During the COVID-19 pandemic and mandated global lockdowns, people and busi- nesses started the extensive use of video-conferencing applications for staying connected. This surge in demand and the usability of video-conferencing services has been severely overlooked in developing countries like South Africa, where one-third of adults rely on mo- bile devices to access the internet, and the per-gigabyte data cost is among the highest in Africa. Considering these numbers, we conduct a two-pronged study where 1) we measure data consumption of different Android apps through data measurement experiments and 2) we conduct interviews and usability assessments with bandwidth-constrained users to bet- ter understand the usability and Quality of Experience (QoE) of mobile video-conferencing apps. Usability is the degree to which specified users can use a product to achieve specified goals. In contrast, QoE measures the subjective perception of the quality of an application and the level of delight or annoyance with a service. The key benefit of this study will be to inform organisations that seek to be inclusive about these tools’ relative usability by letting them know about the factors influencing users’ QoE.
{"title":"Investigating the Usability and Quality of Experience of Mobile Video-Conferencing Apps Among Bandwidth-Constrained Users in South Africa","authors":"Dominique Oosthuizen, Taveesh Sharma, Josiah Chavula, Melissa Densmore","doi":"10.29007/wwft","DOIUrl":"https://doi.org/10.29007/wwft","url":null,"abstract":"During the COVID-19 pandemic and mandated global lockdowns, people and busi- nesses started the extensive use of video-conferencing applications for staying connected. This surge in demand and the usability of video-conferencing services has been severely overlooked in developing countries like South Africa, where one-third of adults rely on mo- bile devices to access the internet, and the per-gigabyte data cost is among the highest in Africa. Considering these numbers, we conduct a two-pronged study where 1) we measure data consumption of different Android apps through data measurement experiments and 2) we conduct interviews and usability assessments with bandwidth-constrained users to bet- ter understand the usability and Quality of Experience (QoE) of mobile video-conferencing apps. Usability is the degree to which specified users can use a product to achieve specified goals. In contrast, QoE measures the subjective perception of the quality of an application and the level of delight or annoyance with a service. The key benefit of this study will be to inform organisations that seek to be inclusive about these tools’ relative usability by letting them know about the factors influencing users’ QoE.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69453508","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 medical history information contained in electronic health records (EHR) is a valuable and largely untapped data mining source for predicting patient outcomes and thereby improving treatment. This paper presents a simple but novel evolutionary algorithm (EA) for identifying how various medical history and demographic factors predict clinical outcomes. For this initial study, our EA was tested using synthetic data concerning COVID-19 hospitalization rates and we show that the EA results are more informative than logistic regression, neural network, or decision tree results.
{"title":"Simple evolutionary algorithm for quantifying how medical history factors predict disease outcomes","authors":"J. Camp, H. Al-Mubaid","doi":"10.29007/7pd1","DOIUrl":"https://doi.org/10.29007/7pd1","url":null,"abstract":"The medical history information contained in electronic health records (EHR) is a valuable and largely untapped data mining source for predicting patient outcomes and thereby improving treatment. This paper presents a simple but novel evolutionary algorithm (EA) for identifying how various medical history and demographic factors predict clinical outcomes. For this initial study, our EA was tested using synthetic data concerning COVID-19 hospitalization rates and we show that the EA results are more informative than logistic regression, neural network, or decision tree results.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69423532","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}
