Pub Date : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00030
Lubomír Štěpánek, Filip Habarta, I. Malá, L. Marek
Estimates performed particularly using small samples are a priori inaccurate. Furthermore, estimations of m-year survival rates, especially for large m ≫ 0, are inevitable of low precision because they are calculated as fractions with both low numerators and denominators. In this study, we use different degrees of jack-knifing of the original dataset used for m-year survival rates estimations to optimize the trade-off between decreasing variance (and increasing accuracy) and increasing bias of the estimates. Assuming the jack-knife enriches the original data in an allowed way since it does not generate new, non-existing observations, the results could suggest overcoming the small sample issue.
{"title":"Jack-knifing in small samples of survival data: when bias meets variance to increase estimate precision","authors":"Lubomír Štěpánek, Filip Habarta, I. Malá, L. Marek","doi":"10.1109/ICCMA53594.2021.00030","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00030","url":null,"abstract":"Estimates performed particularly using small samples are a priori inaccurate. Furthermore, estimations of m-year survival rates, especially for large m ≫ 0, are inevitable of low precision because they are calculated as fractions with both low numerators and denominators. In this study, we use different degrees of jack-knifing of the original dataset used for m-year survival rates estimations to optimize the trade-off between decreasing variance (and increasing accuracy) and increasing bias of the estimates. Assuming the jack-knife enriches the original data in an allowed way since it does not generate new, non-existing observations, the results could suggest overcoming the small sample issue.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120963654","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00025
F. Oduro-Gyimah, K. Boateng, Prince Boahen Adu, Kester Quist-Aphetsi
As the demand in communication traffic grows; there should be the provision of reliable telecommunication network to users. Operators however, face a myriad of challenges in fulfilling their part of the contract such as network outage. The phenomenon of network outage has been a challenge that every network operator is consistently trying to avoid. In this study, a multilayer feedforward neural network also called multilayer perceptron (MLP) was adopted to model network outage time of network elements or systems. The MLP network was trained on a 150 samples of daily network outage time data obtained from the Network Operating Centre of an operator in Ghana. The data covered a period of 1st January to 30th May 2018 and was analysed with Matlab software. In developing the model, the input and output layers were kept constant, while the number of neurons were varied from 1 to 20 to obtain a good prediction. The performance of the models were measured by the Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and the Correlation Coefficient (R). After careful and extensive training, validation and testing, 20 models were developed. The MLP selected was 1-4-1 which produced MSE, RMSE, and an R-value of 0.0000024321, 0.00160 and 0.99993 respectively with a prediction accuracy of 97.5%. The study concludes that downtime prediction can be improved by feed forward neural network optimized using Levenberg-Marquardt with sigmoid function in the hidden and linear activation function in the output layer.
{"title":"Prediction of Telecommunication Network Outage Time Using Multilayer Perceptron Modelling Approach","authors":"F. Oduro-Gyimah, K. Boateng, Prince Boahen Adu, Kester Quist-Aphetsi","doi":"10.1109/ICCMA53594.2021.00025","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00025","url":null,"abstract":"As the demand in communication traffic grows; there should be the provision of reliable telecommunication network to users. Operators however, face a myriad of challenges in fulfilling their part of the contract such as network outage. The phenomenon of network outage has been a challenge that every network operator is consistently trying to avoid. In this study, a multilayer feedforward neural network also called multilayer perceptron (MLP) was adopted to model network outage time of network elements or systems. The MLP network was trained on a 150 samples of daily network outage time data obtained from the Network Operating Centre of an operator in Ghana. The data covered a period of 1st January to 30th May 2018 and was analysed with Matlab software. In developing the model, the input and output layers were kept constant, while the number of neurons were varied from 1 to 20 to obtain a good prediction. The performance of the models were measured by the Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and the Correlation Coefficient (R). After careful and extensive training, validation and testing, 20 models were developed. The MLP selected was 1-4-1 which produced MSE, RMSE, and an R-value of 0.0000024321, 0.00160 and 0.99993 respectively with a prediction accuracy of 97.5%. The study concludes that downtime prediction can be improved by feed forward neural network optimized using Levenberg-Marquardt with sigmoid function in the hidden and linear activation function in the output layer.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132556696","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00029
Lubomír Štěpánek, Filip Habarta, I. Malá, L. Marek
There are several established methods for comparing more than two survival curves, namely the scale-rank test or Cox’s proportional hazard model. However, when their statistical assumptions are not met, their results’ validity is affected.In this study, we address the mentioned issue and propose a new statistical approach on how to compare more than two survival curves using a random forest algorithm, which is practically assumption-free. The repetitive generating of many decision trees covered by one random forest model enables to calculate of a proportion of trees with sufficient complexity classifying into all groups (depicted by their survival curves), which is the p-value estimate as an analogy of the classical Wald’s t-test output of the Cox’s regression. Furthermore, a level of the pruning of decision trees the random forest model is built with, can modify both the robustness and statistical power of the random forest alternative. The discussed results are confirmed using COVID-19 survival data with varying the tree pruning level.The introduced method for survival curves comparison, based on random forest algorithm, seems to be a valid alternative to Cox’s regression; however, it has no statistical assumptions and tends to reach higher statistical power.
