It is realistic to describe Artificial Intelligence (AI) as the most important of emerging technologies because of its increasing dominance in almost every field of modern life and the crucial role it plays in boosting high-tech multidisciplinary developments integrated in steady innovations. The implementation of AI-based solutions for real world problems helps to create new insights into old problems and to produce unique knowledge about intractable problems which are too complex to be efficiently solved with conventional methods. Biomedical data analysis, computer-assisted drug discovery, pandemic predictions and preparedness are only but a few examples of applied research areas that use machine learning as a pivotal data evaluation tool. Such tools process enormous amounts of data trying to discover causal relations and risk factors and predict outcomes that for example can change the course of diseases. The growing number of remarkable achievements delivered by modern machine learning algorithms in the last years raises enthusiasm for all those things that AI can do. The value of the global artificial intelligence market was calculated at USD 136.55 billion in 2022 and is estimated to expand at an annual growth rate of 37.3% from 2023 to 2030. Novel machine-learning applications in finance, national security, health, criminal justice, transportation, smart cities etc. justify the forecast that AI will have a disruptive impact on economies, societies and governance. The traditional rule-based or expert systems, known in computer science since decades implement factual, widely accepted knowledge and heuristic of human experts and they operate by practically imitating the decision making process and reasoning functionalities of professionals. In contrast, modern statistical machine learning systems discover their own rules based on examples on the basis of vast amounts of training data introduced to them. Unfortunately the predictions of these systems are generally not understandable by humans and quite often they are neither definite or unique. Raising the accuracy of the algorithms doesn't improve the situation. Various multi-state initiatives and business programs have been already launched and are in progress to develop technical and ethical criteria for reliable and trustworthy artificial intelligence. Considering the complexity of famous leading machine learning models (up to hundreds of billion parameters) and the influence they can exercise for example by creating text and news and also fake news, generate technical articles, identify human emotions, identify illness etc. it is necessary to expand the definition of HMI (Human Machine Interface) and invent new security concepts associated with it. The definition of HMI has to be extended to account for real-time procedural interactions of humans with algorithms and machines, for instance when faces, body movement patterns, thoughts, emotions and so on ar
{"title":"Human Machine Interaction and Security in the era of modern Machine Learning","authors":"A. Leventi-Peetz","doi":"10.54941/ahfe1002963","DOIUrl":"https://doi.org/10.54941/ahfe1002963","url":null,"abstract":"It is realistic to describe Artificial Intelligence (AI) as the most important of\u0000 emerging technologies because of its increasing dominance in almost every field of\u0000 modern life and the crucial role it plays in boosting high-tech multidisciplinary\u0000 developments integrated in steady innovations. The implementation of AI-based solutions\u0000 for real world problems helps to create new insights into old problems and to produce\u0000 unique knowledge about intractable problems which are too complex to be efficiently\u0000 solved with conventional methods. Biomedical data analysis, computer-assisted drug\u0000 discovery, pandemic predictions and preparedness are only but a few examples of applied\u0000 research areas that use machine learning as a pivotal data evaluation tool. Such tools\u0000 process enormous amounts of data trying to discover causal relations and risk factors\u0000 and predict outcomes that for example can change the course of diseases. The growing\u0000 number of remarkable achievements delivered by modern machine learning algorithms in the\u0000 last years raises enthusiasm for all those things that AI can do. The value of the\u0000 global artificial intelligence market was calculated at USD 136.55 billion in 2022 and\u0000 is estimated to expand at an annual growth rate of 37.3% from 2023 to 2030. Novel\u0000 machine-learning applications in finance, national security, health, criminal justice,\u0000 transportation, smart cities etc. justify the forecast that AI will have a disruptive\u0000 impact on economies, societies and governance. The traditional rule-based or expert\u0000 systems, known in computer science since decades implement factual, widely accepted\u0000 knowledge and heuristic of human experts and they operate by practically imitating the\u0000 decision making process and reasoning functionalities of professionals. In contrast,\u0000 modern statistical machine learning systems discover their own rules based on examples\u0000 on the basis of vast amounts of training data introduced to them. Unfortunately the\u0000 predictions of these systems are generally not understandable by humans and quite often\u0000 they are neither definite or unique. Raising the accuracy of the algorithms doesn't\u0000 improve the situation. Various multi-state initiatives and business programs have been\u0000 already launched and are in progress to develop technical and ethical criteria for\u0000 reliable and trustworthy artificial intelligence. Considering the complexity of famous\u0000 leading machine learning models (up to hundreds of billion parameters) and the influence\u0000 they can exercise for example by creating text and news and also fake news, generate\u0000 technical articles, identify human emotions, identify illness etc. it is necessary to\u0000 expand the definition of HMI (Human Machine Interface) and invent new security concepts\u0000 associated with it. The definition of HMI has to be extended to account for real-time\u0000 procedural interactions of humans with algorithms and machines, for instance when faces,\u0000 body movement patterns, thoughts, emotions and so on ar","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133678103","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}
