Finding Knee Points","authors":"Junfeng Tang, Handing Wang","doi":"10.1109/SSCI50451.2021.9660167","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9660167","url":null,"abstract":"In the preference-based multi-objective optimization, decision makers may be interested in only a part of the representative solutions and hardly specify their preferences. In this case, knee points are considered as the naturally preferred trade-off solutions. Most research utilizes the trade-off information or certain properties to find knee points. However, little attention has been paid to combine them to further enhance the knee identification. This paper proposes a multi-objective evolutionary algorithm using a hybrid identification method and a bi-population structure to find knee points. The hybrid identification method is based on the localized α-dominance and the distance to the hyperplane. Firstly, two populations are partitioned by a set of predefined reference vectors and apply the localized α-dominance to guide the search towards potential knee regions. Then knee solutions are detected based on the distance to hyperplane constructed by the extreme points. Finally in the environmental selection, a niche-preserving operation is applied to take the knee solutions of all sub-populations into account. The first population is the main part of the search, and affects the offspring generation and environmental selection of the second population. The experiments demonstrate that the proposed method is effective and competitive in identifying knee solutions.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131208731","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9659549
Chun Hua
Hybrid clustering algorithm that combine the swarm intelligence algorithm and K-means is widely used in clustering areas. Such as But, the hybrid particle swarm optimization clustering algorithm, the hybrid genetic clustering algorithm and ant colony algorithm. In which, the hybrid particle swarm optimization algorithm clustering algorithm may appear empty cluster in the iteration process, which will result in a bad clustering results. To improve this phenomenon, we combine the particle swarm algorithm with K-means++ (PSOK-means++), to some extent, which improve the clustering result. But, empty clusters may appear during the iteration of PSOK-means++, as a remedy, we introduce the empty-cluster-reassignment technique and use it to modify particle swarm optimization K-means++, resulting in a particle swarm optimization K-means++ clustering algorithm with empty cluster reassignment (EPSOK-means++). Furthermore, we combine the EPSOK-means++ with quantum computing theory, referred to as QEPSOK-means++ clustering algorithm. The experimental results show that QEPSOK-means++ is effective and promising.
{"title":"A Quantum-inspired Particle Swarm Optimization K-means++ Clustering Algorithm","authors":"Chun Hua","doi":"10.1109/SSCI50451.2021.9659549","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9659549","url":null,"abstract":"Hybrid clustering algorithm that combine the swarm intelligence algorithm and K-means is widely used in clustering areas. Such as But, the hybrid particle swarm optimization clustering algorithm, the hybrid genetic clustering algorithm and ant colony algorithm. In which, the hybrid particle swarm optimization algorithm clustering algorithm may appear empty cluster in the iteration process, which will result in a bad clustering results. To improve this phenomenon, we combine the particle swarm algorithm with K-means++ (PSOK-means++), to some extent, which improve the clustering result. But, empty clusters may appear during the iteration of PSOK-means++, as a remedy, we introduce the empty-cluster-reassignment technique and use it to modify particle swarm optimization K-means++, resulting in a particle swarm optimization K-means++ clustering algorithm with empty cluster reassignment (EPSOK-means++). Furthermore, we combine the EPSOK-means++ with quantum computing theory, referred to as QEPSOK-means++ clustering algorithm. The experimental results show that QEPSOK-means++ is effective and promising.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133397266","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9659547
L. David, Hélio Pedrini, Z. Dias, A. Rocha
Authorship attribution and matching have become paramount activities in current digital art repositories and communities, which seek to efficiently catalog and authenticate the ever-growing number of digitized paintings, uploaded in professional and casual capturing setups, by their own authors or enthusiasts alike. In this work, we employ convolutional network-based strategies to identify and classify art-related digital artifacts over the Painter by Numbers dataset. Firstly, we propose to exploit the authorship, style and genre annotated information in a multi-task setup, in which patches of paintings are encoded through a multiple outputs network and, in a second stage, used in an Siamese discriminating network to solve the authorship matching problem. Secondly, we combine the available annotated information in a more efficient manner, by posing the Painter by Numbers challenge as a multi-label problem. Empirical results show a substantial increase in class-balanced accuracy and ROC AUC score for both multi-task solutions, compared with their simpler counterparts trained using only authorship annotation. Furthermore, a slight increase in ROC AUC score is observed in the multi-label setup, indicating that this simple combination strategy is beneficial to training convergence.