Drawing on the digital experiences of almost 76,000 learners/students, teaching staff and professional services staff from UK further and higher education, this session will explore the successes and challenges of learning, teaching and working online throughout the coronavirus pandemic. COVID-19 and the enforced move to remote engagement meant that all needed to embrace digital practices. It galvanised colleges and universities to push forward with digital transformation projects that may otherwise have taken far longer.Understanding how students and staff use technology is essential. Jisc has been running the digital experience insights surveys to gather staff and students’ expectations and experiences of technology since 2016, providing valid, representative and actionable data to inform digital transformation.Alongside Jisc’s work on learning and teaching reimagined and shaping the digital future, the survey findings highlight current digital practices and provide data to inform strategic planning. Knowing what works, what the barriers are and listening to the voices of these key stakeholders as they describe their experiences will help us to further advance digital practice and develop effective models of hybrid and blended models.Key themes explored in this session include:* Infrastructure and access to technology* Support to learn, teach and assess/be assessed online* Actively engaging all stakeholders as partners in online digital education* Wellbeing when learning, teaching or working onlineDelegates will takeaway from the sessions:1. An overview of the findings from the learner/student, teaching staff and professional services surveys (with digital copies of each of the reports)2. Opportunities to reflect on how these findings align or differ from their own experiences, engage in discussions and share practice on approaches to digital transformation
{"title":"Digital learning and teaching throughout the pandemic: learning from the digital experiences of students and staff during 2020 and 2021","authors":"Clare Killen, K. Heywood","doi":"10.29007/b4hw","DOIUrl":"https://doi.org/10.29007/b4hw","url":null,"abstract":"Drawing on the digital experiences of almost 76,000 learners/students, teaching staff and professional services staff from UK further and higher education, this session will explore the successes and challenges of learning, teaching and working online throughout the coronavirus pandemic. COVID-19 and the enforced move to remote engagement meant that all needed to embrace digital practices. It galvanised colleges and universities to push forward with digital transformation projects that may otherwise have taken far longer.Understanding how students and staff use technology is essential. Jisc has been running the digital experience insights surveys to gather staff and students’ expectations and experiences of technology since 2016, providing valid, representative and actionable data to inform digital transformation.Alongside Jisc’s work on learning and teaching reimagined and shaping the digital future, the survey findings highlight current digital practices and provide data to inform strategic planning. Knowing what works, what the barriers are and listening to the voices of these key stakeholders as they describe their experiences will help us to further advance digital practice and develop effective models of hybrid and blended models.Key themes explored in this session include:* Infrastructure and access to technology* Support to learn, teach and assess/be assessed online* Actively engaging all stakeholders as partners in online digital education* Wellbeing when learning, teaching or working onlineDelegates will takeaway from the sessions:1. An overview of the findings from the learner/student, teaching staff and professional services surveys (with digital copies of each of the reports)2. Opportunities to reflect on how these findings align or differ from their own experiences, engage in discussions and share practice on approaches to digital transformation","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69429887","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}
Generalized Mutual Assignment Problem (GMAP) is a multi-agent based distributed optimization where the agents try to obtain the most profitable job assignment. Since it is NP-hard and even a problem of judging the existence of a feasible solution is NP-complete, it is a challenging issue to solve GMAP. In this paper, a consensus based distributed subgradient method is considered to obtain feasible solutions of GMAP as good as possible. Adaptive step size which is calculated by the lower and estimated upper bounds is proposed for the step size in the subgradient method. In addition, a protocol how to estimate the upper bound is also proposed, where each agent do not have to synchronize it.