{"title":"An alternative to Cox’s regression for multiple survival curves comparison: A random forest-based approach using covariate structure","authors":"Lubomír Štěpánek, Filip Habarta, I. Malá, L. Marek","doi":"10.1109/ICCMA53594.2021.00029","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00029","url":null,"abstract":"There are several established methods for comparing more than two survival curves, namely the scale-rank test or Cox’s proportional hazard model. However, when their statistical assumptions are not met, their results’ validity is affected.In this study, we address the mentioned issue and propose a new statistical approach on how to compare more than two survival curves using a random forest algorithm, which is practically assumption-free. The repetitive generating of many decision trees covered by one random forest model enables to calculate of a proportion of trees with sufficient complexity classifying into all groups (depicted by their survival curves), which is the p-value estimate as an analogy of the classical Wald’s t-test output of the Cox’s regression. Furthermore, a level of the pruning of decision trees the random forest model is built with, can modify both the robustness and statistical power of the random forest alternative. The discussed results are confirmed using COVID-19 survival data with varying the tree pruning level.The introduced method for survival curves comparison, based on random forest algorithm, seems to be a valid alternative to Cox’s regression; however, it has no statistical assumptions and tends to reach higher statistical power.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133401986","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00032
Mêtowanou H. Ahouandjinou, D. Medenou, R. Houessouvo, M.A. Godwind Houdji
Benin’s health system, like all health systems, is faced with the challenge of providing quality, safe and affordable health care. The problems of understaffing of health care personnel compared to the WHO recommendation on the one hand, and the problems of poor distribution of these health care personnel over the extent of the health care system on the other hand, lead us to think about a model of mobility and accessibility of health care in Benin. This work aims at setting up an intelligent algorithm of accessibility and mobility of health care and will allow any patient embarked at any point of the health system to be taken care of automatically by a doctor and a nurse. To achieve this, we have (i) studied the state of the art of healthcare accessibility and mobility, (ii) modeled the healthcare trajectory, (iii) developed an algorithm for the automatic assignment and management of a patient in a healthcare system and simulated it using operations research and graph tools. The work allowed to set up a dynamic algorithm of accessibility to health care and to answer the challenges of the health care systems.
{"title":"Smart model of accessibility and mobility of health care","authors":"Mêtowanou H. Ahouandjinou, D. Medenou, R. Houessouvo, M.A. Godwind Houdji","doi":"10.1109/ICCMA53594.2021.00032","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00032","url":null,"abstract":"Benin’s health system, like all health systems, is faced with the challenge of providing quality, safe and affordable health care. The problems of understaffing of health care personnel compared to the WHO recommendation on the one hand, and the problems of poor distribution of these health care personnel over the extent of the health care system on the other hand, lead us to think about a model of mobility and accessibility of health care in Benin. This work aims at setting up an intelligent algorithm of accessibility and mobility of health care and will allow any patient embarked at any point of the health system to be taken care of automatically by a doctor and a nurse. To achieve this, we have (i) studied the state of the art of healthcare accessibility and mobility, (ii) modeled the healthcare trajectory, (iii) developed an algorithm for the automatic assignment and management of a patient in a healthcare system and simulated it using operations research and graph tools. The work allowed to set up a dynamic algorithm of accessibility to health care and to answer the challenges of the health care systems.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124032167","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00013
Owen Casey, Rushit Dave, Naeem Seliya, E. S. Boone
In this paper, machines learning networks are explored for their use in restoring degraded and compressed speech audio. The project intent is to build a new trained model from voice data to learn features of compression artifacting (distortion introduced by data loss from lossy compression) and resolution loss with an existing algorithm presented in ‘SEGAN: Speech Enhancement Generative Adversarial Network’. The resulting generator from the model was then to be used to restore degraded speech audio. This paper details an examination of the subsequent compatibility and operational issues presented by working with deprecated code, which obstructed the trained model from successfully being developed. This paper further serves as an examination of the challenges, limitations, and compatibility in the current state of machine learning.
