Towards Data-Driven Decision-Making in the Korean Film Industry: An XAI Model for Box Office Analysis Using Dimension Reduction, Clustering, and Classification

The Korean film market has been rapidly growing, and the importance of explainable artificial intelligence (XAI) in the film industry is also increasing. In this highly competitive market, where producing a movie incurs substantial costs, it is crucial for film industry professionals to make informed decisions. To assist these professionals, we propose DRECE (short for Dimension REduction, Clustering, and classification for Explainable artificial intelligence), an XAI-powered box office classification and trend analysis model that provides valuable insights and data-driven decision-making opportunities for the Korean film industry. The DRECE framework starts with transforming multi-dimensional data into two dimensions through dimensionality reduction techniques, grouping similar data points through K-means clustering, and classifying movie clusters through machine-learning models. The XAI techniques used in the model make the decision-making process transparent, providing valuable insights for film industry professionals to improve the box office performance and maximize profits. With DRECE, the Korean film market can be understood in new and exciting ways, and decision-makers can make informed decisions to achieve success.

Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement

A voiceprint signal as a non-contact test medium has a broad application prospect in power-transformer operation condition monitoring. Due to the high imbalance in the number of fault samples, when training the classification model, the classifier is prone to bias to the fault category with a large number of samples, resulting in poor prediction performance of other fault samples, and affecting the generalization performance of the classification system. To solve this problem, a method of power-transformer fault voiceprint signal diagnosis based on Mixup data enhancement and a convolution neural network (CNN) is proposed. First, the parallel Mel filter is used to reduce the dimension of the fault voiceprint signal to obtain the Mel time spectrum. Then, the Mixup data enhancement algorithm is used to reorganize the generated small number of samples, effectively expanding the number of samples. Finally, CNN is used to classify and identify the transformer fault types. The diagnosis accuracy of this method for a typical unbalanced fault of a power transformer can reach 99%, which is superior to other similar algorithms. The results show that this method can effectively improve the generalization ability of the model and has good classification performance.

Analysis of the Snake Robot Kinematics with Virtual Reality Visualisation

In this article, we present a novel approach to performing engineering simulation in an interactive environment. A synesthetic design approach is employed, which enables the user to gather information about the system's behaviour more holistically, at the same time as facilitating interaction with the simulated system. The system considered in this work is a snake robot moving on a flat surface. The dynamic simulation of the robot's movement is realised in dedicated engineering software, whereas this software exchanges information with the 3D visualisation software and a Virtual Reality (VR) headset. Several simulation scenarios have been presented, comparing the proposed method with standard ways for visualising the robot's motion, such as 2D plots and 3D animations on a computer screen. This illustrates how, in the engineering context, this more immersive experience, allowing the viewer to observe the simulation results and modify the simulation parameters within the VR environment, can facilitate the analysis and design of systems.

Accurate prediction of 11B NMR chemical shift of BODIPYs via machine learning

In this article, we present the results of developing a model based on an RFR machine learning method using the ISIDA fragment descriptors for predicting the ¹¹B NMR chemical shift of BODIPYs. The model is freely available at https://ochem.eu/article/146458. The model demonstrates the high quality of predicting the ¹¹B NMR chemical shift (RMSE, 5CV (FINALE training set) = 0.40 ppm, RMSE (TEST set) = 0.14 ppm). In addition, we compared the "cost" and the user-friendliness for calculations using the quantum-chemical model with the DFT/GIAO approach. The ¹¹B NMR chemical shift prediction accuracy (RMSE) of the model considered is more than three times higher and tremendously faster than the DFT/GIAO calculations. As a result, we provide a convenient tool and database that we collected for all researchers, that allows them to predict the ¹¹B NMR chemical shift of boron-containing dyes. We believe that the new model will make it easier for researchers to correctly interpret the ¹¹B NMR chemical shifts experimentally determined and to select more optimal conditions to perform an NMR experiment.

A Comparative Analysis of Perceived Advantages and Disadvantages of Online Learning

The use of electronic media has increased dramatically in the past decade due to the general increase in digitization of global societies. This trend has been recently enhanced by the COVID-19 occurrence and following forced implementation of various forms of eLearning into university curricula, including all forms of second language (L2) acquisition. The present study focuses on the evaluation of perceived advantages and disadvantages of online L2 acquisition via electronic media by university students of the Czech Republic (n = 114) and Poland (n = 121). The research methodology was an online questionnaire asking the users of digital media for L2 acquisition about their perceived advantages and disadvantages regarding the use of print and digital media and their potential impact on their L2 acquisition. To understand their evaluation is crucial as it could lead to increased motivation or demotivation to learn a foreign language. The results clearly show that the students realize the drawbacks of digital media and this could lead to their dissatisfaction and frustration when they have to use these media excessively. The implications of the findings could be helpful and necessary for various course designers, curricula makers, and course tutors as they are responsible for the smooth implementation of various digital tools into the educational process.

Comparison of Machine Learning-based Approaches to Predict the Conversion to Alzheimer's Disease from Mild Cognitive Impairment

In Mild Cognitive Impairment (MCI), identifying a high risk of conversion to Alzheimer's Disease Dementia (AD) is a primary goal for patient management. Machine Learning (ML) algorithms are widely employed to pursue data-driven diagnostic and prognostic goals. An agreement on the stability of these algorithms -when applied to different biomarkers and other conditions- is far from being reached. In this study, we compared the different prognostic performances of three supervised ML algorithms fed with multimodal biomarkers of MCI subjects obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Random Forest, Gradient Boosting, and eXtreme Gradient Boosting algorithms predict MCI conversion to AD. They can also be simultaneously employed -with the voting procedure- to improve predictivity. AD prediction accuracy is influenced by the nature of the data (i.e., neuropsychological test scores, cerebrospinal fluid AD-related proteins and APOE ε4, cerebral structural MRI (sMRI) data). In our study, independent of the applied ML algorithms, sMRI data showed the lowest accuracy (0.79) compared to other classes. Multimodal data were helpful in the algorithms' performances by combining clinical and biological measures. Accordingly, using the three ML algorithms, the highest accuracy (0.90) was reached by employing neuropsychological and AD-related biomarkers. Finally, the feature selection procedure indicated that the most critical variables in the respective classes were the ADAS-Cog-13 scale, the medial temporal lobe and hippocampus atrophy, and the ratio between phosphorylated Tau and Aβ42 proteins. In conclusion, our data support the notion that using multiple ML algorithms and multimodal biomarkers helps make more accurate and solid predictions.

Can Blockchain Payment Services Influence Customers’ Loyalty Intention in the Hospitality Industry? A Mediation Assessment

This study analyzes the impact of blockchain mobile payment services on customer loyalty intention through the mediating role of service quality, privacy and security, and customer satisfaction in the Bangladeshi hospitality industry. Data were collected through a survey using a structured questionnaire from 326 respondents who stayed in 4- and 5-star hotels in Chattogram and Cox’s Bazar. Respondents’ (N = 326) opinions were analyzed employing Smart PLS software. The results ensure that privacy and security and customer satisfaction mediate the blockchain-based mobile payment services and loyalty intention relationship. However, service quality does not mediate that relationship. The findings of the mediation effect of privacy and security and customer satisfaction are a unique contribution to the blockchain literature in the field of the hospitality industry. Hoteliers are encouraged to employ appropriate blockchain mobile payment services for better quality customer service and ensured safety and security, and in turn, loyalty intention.

