AHFE Open AccessCognitive Computing and Internet of Things
Editors: Lucas Paletta, Hasan Ayaz
Topics: Cognitive Computing and Internet of Things
Publication Date: 2022
ISBN: 978-1-958651-19-3
DOI: 10.54941/ahfe1001831
Articles
Adaptive Weighted 3D Object Image Inference Model Based on Image Complexity
The research on product style classification based on CNN is very active, but the data used to train CNN(Convolutional Neural Networks) are often single-view images of 3D objects, which will lead to the loss of unpredictable object feature information and does not match the real scene. It reduces the quality of the model training. This paper proposes an adaptive weighted CNN model based on image complexity. Feature extraction is performed on images of 3D objects from different perspectives through convolutional neural networks, and the final classification result is obtained by weighting based on image complexity. The 3D object discrimination model in this paper is more in line with the cognitive process of the audience, and can improve the quality of style inference of 3D objects.
Yueqi Liu, Pu Meng, Zhuoyue Diao, Xin Meng, Liqun Zhang, Xiaodong Li
Open Access
Article
Conference Proceedings
Computational Aesthetics of Visual Artworks: Review and Outlook
Beauty has always been the goal of human activity. The meaning of beauty is defined during its creation. The discussion of beauty by mathematicians has created the computational aesthetics. This paper reviews the related works in computational aesthetics of visual arts and summarizes the features used in aesthetic measurement. The features extracted from the visual artworks are divided into five types including visual, compositional, statistical, perceptual and artistic features. Based on those features, the visual images are quantified and analyzed on their aesthetic and artistic properties. The previous studies are mostly focused on the aesthetics of art production, the continuous process for artistic creation cannot be represented. Moreover, new forms of visual arts such as generative art emerged, which provide new opportunities and challenges to the field of computational aesthetics. A prospective on the algorithms for the evaluation of this new forms of visual arts will be given.
Pu Meng, Yueqi Liu, Liqun Zhang, Xiaodong Li
Open Access
Article
Conference Proceedings
Office-Based Workplace Monitoring and Time-Aware Feedback by using Ambient IoT Sensors
During the COVID pandemic, our understanding of a workplace (e.g. office building, home office, other offices) has changed. For example, we are constantly changing our workspace in office jobs. It is a post-COVID phenomenon that we change our work environment more frequently and more often during a week. In this paper, we investigate what sensors and software tools we need to determine that we are working in ideal conditions, including good air quality, low CO2, etc. From an employee’s point of view, it is interesting if such monitoring devices can be easily used and combined. The evaluation should be possible and combinable by simple means. Why is this difficult? Considering that there is no common agreement among researchers on the definition of workplaces and new hybrid workplaces (i.e. office in company building, home office, and third office places) make the challenges even more complex. In this context, quantitative data from novel low-cost biosensors, such as for measuring carbon dioxide concentration distribution, highlighting the presence and attention of employees and their change in behavior within a working environment, are discussed, and the paper also provides an outlook towards novel research pathways for using a connected network of IoT devices and ambient biosensor technologies.
Herwig Zeiner, Roland Unterberger, Dietmar Maurer, Silvia Russegger, Lucas Paletta
Open Access
Article
Conference Proceedings
Time-Aware and Spatial Oriented Driven User Interfaces in the Context of Safe Zones for Underground Mining
This paper deals with visualization of time and safety critical data collected in underground mining operations. These data contain information of the rock mass and its behavior, the environmental conditions as well as general geometric, and time dependent information. Eventually, the combination of the data shall secure safe and sustainable extraction of valuable raw materials by combining information from a wide range of sensors in a data-driven Internet of Things platform, performing suitable evaluations, and, finally, feeding back the extracted learning to all stakeholders involved in a convenient and platform independent way from mine management to foremen and equipment operators. The results are novel visualization techniques for underground mining. The most suitable UIs in heavy duty mining operations are robust and customizable, using latest web technology in their dashboards. Depending on the required user category, the dashboard display may be configured accordingly. In this work we focus on the workers’ and the mine operators’ (e.g. underground, on-site workers including technicians and engineers) needs to display in real-time relevant operational information on immediate or urgent tasks/actions.