{"title":"Machine Learning: Challenges, Limitations, and Compatibility for Audio Restoration Processes","authors":"Owen Casey, Rushit Dave, Naeem Seliya, E. S. Boone","doi":"10.1109/ICCMA53594.2021.00013","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00013","url":null,"abstract":"In this paper, machines learning networks are explored for their use in restoring degraded and compressed speech audio. The project intent is to build a new trained model from voice data to learn features of compression artifacting (distortion introduced by data loss from lossy compression) and resolution loss with an existing algorithm presented in ‘SEGAN: Speech Enhancement Generative Adversarial Network’. The resulting generator from the model was then to be used to restore degraded speech audio. This paper details an examination of the subsequent compatibility and operational issues presented by working with deprecated code, which obstructed the trained model from successfully being developed. This paper further serves as an examination of the challenges, limitations, and compatibility in the current state of machine learning.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128049409","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00027
Emmanuel Kwabla Ocloo, Ebenezer Malcalm, G. Kumar
Micro Small and Medium Enterprises (MSMEs) are considered the most enterprises that create jobs in the country when running consistently and very well leading to the achievement of high Gross Domestic Product (GDP) reflecting in the macro economy. However, this inheritance and dreams of MSMEs are not realized due to some endogenous (internal) metrics or factors. The study seeks to investigate the underlying internal factors leading to failure of selected MSMEs in Mallam in Greater Accra Region of Ghana. However, the entire population targeted for this research was 85 while 70 respondents were randomly drawn out of the total population. The 70 selected respondents assisted in proper flow of information required for the success of the research.The research has employed descriptive research design since it portrays accurate responses from owners that are targeted, MSMEs’ managers in the targeted population. Structured questionnaires were used to collect primary data through direct interview of entrepreneurs. Both qualitative and quantitative methods of data collection were applied in this study. The collected data was analyzed using Statistical Package for Social Sciences (SPSS). The findings unraveled two set of endogenous constraints such as entrepreneurial constraints and business or enterprise constraints that lead selected MSMEs to fail in their businesses. Some of the entrepreneurial constraints are poor skills in management, gender and age of entrepreneur, lack of education, and lack of experience. On the other hand, the business challenges are lack of capital, lack of recording accounting data, poor business plan, age and size of company.The study would assist industry players to apply the various constraints identified in their decision-making process. In addition, the research would contribute to existing literature.
微型中小企业(MSMEs)被认为是在该国创造就业机会最多的企业，在持续运行和非常好的情况下，实现了反映在宏观经济中的高国内生产总值(GDP)。然而，由于一些内源性(内部)指标或因素，中小微企业的这种继承和梦想并没有实现。本研究旨在调查导致加纳大阿克拉地区马拉姆中小微企业失败的潜在内部因素。然而，本次研究的目标人群是85人，而70名受访者是随机抽取的。70个选定的答复者协助了研究成功所需的适当信息流动。该研究采用了描述性研究设计，因为它描绘了目标人群中的业主，中小微企业经理的准确反应。采用结构化问卷法，通过对企业家的直接访谈收集原始数据。本研究采用定性与定量相结合的数据收集方法。收集的数据使用SPSS (Statistical Package for Social Sciences)软件进行分析。研究结果揭示了两组内生约束，如创业约束和商业或企业约束，导致选定的中小微企业在其业务中失败。一些创业的制约因素是管理技能差，企业家的性别和年龄，缺乏教育，缺乏经验。另一方面，商业挑战是缺乏资金，缺乏记录会计数据，糟糕的商业计划，公司的年龄和规模。这项研究将协助工业参与者应用其决策过程中确定的各种限制因素。此外，该研究将有助于现有文献。
{"title":"Exploration of Endogenous Constraints Leading to Failure of Micro Small and Medium Enterprises (MSMEs) in Developing Countries (A Case Study of Mallam, Greater Accra Region of Ghana)","authors":"Emmanuel Kwabla Ocloo, Ebenezer Malcalm, G. Kumar","doi":"10.1109/ICCMA53594.2021.00027","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00027","url":null,"abstract":"Micro Small and Medium Enterprises (MSMEs) are considered the most enterprises that create jobs in the country when running consistently and very well leading to the achievement of high Gross Domestic Product (GDP) reflecting in the macro economy. However, this inheritance and dreams of MSMEs are not realized due to some endogenous (internal) metrics or factors. The study seeks to investigate the underlying internal factors leading to failure of selected MSMEs in Mallam in Greater Accra Region of Ghana. However, the entire population targeted for this research was 85 while 70 respondents were randomly drawn out of the total population. The 70 selected respondents assisted in proper flow of information required for the success of the research.The research has employed descriptive research design since it portrays accurate responses