Whitelist or Leave Our Website! Advances in the Understanding of User Response to Anti-Ad-Blockers

Website publishers cannot monetize the ad impressions that are prevented by ad-blockers. Publishers can then employ anti-ad-blockers that force users to choose between either accepting ad impressions by whitelisting the website in the ad-blocker, or leaving the website without accessing the content. This study delineates the mechanisms of how willingness to whitelist/leave the website are affected by the request’s sensitivity to recipients as well as the users’ psychological reactance and evaluation of the website advertising. We tested the proposed relationships using an online panel sample of 500 ad-blocker users, who were asked about their willingness to whitelist/leave their favorite online newspaper after receiving a hypothetical anti-ad-blocker request—four alternative requests with different sensitivity levels were created and randomly assigned to the participants. The results confirmed that (a) the request’s sensitivity can improve the recipient’s compliance, (b) users’ psychological reactance plays an important role in explaining the overall phenomenon, and (c) a favorable evaluation of the website advertising can improve willingness to whitelist. These findings help to better understand user response to anti-ad-blockers and may also help publishers increase their whitelist ratios.

Understanding mindsets, skills, current practices, and barriers of adoption of digital accessibility in Kuwait's software development landscape

The responsibility for creating accessible software within the development of digital services is important for multiple reasons, mainly equity and inclusion. However, adopting and sustaining the development of accessible digital solutions has always been challenging, more so in countries that are relatively new to the concept of universal design, and physical and digital accessibility, and where legal sanctions are not yet established. This work investigates the technology scene in the State of Kuwait and analyses the responses of computing professionals with regard to their skills, best practices and procurement of accessible tech and to their level of awareness toward people with disabilities. The findings reveal a low level of awareness among tech professionals with regard to disabilities and digital accessibility-related standards. The findings also highlight a lack of available guidance for developing inclusive design and accessibility. Additionally, time constraints, lack of training, legal enforcement and fundamentals concepts during undergraduate and higher education contributed to observed weaknesses. Participants were keen to learn more and benefited from flyers and free professional development courses offered as incentives for survey completion.

An Integrated System of Braden Scale and Random Forest Using Real-Time Diagnoses to Predict When Hospital-Acquired Pressure Injuries (Bedsores) Occur

BACKGROUND AND OBJECTIVES

Bedsores/Pressure Injuries (PIs) are the second most common diagnosis in healthcare system billing records in the United States and account for 60,000 deaths annually. Hospital-Acquired Pressure Injuries (HAPIs) are one classification of PIs and indicate injuries that occurred while the patient was cared for within the hospital. Until now, all studies have predicted who will develop HAPI using classic machine algorithms, which provides incomplete information for the clinical team. Knowing who will develop HAPI does not help differentiate at which point those predicted patients will develop HAPIs; no studies have investigated when HAPI develops for predicted at-risk patients. This research aims to develop a hybrid system of Random Forest (RF) and Braden Scale to predict HAPI time by considering the changes in patients' diagnoses from admission until HAPI occurrence.

METHODS

Real-time diagnoses and risk factors were collected daily for 485 patients from admission until HAPI occurrence, which resulted in 4619 records. Then for each record, HAPI time was calculated from the day of diagnosis until HAPI occurrence. Recursive Feature Elimination (RFE) selected the best factors among the 60 factors. The dataset was separated into 80% training (10-fold cross-validation) and 20% testing. Grid Search (GS) with RF (GS-RF) was adopted to predict HAPI time using collected risk factors, including Braden Scale. Then, the proposed model was compared with the seven most common algorithms used to predict HAPI; each was replicated for 50 different experiments.

RESULTS

GS-RF achieved the best Area Under the Curve (AUC) (91.20 ± 0.26) and Geometric Mean (G-mean) (91.17 ± 0.26) compared to the seven algorithms. RFE selected 43 factors. The most dominant interactable risk factors in predicting HAPI time were visiting ICU during hospitalization, Braden subscales, BMI, Stimuli Anesthesia, patient refusal to change position, and another lab diagnosis.

CONCLUSION

Identifying when the patient is likely to develop HAPI can target early intervention when it is needed most and reduces unnecessary burden on patients and care teams when patients are at lower risk, which further individualizes the plan of care.

Enhancing Small Medical Dataset Classification Performance Using GAN

Developing an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier’s generalization performance, stability, and precision through the generation of synthetic data that closely resemble real data. We employed feature selection and applied five classification algorithms to thirteen benchmark medical datasets, augmented using the least-square GAN (LS-GAN). Evaluation of the generated samples using different ratios of augmented data showed that the support vector machine model outperforms other methods with larger samples. The proposed data augmentation approach using a GAN presents a promising solution for enhancing the performance of classification models in the healthcare field.

A Software Engineering Framework for Reusable Design of Personalized Serious Games for Health: Development Study

BACKGROUND

The use of serious games in health care is on the rise, as these games motivate treatment adherence, reduce treatment costs, and educate patients and families. However, current serious games fail to offer personalized interventions, ignoring the need to abandon the one-size-fits-all approach. Moreover, these games, with a primary objective other than pure entertainment, are costly and complex to develop and require the constant involvement of a multidisciplinary team. No standardized approach exists on how serious games can be personalized, as existing literature focuses on specific use cases and scenarios. The serious game development domain fails to consider any transfer of domain knowledge, which means this labor-intensive process must be repeated for each serious game.

OBJECTIVE

We proposed a software engineering framework that aims to streamline the multidisciplinary design process of personalized serious games in health care and facilitates the reuse of domain knowledge and personalization algorithms. By focusing on the transfer of knowledge to new serious games by reusing components and personalization algorithms, the comparison and evaluation of different personalization strategies can be simplified and expedited. In doing so, the first steps are taken in advancing the state of the art of knowledge regarding personalized serious games in health care.

METHODS

The proposed framework aimed to answer 3 questions that need to be asked when designing personalized serious games: Why is the game personalized? What parameters can be used for personalization? and How is the personalization achieved? The 3 involved stakeholders, namely, the domain expert, the (game) developer, and the software engineer, were each assigned a question and then assigned responsibilities regarding the design of the personalized serious game. The (game) developer was responsible for all the game-related components; the domain expert was in charge of the modeling of the domain knowledge using simple or complex concepts (eg, ontologies); and the software engineer managed the personalization algorithms or models integrated into the system. The framework acted as an intermediate step between game conceptualization and implementation; it was illustrated by developing and evaluating a proof of concept.

RESULTS

The proof of concept, a serious game for shoulder rehabilitation, was evaluated using simulations of heart rate and game scores to assess how personalization was achieved and whether the framework responded as expected. The simulations indicated the value of both real-time and offline personalization. The proof of concept illustrated how the interaction between different components worked and how the framework was used to simplify the design process.

CONCLUSIONS

The proposed framework for personalized serious games in health care identifies the responsibilities of the involved stakeholders in the design process, using 3 key questions for personalization. The framework focuses on the transferability of knowledge and reusability of personalization algorithms to simplify the design process of personalized serious games.