作者归属和匹配已经成为当前数字艺术存储库和社区的首要活动，它们寻求有效地对数量不断增长的数字化绘画进行分类和认证，这些绘画由自己的作者或爱好者以专业和休闲的捕获设置上传。在这项工作中，我们采用基于卷积网络的策略来识别和分类画家数字数据集上与艺术相关的数字文物。首先，我们提出在多任务设置中利用作者身份、风格和流派注释信息，其中通过多输出网络对绘画片段进行编码，在第二阶段，使用暹罗鉴别网络来解决作者身份匹配问题。其次，我们通过将Painter by Numbers挑战作为一个多标签问题，以更有效的方式组合可用的注释信息。实证结果显示，与仅使用作者标注训练的简单对应方案相比，两种多任务解决方案的类平衡精度和ROC AUC得分都有显著提高。此外，在多标签设置中观察到ROC AUC评分略有增加，表明这种简单的组合策略有利于训练收敛。
{"title":"Connoisseur: Provenance Analysis in Paintings","authors":"L. David, Hélio Pedrini, Z. Dias, A. Rocha","doi":"10.1109/SSCI50451.2021.9659547","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9659547","url":null,"abstract":"Authorship attribution and matching have become paramount activities in current digital art repositories and communities, which seek to efficiently catalog and authenticate the ever-growing number of digitized paintings, uploaded in professional and casual capturing setups, by their own authors or enthusiasts alike. In this work, we employ convolutional network-based strategies to identify and classify art-related digital artifacts over the Painter by Numbers dataset. Firstly, we propose to exploit the authorship, style and genre annotated information in a multi-task setup, in which patches of paintings are encoded through a multiple outputs network and, in a second stage, used in an Siamese discriminating network to solve the authorship matching problem. Secondly, we combine the available annotated information in a more efficient manner, by posing the Painter by Numbers challenge as a multi-label problem. Empirical results show a substantial increase in class-balanced accuracy and ROC AUC score for both multi-task solutions, compared with their simpler counterparts trained using only authorship annotation. Furthermore, a slight increase in ROC AUC score is observed in the multi-label setup, indicating that this simple combination strategy is beneficial to training convergence.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133705385","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9660176
Maher A. Alhossaini, Mohammed Aloqeely
The use of on-line tutoring, especially after the COVID-19 pandemic, has increased dramatically. It has become clear that measuring the effectiveness of on-line tutoring, especially on low-income students, is much needed in such difficult times. This paper, which is based on observational data collected before the COVID-19 era, is targeting measuring the impact of a web-based math tutoring program, Noon Academy, on the academic achievement of low-income high school students (grades 10 to 12) in Saudi Arabia. We use a large amount of data collected in a student registration process and two Bayesian generalized linear models (GLM) to measure the tutoring causal effects. Model 1 uses a binomial logistic regression to predict the impact of enrolling in the tutoring program on the rate of passing in a number of students. Model 2 uses a multi-level Beta regression to measure the impact of the number of minutes on the total mark. Model 1 results show that giving math tutoring to higher-failing-risk students significantly improves the rate of passing by +5 %, reaching a maximum of + 17.15 % in some classes of students. Model 2 shows a significant positive impact of the number of tutoring minutes on the yearly math mark (max of 100), reaching an average of +3.52 marks for the highest number of minutes taken. The paper presents an application of a causal analysis approaches on a real-life social problem. It demonstrates how the model is used to obtain a measure of the impact with quantifiable uncertainty that can be used in practice.