from owners that are targeted, MSMEs’ managers in the targeted population. Structured questionnaires were used to collect primary data through direct interview of entrepreneurs. Both qualitative and quantitative methods of data collection were applied in this study. The collected data was analyzed using Statistical Package for Social Sciences (SPSS). The findings unraveled two set of endogenous constraints such as entrepreneurial constraints and business or enterprise constraints that lead selected MSMEs to fail in their businesses. Some of the entrepreneurial constraints are poor skills in management, gender and age of entrepreneur, lack of education, and lack of experience. On the other hand, the business challenges are lack of capital, lack of recording accounting data, poor business plan, age and size of company.The study would assist industry players to apply the various constraints identified in their decision-making process. In addition, the research would contribute to existing literature.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123560500","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00026
Michael Agyare, J. J. Kponyo, F. Oduro-Gyimah
A selective mobile phone communication blocking active interceptor system for specific mobile phone restricted zones is designed. The system provides eligibility of communication based on the type of communication service permitted for the specific restricted locations. The designed system was simulated using a Fuzzy Inference System (FIS) toolbox with a set of IF-THEN rules and membership functions (MFs) for the input and output of the system. The eligibility for communication services was designed to suit specific user locations. These locations were converted into input triangular MFs. The output is the decision (“allow” and “not allow”) for each of the inputs. S-shape and Z-shape MFs were used as the output decision variables. The results indicate selective blocking of communication services according to the type of communication service permitted for a specific location. In addition, privileged users were given total access to all communication services for each specific location.
{"title":"Selective Blocking Approach of User Equipment in Restricted Communication Zones","authors":"Michael Agyare, J. J. Kponyo, F. Oduro-Gyimah","doi":"10.1109/ICCMA53594.2021.00026","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00026","url":null,"abstract":"A selective mobile phone communication blocking active interceptor system for specific mobile phone restricted zones is designed. The system provides eligibility of communication based on the type of communication service permitted for the specific restricted locations. The designed system was simulated using a Fuzzy Inference System (FIS) toolbox with a set of IF-THEN rules and membership functions (MFs) for the input and output of the system. The eligibility for communication services was designed to suit specific user locations. These locations were converted into input triangular MFs. The output is the decision (“allow” and “not allow”) for each of the inputs. S-shape and Z-shape MFs were used as the output decision variables. The results indicate selective blocking of communication services according to the type of communication service permitted for a specific location. In addition, privileged users were given total access to all communication services for each specific location.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123366400","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00020
Abel Yeboah-Ofori, Umar Mukhtar Ismail, Tymoteusz Swidurski, F. Opoku-Boateng
Machine learning has been used in the cybersecurity domain to predict cyberattack trends. However, adversaries can inject malicious data into the dataset during training and testing to cause perturbance and predict false narratives. It has become challenging to analyse and predicate cyberattack correlations due to their fuzzy nature and lack of understanding of the threat landscape. Thus, it is imperative to use cyber threat ontology (CTO) concepts to extract relevant attack instances in CSC security for knowledge representation. This paper explores the challenges of CTO and adversarial machine learning (AML) attacks for threat prediction to improve cybersecurity. The novelty contributions are threefold. First, CTO concepts are considered for semantic mapping and definition of relationships for explicit knowledge of threat indicators. Secondly, AML techniques are deployed maliciously to manipulate algorithms during training and testing to predict false classifications models. Finally, we discuss the performance analysis of the classification models and how CTO provides automated means. The result shows that analysis of AML attacks and CTO concepts could be used for validating a mediated schema for specific vulnerabilities.