{"title":"Adaptive Step Size for a Consensus based Distributed Subgradient Method in Generalized Mutual Assignment Problem","authors":"Yuki Amemiya, Kenta Hanada, Kenji Sugimoto","doi":"10.29007/k1bg","DOIUrl":"https://doi.org/10.29007/k1bg","url":null,"abstract":"Generalized Mutual Assignment Problem (GMAP) is a multi-agent based distributed optimization where the agents try to obtain the most profitable job assignment. Since it is NP-hard and even a problem of judging the existence of a feasible solution is NP-complete, it is a challenging issue to solve GMAP. In this paper, a consensus based distributed subgradient method is considered to obtain feasible solutions of GMAP as good as possible. Adaptive step size which is calculated by the lower and estimated upper bounds is proposed for the step size in the subgradient method. In addition, a protocol how to estimate the upper bound is also proposed, where each agent do not have to synchronize it.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69432140","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}
Gurmit S. Sandhu, A. Kilburg, A. Martin, Charuta Pande, Hans Friedrich Witschel, Emanuele Laurenzi, E. Billing
Preschool children, when diagnosed with Autism Spectrum Disorder (ASD), often ex- perience a long and painful journey on their way to self-advocacy. Access to standard of care is poor, with long waiting times and the feeling of stigmatization in many social set- tings. Early interventions in ASD have been found to deliver promising results, but have a high cost for all stakeholders. Some recent studies have suggested that digital biomarkers (e.g., eye gaze), tracked using affordable wearable devices such as smartphones or tablets, could play a role in identifying children with special needs. In this paper, we discuss the possibility of supporting neurodiverse children with technologies based on digital biomark- ers which can help to a) monitor the performance of children diagnosed with ASD and b) predict those who would benefit most from early interventions. We describe an ongoing feasibility study that uses the “DREAM dataset”, stemming from a clinical study with 61 pre-school children diagnosed with ASD, to identify digital biomarkers informative for the child’s progression on tasks such as imitation of gestures. We describe our vision of a tool that will use these prediction models and that ASD pre-schoolers could use to train certain social skills at home. Our discussion includes the settings in which this usage could be embedded.
{"title":"Practice Track: A Learning Tracker using Digital Biomarkers for Autistic Preschoolers","authors":"Gurmit S. Sandhu, A. Kilburg, A. Martin, Charuta Pande, Hans Friedrich Witschel, Emanuele Laurenzi, E. Billing","doi":"10.29007/m2jx","DOIUrl":"https://doi.org/10.29007/m2jx","url":null,"abstract":"Preschool children, when diagnosed with Autism Spectrum Disorder (ASD), often ex- perience a long and painful journey on their way to self-advocacy. Access to standard of care is poor, with long waiting times and the feeling of stigmatization in many social set- tings. Early interventions in ASD have been found to deliver promising results, but have a high cost for all stakeholders. Some recent studies have suggested that digital biomarkers (e.g., eye gaze), tracked using affordable wearable devices such as smartphones or tablets, could play a role in identifying children with special needs. In this paper, we discuss the possibility of supporting neurodiverse children with technologies based on digital biomark- ers which can help to a) monitor the performance of children diagnosed with ASD and b) predict those who would benefit most from early interventions. We describe an ongoing feasibility study that uses the “DREAM dataset”, stemming from a clinical study with 61 pre-school children diagnosed with ASD, to identify digital biomarkers informative for the child’s progression on tasks such as imitation of gestures. We describe our vision of a tool that will use these prediction models and that ASD pre-schoolers could use to train certain social skills at home. Our discussion includes the settings in which this usage could be embedded.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69435447","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}
Purpose – Multiple water accounting techniques exist and suffer from data gaps and mis- aligned stakeholders which creates standardization and consolidation problems in the data of the industry. This study identifies domain-based stakeholders and defines stakeholder data relationships to improve inter-stakeholder data efficiency.Design/methodology/approach – The research design follows an inductive data col- lection of qualitative cross-sectional data through semi-structured expert interviews. The recorded interviews were transcribed, thematically coded, and the findings summarized.Findings – The result is an improved specificity of water accounting data stakeholders which have different data input and output requirements. Our research found that these stakeholders can be chained together based on their data relationships which enables iden- tifying inter-stakeholder relationships and improved data efficiency.Social Implications – Water is a vital resource for humans and the United Nations Sustainable Development Goals. More precise description of stakeholders and data factors enable more efficient data flow which can improve the efficacy of terminal impact.Originality/value – The awareness of problem is refined by increasing stakeholder speci- ficity and identifying data input/output requirements. This enables chaining of stake- holders and data to clarify stakeholder data requirements and improve data efficiency for purposes such as collaboration and policy guidance.