Objectives:The presented work arises in the context of designing for individuals with visual impairment, specifically we refer to a target group of children from two to seven years of age. The study was conducted with the contribution of the XXX research group within the XXX project funded by the European Community (2020-2023), with the aim of creating a specific curriculum for training the profession of a visual rehabilitator for children. In this perspective, the paper shows a practical case study carried out through the simulation technique at XXX.The approach that would be applied to this course is innovative, as it involves the immersive and experiential participation of students and the adoption of the most advanced training technologies in the field of simulation.In order to proceed with the implementation of the experiment, the contribution of multiple figures, such as expert designers, doctors, ophthalmologists, psychologists, and visual rehabilitators, was planned, creating a multidisciplinary and interdisciplinary study. The ultimate goal is to provide students with standardized criteria for assessing and intervening appropriately within the living spaces of the child with visual impairment.Methods:The preliminary phase involved the simulation of a typical home environment for the considered target, specifically the set-up of a children's bedroom. The set-up of XXX is based on a movie set. Equipped with the most advanced technologies, it allows for the recording and creation of digital content (real-time recordings) and the configuration of environments, such as the arrangement and number of furnishings and the variation of ambient brightness, which are fundamental elements to ensure the autonomy of actions such as eating, playing, washing and orienting oneself, planned in each educational module.Specifically, the bedroom was set up with basic and standard elements, trying to recreate a real context in the most realistic way. The furniture included a bed, a bedside table, a small table for playing, a small chair, a bookshelf, a desk, various soft toys and games, two closets with sliding doors, and a desk chair.The entrance door and a window were also simulated in the room.The placement of the various elements within the room was designed based on the needs of visually impaired and blind children and the experimentation was divided into two moments characterized by two different setups. The first set-up involved a glaring light setting and the selection of objects that were difficult to distinguish, then the environment was modified through the use of contrasting elements, visual markers, and appropriate lighting through dimmable lights.Results:The experiment, which took place as part of the activities of TWP4 - Task 4.2 Lesson Plan Development: guides and plans for teachers supporting the localization of the curriculum, was carried out by a series of students from various European countries who partici
{"title":"HCD methodologies and simulation for visual rehabilitator’s education in oMERO\u0000 project","authors":"Isabella Nevoso, Niccolò Casiddu, Annapaola Vacanti, Claudia Porfirione, Isabel Leggiero, Francesco Burlando","doi":"10.54941/ahfe1002923","DOIUrl":"https://doi.org/10.54941/ahfe1002923","url":null,"abstract":"Objectives:The presented work arises in the context of designing for individuals\u0000 with visual impairment, specifically we refer to a target group of children from two to\u0000 seven years of age. The study was conducted with the contribution of the XXX research\u0000 group within the XXX project funded by the European Community (2020-2023), with the aim\u0000 of creating a specific curriculum for training the profession of a visual rehabilitator\u0000 for children. In this perspective, the paper shows a practical case study carried out\u0000 through the simulation technique at XXX.The approach that would be applied to this\u0000 course is innovative, as it involves the immersive and experiential participation of\u0000 students and the adoption of the most advanced training technologies in the field of\u0000 simulation.In order to proceed with the implementation of the experiment, the\u0000 contribution of multiple figures, such as expert designers, doctors, ophthalmologists,\u0000 psychologists, and visual rehabilitators, was planned, creating a multidisciplinary and\u0000 interdisciplinary study. The ultimate goal is to provide students with standardized\u0000 criteria for assessing and intervening appropriately within the living spaces of the\u0000 child with visual impairment.Methods:The preliminary phase involved the simulation of a\u0000 typical home environment for the considered target, specifically the set-up of a\u0000 children's bedroom. The set-up of XXX is based on a movie set. Equipped with the most\u0000 advanced technologies, it allows for the recording and creation of digital content\u0000 (real-time recordings) and the configuration of environments, such as the arrangement\u0000 and number of furnishings and the variation of ambient brightness, which are fundamental\u0000 elements to ensure the autonomy of actions such as eating, playing, washing and\u0000 orienting oneself, planned in each educational module.Specifically, the bedroom was set\u0000 up with basic and standard elements, trying to recreate a real context in the most\u0000 realistic way. The furniture included a bed, a bedside table, a small table for playing,\u0000 a small chair, a bookshelf, a desk, various soft toys and games, two closets with\u0000 sliding doors, and a desk chair.The entrance door and a window were also simulated in\u0000 the room.The placement of the various elements within the room was designed based on the\u0000 needs of visually impaired and blind children and the experimentation was divided into\u0000 two moments characterized by two different setups. The first set-up involved a glaring\u0000 light setting and the selection of objects that were difficult to distinguish, then the\u0000 environment was modified through the use of contrasting elements, visual markers, and\u0000 appropriate lighting through dimmable lights.Results:The experiment, which took place as\u0000 part of the activities of TWP4 - Task 4.2 Lesson Plan Development: guides and plans for\u0000 teachers supporting the localization of the curriculum, was carried out by a series of\u0000 students from various European countries who partici","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132390394","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}