Influence of Hand Tracking in Immersive Virtual Reality for Memory Assessment

Few works analyze the parameters inherent to immersive virtual reality (IVR) in applications for memory evaluation. Specifically, hand tracking adds to the immersion of the system, placing the user in the first person with full awareness of the position of their hands. Thus, this work addresses the influence of hand tracking in memory assessment with IVR systems. For this, an application based on activities of daily living was developed, where the user must remember the location of the elements. The data collected by the application are the accuracy of the answers and the response time; the participants are 20 healthy subjects who pass the MoCA test with an age range between 18 to 60 years of age; the application was evaluated with classic controllers and with the hand tracking of the Oculus Quest 2. After the experimentation, the participants carried out presence (PQ), usability (UMUX), and satisfaction (USEQ) tests. The results indicate no difference with statistical significance between both experiments; controller experiments have 7.08% higher accuracy and 0.27 ys. faster response time. Contrary to expectations, presence was 1.3% lower for hand tracking, and usability (0.18%) and satisfaction (1.43%) had similar results. The findings indicate no evidence to determine better conditions in the evaluation of memory in this case of IVR with hand tracking.

Blockchain-smart contracts for sustainable project performance: bibliometric and content analyses

Blockchain-smart contracts have emerged as a new value proposition in improving certain aspects of sustainability in projects. However, there is little knowledge on how smart contracts can be leveraged to stimulate sustainable project performance from the integrated perspective. This study aims to capture the latest research development and applications of smart contracts for sustainable outcomes throughout the project lifecycle. Bibliometric and content analyses were conducted to critically review smart contracts and sustainable project performance. The results show that various new applications of smart contracts for sustainability have become more popular in the architecture, engineering, construction, and operation (AECO) industry. A smart contracts-sustainable project performance framework has been developed to fill up the research gaps for improving each dimension of sustainability and the integrated dimensions of sustainability during the project lifecycle. This study renders important implications for promoting sustainable project performance in the context of the engineering, construction, and operation industry, particularly for the required interdisciplinary research and practice in smart contracts.

Signatures of Life Detected in Images of Rocks Using Neural Network Analysis Demonstrate New Potential for Searching for Biosignatures on the Surface of Mars

Microorganisms play a role in the construction or modulation of various types of landforms. They are especially notable for forming microbially induced sedimentary structures (MISS). Such microbial structures have been considered to be among the most likely biosignatures that might be encountered on the martian surface. Twenty-nine algorithms have been tested with images taken during a laboratory experiment for testing their performance in discriminating mat cracks (MISS) from abiotic mud cracks. Among the algorithms, neural network types produced excellent predictions with similar precision of 0.99. Following that step, a convolutional neural network (CNN) approach has been tested to see whether it can conclusively detect MISS in images of rocks and sediment surfaces taken at different natural sites where present and ancient (fossil) microbial mat cracks and abiotic desiccation cracks were observed. The CNN approach showed excellent prediction of biotic and abiotic structures from the images (global precision, sensitivity, and specificity, respectively, 0.99, 0.99, and 0.97). The key areas of interest of the machine matched well with human expertise for distinguishing biotic and abiotic forms (in their geomorphological meaning). The images indicated clear differences between the abiotic and biotic situations expressed at three embedded scales: texture (size, shape, and arrangement of the grains constituting the surface of one form), form (outer shape of one form), and pattern of form arrangement (arrangement of the forms over a few square meters). The most discriminative components for biogenicity were the border of the mat cracks with their tortuous enlarged and blistered morphology more or less curved upward, sometimes with thin laminations. To apply this innovative biogeomorphological approach to the images obtained by rovers on Mars, the main physical and biological sources of variation in abiotic and biotic outcomes must now be further considered.

Embedding patient-reported outcomes at the heart of artificial intelligence health-care technologies

Integration of patient-reported outcome measures (PROMs) in artificial intelligence (AI) studies is a critical part of the humanisation of AI for health. It allows AI technologies to incorporate patients' own views of their symptoms and predict outcomes, reflecting a more holistic picture of health and wellbeing and ultimately helping patients and clinicians to make the best health-care decisions together. By positioning patient-reported outcomes (PROs) as a model input or output we propose a framework to embed PROMs within the function and evaluation of AI health care. However, the integration of PROs in AI systems presents several challenges. These challenges include (1) fragmentation of PRO data collection; (2) validation of AI systems trained and validated against clinician performance, rather than outcome data; (3) scarcity of large-scale PRO datasets; (4) inadequate selection of PROMs for the target population and inadequate infrastructure for collecting PROs; and (5) clinicians might not recognise the value of PROs and therefore not prioritise their adoption; and (6) studies involving PRO or AI frequently present suboptimal design. Notwithstanding these challenges, we propose considerations for the inclusion of PROs in AI health-care technologies to avoid promoting survival at the expense of wellbeing.

Epidemic Waves and Exact Solutions of a Sequence of Nonlinear Differential Equations Connected to the SIR Model of Epidemics

The SIR model of epidemic spreading can be reduced to a nonlinear differential equation with an exponential nonlinearity. This differential equation can be approximated by a sequence of nonlinear differential equations with polynomial nonlinearities. The equations from the obtained sequence are treated by the Simple Equations Method (SEsM). This allows us to obtain exact solutions to some of these equations. We discuss several of these solutions. Some (but not all) of the obtained exact solutions can be used for the description of the evolution of epidemic waves. We discuss this connection. In addition, we use two of the obtained solutions to study the evolution of two of the COVID-19 epidemic waves in Bulgaria by a comparison of the solutions with the available data for the infected individuals.

Physical activity in Norwegian teenagers and young adults with haemophilia A compared to general population peers

INTRODUCTION

Limited evidence exists on objectively measured habitual physical activity (PA) of young people with haemophilia (PWH).

AIMS

To compare different outcomes of objective PA between young PWH A and controls using a commercial activity tracker.

METHODS

We enrolled males aged 13-30 years with moderate and severe haemophilia A, without inhibitors on regular prophylaxis. PA was measured with the activity tracker Fitbit Charge 3 for 12 weeks. Control group data was obtained from ≈60,000 Fitbit users, matched on age, sex and measurement period. PA variables [steps, intensities, volume, activity types, exercise frequencies and proportion meeting the World Health Organization's moderate-to-vigorous PA (MVPA) recommendations] were compared between groups descriptively and using Welch's two-sample t-test and two-sample test of proportions.

RESULTS

Forty PWH A were enrolled (mean age 19.5 years, 50% teenagers, 50% adults, three (7.5%) with moderate and 37 (92.5%) with severe haemophilia). Mean daily steps and minutes MVPA were similar between PWH and controls. PWH spent more time in light PA (mean 227 vs. 192 min/day, P = .033) and exercised more frequently (mean 5.6 vs. 3.9 exercise sessions/week, P < .001). Among teenagers, 40% PWH and 8% controls reached MVPA recommendations, compared to 95% and 100% among adults. The most common type of PA was walking.

CONCLUSION

This cohort of young PWH A on prophylactic treatment had PA levels comparable to controls. Still, a considerable proportion of teenagers did not meet the recommended weekly volume of MVPA, and we encourage clinicians to have a particular focus on promoting PA for this group.

Wearable Drone Controller: Machine Learning-Based Hand Gesture Recognition and Vibrotactile Feedback

We proposed a wearable drone controller with hand gesture recognition and vibrotactile feedback. The intended hand motions of the user are sensed by an inertial measurement unit (IMU) placed on the back of the hand, and the signals are analyzed and classified using machine learning models. The recognized hand gestures control the drone, and the obstacle information in the heading direction of the drone is fed back to the user by activating the vibration motor attached to the wrist. Simulation experiments for drone operation were performed, and the participants' subjective evaluations regarding the controller's convenience and effectiveness were investigated. Finally, experiments with a real drone were conducted and discussed to validate the proposed controller.