{"title":"Identification and Chaining of Water Accounting Data Stakeholders","authors":"Ryan Prater, Barbara Eisenbart","doi":"10.29007/mjn2","DOIUrl":"https://doi.org/10.29007/mjn2","url":null,"abstract":"Purpose – Multiple water accounting techniques exist and suffer from data gaps and mis- aligned stakeholders which creates standardization and consolidation problems in the data of the industry. This study identifies domain-based stakeholders and defines stakeholder data relationships to improve inter-stakeholder data efficiency.Design/methodology/approach – The research design follows an inductive data col- lection of qualitative cross-sectional data through semi-structured expert interviews. The recorded interviews were transcribed, thematically coded, and the findings summarized.Findings – The result is an improved specificity of water accounting data stakeholders which have different data input and output requirements. Our research found that these stakeholders can be chained together based on their data relationships which enables iden- tifying inter-stakeholder relationships and improved data efficiency.Social Implications – Water is a vital resource for humans and the United Nations Sustainable Development Goals. More precise description of stakeholders and data factors enable more efficient data flow which can improve the efficacy of terminal impact.Originality/value – The awareness of problem is refined by increasing stakeholder speci- ficity and identifying data input/output requirements. This enables chaining of stake- holders and data to clarify stakeholder data requirements and improve data efficiency for purposes such as collaboration and policy guidance.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69445801","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}
Maren Lübcke, Elke Bosse, Astrid Book, Klaus Wannemacher, Harald Gilch
The HIS-Institute of Higher Education Development (HIS-HE) conducted a nationwide survey among Higher Education leaders about the extent to which the push for digitalization at German higher education institutions related to the COVID-19 pandemic has promoted strategic engagement with digitalization and how such experiences have been integrated into concepts for the future of teaching and learning. The findings show that the effects of the pandemic are most evident in the digitalization of teaching formats, while many infrastructural and technical developments had already been initiated before the pandemic and were at most accelerated.When the COVID-19-related developments of digitalization are analyzed with regard to structural characteristics of the HEIs represented in the sample, it becomes apparent that there are no fundamental differences between universities and universities of applied sciences. Only the universities of arts and music are distinguished by the fact that the pandemic-related changes are generally smaller and fewer innovations are to be expected after the pandemic.The range of disciplines of the HEIs also proves to be relevant when comparing HEIs with and without STEM subjects, as the former group shows a significantly greater dynamic of change.Last but not least, differences can also be found with regard to the existence of a digitalization strategy. Universities with a digitalization strategy not only have a head start in terms of experience, since they already offered online teaching or hybrid formats before the pandemic. Rather, they have changed their teaching and examination formats particularly extensively in the course of the pandemic and are planning to a greater extent to use instruments and formats for digital teaching in the future.
{"title":"Impact of the COVID-19 pandemic on the digitalization and strategic development of German universities","authors":"Maren Lübcke, Elke Bosse, Astrid Book, Klaus Wannemacher, Harald Gilch","doi":"10.29007/p9lb","DOIUrl":"https://doi.org/10.29007/p9lb","url":null,"abstract":"The HIS-Institute of Higher Education Development (HIS-HE) conducted a nationwide survey among Higher Education leaders about the extent to which the push for digitalization at German higher education institutions related to the COVID-19 pandemic has promoted strategic engagement with digitalization and how such experiences have been integrated into concepts for the future of teaching and learning. The findings show that the effects of the pandemic are most evident in the digitalization of teaching formats, while many infrastructural and technical developments had already been initiated before the pandemic and were at most accelerated.When the COVID-19-related developments of digitalization are analyzed with regard to structural characteristics of the HEIs represented in the sample, it becomes apparent that there are no fundamental differences between universities and universities of applied sciences. Only the universities of arts and music are distinguished by the fact that the pandemic-related changes are generally smaller and fewer innovations are to be expected after the pandemic.The range of disciplines of the HEIs also proves to be relevant when comparing HEIs with and without STEM subjects, as the former group shows a significantly greater dynamic of change.Last but not least, differences can also be found with regard to the existence of a digitalization strategy. Universities with a digitalization strategy not only have a head start in terms of experience, since they already offered online teaching or hybrid formats before the pandemic. Rather, they have changed their teaching and examination formats particularly extensively in the course of the pandemic and are planning to a greater extent to use instruments and formats for digital teaching in the future.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69448370","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}
Establishing intelligent crop management techniques for preserving the soil, while providing next-generational food supply for an increasing population is critical. Nitrogen fertilizer is used in current farming practice as a way of encouraging crop development; however, its excessive use is found to have disastrous and long-lasting effects on the environment. This can be reduced through the optimization of fertilizer application strategies. In this work, we apply a set of reinforcement learning algorithms – the DQN, Double DQN, Dueling DDQN, and PPO – to learn novel strategies for reducing this application in a simulated crop growth setting. We provide an analysis of each agent’s ability and show that the Dueling DDQN agent can learn favourable strategies for minimizing nitrogen fertilizer application amounts, while maintaining a sufficient yield comparable to standard farming practice.