With highly automated and Autonomous Vehicles (AVs) being one of the most prominent emerging technologies in the automotive industry, efforts to achieve SAE Level 3+ vehicles have skyrocketed in recent years. As new technologies emerge on a daily basis, these systems are becoming increasingly complex. To help people understand - and also accept - these new technologies, there is a need for explanation. There are three essential dimensions to designing explanations, namely content, frequency, and timing. Our goal is to develop an algorithm that optimises explanation in AVs. Most of the existing research focuses on the content of an explanation, whereas the fine-granularity of the frequency and timing of an explanation is relatively unexplored. Previous studies concerning "when to explain" have tended to make broad distinctions between explaining before, during or after an action is performed. For AVs, studies have shown that passengers prefer to receive an explanation before an autonomous action takes place. However, it seems likely that the acclimatisation that occurs through prolonged exposure to and use of a particular AV will reduce the need for explanation. As comprehension of explanations is workload-intensive, it is necessary to optimise both the frequency, i.e. skipping explanations when they are not helpful to reduce workload, and the precise point in time when an explanation is given, i.e. giving an explanation when it provides the maximum workload reduction. Extra mental workload for passengers can be caused by both giving and omitting an explanation. Every explanation that is presented requires cognitive processing in order to be understood, even if its content is considered to be redundant or if it will not be remembered by the addressee. On the other hand, skipping the explanation can cause the passenger to actively scan the environment for potential cues themselves, if necessary. Such an attention strategy would also impose a significant cognitive load on the passenger. In our work, to predict the mental workload of the passenger, we use the state-of-the-art attention model called SEEV (Salience, Effort, Expectancy, and Value). The SEEV model is dynamically used for forecasting the likelihood of the direction of attention. Our work aims to generate an optimally timed strategy for presenting an explanation. Using the SEEV model we build a probabilistic reactive game, i.e., 1.5-player game or Markov Decision Process, and we use reactive synthesis to generate an optimal reactive strategy for presenting an explanation that minimises workload.
{"title":"Optimal Explanation Generation using Attention Distribution Model","authors":"Akhila Bairy, M. Fränzle","doi":"10.54941/ahfe1002928","DOIUrl":"https://doi.org/10.54941/ahfe1002928","url":null,"abstract":"With highly automated and Autonomous Vehicles (AVs) being one of the most\u0000 prominent emerging technologies in the automotive industry, efforts to achieve SAE Level\u0000 3+ vehicles have skyrocketed in recent years. As new technologies emerge on a daily\u0000 basis, these systems are becoming increasingly complex. To help people understand - and\u0000 also accept - these new technologies, there is a need for explanation. There are three\u0000 essential dimensions to designing explanations, namely content, frequency, and timing.\u0000 Our goal is to develop an algorithm that optimises explanation in AVs. Most of the\u0000 existing research focuses on the content of an explanation, whereas the fine-granularity\u0000 of the frequency and timing of an explanation is relatively unexplored. Previous studies\u0000 concerning \"when to explain\" have tended to make broad distinctions between explaining\u0000 before, during or after an action is performed. For AVs, studies have shown that\u0000 passengers prefer to receive an explanation before an autonomous action takes place.\u0000 However, it seems likely that the acclimatisation that occurs through prolonged exposure\u0000 to and use of a particular AV will reduce the need for explanation. As comprehension of\u0000 explanations is workload-intensive, it is necessary to optimise both the frequency, i.e.\u0000 skipping explanations when they are not helpful to reduce workload, and the precise\u0000 point in time when an explanation is given, i.e. giving an explanation when it provides\u0000 the maximum workload reduction. Extra mental workload for passengers can be caused by\u0000 both giving and omitting an explanation. Every explanation that is presented requires\u0000 cognitive processing in order to be understood, even if its content is considered to be\u0000 redundant or if it will not be remembered by the addressee. On the other hand, skipping\u0000 the explanation can cause the passenger to actively scan the environment for potential\u0000 cues themselves, if necessary. Such an attention strategy would also impose a\u0000 significant cognitive load on the passenger. In our work, to predict the mental workload\u0000 of the passenger, we use the state-of-the-art attention model called SEEV (Salience,\u0000 Effort, Expectancy, and Value). The SEEV model is dynamically used for forecasting the\u0000 likelihood of the direction of attention. Our work aims to generate an optimally timed\u0000 strategy for presenting an explanation. Using the SEEV model we build a probabilistic\u0000 reactive game, i.e., 1.5-player game or Markov Decision Process, and we use reactive\u0000 synthesis to generate an optimal reactive strategy for presenting an explanation that\u0000 minimises workload.","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122196461","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}
Ikram Ghouri Mukarram Mohammed, I. Kurnikova, Maiorov Vladimir, Iuliia Verzina, T. Meleshkevich, Evgeniya Tavlueva
Background: The method of comparative analysis is one of the most common in science where optimal choices are required. Despite the fact the method is empirical, under the conditions of epidemics such as Covid-19, it is one of the most affordable in assessing the effectiveness of the therapy. Patients with diabetes having coronavirus infection are included in the risk group which required steroid therapy. In patients with diabetes, excessive usage of Exogenous corticosteroids creates insulin deficiency which leads to hyperglycemia and the risk of developing coma. Purpose of the study: сompare the effectiveness and safety of using corticosteroids in patients with Covid-19 and diabetes prescribed "by standards" and "method of calculation". Method: Diabetic Patients with novel coronavirus infection were screened (n = 107).All patients were divided into 3 groups.In group 1(n=35) patients received dexamethasone at a dosage of 0.1 mg/kg once a day in the morning intravenously; in group 2(n = 