Deep learning-based EEG emotion recognition: Current trends and future perspectives

Automatic electroencephalogram (EEG) emotion recognition is a challenging component of human-computer interaction (HCI). Inspired by the powerful feature learning ability of recently-emerged deep learning techniques, various advanced deep learning models have been employed increasingly to learn high-level feature representations for EEG emotion recognition. This paper aims to provide an up-to-date and comprehensive survey of EEG emotion recognition, especially for various deep learning techniques in this area. We provide the preliminaries and basic knowledge in the literature. We review EEG emotion recognition benchmark data sets briefly. We review deep learning techniques in details, including deep belief networks, convolutional neural networks, and recurrent neural networks. We describe the state-of-the-art applications of deep learning techniques for EEG emotion recognition in detail. We analyze the challenges and opportunities in this field and point out its future directions.

Exploring social media adoption by nurses for nursing practice in rural Volta, Ghana

AIM

The purpose of the study was to inquire into social media adoption by nurses for nursing practice.

DESIGN

An exploratory descriptive qualitative design was employed in understanding social media adoption for nursing care among nurses.

METHOD

A purposive sampling technique was employed to recruit 12 participants for the study. A semi-structured interview guide was used to conduct in-depth interviews which were audiotaped, transcribed verbatim, coded and analysed. Thematic analysis was used to analyse the data with NVivo 12.

RESULTS

The findings revealed nurses found social media to be useful for the dissemination, and reception of information, professional development and enhanced referral networks. Apart from its usefulness, participants believe that it is easy to navigate its apps, clear and understandable to use and does not involve much mental effort hence their favourable attitude towards use. Some participants also believe that inaccurate information, privacy and confidentiality concerns, distraction and addiction were some potential risks that are associated with its usage in nursing practice. Due to this, some participants developed a negative attitude towards its usage.

PATIENT OR PUBLIC CONTRIBUTION

Twelve nurses actively participated in the study.

How Virtual Hand Representations Affect the Perceptions of Dynamic Affordances in Virtual Reality

User representations are critical to the virtual experience, and involve both the input device used to support interactions as well as how the user is virtually represented in the scene. Inspired by previous work that has shown effects of user representations on the perceptions of relatively static affordances, we attempt to investigate how end-effector representations affect the perceptions of affordances that dynamically change over time. Towards this end, we empirically evaluated how different virtual hand representations affect users' perceptions of dynamic affordances in an object retrieval task wherein users were tasked with retrieving a target from a box for a number of trials while avoiding collisions with its moving doors. We employed a 3 (virtual end-effector representation) X 13 (frequency of moving doors) X 2 (target object size) multi-factorial design, manipulating the input modality and its concomitant virtual end-effector representation as a between-subjects factor across three experimental conditions: (1) Controller (using a controller represented as a virtual controller); (2) Controller-hand (using a controller represented as a virtual hand); (3) Glove (using a hand tracked hi-fidelity glove represented as a virtual hand). Results indicated that the controller-hand condition produced lower levels of performance than both the other conditions. Furthermore, users in this condition exhibited a diminished ability to calibrate their performance over trials. Overall, we find that representing the end-effector as a hand tends to increase embodiment but can also come at the cost of performance, or an increased workload due to a discordant mapping between the virtual representation and the input modality used. It follows that VR system designers should carefully consider the priorities and target requirements of the application being developed when choosing the type of end-effector representation for users to embody in immersive virtual experiences.

Medical Image Classifications for 6G IoT-Enabled Smart Health Systems

As day-to-day-generated data become massive in the 6G-enabled Internet of medical things (IoMT), the process of medical diagnosis becomes critical in the healthcare system. This paper presents a framework incorporated into the 6G-enabled IoMT to improve prediction accuracy and provide a real-time medical diagnosis. The proposed framework integrates deep learning and optimization techniques to render accurate and precise results. The medical computed tomography images are preprocessed and fed into an efficient neural network designed for learning image representations and converting each image to a feature vector. The extracted features from each image are then learned using a MobileNetV3 architecture. Furthermore, we enhanced the performance of the arithmetic optimization algorithm (AOA) based on the hunger games search (HGS). In the developed method, named AOAHG, the operators of the HGS are applied to enhance the AOA's exploitation ability while allocating the feasible region. The developed AOAG selects the most relevant features and ensures the overall model classification improvement. To assess the validity of our framework, we conducted evaluation experiments on four datasets, including ISIC-2016 and PH2 for skin cancer detection, white blood cell (WBC) detection, and optical coherence tomography (OCT) classification, using different evaluation metrics. The framework showed remarkable performance compared to currently existing methods in the literature. In addition, the developed AOAHG provided results better than other FS approaches according to the obtained accuracy, precision, recall, and F1-score as performance measures. For example, AOAHG had 87.30%, 96.40%, 88.60%, and 99.69% for the ISIC, PH2, WBC, and OCT datasets, respectively.

A Deep Learning-Based Semantic Segmentation Model Using MCNN and Attention Layer for Human Activity Recognition

With the development of wearable devices such as smartwatches, several studies have been conducted on the recognition of various human activities. Various types of data are used, e.g., acceleration data collected using an inertial measurement unit sensor. Most scholars segmented the entire timeseries data with a fixed window size before performing recognition. However, this approach has limitations in performance because the execution time of the human activity is usually unknown. Therefore, there have been many attempts to solve this problem through the method of activity recognition by sliding the classification window along the time axis. In this study, we propose a method for classifying all frames rather than a window-based recognition method. For implementation, features extracted using multiple convolutional neural networks with different kernel sizes were fused and used. In addition, similar to the convolutional block attention module, an attention layer to each channel and spatial level is applied to improve the model recognition performance. To verify the performance of the proposed model and prove the effectiveness of the proposed method on human activity recognition, evaluation experiments were performed. For comparison, models using various basic deep learning modules and models, in which all frames were classified for recognizing a specific wave in electrocardiography data were applied. As a result, the proposed model reported the best F1-score (over 0.9) for all kinds of target activities compared to other deep learning-based recognition models. Further, for the improvement verification of the proposed CEF method, the proposed method was compared with three types of SW method. As a result, the proposed method reported the 0.154 higher F1-score than SW. In the case of the designed model, the F1-score was higher as much as 0.184.

Engagement, acceptability, usability and satisfaction with Active for Life, a computer-tailored web-based physical activity intervention using Fitbits in older adults

BACKGROUND

Preliminary evidence suggests that web-based physical activity interventions with tailored advice and Fitbit integration are effective and may be well suited to older adults. Therefore, this study aimed to examine the engagement, acceptability, usability, and satisfaction with 'Active for Life,' a web-based physical activity intervention providing computer-tailored physical activity advice to older adults.

METHODS

Inactive older adults (n = 243) were randomly assigned into 3 groups: 1) tailoring + Fitbit, 2) tailoring only, or 3) a wait-list control. The tailoring + Fitbit group and the tailoring-only group received 6 modules of computer-tailored physical activity advice over 12 weeks. The advice was informed by objective Fitbit data in the tailoring + Fitbit group and self-reported physical activity in the tailoring-only group. This study examined the engagement, acceptability, usability, and satisfaction of Active for Life in intervention participants (tailoring + Fitbit n = 78, tailoring only n = 96). Wait-list participants were not included. Engagement (Module completion, time on site) were objectively recorded through the intervention website. Acceptability (7-point Likert scale), usability (System Usability Scale), and satisfaction (open-ended questions) were assessed using an online survey at post intervention. ANOVA and Chi square analyses were conducted to compare outcomes between intervention groups and content analysis was used to analyse program satisfaction.