Norbert Gomolla, Herwig Zeiner, Roland Unterberger, Raúl Miñón Jiménez, Philipp Hartlieb
Open Access
Article
Conference Proceedings
Internet of Things Security Policy in Enterprises
The aim of the article is to discuss the risks resulting from expanding access to the network of new devices, and at the same time to show to what extent the implementation of procedures in the field of data security and architecture of systems used for data processing may affect the security of the continuity of the company's technological processes, but also data protection. The author draws attention to the fact that the problem of data and process security in the Internet of Things should be considered not only in terms of the protection of the content of information, but also its authenticity and topicality. On the other hand, inadequate formulation of the rules of the Internet of Things security policy in a given enterprise may mean limiting the availability of solutions and access to data, often eliminating the possibility of obtaining and processing them altogether. Enterprises must therefore act in such a way as to help maintain both the functionality and security of their systems.
Michal Trziszka
Open Access
Article
Conference Proceedings
Application of Industry4.0 Tools: Integrated Building Site Payment Management Portal for Construction Works
Management of construction site financial engagement is one of prerequisite of an effective site management. In recent times Building informatics concept has been useful in developing state of art equipment and process. In this study therefore, building informatics planning was generated that could be used for financial management purpose on site. The research was carried out using qualitative and quantitative research method, quantitative research method involved the use of structured questionnaire developed in Likert scale 1 to 5. Therefore with the aid of purposive sampling method, fifty (50) samples were picked using purposive sampling method. Construction professional constitute the nucleus of the respondents. The statistical inference was carried out on the data with Relative agreement Index and presented in tables. Qualitative method was used to develop the proposed integrated system. The study developed an integrated system that could assist in overcoming the negative vices of payment on site. The following task was carried out in line with aim of the study: identification of existing web-based financial platform, critical success factor in deployment of payment interface, methods of preventing financial conflict on site, challenges of web- interface, critical success factor in deployment of payment interface, identification of strengths and weaknesses of existing web-based financial platforms, among others. The interface can help solve basic problem about financial payment difficulty on site. The direction of choice should be in automating different aspect of building and construction for maximum productivity. The system that was developed in the context of this study can help prevent cost overrun on site, payment conflict, and delay payment among others.
Lekan Amusan, Terdoo Udendeh, Clinton Aigbavboa
Open Access
Article
Conference Proceedings
Design of the Heart Rate Measurement Module in a Telemonitoring Device for First Responders Deployed in Extreme Environments
This paper presents results of the SIXTHSENSE project, a research and innovation action within the H2020 program, aiming to develop new methods for unobtrusive monitoring of first responders based on multimodal sensing. The goal is to determine Heart Rate signal from ECG recorded by a multi sensor smart patch in the specific conditions the first responders are facing on their deployments. In addition to the challenges commonly faced when processing ECG signals recorded by wearables in high intensity activities, the work presented tackles the issues of noise generated by active sensors collocated with the ECG electrodes. Furthermore, the ergonomic requirements of the targeted users, namely firefighters and mountain rescuers, imposed positioning the multi sensor smart patch on the user’s back, making the analysis of recorder ECG signal more challenging. Initial experiments were conducted to determine the optimal electrode position on the back for ECG recording, and the design of the patch that would allow robust measurement of the signals, while not impeding the user during intense physical activity.Analysis of different algorithms for ECG signal processing was performed, considering both the specific distortions for ECG signals recorded on the back, and the effects of active system modules on the acquisition, namely electrotactile stimulation and iontophoretic analyte extraction.The prosposed multi sensor patch design and processing algorithm are presented and demonstrated in experiments simulating relevant conditions for the application of interest.
Tanja Boljanic, Matija Strbac, Jovana Malesevic, Vladimir Kojic, Nikola Topalovic, Goran Bijelic, Milos Kostic
Open Access
Article
Conference Proceedings
Effect of Exercise Intensity and Thermal Strain on Wildland Firefighters' Central Nervous System Fatigue
The arduous conditions (i.e., harsh environmental conditions, high physical and mental demands) in which wildland firefighters (WFFs) have to perform their work during wildfire suppression can lead to states of both physical and mental fatigue. Although several studies have delved into the first type of fatigue, there is a paucity of research on the decrease in WFFs’ cognitive performance. A decreased cognitive performance has been observed throughout multi-day suppression tasks, which could lead to poor decision-making and have unintended consequences on deployments. To our knowledge, the acute effect of tasks performed by WFFs on cognitive fatigue has not been studied. Therefore, the aim of this study was to analyze the effect of performing a specific circuit, which simulated the tasks performed by WFFs in their deployments, on central nervous system fatigue. Ten WFFs (34.4 ± 5.6 yr, 182.9 ± 6.1 cm and 92.8 ± 14.9 kg) participated in the study, who performed a field test composed of 4 specific tasks commonly used in their deployments. Each task was executed for 5 min interspersed by 90 s of recovery. This interval bout was repeated twice with 10 min of recovery in between. During the test heart rate (HR) and core temperature (CT) response were monitored. Both variables were used to calculate the physiological strain index (PSI). In addition, before and at the end of the field test, subjects’ critical flicker fusion (CFF) threshold was measured. The results obtained showed that the WFFs performed a high-exercise demand (mean HR, 85.3 ± 2.5% of maximal HR; CT, 38.3 ± 0.4 ºC and PSI, 6.0 ± 0.7). Despite this, CFF threshold measurements showed an increase (6.0 ± 6.0%, p < 0.05) in the sensory sensitivity threshold, suggesting an exercise induced increase in cortical arousal. Significant (p < 0.05) relationships between sensory sensitivity and time spent at high percentage of maximal HR (>90%), TC and PSI were found (r = -0.71, -0.74 and -0.69, respectively). In conclusion, the specific field test led an enhancement of sensory sensitivity and cortical arousal. However, the correlations found seem to indicate the potential negative effect of high-intensity exercise and thermal strain on central nervous system fatigue.