38), patients received dexamethasone 20 mg twice daily intravenously in the morning and evening (more than 0.2 mg/kg/day) and in group 3(n = 34) patients received dexamethasone 0.1 mg /kg once a day in the morning intramuscularly. Comparative analysis were carried out according to the criteria: the period of intoxication, glycemic variability, CRP, leukocyte counts, D-dimer, and transaminases. For analysis STATISTIC 10,0 computer program was used (Matematica®, Matlab®, HarvardGraphics®) StatSoft). Results: In all the groups after therapy it was noted redistributive leukocytosis.In patients receiving high therapeutic dose (group 2) initially suppressed production of leukocytes is activated and reaches the normative indicator (p<0.001) and the indicators are comparable to the data of group 3(p<0.001)in which patients received glucocorticoids at a lower dose (0.1 mg/kg/day) intramuscularly. The most significant decrease in D-dimer levels was in patients with a dosage of dexamethasone at the rate of 0.1 units/kg once a day intravenously by 80.9%(P <0.0001);intramuscularly by 73.2%(P<0.00001)and with intravenously at a dose of more than 0.2 units/kg there was a decrease in the level of D-dimer by 67.9% (P <0.00001). Decrease in CRP (cytokine storm relief rate) did not differ significantly between the groups, which eliminates the role of inexpedient usage of dexamethasone in dosages of more than 0.2 units/kg/day.Fasting blood glucose in patients in group 3 increased by 22% (P<0.0002); in group 1 only by 12% (P <0.05)and in group 2 by 32% (P <0.0001). In all the groups, an increase was observed in postprandial glucose, and in group 2 to the level of developing ketoacidosis and required emergency intervention by increasing the dose of insulin. Conclusion: For patients without diabetes, the dose of dexamethasone is prescribed in accordance with standards (average dose) regardless of body weight and concomitant diseases. In patients with d
{"title":"Comparative Analysis Methods in Optimizing Corticosteroid Therapy in Patients with\u0000 Covid-19 and Diabetes Mellitus","authors":"Ikram Ghouri Mukarram Mohammed, I. Kurnikova, Maiorov Vladimir, Iuliia Verzina, T. Meleshkevich, Evgeniya Tavlueva","doi":"10.54941/ahfe1002958","DOIUrl":"https://doi.org/10.54941/ahfe1002958","url":null,"abstract":"Background: The method of comparative analysis is one of the most common in\u0000 science where optimal choices are required. Despite the fact the method is empirical,\u0000 under the conditions of epidemics such as Covid-19, it is one of the most affordable in\u0000 assessing the effectiveness of the therapy. Patients with diabetes having coronavirus\u0000 infection are included in the risk group which required steroid therapy. In patients\u0000 with diabetes, excessive usage of Exogenous corticosteroids creates insulin deficiency\u0000 which leads to hyperglycemia and the risk of developing coma. Purpose of the study:\u0000 сompare the effectiveness and safety of using corticosteroids in patients with Covid-19\u0000 and diabetes prescribed \"by standards\" and \"method of\u0000 calculation\". Method: Diabetic Patients with novel coronavirus infection were\u0000 screened (n = 107).All patients were divided into 3 groups.In group 1(n=35) patients\u0000 received dexamethasone at a dosage of 0.1 mg/kg once a day in the morning intravenously;\u0000 in group 2(n = 38), patients received dexamethasone 20 mg twice daily intravenously in\u0000 the morning and evening (more than 0.2 mg/kg/day) and in group 3(n = 34) patients\u0000 received dexamethasone 0.1 mg /kg once a day in the morning intramuscularly. Comparative\u0000 analysis were carried out according to the criteria: the period of intoxication,\u0000 glycemic variability, CRP, leukocyte counts, D-dimer, and transaminases. For analysis\u0000 STATISTIC 10,0 computer program was used (Matematica®, Matlab®, HarvardGraphics®)\u0000 StatSoft). Results: In all the groups after therapy it was noted redistributive\u0000 leukocytosis.In patients receiving high therapeutic dose (group 2) initially suppressed\u0000 production of leukocytes is activated and reaches the normative indicator\u0000 (p<0.001) and the indicators are comparable to the data of group\u0000 3(p<0.001)in which patients received glucocorticoids at a lower dose (0.1\u0000 mg/kg/day) intramuscularly. The most significant decrease in D-dimer levels was in\u0000 patients with a dosage of dexamethasone at the rate of 0.1 units/kg once a day\u0000 intravenously by 80.9%(P <0.0001);intramuscularly by\u0000 73.2%(P<0.00001)and with intravenously at a dose of more than 0.2 units/kg\u0000 there was a decrease in the level of D-dimer by 67.9% (P <0.00001). Decrease\u0000 in CRP (cytokine storm relief rate) did not differ significantly between the groups,\u0000 which eliminates the role of inexpedient usage of dexamethasone in dosages of more than\u0000 0.2 units/kg/day.Fasting blood glucose in patients in group 3 increased by 22%\u0000 (P<0.0002); in group 1 only by 12% (P <0.05)and in group 2 by 32%\u0000 (P <0.0001). In all the groups, an increase was observed in postprandial\u0000 glucose, and in group 2 to the level of developing ketoacidosis and required emergency\u0000 intervention by increasing the dose of insulin. Conclusion: For patients without\u0000 diabetes, the dose of dexamethasone is prescribed in accordance with standards (average\u0000 dose) regardless of body weight and concomitant diseases. In patients with d","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129246893","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}
In this case study, we report experiences deploying a conversational chatbot as a pre-class and post-class engagement tool for undergraduate students enrolled in sustainability-related courses aimed at educating them about the severity of climate change and the importance of climate action by offsetting one’s carbon footprint (e.g, by planting trees or mangroves in SEA). The intitiative supports the university’s sustainability efforts in general and our new sustainability major in particular aimed at helping students to achieve sustainability-related learning outcomes with reference to climate change and climate action (SDG 13), one of the 17 Sustainable Development Goals established by the United Nations in 2015.Climate action means stepped-up efforts to reduce greenhouse gas emissions and strengthen resilience and adaptive capacity to climate-induced impacts, including: climate-related hazards in all countries; integrating climate change measures into national policies, strategies and planning; and