RESULTS

At post-intervention (week 12), study attrition was 28% (22/78) in the Fitbit + tailoring group and 39% (37/96) in the tailoring-only group. Engagement and acceptability were good in both groups, however there were no group differences (module completions: tailoring + Fitbit: 4.72 ± 2.04, Tailoring-only: 4.23 ± 2.25 out of 6 modules, p = .14, time on site: tailoring + Fitbit: 103.46 ± 70.63, Tailoring-only: 96.90 ± 76.37 min in total, p = .56, and acceptability of the advice: tailoring + Fitbit: 5.62 ± 0.89, Tailoring-only: 5.75 ± 0.75 out of 7, p = .41). Intervention usability was modest but significantly higher in the tailoring + Fitbit group (tailoring + Fitbit: 64.55 ± 13.59, Tailoring-only: 57.04 ± 2.58 out of 100, p = .003). Participants reported that Active for Life helped motivate them, held them accountable, improved their awareness of how active they were and helped them to become more active. Conversely, many participants felt as though they would prefer personal contact, more detailed tailoring and more survey response options.

CONCLUSIONS

This study supports web-based physical activity interventions with computer-tailored advice and Fitbit integration as engaging and acceptable in older adults.

TRIAL REGISTRATION

Australian and New Zealand Clinical Trials Registry: ACTRN12618000646246. Registered April 23 2018, https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=374901.

Urban Traffic Noise Analysis Using UAV-Based Array of Microphones

(1) Background: Transition to smart cities involves many actions in different fields of activity, such as economy, environment, energy, government, education, living and health, safety and security, and mobility. Environment and mobility are very important in terms of ensuring a good living in urban areas. Considering such arguments, this paper proposes monitoring and mapping of a 3D traffic-generated urban noise emissions using a simple, UAV-based, and low-cost solution. (2) Methods: The collection of relevant sound recordings is performed via a UAV-borne set of microphones, designed in a specific array configuration. Post-measurement data processing is performed to filter unwanted sound and vibrations produced by the UAV rotors. Collected noise information is location- and altitude-labeled to ensure a relevant 3D profile of data. (3) Results: Field measurements of sound levels in different directions and altitudes are presented in the paperwork. (4) Conclusions: The solution of employing UAV for environmental noise mapping results in being minimally invasive, low-cost, and effective in terms of rapidly producing environmental noise pollution maps for reports and future improvements in road infrastructure.

Assessing the Contribution of Managerial Accounting in Sustainable Organizational Development in the Healthcare Industry

Sustainability and digital transformation are two phenomena influencing the activities of all organizations. Managerial accounting is an essential component of these transformations, having complex roles in decision-making to ensure sustainable development through implementing modern technologies in the accounting process. This paper studies the roles of digitized managerial accounting in organizational sustainability drivers from a decision-making perspective. The empirical investigation assesses the influence of managerial accounting on the economic, social, and environmental drivers of sustainability from the perception of 396 Romanian accountants using an artificial neural network analysis and structural equation modeling. As a result, the research provides a holistic view of the managerial accounting roles enhanced by digital technologies in the sustainable development of healthcare organizations. From the accountants' perception, the leading managerial accounting roles on organizational sustainability are enablers and reporters of the sustainable value created in the organization. Additionally, the roles of creators and preservers are seen as relevant by a significant part of the respondents. Therefore, healthcare organizations must implement a sustainability vision in managerial accounting and accounting information systems using the capabilities offered by new digital technologies.

Low-cost depth/IMU intelligent sensor fusion for indoor robot navigation

This paper presents a mobile robot platform, which performs both indoor and outdoor localization based on an intelligent low-cost depth–inertial fusion approach. The proposed sensor fusion approach uses depth-based localization data to enhance the accuracy obtained by the inertial measurement unit (IMU) pose data through a depth–inertial fusion. The fusion approach is based on feedforward cascade correlation networks (CCNs). The aim of this fusion approach is to correct the drift accompanied by the use of the IMU sensor, using a depth camera. This approach also has the advantage of maintaining the high frequency of the IMU sensor and the accuracy of the depth camera. The estimated mobile robot dynamic states through the proposed approach are deployed and examined through real-time autonomous navigation. It is shown that using both the planned path and the continuous localization approach, the robot successfully controls its movement toward the destination. Several tests were conducted with different numbers of layers and percentages of the training set. It is shown that the best performance is obtained with 12 layers and 80% of the pose data used as a training set for CCN. The proposed framework is then compared to the solution based on fusing the information given by the XSens IMU–GPS sensor and the Kobuki robot built-in odometry solution. As demonstrated in the results, an enhanced performance was achieved with an average Euclidean error of 0.091 m by the CCN, which is lower than the error achieved by the artificial neural network by 56%.

Is machine translation a dim technology for its users? An eye tracking study

State-of-the-art research shows that the impact of language technologies on public awareness and attitudes toward using machine translation has been changing. As machine translation acceptability is considered to be a multilayered concept, this paper employs criteria of usability, satisfaction and quality as components of acceptability measurement. The study seeks to determine whether there are any differences in the machine-translation acceptability between professional users, i.e., translators and language editors, and non-professional users, i.e., ordinary users of machine translation who use it for non-professional everyday purposes. The main research questions whether non-professional users process raw machine translation output in the same way as professional users and whether there is a difference in the processing of raw machine-translated output between users with different levels of machine-translated text acceptability are analyzed. The results of an eye tracking experiment, measuring fixation time, dwell time and glance count, indicate a difference between professional and non-professional users' cognitive processing and acceptability of machine translation output: translators and language editors spend more time overall reading the machine-translated texts, possibly because of their deeper critical awareness as well as professional attitude toward the text. In terms of acceptability overall, professional translators critically assess machine translation on all components of which confirms the findings of previous similar research. However, the study draws attention to non-professional users' lower awareness regarding machine translation quality. The study was conducted within a research project that received funding from the Research Council of Lithuania (LMTLT, agreement No S-MOD-21-2), seeking to explore and evaluate the impact on society of machine translation technological solutions.

Machine learning to improve frequent emergency department use prediction: a retrospective cohort study

Frequent emergency department use is associated with many adverse events, such as increased risk for hospitalization and mortality. Frequent users have complex needs and associated factors are commonly evaluated using logistic regression. However, other machine learning models, especially those exploiting the potential of large databases, have been less explored. This study aims at comparing the performance of logistic regression to four machine learning models for predicting frequent emergency department use in an adult population with chronic diseases, in the province of Quebec (Canada). This is a retrospective population-based study using medical and administrative databases from the Régie de l'assurance maladie du Québec. Two definitions were used for frequent emergency department use (outcome to predict): having at least three and five visits during a year period. Independent variables included sociodemographic characteristics, healthcare service use, and chronic diseases. We compared the performance of logistic regression with gradient boosting machine, naïve Bayes, neural networks, and random forests (binary and continuous outcome) using Area under the ROC curve, sensibility, specificity, positive predictive value, and negative predictive value. Out of 451,775 ED users, 43,151 (9.5%) and 13,676 (3.0%) were frequent users with at least three and five visits per year, respectively. Random forests with a binary outcome had the lowest performances (ROC curve: 53.8 [95% confidence interval 53.5-54.0] and 51.4 [95% confidence interval 51.1-51.8] for frequent users 3 and 5, respectively) while the other models had superior and overall similar performance. The most important variable in prediction was the number of emergency department visits in the previous year. No model outperformed the others. Innovations in algorithms may slightly refine current predictions, but access to other variables may be more helpful in the case of frequent emergency department use prediction.