Jose A Rodríguez-Marroyo, Belén Carballo Leyenda, Pilar Sánchez Collado, David Suárez Iglesias, José G Villa
Open Access
Article
Conference Proceedings
Evaluation of Virtual Reality-based First Responder Training under Physiological and Cognitive-Emotional Strain
First responders are faced with various challenges and critical situations during their operations. Virtual Reality (VR) training environments offer a great opportunity to create realistic operational scenarios with appropriate levels of difficulty. To evaluate VR-based training regarding cognitive-emotional and physical strain, a pilot study with 13 first responders (firefighters and paramedics) was conducted. The study plan aimed to induce equivalent strain in both, real environment (‘RC’) and VR-based (‘VR’), training scenarios. In summary, the results indicate that training sessions in real and in VR-based environments have a comparable impact on physical strain, on different dimensions of workload like physical and cognitive demand, and specific physical and emotional states. Most important, we could show that physical strain, which is a critical factor for appropriate training of first responders, cannot only be induced by traditional real-life training, but also by an immersive VR training environment. These results confirm and motivate the use of VR environments for the training of stress-resilient decision-making behaviour for emergency forces.
Lilian Reim, K Wolfgang Kallus, Martin Pszeida, Michael Schneeberger, Christian Schönauer, Andreas Peer, Richard Feischl, Georg Aumayr, Dietmar Wallner, Amir Dini, Anna Weber, Stefan Ladstätter, Alexander Almer, Lucas Paletta
Open Access
Article
Conference Proceedings
First Responder Situation Reporting in Virtual Reality Training with Evaluation of Cognitive-emotional Stress using Psychophysiological Measures
First responders engage in highly stressful situations at the emergency site that may induce stress, fear, panic and a collapse of clear thinking. Staying cognitively under control under these circumstances is a necessary condition to avoid useless risk-taking and particularly to provide accurate situation reports to remote units to be able to organize appropriate support in time. This work applied a flexible virtual reality (VR) training environment with the purpose to investigate the performance of reporting under rather realistically simulated mission conditions. In a pilot study, representative emergency forces of the Austrian volunteer fire brigade and paramedics of the Johanniter organization were subjected to a test program that tested a formalized reporting schema (LEDVV), inducing equivalent strain in both, real environment and VR-based training scenarios. Wearable psychophysiological measuring technology was applied to estimate the cognitive-emotional stress level under both training conditions. The results indicate that both situation reports achieve a rather high level of cognitive-emotional stress and should be thoroughly trained. Furthermore, the results motivate the use of VR environments for the training of stress-resilient decision-making behavior of emergency forces.
Michael Schneeberger, Lucas Paletta, K Wolfgang Kallus, Lilian Reim, Christian Schönauer, Andreas Peer, Richard Feischl, Georg Aumayr, Martin Pszeida, Amir Dini, Stefan Ladstätter, Anna Weber, Alexander Almer, Dietmar Wallner
Open Access
Article
Conference Proceedings
VR4care: Gender-sensitive Virtual Reality Technologies and Semantic Content Categories for Activation in Nursing Homes
People living in long-term care facilities due to physical or mental impairments have few opportunities for self-determined activity. Virtual reality (VR) technologies offer a potential to expand individual experience through immersive presence in artificial environments, to activate mentally and to promote autonomy through the impact of self-efficacy. The overall goal of the Austrian project VR4Care was to research design basics for the development of a motivating, gender-sensitive, personalized and cost-effective VR technology to increase the activation and quality of life primarily of residents in inpatient long-term care. In the further development of VR for senior citizens, gender-specific differences were taken into account, such as gender-specific requirements for user interfaces, gender-specific preferences in interests with regard to content and different expectations of support when using the VR-based system.