improving education, awareness-raising and human and institutional capacity with respect to climate change mitigation, adaptation, impact reduction and early warning… (https://www.sdfinance.undp.org/content/sdfinance/en/home/sdg/goal-13--climate-action.html).Related teaching and learning challenges we have observed in our classes include climate change ignorance / indifference, lack of confidence in calculating one’s own carbon footprint, not knowing why personal climate action is important and how it can contribute to active decarbonisation etc. to mitigate climate change. Several research studies have underlined the potentially positive effect of Chatbots on students’ learning in educational institutions ranging from primary schools to IHLs. “Conveniency”, “satisfaction”, “engagement” and “motivation” have been highlighted in previous studies as benefits of using conversational pedagogical agents (= “Chatbots”) in teaching and learning (Smutny & Schreiberova, 2020; Martha & Santoso, 2019; Satow, 2017; Fadhill & Villaforita, 2017; Pereira, 2016; Kim & Baylor, 2007).Conceptually, the ongoing project relates to the study of technology-mediated learning in general and chatbot-mediated learning in particular Winkler & Söllner (2018) have highlighted the advantages of chatbot-mediated learning (CML) in educational settings with regard to positive learning outcomes that include learning success and student satisfaction. Chatbot-mediated learning (CML) has enabled learners to take on a proactive approach in creating an individualized learning experience in the context of large-scale lectures and massive open online courses (MOOC) where individualized support was lacking. Chatbots play an essential role in T&L by supporting teachers to create interactive learning experience when teachers are not physically present, monitoring results and performance, and disseminating regular reminders to check on homework and encourage st
{"title":"Engaging Students through Conversational Chatbots and Digital Content: A Climate\u0000 Action Perspective","authors":"T. Menkhoff, B. Gan","doi":"10.54941/ahfe1002960","DOIUrl":"https://doi.org/10.54941/ahfe1002960","url":null,"abstract":"In this case study, we report experiences deploying a conversational chatbot as a\u0000 pre-class and post-class engagement tool for undergraduate students enrolled in\u0000 sustainability-related courses aimed at educating them about the severity of climate\u0000 change and the importance of climate action by offsetting one’s carbon footprint (e.g,\u0000 by planting trees or mangroves in SEA). The intitiative supports the university’s\u0000 sustainability efforts in general and our new sustainability major in particular aimed\u0000 at helping students to achieve sustainability-related learning outcomes with reference\u0000 to climate change and climate action (SDG 13), one of the 17 Sustainable Development\u0000 Goals established by the United Nations in 2015.Climate action means stepped-up efforts\u0000 to reduce greenhouse gas emissions and strengthen resilience and adaptive capacity to\u0000 climate-induced impacts, including: climate-related hazards in all countries;\u0000 integrating climate change measures into national policies, strategies and planning; and\u0000 improving education, awareness-raising and human and institutional capacity with respect\u0000 to climate change mitigation, adaptation, impact reduction and early warning…\u0000 (https://www.sdfinance.undp.org/content/sdfinance/en/home/sdg/goal-13--climate-action.html).Related\u0000 teaching and learning challenges we have observed in our classes include climate change\u0000 ignorance / indifference, lack of confidence in calculating one’s own carbon footprint,\u0000 not knowing why personal climate action is important and how it can contribute to active\u0000 decarbonisation etc. to mitigate climate change. Several research studies have\u0000 underlined the potentially positive effect of Chatbots on students’ learning in\u0000 educational institutions ranging from primary schools to IHLs. “Conveniency”,\u0000 “satisfaction”, “engagement” and “motivation” have been highlighted in previous studies\u0000 as benefits of using conversational pedagogical agents (= “Chatbots”) in teaching and\u0000 learning (Smutny & Schreiberova, 2020; Martha & Santoso, 2019; Satow, 2017;\u0000 Fadhill & Villaforita, 2017; Pereira, 2016; Kim & Baylor, 2007).Conceptually,\u0000 the ongoing project relates to the study of technology-mediated learning in general and\u0000 chatbot-mediated learning in particular Winkler & Söllner (2018) have highlighted\u0000 the advantages of chatbot-mediated learning (CML) in educational settings with regard to\u0000 positive learning outcomes that include learning success and student satisfaction.\u0000 Chatbot-mediated learning (CML) has enabled learners to take on a proactive approach in\u0000 creating an individualized learning experience in the context of large-scale lectures\u0000 and massive open online courses (MOOC) where individualized support was lacking.\u0000 Chatbots play an essential role in T&L by supporting teachers to create interactive\u0000 learning experience when teachers are not physically present, monitoring results and\u0000 performance, and disseminating regular reminders to check on homework and encourage\u0000 st","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115801949","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}
Perceiving the transmitted speech is a task that puts certain amount of cognitive load on the human brain. The degree of this load depends on several factors, e.g., the loudness of the perceived speech, the type and intensity of background noise, the quality and accent of the speech, familiarity with the topic of the message, etc. This load also varies between the native and non-native language (of the listener). Different levels of such load are manifested in longer duration workloads (e.g., during a work shift) by different levels of overall fatigue, which affects the decrease in the worker's action or decision error rate when performing other concurrent tasks (the so-called parallel-task paradigm). For technologies used in speech transmission or synthesis, e.g., in telecommunications, radio communications, and machine to human communications, the above implies a strong need to optimize the coding of human (or synthetic) voice to minimize listening effort during communication. Listening effort (LE) can be assessed by subjective tests following, e.g., ITU-T P.800 Recommendation, along with listening quality (LQ) as specified in P.800. A natural (but nowhere explicitely mentioned) requirement is that male and female voices are transferred with similar LQ and LE parameters; in other words, the transmission technology, including coding algorithms, frequency filters, or sampling rates, should not privilege one gender over the other to maintain similar working conditions and opportunities for all.The subjective test laboratory has performed gender analysis for all subjective test projects since 2018 to see how (mis)balanced the transmission quality between male and female speakers is. The identified misbalance can affect many professionals that deploy distant voice communication in their daily duties – think of female airport approach control dispatchers or other professionals (policewomen) who are principally handicapped by technological aspects of their job - worse voice transmission quality means higher listening effort is needed and may lead to consequent (subconscious) discomfort of their communication partners, or even intelligibility issues. Of course, this fact is not surprising for narrow-band or even old analog AM transmissions (as still used in AIRCOM). It can only be used as an argument to upgrade communication means to a suitable digital format. Unfortunately, some contemporary wide-band or even full-band digital communications also show statistically significant differences between quality of transferred male and female voices. The detailed results will be presented, including interesting systematic language dependencies (English, German, Mandarin).In the conclusions, suggestions for future codec designs considering the human-centric gender-balanced requirements are proposed. These include the minimum frequency response of the future coders, granularity of the perceptual frequency scaling, etc. Also, s
{"title":"Human-Centered Design of Voice Communications: Gender Aspects","authors":"J. Holub, Yann Kowalczuk","doi":"10.54941/ahfe1002926","DOIUrl":"https://doi.org/10.54941/ahfe1002926","url":null,"abstract":"Perceiving the transmitted speech is a task that puts certain amount of cognitive\u0000 load on the human brain. The degree of this load depends on several factors, e.g., the\u0000 loudness of the perceived speech, the type and intensity of background noise, the\u0000 quality and accent of the speech, familiarity with the topic of the message, etc. This\u0000 load also varies between the native and non-native language (of the listener). Different\u0000 levels of such load are manifested in longer duration workloads (e.g., during a work\u0000 shift) by different levels of overall fatigue, which affects the decrease in the\u0000 worker's action or decision error rate when performing other concurrent tasks (the\u0000 so-called parallel-task paradigm). For technologies used in speech transmission or\u0000 synthesis, e.g., in telecommunications, radio communications, and machine to human\u0000 communications, the above implies a strong need to optimize the coding of human (or\u0000 synthetic) voice to minimize listening effort during communication. Listening effort\u0000 (LE) can be assessed by subjective tests following, e.g., ITU-T P.800 Recommendation,\u0000 along with listening quality (LQ) as specified in P.800. A natural (but nowhere\u0000 explicitely mentioned) requirement is that male and female voices are transferred with\u0000 similar LQ and LE parameters; in other words, the transmission technology, including\u0000 coding algorithms, frequency filters, or sampling rates, should not privilege one gender\u0000 over the other to maintain similar working conditions and opportunities for all.The\u0000 subjective test laboratory has performed gender analysis for all subjective test\u0000 projects since 2018 to see how (mis)balanced the transmission quality between male and\u0000 female speakers is. The identified misbalance can affect many professionals that deploy\u0000 distant voice communication in their daily duties – think of female airport approach\u0000 control dispatchers or other professionals (policewomen) who are principally handicapped\u0000 by technological aspects of their job - worse voice transmission quality means higher\u0000 listening effort is needed and may lead to consequent (subconscious) discomfort of their\u0000 communication partners, or even intelligibility issues. Of course, this fact is not\u0000 surprising for narrow-band or even old analog AM transmissions (as still used in\u0000 AIRCOM). It can only be used as an argument to upgrade communication means to a suitable\u0000 digital format. Unfortunately, some contemporary wide-band or even full-band digital\u0000 communications also show statistically significant differences between quality of\u0000 transferred male and female voices. The detailed results will be presented, including\u0000 interesting systematic language dependencies (English, German, Mandarin).In the\u0000 conclusions, suggestions for future codec designs considering the human-centric\u0000 gender-balanced requirements are proposed. These include the minimum frequency response\u0000 of the future coders, granularity of the perceptual frequency scaling, etc. Also,\u0000 s","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115487354","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}
Swenja Sawilla, Waldemar Titov, Mathias Trefzger, N. Fricke
Augmented Reality (AR) enables new forms of interaction and knowledge transfer for users. This paper describes a novel approach to visualize information of energy transformation on an AR-Surface. Aiming to provide a playful tangible interaction method with real data for citizens, especially for those locally effected by the changes in future energy production facilities; we analyzed which bifacial aspects can be drawn from the two novel interaction and visualization methods. Therefore, we projected databased information on the AR-Surface so that users were able to interact with the displayed information by placing or moving our own designed tangibles on the surface. In our user study, the participants interacted with a data set on renewable energy production. Through the tangible interaction, the user receives important information, e.g. about renewable energies and their performance. As an outcome of the study, we showed that the use of tangibles offers many advantages, such as fast and easy interaction on an AR-Surface as well as an improved user understanding. The gained insights will help for further implementations and visualizations in the field of AR combined with simple communication of energy topics.