Metrics for measuring industrial sustainability performance in small and medium-sized enterprises

Purpose

This paper aims to identify and empirically analyze useful and applicable metrics for measuring and managing the sustainability performance of small and medium-sized enterprises (SMEs).

Design/methodology/approach

To achieve the objective of the paper, potential metrics were adopted from previous research related to industrial sustainability and an empirical analysis was carried to assess the applicability of the metrics by collecting empirical data from Italian footwear SMEs using a structured questionnaire. The SMEs were selected using a convenience sampling method.

Findings

The results of the within-case analysis and the cross-case analysis indicate that the majority of the metrics were found to be useful and applicable to each of the SMEs and across the SMEs, respectively. These metrics emphasized measuring industrial sustainability performance related to financial benefits, costs and market competitiveness for the economic sustainability dimension; resources for the environmental sustainability dimension; and customers, employees and the community for the social sustainability dimension.

Research limitations/implications

Apart from the within-case analysis and cross-case analysis, it was not possible to conduct statistical analysis since a small number of SMEs were accessible to collect empirical data.

Originality/value

The findings of the paper have considerable academic, managerial and policy implications and will provide a theoretical basis for future research on measuring and managing industrial sustainability performance. By providing a set of empirically supported metrics based on the triple bottom line approach (i.e. economic, environmental and social metrics), this paper contributes to the existing knowledge in the field of industrial sustainability performance measurement.

External validation of prediction models for patient-reported outcome measurements collected using the selfBACK mobile app

BACKGROUND

External validation is essential in examining the disparities in the training and validation cohorts during the development of prediction models, especially when the application domain is healthcare-oriented. Currently, the use of prediction models in healthcare research aimed at utilising the under-explored potential of patient-reported outcome measurements (PROMs) is limited, and few are validated using external datasets.

OBJECTIVE

To validate the machine learning prediction models developed in our previous work [29] for predicting four pain-related patient-reported outcomes from the selfBACK clinical trial datasets.

METHODS

We evaluate the validity of three pre-trained prediction models based on three methods- Case-Based Reasoning, Support Vector Regression, and XGBoost Regression-using an external dataset that contains PROMs collected from patients with non-specific neck and or low back pain using the selfBACK mobile application.

RESULTS

Overall, the predictive power was low, except for prediction of one of the outcomes. The results indicate that while the predictions are far from immaculate in either case, the models show ability to generalise and predict outcomes for a new dataset.

CONCLUSION

External validation of the prediction models presents modest results and highlights the individual differences and need for external validation of prediction models in clinical settings. There is need for further development in this area of machine learning application and patient-centred care.

An intelligent non-invasive system for automated diagnosis of anemia exploiting a novel dataset

Anemia is a condition in which the oxygen-carrying capacity of red blood cells is insufficient to meet the body's physiological needs. It affects billions of people worldwide. An early diagnosis of this disease could prevent the advancement of other disorders. Traditional methods used to detect anemia consist of venipuncture, which requires a patient to frequently undergo laboratory tests. Therefore, anemia diagnosis using noninvasive and cost-effective methods is an open challenge. The pallor of the fingertips, palms, nail beds, and eye conjunctiva can be observed to establish whether a patient suffers from anemia. This article addresses the above challenges by presenting a novel intelligent system, based on machine learning, that supports the automated diagnosis of anemia. This system is innovative from different points of view. Specifically, it has been trained on a dataset that contains eye conjunctiva photos of Indian and Italian patients. This dataset, which was created using a very strict experimental set, is now made available to the Scientific Community. Moreover, compared to previous systems in the literature, the proposed system uses a low-cost device, which makes it suitable for widespread use. The performance of the learning algorithms utilizing two different areas of the mucous membrane of the eye is discussed. In particular, the RUSBoost algorithm, when appropriately trained on palpebral conjunctiva images, shows good performance in classifying anemic and nonanemic patients. The results are very robust, even when considering different ethnicities.

A novel approach for estimating and predicting uncertainty in water quality index model using machine learning approaches

With the significant increase in WQI applications worldwide and lack of specific application guidelines, accuracy and reliability of WQI models is a major issue. It has been reported that WQI models produce significant uncertainties during the various stages of their application including: (i) water quality indicator selection, (ii) sub-index (SI) calculation, (iii) water quality indicator weighting and (iv) aggregation of sub-indices to calculate the overall index. This research provides a robust statistically sound methodology for assessment of WQI model uncertainties. Eight WQI models are considered. The Monte Carlo simulation (MCS) technique was applied to estimate model uncertainty, while the Gaussian Process Regression (GPR) algorithm was utilised to predict uncertainties in the WQI models at each sampling site. The sub-index functions were found to contribute to considerable uncertainty and hence affect the model reliability - they contributed 12.86% and 10.27% of uncertainty for summer and winter applications, respectively. Therefore, the selection of sub-index function needs to be made with care. A low uncertainty of less than 1% was produced by the water quality indicator selection and weighting processes. Significant statistical differences were found between various aggregation functions. The weighted quadratic mean (WQM) function was found to provide a plausible assessment of water quality of coastal waters at reduced uncertainty levels. The findings of this study also suggest that the unweighted root means squared (RMS) aggregation function could be potentially also used for assessment of coastal water quality. Findings from this research could inform a range of stakeholders including decision-makers, researchers, and agencies responsible for water quality monitoring, assessment and management.

An unsupervised approach for personalized RHM with reduced mean alert latency

Remote Health Monitoring (RHM) is an important research topic among the researchers, where many challenges are to be addressed with respect to communication, device, synchronization, data analysis, knowledge inferencing, database maintenance, security, timely notification etc. Among these multi challenges, personalization of health data and scheduling of alert generation have been focused on this work. Recognizing the regular health pattern of each individual helps in diagnosing the disease accurately (reduces the False Alarm Ratio (FAR)) and provides the necessary treatment earlier. Similarly, in real time, with multiple patients, the latency should be minimal for timely alert generation. To address these two challenges, a Density-based K- means clustering (DbK-meansC) approach has been proposed in this work that personalize the vital health values. From the personalized health values the abnormalities in the health status of a person can be detected earlier. Here the health records are continuously updated with respect to health values that reflects in personalization of health records. If any abnormality noted in the health values, then the proposed work sends an alert message to the caretaker / the respective doctor using a dynamic preemptive priority scheduling scheme. The scheduling is done with respect to the severity levels of the vital health values of each individual respectively. The arrived results show that the proposed personalized abnormality detection RHM model generate alerts with minimum latency in terms of response and waiting time in a multi patient environment. With proper personalization, the obtained specificity and sensitivity are 91.56% and 92.87% respectively and the computational time is reduced as the degree of personalization increases.