{"title":"Causal Analysis of On-line Math Tutoring Impact on Low-income High School Students Using Bayesian Logistic and Beta Regressions","authors":"Maher A. Alhossaini, Mohammed Aloqeely","doi":"10.1109/SSCI50451.2021.9660176","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9660176","url":null,"abstract":"The use of on-line tutoring, especially after the COVID-19 pandemic, has increased dramatically. It has become clear that measuring the effectiveness of on-line tutoring, especially on low-income students, is much needed in such difficult times. This paper, which is based on observational data collected before the COVID-19 era, is targeting measuring the impact of a web-based math tutoring program, Noon Academy, on the academic achievement of low-income high school students (grades 10 to 12) in Saudi Arabia. We use a large amount of data collected in a student registration process and two Bayesian generalized linear models (GLM) to measure the tutoring causal effects. Model 1 uses a binomial logistic regression to predict the impact of enrolling in the tutoring program on the rate of passing in a number of students. Model 2 uses a multi-level Beta regression to measure the impact of the number of minutes on the total mark. Model 1 results show that giving math tutoring to higher-failing-risk students significantly improves the rate of passing by +5 %, reaching a maximum of + 17.15 % in some classes of students. Model 2 shows a significant positive impact of the number of tutoring minutes on the yearly math mark (max of 100), reaching an average of +3.52 marks for the highest number of minutes taken. The paper presents an application of a causal analysis approaches on a real-life social problem. It demonstrates how the model is used to obtain a measure of the impact with quantifiable uncertainty that can be used in practice.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133453034","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9660076
Anushri Rajendran, P. Kebria, N. Mohajer, A. Khosravi, S. Nahavandi
Reducing aviation fatalities requires a high level of reliable real-time monitoring so that events can be predicted and prevented before they can occur. Situational awareness is essential in the cockpit where manual and autonomous operations co-exist. Many interventions and countermeasures have been designed into cockpits to enhance pilot awareness and performance. This study aims to analyse pilot and copilot teams' awareness by using physiological data which was collected in a flight simulator to train models to predict when pilots are in a state of Channelised Attention (CA), Diverted Attention (DA), and Startle/Surprise (SS). Electrocardiogram (ECG) signals collected for 18 subjects were processed in preparation to develop a comprehensive tool which utilises active Line Oriented Flight Training (LOFT) data to evaluate machine learning tools which are capable of predicting pilot awareness response. A combination of linear, non-linear, binary and multi-class classification were applied to this data. The results indicate that while all classifiers produced stable results, Decision Tree(DT) far outperformed the others. Further analyses revealed that the maximum value for ECG was the most important feature used by all classifiers evaluated for importance in training the classification models. However, for DT which was the best performing classifier both maximum and minimum ECG values were the most important features in predictions made by this model.
{"title":"Machine Learning based Prediction of Situational Awareness in Pilots using ECG Signals","authors":"Anushri Rajendran, P. Kebria, N. Mohajer, A. Khosravi, S. Nahavandi","doi":"10.1109/SSCI50451.2021.9660076","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9660076","url":null,"abstract":"Reducing aviation fatalities requires a high level of reliable real-time monitoring so that events can be predicted and prevented before they can occur. Situational awareness is essential in the cockpit where manual and autonomous operations co-exist. Many interventions and countermeasures have been designed into cockpits to enhance pilot awareness and performance. This study aims to analyse pilot and copilot teams' awareness by using physiological data which was collected in a flight simulator to train models to predict when pilots are in a state of Channelised Attention (CA), Diverted Attention (DA), and Startle/Surprise (SS). Electrocardiogram (ECG) signals collected for 18 subjects were processed in preparation to develop a comprehensive tool which utilises active Line Oriented Flight Training (LOFT) data to evaluate machine learning tools which are capable of predicting pilot awareness response. A combination of linear, non-linear, binary and multi-class classification were applied to this data. The results indicate that while all classifiers produced stable results, Decision Tree(DT) far outperformed the others. Further analyses revealed that the maximum value for ECG was the most important feature used by all classifiers evaluated for importance in training the classification models. However, for DT which was the best performing classifier both maximum and minimum ECG values were the most important features in predictions made by this model.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132152394","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 : 2021-12-05DOI: 10.1109/SSCI50451.2021.9659986
Karen Schnell, K. Roy
Privacy and data protection rights is a growing human concern. This includes individuals with disabilities. When it comes to privacy policies and notices published by institutions and businesses, there are legal, business, and social implications to making them readable, accessible, understandable, and simply being paid attention to by a potentially impacted user. Web Content Accessibility Guidelines (WGAC) provide checkpoints and rules for designing which help developers to make web-based content accessible. The focus of this research is on the web design of privacy notices for the visually impaired. Financial and higher education websites were evaluated for adherence to WGAC checkpoints to support a computer screen reader and the ability to locate and read the privacy policy.
{"title":"Website Privacy Notification for the Visually Impaired","authors":"Karen Schnell, K. Roy","doi":"10.1109/SSCI50451.2021.9659986","DOIUrl":"https://doi.org/10.1109/SSCI50451.2021.9659986","url":null,"abstract":"Privacy and data protection rights is a growing human concern. This includes individuals with disabilities. When it comes to privacy policies and notices published by institutions and businesses, there are legal, business, and social implications to making them readable, accessible, understandable, and simply being paid attention to by a potentially impacted user. Web Content Accessibility Guidelines (WGAC) provide checkpoints and rules for designing which help developers to make web-based content accessible. The focus of this research is on the web design of privacy notices for the visually impaired. Financial and higher education websites were evaluated for adherence to WGAC checkpoints to support a computer screen reader and the ability to locate and read the privacy policy.","PeriodicalId":255763,"journal":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"201 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132441293","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：