{"title":"Cyber Threat Ontology and Adversarial Machine Learning Attacks: Analysis and Prediction Perturbance","authors":"Abel Yeboah-Ofori, Umar Mukhtar Ismail, Tymoteusz Swidurski, F. Opoku-Boateng","doi":"10.1109/ICCMA53594.2021.00020","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00020","url":null,"abstract":"Machine learning has been used in the cybersecurity domain to predict cyberattack trends. However, adversaries can inject malicious data into the dataset during training and testing to cause perturbance and predict false narratives. It has become challenging to analyse and predicate cyberattack correlations due to their fuzzy nature and lack of understanding of the threat landscape. Thus, it is imperative to use cyber threat ontology (CTO) concepts to extract relevant attack instances in CSC security for knowledge representation. This paper explores the challenges of CTO and adversarial machine learning (AML) attacks for threat prediction to improve cybersecurity. The novelty contributions are threefold. First, CTO concepts are considered for semantic mapping and definition of relationships for explicit knowledge of threat indicators. Secondly, AML techniques are deployed maliciously to manipulate algorithms during training and testing to predict false classifications models. Finally, we discuss the performance analysis of the classification models and how CTO provides automated means. The result shows that analysis of AML attacks and CTO concepts could be used for validating a mediated schema for specific vulnerabilities.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114497787","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 : 2021-07-01DOI: 10.1109/ICCMA53594.2021.00017
Ebenezer Nii Ayi Hammond, Shijie Zhou, Qihe Liu
Facial age estimation is an essential feature in many applications satisfying the need to provide users with content that corresponds to their ages. However, providing an inclusive facial age estimation solution that is also high-performing is challenging due to the many different factors that influence the face. This article leverages DeepSets for Symmetric Elements (DSS) to propose an approach that aims to extract a reliable set of rich feature vectors for age estimation. It combines a DSS feature extractor, ternary classifier, and a race determiner. Precisely, the extractor consists of a siamese-like layer that applies a regular convolutional neural network to input images and an aggregation module that sums up all of the images and then adds them to the output from the siamese layer. To estimate the age, the ternary classifier obtains the feature vectors seeking to classify them into three possible outcomes that correspond to younger than, similar to, or older than. The correlation is achieved using identical pairs of input and reference images that belong to the same race. The result indicates the similarity between the images: the higher the score, the closer the similarity. With an accuracy of 94.8%, 95.2%, and 90.5% on the MORPH II, a race-inclusive dataset, and the FG-NET, we demonstrate that our proposal exemplifies facial age estimation particularly when the race factor is considered in the estimation.
面部年龄估算是许多应用中的一项基本功能，它能满足为用户提供与其年龄相符的内容的需求。然而，由于影响人脸的因素多种多样，要提供一种具有包容性且性能卓越的人脸年龄估计解决方案具有很大的挑战性。本文利用对称元素深度集（DeepSets for Symmetric Elements，DSS）提出了一种方法，旨在为年龄估计提取一组可靠的丰富特征向量。它结合了 DSS 特征提取器、三元分类器和种族判定器。准确地说，特征提取器由一个类似连体的层和一个聚合模块组成，前者对输入图像应用常规卷积神经网络，后者对所有图像进行汇总，然后将其添加到连体层的输出中。为了估算年龄，三元分类器获取特征向量，将其分为三种可能的结果，分别对应于小于、类似于或大于。相关性是使用属于同一种族的相同输入图像和参考图像对来实现的。结果显示了图像之间的相似度：得分越高，相似度越高。在包含种族的数据集 MORPH II 和 FG-NET 上，我们的准确率分别为 94.8%、95.2% 和 90.5%，证明了我们的建议是面部年龄估算的典范，尤其是在估算中考虑种族因素时。
{"title":"A DSS-based Comparator for Facial Race Age Estimation","authors":"Ebenezer Nii Ayi Hammond, Shijie Zhou, Qihe Liu","doi":"10.1109/ICCMA53594.2021.00017","DOIUrl":"https://doi.org/10.1109/ICCMA53594.2021.00017","url":null,"abstract":"Facial age estimation is an essential feature in many applications satisfying the need to provide users with content that corresponds to their ages. However, providing an inclusive facial age estimation solution that is also high-performing is challenging due to the many different factors that influence the face. This article leverages DeepSets for Symmetric Elements (DSS) to propose an approach that aims to extract a reliable set of rich feature vectors for age estimation. It combines a DSS feature extractor, ternary classifier, and a race determiner. Precisely, the extractor consists of a siamese-like layer that applies a regular convolutional neural network to input images and an aggregation module that sums up all of the images and then adds them to the output from the siamese layer. To estimate the age, the ternary classifier obtains the feature vectors seeking to classify them into three possible outcomes that correspond to younger than, similar to, or older than. The correlation is achieved using identical pairs of input and reference images that belong to the same race. The result indicates the similarity between the images: the higher the score, the closer the similarity. With an accuracy of 94.8%, 95.2%, and 90.5% on the MORPH II, a race-inclusive dataset, and the FG-NET, we demonstrate that our proposal exemplifies facial age estimation particularly when the race factor is considered in the estimation.","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127028188","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 : 2021-07-01DOI: 10.1109/iccma53594.2021.00002
{"title":"[Title page iii]","authors":"","doi":"10.1109/iccma53594.2021.00002","DOIUrl":"https://doi.org/10.1109/iccma53594.2021.00002","url":null,"abstract":"","PeriodicalId":131082,"journal":{"name":"2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134197715","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：