The Stakeholders' Involvement in Healthcare 4.0 Services Provision: The Perspective of Co-Creation

Literature research on cocreation in healthcare indicates the theoretical sophistication of research on collaboration between healthcare professionals and patients. Our research continues in the new area of Health 4.0. Cocreation has become an essential concept in the value creation process; by involving consumers in the creation process, better results are achieved regarding product quality and alignment with customer expectations and needs. In addition, consumer involvement in the creation process improves its efficiency. Cocreation allows for more efficient diagnosis and treatment of patients, as well as better and more effective use of the skills and experience of the health workforce. Our main objective is to determine the scope and depth of the cocreation of health services based on modern technological solutions (Health 4.0). We selected four cases involving Health 4.0 solutions, verified the scale and scope of cocreation using them as examples, and used the cocreation matrix. We used literature, case studies, and interviews in our research. Our analysis shows that patients can emerge as cocreators in the value creation process in Health 4.0. This can happen when they are genuinely involved in the process and when they feel responsible for the results. The article contributes to the existing theory of service cocreation by pointing out the limited scope of patient involvement in the service management process. For cocreation in Health 4.0 to increase the effectiveness of medical services, it is necessary to implement the full scope of cocreation and meaningfully empower the patient and medical workers in the creation process. This article verifies the theoretical analysis presented in our team's previous article.

Comparing virtual political campaigns with traditional political campaigns: evidence from Kuwait during the COVID-19 pandemic

Purpose

This study aims to focus on how virtual campaigns are affecting voters in the elections of Kuwait, as well as whether such virtual campaigns will replace traditional campaigns in the post-COVID era.

Design/methodology/approach

This qualitative research adopts a purposeful sample when selecting participants from candidates and the managers of electoral campaigns in Kuwait. Fifteen participants were selected, which has been sufficient to achieve data saturation, and then, textual data were collected via semistructured interviews from 15 candidates and the managers of electoral campaigns in Kuwait during the COVID-19 pandemic.

Findings

The findings indicate that candidates preferred using virtual campaigns which enabled them to reach voters during the time of COVID-19’s lockdown. Majority of responses underlined that social media platforms do direct political messages to the voters. Hence, social media platforms should be perceived as preferred medium for communicating with supporters, especially in the post-COVID-19 era. However, some responses uphold the importance of keeping traditional political campaigns due to the peculiar nature of the Kuwaiti community where there is a need for socialization and meeting face-to-face with voters.

Originality/value

This research provides a new evaluation about the role of virtual political campaigns in Kuwait. It highlights the crucial and increasing role of virtual political campaigns in attracting voters; nevertheless, it found that virtual campaigns should be used as addendum to conventional political campaigns in the post-COVID-19 era in Kuwait.

The Oesophageal Cancer Multidisciplinary Team: Can Machine Learning Assist Decision-Making?

BACKGROUND

The complexity of the upper gastrointestinal (UGI) multidisciplinary team (MDT) is continually growing, leading to rising clinician workload, time pressures, and demands. This increases heterogeneity or 'noise' within decision-making for patients with oesophageal cancer (OC) and may lead to inconsistent treatment decisions. In recent decades, the application of artificial intelligence (AI) and more specifically the branch of machine learning (ML) has led to a paradigm shift in the perceived utility of statistical modelling within healthcare. Within oesophageal cancer (OC) care, ML techniques have already been applied with early success to the analyses of histological samples and radiology imaging; however, it has not yet been applied to the MDT itself where such models are likely to benefit from incorporating information-rich, diverse datasets to increase predictive model accuracy.

METHODS

This review discusses the current role the MDT plays in modern UGI cancer care as well as the utilisation of ML techniques to date using histological and radiological data to predict treatment response, prognostication, nodal disease evaluation, and even resectability within OC.

RESULTS

The review finds that an emerging body of evidence is growing in support of ML tools within multiple domains relevant to decision-making within OC including automated histological analysis and radiomics. However, to date, no specific application has been directed to the MDT itself which routinely assimilates this information.

CONCLUSIONS

The authors feel the UGI MDT offers an information-rich, diverse array of data from which ML offers the potential to standardise, automate, and produce more consistent, data-driven MDT decisions.

Artificial Intelligence Based Approach for Classification of Human Activities Using MEMS Sensors Data

The integration of Micro Electronic Mechanical Systems (MEMS) sensor technology in smartphones has greatly improved the capability for Human Activity Recognition (HAR). By utilizing Machine Learning (ML) techniques and data from these sensors, various human motion activities can be classified. This study performed experiments and compiled a large dataset of nine daily activities, including Laying Down, Stationary, Walking, Brisk Walking, Running, Stairs-Up, Stairs-Down, Squatting, and Cycling. Several ML models, such as Decision Tree Classifier, Random Forest Classifier, K Neighbors Classifier, Multinomial Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine, were trained on sensor data collected from accelerometer, gyroscope, and magnetometer embedded in smartphones and wearable devices. The highest test accuracy of 95% was achieved using the random forest algorithm. Additionally, a custom-built Bidirectional Long-Short-Term Memory (Bi-LSTM) model, a type of Recurrent Neural Network (RNN), was proposed and yielded an improved test accuracy of 98.1%. This approach differs from traditional algorithmic-based human activity detection used in current wearable technologies, resulting in improved accuracy.

Hyperparameter Search for Machine Learning Algorithms for Optimizing the Computational Complexity

For machine learning algorithms, fine-tuning hyperparameters is a computational challenge due to the large size of the problem space. An efficient strategy for adjusting hyperparameters can be established with the use of the greedy search and Swarm intelligence algorithms. The Random Search and Grid Search optimization techniques show promise and efficiency for this task. The small population of solutions used at the outset, and the costly goal functions used by these searches, can lead to slow convergence or execution time in some cases. In this research, we propose using the machine learning model known as Support Vector Machine and optimizing it using four distinct algorithms—the Ant Bee Colony Algorithm, the Genetic Algorithm, the Whale Optimization, and the Particle Swarm Optimization—to evaluate the computational cost of SVM after hyper-tuning. Computational complexity comparisons of these optimization algorithms were performed to determine the most effective strategies for hyperparameter tuning. It was found that the Genetic Algorithm had a lower temporal complexity than other algorithms.

Role of social capital in response to and recovery from the first wave of COVID-19 in Thailand: a qualitative study

OBJECTIVE

This study assesses the role of social capital among people and communities in response to the first wave of the pandemic in 2020.

DESIGN

Qualitative study using focus group discussions.

SETTING

Capital city (Bangkok) and the four regions (north, northeast, south and central) of Thailand.

PARTICIPANTS

161 participants of 19 focus groups with diverse backgrounds in terms of gender, profession, education and geography (urban/rural; regions). They are selected for different levels of impact from the pandemic.

FINDINGS

The solidarity among the Thai people was a key contributing factor to societal resilience during the pandemic. Findings illustrate how three levels of social capital structure-family, community and local networks-mobilised resources from internal and external social networks to support people affected by the pandemic. The results also highlight different types of resources mobilised from the three levels of social capital, factors that affect resilience, collective action to combat the negative impacts of the pandemic, and the roles of social media and gender.

CONCLUSION

Social capital plays significant roles in the resilience of individuals, households and communities to respond to and recover from the impacts of the pandemic. In many instances, social capital is a faster and more efficient response than other kinds of formal support. Social capital can be enhanced by interactions and exchanges in the communities. While face-to-face social contacts are challenged by the need for social distancing and travel restrictions, social media steps in as alternative socialisation to enhance social capital.