{"title":"Development of an Interaction Concept to Illustrate the Energy Transformation on an\u0000 AR-Surface","authors":"Swenja Sawilla, Waldemar Titov, Mathias Trefzger, N. Fricke","doi":"10.54941/ahfe1002947","DOIUrl":"https://doi.org/10.54941/ahfe1002947","url":null,"abstract":"Augmented Reality (AR) enables new forms of interaction and knowledge transfer for\u0000 users. This paper describes a novel approach to visualize information of energy\u0000 transformation on an AR-Surface. Aiming to provide a playful tangible interaction method\u0000 with real data for citizens, especially for those locally effected by the changes in\u0000 future energy production facilities; we analyzed which bifacial aspects can be drawn\u0000 from the two novel interaction and visualization methods. Therefore, we projected\u0000 databased information on the AR-Surface so that users were able to interact with the\u0000 displayed information by placing or moving our own designed tangibles on the surface. In\u0000 our user study, the participants interacted with a data set on renewable energy\u0000 production. Through the tangible interaction, the user receives important information,\u0000 e.g. about renewable energies and their performance. As an outcome of the study, we\u0000 showed that the use of tangibles offers many advantages, such as fast and easy\u0000 interaction on an AR-Surface as well as an improved user understanding. The gained\u0000 insights will help for further implementations and visualizations in the field of AR\u0000 combined with simple communication of energy topics.","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125925331","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}
Seonyoung Youn, Kavita Mathur, Caitlin G. Knowles, Beomjun Ju, B. Sennik, J. Jur
This paper proposes a simulation-based contact pressure (CP) prediction model for prototyping electronic textile (e-textile) wearable devices for health monitoring. This study uses a CLO 3D garment simulator, and knit fabrics are investigated in different weights and polyurethane contents. The first phase presents a comparative analysis of simulated and experimental stress. Based on the understanding of simulated stress, the CP model is developed by modifying Laplace’s law and using the simulated stress. The CP model is validated using a pressure sensor to compare the actual contact pressure. The developed CP model helps garment designers and engineers select the appropriate material and product size to achieve the target pressure required for ECG health monitoring in their decision-making.
{"title":"Simulation-based Prediction Model to Optimize Contact Pressure of Knitted Fabrics\u0000 for Wearable Garments","authors":"Seonyoung Youn, Kavita Mathur, Caitlin G. Knowles, Beomjun Ju, B. Sennik, J. Jur","doi":"10.54941/ahfe1002944","DOIUrl":"https://doi.org/10.54941/ahfe1002944","url":null,"abstract":"This paper proposes a simulation-based contact pressure (CP) prediction model for\u0000 prototyping electronic textile (e-textile) wearable devices for health monitoring. This\u0000 study uses a CLO 3D garment simulator, and knit fabrics are investigated in different\u0000 weights and polyurethane contents. The first phase presents a comparative analysis of\u0000 simulated and experimental stress. Based on the understanding of simulated stress, the\u0000 CP model is developed by modifying Laplace’s law and using the simulated stress. The CP\u0000 model is validated using a pressure sensor to compare the actual contact pressure. The\u0000 developed CP model helps garment designers and engineers select the appropriate material\u0000 and product size to achieve the target pressure required for ECG health monitoring in\u0000 their decision-making.","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133272860","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}
Ian Gonsher, Matt Lee, Yu-Chen Ma, Ivan Pineda-dominguez, Yuxin Han
The growth in remote and hybrid work has resulted in an increased demand for collaborative, videoconferencing experiences that offer a more seamless and immersive transition between virtual and physical environments. The Mixed Reality Passthrough Window (MRPW) addresses this demand by introducing a new paradigm for the integration of augmented/mixed reality into laptop design. The design is characterized by two screens, situated back to back, with two mounted cameras, facing in opposite directions. This creates the effect of looking through a window, upon which virtual content can be augmented and overlaid. This configuration allows local users sitting around the laptop to more easily interact with remote users, who appear on both sides of the Mixed Reality Passthrough Window, giving the sense that all users are sharing the same space in the round. Additionally, these features create affordances for the outward facing screen to serve as a site for presentations (e.g. slide decks) and other sharable content.