{"title":"Analyzing Reinforcement Learning Algorithms for Nitrogen Fertilizer Management in Simulated Crop Growth","authors":"Michael Vogt, Benjamin Rosman","doi":"10.29007/1v4x","DOIUrl":"https://doi.org/10.29007/1v4x","url":null,"abstract":"Establishing intelligent crop management techniques for preserving the soil, while providing next-generational food supply for an increasing population is critical. Nitrogen fertilizer is used in current farming practice as a way of encouraging crop development; however, its excessive use is found to have disastrous and long-lasting effects on the environment. This can be reduced through the optimization of fertilizer application strategies. In this work, we apply a set of reinforcement learning algorithms – the DQN, Double DQN, Dueling DDQN, and PPO – to learn novel strategies for reducing this application in a simulated crop growth setting. We provide an analysis of each agent’s ability and show that the Dueling DDQN agent can learn favourable strategies for minimizing nitrogen fertilizer application amounts, while maintaining a sufficient yield comparable to standard farming practice.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69420560","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}
B. I. Akhigbe, Khanyisa Mtombeni, Melissa Densmore, H. Suleman
Existing user studies on how users use digital archives as information systems seldom focus on what influences users’ needs and expectations. Similarly, not much is known about how the low resource context influences users’ needs. What users expect from searching and other related functionalities is rarely addressed in the cultural heritage and historical digital archives. These gaps unveil the mismatch between users’ needs (and expectations) and deployed technologies in the low resource context. As a result, delivering novel services through these digital archives is impossible because of the gap between design and reality. Users in the low resource environment are thus constrained to use whatever functionalities are available. This paper presents the empirical result of a user study. We determined the study’s sample framing using the future determination analysis technique. This analysis also guided the scoping of the study’s survey. The study foregrounds the need to adapt to users’ ever-changing expectations by understanding their needs. This is critical for a better system design that meets users’ expectations. A key finding is that users strongly prefer simple search functionalities in low resource environments. Regardless, they would prefer to use advanced features if given the opportunity. However, the expertise (and sometimes funding) needed to satisfy this desire is scarce. The surveyed users are only end-users without the expertise to innovate and build digital archives to meet their needs. This dearth of “resource(s)” was found to be characteristic of the experience of low resource (or resource-poor) settings like South Africa.