Self-supervised Learning: A Succinct Review

Machine learning has made significant advances in the field of image processing. The foundation of this success is supervised learning, which necessitates annotated labels generated by humans and hence learns from labelled data, whereas unsupervised learning learns from unlabeled data. Self-supervised learning (SSL) is a type of un-supervised learning that helps in the performance of downstream computer vision tasks such as object detection, image comprehension, image segmentation, and so on. It can develop generic artificial intelligence systems at a low cost using unstructured and unlabeled data. The authors of this review article have presented detailed literature on self-supervised learning as well as its applications in different domains. The primary goal of this review article is to demonstrate how images learn from their visual features using self-supervised approaches. The authors have also discussed various terms used in self-supervised learning as well as different types of learning, such as contrastive learning, transfer learning, and so on. This review article describes in detail the pipeline of self-supervised learning, including its two main phases: pretext and downstream tasks. The authors have shed light on various challenges encountered while working on self-supervised learning at the end of the article.

Inertial Sensor-Based Sport Activity Advisory System Using Machine Learning Algorithms

The aim of this study was to develop a physical activity advisory system supporting the correct implementation of sport exercises using inertial sensors and machine learning algorithms. Specifically, three mobile sensors (tags), six stationary anchors and a system-controlling server (gateway) were employed for 15 scenarios of the series of subsequent activities, namely squats, pull-ups and dips. The proposed solution consists of two modules: an activity recognition module (ARM) and a repetition-counting module (RCM). The former is responsible for extracting the series of subsequent activities (so-called scenario), and the latter determines the number of repetitions of a given activity in a single series. Data used in this study contained 488 three defined sport activity occurrences. Data processing was conducted to enhance performance, including an overlapping and non-overlapping window, raw and normalized data, a convolutional neural network (CNN) with an additional post-processing block (PPB) and repetition counting. The developed system achieved satisfactory accuracy: CNN + PPB: non-overlapping window and raw data, 0.88; non-overlapping window and normalized data, 0.78; overlapping window and raw data, 0.92; overlapping window and normalized data, 0.87. For repetition counting, the achieved accuracies were 0.93 and 0.97 within an error of ±1 and ±2 repetitions, respectively. The archived results indicate that the proposed system could be a helpful tool to support the correct implementation of sport exercises and could be successfully implemented in further work in the form of web application detecting the user's sport activity.

Dictating translations with automatic speech recognition: Effects on translators' performance

Technologies can greatly improve translators' productivity and reduce their workload. Previous research has found that the use of automatic speech recognition (ASR) tools for dictating translations can increase productivity. However, these studies often had small sample sizes and did not consider other important aspects of translators' performance, such as translation quality and cognitive effort. This study aims to investigate the impact of text input method on translators' performance in terms of task duration, time allocation, editing operations, cognitive effort, and translation quality, as well as whether text difficulty affects these factors. To do this, 60 Chinese translation trainees were randomly assigned to either a dictation group or a typing group, and completed two English-Chinese translations of varying levels of source-text difficulty. Data were collected using keylogging, subjective ratings, screen recording, and a questionnaire. The results showed that using ASR reduced the typing effort of participants without negatively affecting translation quality, but did not save time or reduce cognitive effort. No effect of text difficulty was observed. Analysis of the revisions made by the dictation group and the results of the post-test questionnaire provide insights into how ASR systems can be optimized for translation purposes.

Trends and challenges of digital divide and digital inclusion: A bibliometric analysis

Information and Communication Technologies (ICTs) are of great importance in today’s society and have permeated different aspects of human life. In fact, access to them is now considered a fundamental right. There exists, however, a gap between individuals and populations who have access to these technologies and those who do not, which has led to social exclusion. In addition, the COVID-19 pandemic has exacerbated the effects of this disparity. In this regard, digital inclusion, through ICTs, becomes a strategy to close not only technical but also social gaps, thereby bringing well-being to vulnerable groups and favouring compliance with the Sustainable Development Goals (SDGs). Given the importance and topicality of this matter, we conducted a bibliometric analysis, which aims to answer what are the main trends in digital inclusion and digital divide studies and what are the challenges facing digital inclusion initiatives in the social context? For this purpose, we applied a search equation in Scopus and used VOSviewer. With this analysis, we were able to identify the evolution of publications over time and the main authors, countries and topics in the field, and the trends and challenges in digital inclusion initiatives. Finally, we conclude that this study can be used to address other research topics, such as the role of ICTs in the promotion of the SDGs through digital inclusion initiatives, the psychosocial aspects of technology adoption and the need for public policies that serve as a platform for digital and social inclusion.

Addressing Complexity in the Pandemic Context: How Systems Thinking Can Facilitate Understanding of Design Aspects for Preventive Technologies

The COVID-19 pandemic constitutes a wicked problem that is defined by rapidly evolving and dynamic conditions, where the physical world changes (e.g., pathogens mutate) and, in parallel, our understanding and knowledge rapidly progress. Various preventive measures have been developed or proposed to manage the situation, including digital preventive technologies to support contact tracing or physical distancing. The complexity of the pandemic and the rapidly evolving nature of the situation pose challenges for the design of effective preventive technologies. The aim of this conceptual paper is to apply a systems thinking model, DSRP (distinctions, systems, relations, perspectives) to explain the underlying assumptions, patterns, and connections of the pandemic domain, as well as to identify potential leverage points for design of preventive technologies. Two different design approaches, contact tracing and nudging for distance, are compared, focusing on how their design and preventive logic are related to system complexity. The analysis explains why a contact tracing technology involves more complexity, which can challenge both implementation and user understanding. A system utilizing nudges can operate using a more distinct system boundary, which can benefit understanding and implementation. However, frequent nudges might pose challenges for user experience. This further implies that these technologies have different contextual requirements and are useful at different levels in society. The main contribution of this work is to show how systems thinking can organize our understanding and guide the design of preventive technologies in the context of epidemics and pandemics.

Ten Years of Medical Informatics and Standards Support for Clinical Research in an Infectious Diseases Network

BACKGROUND

It is 30 years since evidence-based medicine became a great support for individual clinical expertise in daily practice and scientific research. Electronic systems can be used to achieve the goal of collecting data from heterogeneous datasets and to support multicenter clinical trials. The Ligurian Infectious Diseases Network (LIDN) is a web-based platform for data collection and reuse originating from a regional effort and involving many professionals from different fields.

OBJECTIVES

The objective of this work is to present an integrated system of ad hoc interfaces and tools that we use to perform pseudonymous clinical data collection, both manually and automatically, to support clinical trials.

METHODS

The project comprehends different scenarios of data collection systems, according to the degree of information technology of the involved centers. To be compliant with national regulations, the last developed connection is based on the standard Clinical Document Architecture Release 2 by Health Level 7 guidelines, interoperability is supported by the involvement of a terminology service.

RESULTS

Since 2011, the LIDN platform has involved more than 8,000 patients from eight different hospitals, treated or under treatment for at least one infectious disease among human immunodeficiency virus (HIV), hepatitis C virus, severe acute respiratory syndrome coronavirus 2, and tuberculosis. Since 2013, systems for the automatic transfer of laboratory data have been updating patients' information for three centers, daily. Direct communication was set up between the LIDN architecture and three of the main national cohorts of HIV-infected patients.

CONCLUSION

The LIDN was originally developed to support clinicians involved in the project in the management of data from HIV-infected patients through a web-based tool that could be easily used in primary-care units. Then, the developed system grew modularly to respond to the specific needs that arose over a time span of more than 10 years.