{"title":"The Mixed Reality Passthrough Window: Rethinking the Laptop Videoconferencing\u0000 Experience","authors":"Ian Gonsher, Matt Lee, Yu-Chen Ma, Ivan Pineda-dominguez, Yuxin Han","doi":"10.54941/ahfe1002954","DOIUrl":"https://doi.org/10.54941/ahfe1002954","url":null,"abstract":"The growth in remote and hybrid work has resulted in an increased demand for\u0000 collaborative, videoconferencing experiences that offer a more seamless and immersive\u0000 transition between virtual and physical environments. The Mixed Reality Passthrough\u0000 Window (MRPW) addresses this demand by introducing a new paradigm for the integration of\u0000 augmented/mixed reality into laptop design. The design is characterized by two screens,\u0000 situated back to back, with two mounted cameras, facing in opposite directions. This\u0000 creates the effect of looking through a window, upon which virtual content can be\u0000 augmented and overlaid. This configuration allows local users sitting around the laptop\u0000 to more easily interact with remote users, who appear on both sides of the Mixed Reality\u0000 Passthrough Window, giving the sense that all users are sharing the same space in the\u0000 round. Additionally, these features create affordances for the outward facing screen to\u0000 serve as a site for presentations (e.g. slide decks) and other sharable content.","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"602 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134462525","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}
ContextFear of public speaking (glossophobia) is one form of anxiety. People may struggle to speak in a classroom, meeting, and in other group settings. This can make it very difficult for sufferers to communicate verbally to express their knowledge and thoughts. As a result, glossophobia may hamper the sufferer’s ability to further own academic, social or career opportunities.Purpose/approachThe aim of our study was to share experience with a teaching program based on VR to help future teachers improve their presentation and speaking skills. Our study followed a descriptive mixed research design. Participants of 5 groups, each of 5 members went through the regular course of speaking and presentation skills or through a course based on VR. Several characteristics of an individual speech were measured by VR: eye contact, speed of speech, use of crutch words, speech pausing, clarity, loudness, monotony and word repetition. Reduction of glossophobia was measured by a questionnaire and through personal interviews.Actual research outcomes -Interviews with teachers (6 trainers)Pros: high motivation, visible progress, more self-assurance, better performanceCons: cost of equipment, need of technical support-Interviews with course participants (25 future teachers)Pros: felt like being in „real“ classroom and with „real“ students, enjoyment, new experience, emotions, enthusiasm, fun, loss of fear,Cons: made me tired, had to share the equipment with other students, lost my concentration-QuestionnairesClear reduction of glossophobia as measured by self-report of future teachersConclusions VR is eligible to be used in different environments, and many applications successfully apply it to improve learning. Our findings indicate that VR applications are more likely to lead to certain benefits such as increased motivation of users.
{"title":"Virtual Reality to Improve Technical Teacher Presenting and Speaking Skills","authors":"D. Vaněček, D. Dobrovská","doi":"10.54941/ahfe1002946","DOIUrl":"https://doi.org/10.54941/ahfe1002946","url":null,"abstract":"ContextFear of public speaking (glossophobia) is one form of anxiety. People may\u0000 struggle to speak in a classroom, meeting, and in other group settings. This can make it\u0000 very difficult for sufferers to communicate verbally to express their knowledge and\u0000 thoughts. As a result, glossophobia may hamper the sufferer’s ability to further own\u0000 academic, social or career opportunities.Purpose/approachThe aim of our study was to\u0000 share experience with a teaching program based on VR to help future teachers improve\u0000 their presentation and speaking skills. Our study followed a descriptive mixed research\u0000 design. Participants of 5 groups, each of 5 members went through the regular course of\u0000 speaking and presentation skills or through a course based on VR. Several\u0000 characteristics of an individual speech were measured by VR: eye contact, speed of\u0000 speech, use of crutch words, speech pausing, clarity, loudness, monotony and word\u0000 repetition. Reduction of glossophobia was measured by a questionnaire and through\u0000 personal interviews.Actual research outcomes -Interviews with teachers (6 trainers)Pros:\u0000 high motivation, visible progress, more self-assurance, better performanceCons: cost of\u0000 equipment, need of technical support-Interviews with course participants (25 future\u0000 teachers)Pros: felt like being in „real“ classroom and with „real“ students, enjoyment,\u0000 new experience, emotions, enthusiasm, fun, loss of fear,Cons: made me tired, had to\u0000 share the equipment with other students, lost my concentration-QuestionnairesClear\u0000 reduction of glossophobia as measured by self-report of future teachersConclusions VR is\u0000 eligible to be used in different environments, and many applications successfully apply\u0000 it to improve learning. Our findings indicate that VR applications are more likely to\u0000 lead to certain benefits such as increased motivation of users.","PeriodicalId":383834,"journal":{"name":"Human Interaction and Emerging Technologies (IHIET-AI 2023): Artificial\n Intelligence and Future Applications","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123230035","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：