{"title":"Do People in Low Resource Environments only Need Search? Exploring Digital Archive Functionalities in South Africa","authors":"B. I. Akhigbe, Khanyisa Mtombeni, Melissa Densmore, H. Suleman","doi":"10.29007/9cwr","DOIUrl":"https://doi.org/10.29007/9cwr","url":null,"abstract":"Existing user studies on how users use digital archives as information systems seldom focus on what influences users’ needs and expectations. Similarly, not much is known about how the low resource context influences users’ needs. What users expect from searching and other related functionalities is rarely addressed in the cultural heritage and historical digital archives. These gaps unveil the mismatch between users’ needs (and expectations) and deployed technologies in the low resource context. As a result, delivering novel services through these digital archives is impossible because of the gap between design and reality. Users in the low resource environment are thus constrained to use whatever functionalities are available. This paper presents the empirical result of a user study. We determined the study’s sample framing using the future determination analysis technique. This analysis also guided the scoping of the study’s survey. The study foregrounds the need to adapt to users’ ever-changing expectations by understanding their needs. This is critical for a better system design that meets users’ expectations. A key finding is that users strongly prefer simple search functionalities in low resource environments. Regardless, they would prefer to use advanced features if given the opportunity. However, the expertise (and sometimes funding) needed to satisfy this desire is scarce. The surveyed users are only end-users without the expertise to innovate and build digital archives to meet their needs. This dearth of “resource(s)” was found to be characteristic of the experience of low resource (or resource-poor) settings like South Africa.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69427643","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}
Minal Khatri, Adam Voshall, S. Batra, Sukhwinder Kaur, Dr. Jitender S. Deogun
Massive amounts of data gathered over the last decade have contributed significantly to the applicability of deep neural networks. Deep learning is a good technique to process huge amounts of data because they get better as we feed more data into them. However, in the existing literature, a deep neural classifier is often treated as a ”black box” technique because the process is not transparent and the researchers cannot gain information about how the input is associated to the output. In many domains like medicine, interpretability is very critical because of the nature of the application. Our research focuses on adding interpretability to the black box by integrating Formal Concept Analysis (FCA) into the image classification pipeline and convert it into a glass box. Our proposed approach pro- duces a low dimensional feature vector for an image dataset using autoencoder followed by a supervised fine-tuning of features using a deep neural classifier and Linear Discriminant Analysis (LDA). The low dimensional feature vector produced is then processed by FCA based classifier. The FCA framework helps us develop a glass box classifier from which the relationship between the target class and the low dimensional feature set can be derived. Further, it helps the researchers to understand the classification task and refine it. We use the MNIST dataset to test the interfacing between deep neural networks and the FCA classifier. The classifier achieves an accuracy of 98.7% for binary classification and 97.38% for multi-class classification. We compare the performance of the proposed classifier with Convolutional neural networks (CNN) and Random forest.
{"title":"Interpretable Image Classification Model Using Formal Concept Analysis Based Classifier","authors":"Minal Khatri, Adam Voshall, S. Batra, Sukhwinder Kaur, Dr. Jitender S. Deogun","doi":"10.29007/rp6q","DOIUrl":"https://doi.org/10.29007/rp6q","url":null,"abstract":"Massive amounts of data gathered over the last decade have contributed significantly to the applicability of deep neural networks. Deep learning is a good technique to process huge amounts of data because they get better as we feed more data into them. However, in the existing literature, a deep neural classifier is often treated as a ”black box” technique because the process is not transparent and the researchers cannot gain information about how the input is associated to the output. In many domains like medicine, interpretability is very critical because of the nature of the application. Our research focuses on adding interpretability to the black box by integrating Formal Concept Analysis (FCA) into the image classification pipeline and convert it into a glass box. Our proposed approach pro- duces a low dimensional feature vector for an image dataset using autoencoder followed by a supervised fine-tuning of features using a deep neural classifier and Linear Discriminant Analysis (LDA). The low dimensional feature vector produced is then processed by FCA based classifier. The FCA framework helps us develop a glass box classifier from which the relationship between the target class and the low dimensional feature set can be derived. Further, it helps the researchers to understand the classification task and refine it. We use the MNIST dataset to test the interfacing between deep neural networks and the FCA classifier. The classifier achieves an accuracy of 98.7% for binary classification and 97.38% for multi-class classification. We compare the performance of the proposed classifier with Convolutional neural networks (CNN) and Random forest.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69450700","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：