Lucas Paletta, Sybille Reidl, Sarah Beranek, B.A., Msc, Robert Hartmann, Martin Sighart, Sebastian Mayer, Patricia Papic, Amir Dini, Martin Pszeida, Sandra Schuessler, Alfred Haeussl, Bscn, Beatrix Koch, Hermine Fürli, Msc, Michael Schneeberger, Melanie Lenger, Silvia Russegger
Open Access
Article
Conference Proceedings
Estimation of Change in Affective State Using Eye Tracking Features from Virtual Reality Technologies
Affective states play a prominent role in the context of human activation and motivation. Immersive VR-based presence provides opportunities to activate elderly people in the context of preferred leisure activities (Häussl et al., 2021) or to apply mindfulness interventions for their cognitive reserve (Paletta et al., 2021). The appropriate design of positively activating content is pivotal for appropriate changes in users’ affective states. The presented study provided insight into the potential of non-invasive VR-based eye tracking for automated estimation of affective state induced by video content, in an explorative pilot study with seven elderly persons living in a nursing home. The results indicate the feasibility of estimating mood change from typical eye movement features, such as, fixation duration and pupil diameter, as a promising future research topic.
Martin Pszeida, Amir Dini, Michael Schneeberger, Melanie Lenger, Lucas Paletta, Silvia Russegger, Sybille Reidl, Sarah Beranek, B.A., Msc, Sandra Schuessler, Alfred Haeussl, Bscn, Robert Hartmann, Martin Sighart, Sebastian Mayer, Patricia Papic, Beatrix Koch, Hermine Fürli, Msc
Open Access
Article
Conference Proceedings
Usability Evaluation after a 6-month Tablet-based Dementia Training Program by People with Alzheimer’s Disease, Relatives, and Dementia Trainers
Non-pharmacological interventions, like tablet-based cognitive trainings, already present an important alternative treatment of dementia. For tablet-based cognitive trainings to be effective, regular practice seems to be required, highlighting the need for such trainings to be applicable not only in well-prepared laboratory settings, but also for continuous use at home. In order to raise the acceptance as well as the user-friendliness of such trainings to consequently increase training intensity, usability research is essential. Therefore, the aim of this study was to explore the experiences of people with Alzheimer’s disease (PwAD), relatives, and dementia trainers regarding the usability of a tablet-based dementia training practiced in the home setting.A qualitative study was performed within the ongoing randomized controlled trial of the project multimodAAL. In total 15 individual interviews (each 5 per target group) were conducted with people with mild AD, their relatives and dementia trainers, who were already assigned to the intervention group for at least 6 months, practicing a dementia training program, including physical and cognitive exercises on a tablet-PC at home. The interviews lasted 91.9 minutes on average. A qualitative content analysis was performed to analyze the data.Participants were predominantly female (73.3 %). PwAD and relatives stated that they had no previous experience with this type of computer-based cognitive training and had experienced the training as positive and enriching. Some relatives saw the joint performance as a meaningful activity with their loved ones. Participants confirmed that the different types of physical exercises (e.g., coordination, strength), presented in a video format were well feasible for PwAD. In this regard, some PwAD reported feeling a bit unchallenged. Relatives and dementia trainers recommended for the exercise videos to be more motivating and fun (e.g., direct motivational address by the gymnast in the video like in a tv show, colorful sportswear). Regarding cognitive exercises, participants appreciated the variety (e.g., quiz, puzzle, calculating) as well as the sequence of the different exercises within a training session. Dementia trainers and relatives perceived that exercises related to topics about past/biography (e.g., previous occupation, hobbies) and to religious/seasonal traditions (e.g., Christmas) were particularly appreciated among PwAD. In view of beneficial factors to complete a training session with its physical and cognitive exercises successfully, relatives and dementia trainers underlined that PwAD needed support in terms of (technical) guidance, motivation/feedback/praise, as well as hints/tips/thought-provoking impulses. Dementia trainers and relatives suggested that this could be achieved by a supporting person (e.g., dementia trainer) or an expansion of the program by written and verbal support (e.g., hint button, voice assistant). Furthermore, participants emphasized the need of a tablet pen for comfortable handling, as well as a high sensitivity of the tablet-PC's touch screen.The results show that the already applied tablet-based dementia training is well received and accepted by participants. However, there is still potential for enhancement regarding motivational and feedback strategies as well as user-friendliness by the addition of a comprehensive application for guiding through the physical and cognitive exercises to enable more independent practice sessions.
Julia Zuschnegg, Sandra Schuessler, Lucas Paletta, Silvia Russegger, Maria Fellner, Karin Ploder, Bernhard Strobl, Maja Sekulic, Marisa Koini, Maria M Hofmarcher Holzhacker, Regina Roller Wirnsberger
Open Access
Article
Conference Proceedings
Accurate Stress detection from Novel Real-Time Electrodermal Activity Signals and Multi-task Learning Models
Stress often is associated with physical and mental health issues. To prevent these issues, an early detection of stress is essential. However, for people with an intellectual disability effectively expressing stress can be difficult and therefore, the necessary intervention can be delayed. An automatic stress detection system could help caregivers in early detection of stress development. This can be achieved using wearable sensors that continuously record physiology. The changes in physiological signals, like in skin conductance can be used to classify moments of stress. The devices recording these signals are however, not always suitable for long term measurements. The present study evaluates a newly developed sock integrated skin conductance sensor (SentiSock) that does not restrict movement and stays comfortable over time. To assess if the sensor can be used for stress detection a comparison was made with the Empatica E4, a commonly used wrist-based skin conductance sensor. Both sensors were worn by 28 participants (mean age 39.25 ± 17.04) in a lab study where stress was induced using mathematical exercises. The data was used to train a multitask learning neural network for each device, following an identical procedure. The models were validated using a 5-fold cross validation that resulted in an average balanced accuracy of 0.824 (SD = 0.018) for Empatica E4 and 0.834 (SD = 0.019) for SentiSock. This demonstrated that both sensors can be used to detect stress adequately in lab conditions. Given these results, SentiSock will be further investigated for long term measurements.
Stefan De Vries, Reon Smits, Michalina Tataj, Mieke Ronckers, Mayra Van Der Pol, Fransje Van Oost, Esmee Adam, Hanneke Smaling, Erwin Meinders
Open Access
Article
Conference Proceedings
The influence of task complexity on acceptance and trust in human-robot interaction - gender and age differences
An increase of human-robot collaboration is expected in the near future. Many people are already experiencing this in their working life, especially in the industrial context for example in production. As technology continues to improve, the number of scenarios and tasks in which humans and robots can interact with each other is also increasing. Therefore, it is important to focus on how humans and robots can work together in the future, while ensuring that negative emotions and mistrust towards this new form of work environment are avoided.The aim of the presented online study was therefore to get more insight in this important future field. Overall, 29 men and 42 women (N = 71) aged between 19 and 64 years (M = 31.44, SD = 13.30) participated in the study. All participants assessed four different scenarios were humans interact with robots in an industrial context. To assess the influence of task complexity on the subjectively assessed acceptance and trust, task complexity was increased with each scenario. The results show, significant assessment differences regarding the different levels of task complexity. Furthermore, women seem to assess the different interaction tasks as significantly more useful and satisfying than men. Regarding trust an interaction of age and gender can be shown.The results of the presented exploratory study can help to understand how the interaction of human and robots is seen today and shall help to get more insight in this important future field.
Verena Wagner-Hartl, Ramona Schmid, Katharina Gleichauf
Open Access
Article
Conference Proceedings
Cognitive Positioning Technologies for IoT Network Devices
Nowadays, wireless technologies are increasingly being used for human needs. Increasingly, technologies are emerging that are used by people not only for the need to transfer data. One of these technologies is the Internet of Things, which often uses wireless sensors with ZigBee data transmission technology as end devices.There are areas that require deployment of these networks on the territory, a large number of sensors are required, which must with sufficient accuracy “know” their position on the deployment area. Usually, devices with built-in GPS modules are used for this, but devices containing this module are significantly more expensive than without it. And if in a large distributed network with many segments, more than 1000 such devices are required, then a device with a GPS module can only be at most one for each segment. Therefore, if this is a forest where there are many thousands of trees and it is necessary to monitor fires at the initial stage, which take place in many US states in the summer, then the cognitive task of teaching those devices, that do not contain a GPS module, to determine their position is relevant. This paper proposes a mathematical formulation of the cognitive task of learning to determine the coordinates of devices in wireless sensor networks. The study of the mathematical model has been carried out. The purpose of these studies was to find new alternative teaching methods for determining the distance between objects of IoT sensor networks, using the function of localizing objects where an emergency occurred.
Andriy Dudnik, Ivan Bakhov, Olha Cholyshkina, Andriy Fesenko, Olexander Grinenko, Volodymyr Brodkevych, Serhii Zybin
Open Access
Article
Conference Proceedings