User Performance Research Articles

Aptitude Training System Using Decision Trees

This paper presents the development of an adaptive online aptitude training system utilizing decision trees for students preparing for campus placements. The system aims to assess and enhance students' aptitude and technical skills through personalized learning experiences. Leveraging a vast question bank, the system employs an adaptive algorithm analyzing users' responses, time spent, and performance data from pre-assessments to tailor subsequent assessments. By integrating AI-based question selection, the system ensures relevance and effectiveness in assessing student proficiency. The focus lies on providing targeted exercises to address individual weaknesses, thereby optimizing preparation for campus interviews. This paper underscores the efficacy of decision tree algorithms in delivering personalized aptitude training, contributing to students' success in securing placements. Keywords: Adaptive Learning, Decision Trees, Aptitude Training, Personalized Education

Cryptocurrency Price Tracker: A Comprehensive Examination of Market Trends, Real-Time Updates, and User-Centric Features

The cryptocurrency market, characterized by its volatility and rapid fluctuations, necessitates robust tools for tracking and analyzing prices in real-time. This project proposes the development of a cryptocurrency price tracker, leveraging the MERN (MongoDB, Express.js, React.js, Node.js) stack for efficient data management and user interface design. The platform aims to provide users with timely and accurate information on cryptocurrency prices, market trends, and historical data. Key features include real-time price updates, customizable watchlists, advanced charting tools, and secure authentication mechanisms. The project focuses on enhancing user experience, scalability, security, and performance to meet the evolving demands of cryptocurrency enthusiasts and traders. By integrating cutting-edge technologies and adhering to best practices in software development, the cryptocurrency price tracker aims to become a valuable resource for both novice and experienced users navigating the complexities of the cryptocurrency market. Keywords: Cryptocurrency, Price Tracker, MERN Stack, Real-time Data, User Experience, Performance.

Impact of example-based XAI for neural networks on trust, understanding, and performance

The purpose of this study is to examine the impact of an example-based explainable artificial intelligence (XAI) interface on trust, understanding, and performance in highly-technical populations. XAI studies often focus on general users in low-risk domains. This study examined the impact of showing the closest matches from the training data from two classes on trust, understanding, and performance for highly-technical users in a high-risk domain. We found that providing example-based explanations significantly increased trust and understanding without decreasing performance. Showing the most similar examples from two classes increased trust more than showing examples from only one class. Participants did not treat different classes the same. The most important features for predicting how well an interface was understood were the helpfulness of the provided examples and the person's trust in the human-machine team. We found priming of highly-technical participants to be particularly important for running XAI studies to mitigate the fear of their jobs being impacted.

A Cable-Based Haptic Interface with a Reconfigurable Structure

Abstract Cable robots have been used as haptic interfaces for several decades now, with the most notable examples being the SPIDAR and its numerous iterations throughout the years, as well as the more recent IPAnema 3 Mini manufactured by Fraunhofer IPA. However, these robots still have drawbacks, particularly their high number of cables required to maintain a high workspace-to-installation-space ratio. Using a hybrid-structure cable robot (HSCR) could prevent some collisions that occur between the cables and the user's body. More specifically, some applications requiring multimodal feedback could benefit from the flexibility that a reduced number of cables offers. Therefore, this paper presents a novel SPIDAR-like VSCR and its sensor-less force control method based on motor current. The purpose of this work is to clarify the advantages that a variable structure can provide for haptic interaction. In this regard, experimental results regarding the device's workspace and its force feedback capabilities are presented. Additionally, since real-time high-frequency updates are required for haptic display, we provide additional data regarding the control algorithm's runtime. Lastly, another experiment was conducted to study changes in user performance when using both the variable and the usual cable configuration. The results showed that feedback accuracy is maintained, and there are no drawbacks to using hybrid configurations.

КОМПЛЕКС АЛГОРИТМОВ ОПТИМАЛЬНОГО ПРОЕКТИРОВАНИЯ И ОЦЕНКИ ЭФФЕКТИВНОСТИ ВИЗУАЛЬНОЙ СОСТАВЛЯЮЩЕЙ ГРАФИЧЕСКИХ ПОЛЬЗОВАТЕЛЬСКИХ ИНТЕРФЕЙСОВ

Modernity is characterized by comprehensive digitalization, leading to an increase in the number of software products, an integral part of which are graphical user interfaces, which act as an intermediary between users and software algorithms, allowing them to comfortably and efficiently perform the required tasks. Most modern software products have low-efficiency interfaces, which leads to a decrease in the performance of users and an increase in intrapsychological stress on them. In order to improve the efficiency of interfaces, this article describes the formulation of the problem of developing a set of algorithms for optimal design and evaluation of the effectiveness of the visual component of graphical user interfaces.
 To develop a set of algorithms, this article presents a range of proprietary indicators for each of the areas, as well as an analysis of existing quantitative methods for assessing the effectiveness of interfaces for the possibility of using them to calculate the indicators mentioned above. It is concluded that existing approaches are capable of providing a formalized representation of only part of the author’s indicators.
 The planned set of algorithms, after implementation, will hypothetically allow for a comprehensive assessment of interfaces, as well as finding defects in them that reduce their effectiveness, which, if eliminated, will improve the quality of both interfaces and programs 
 in general, increasing the performance and comfort of interaction with user programs.

Enhancing robotic telesurgery with sensorless haptic feedback.

This paper evaluates user performance in telesurgical tasks with the da Vinci Research Kit (dVRK), comparing unilateral teleoperation, bilateral teleoperation with force sensors and sensorless force estimation. A four-channel teleoperation system with disturbance observers and sensorless force estimation with learning-based dynamic compensation was developed. Palpation experiments were conducted with 12 users who tried to locate tumors hidden in tissue phantoms with their fingers or through handheld or teleoperated laparoscopic instruments with visual, force sensor, or sensorless force estimation feedback. In a peg transfer experiment with 10 users, the contribution of sensorless haptic feedback with/without learning-based dynamic compensation was assessed using NASA TLX surveys, measured free motion speeds and forces, environment interaction forces as well as experiment completion times. The first study showed a 30% increase in accuracy in detecting tumors with sensorless haptic feedback over visual feedback with only a 5-10% drop in accuracy when compared with sensor feedback or direct instrument contact. The second study showed that sensorless feedback can help reduce interaction forces due to incidental contacts by about 3 times compared with unilateral teleoperation. The cost is an increase in free motion forces and physical effort. We show that it is possible to improve this with dynamic compensation. We demonstrate the benefits of sensorless haptic feedback in teleoperated surgery systems, especially with dynamic compensation, and that it can improve surgical performance without hardware modifications.

Evaluating the performance of gaze interaction for map target selection

ABSTRACT The eye tracking approach has the potential to facilitate more tailored and intelligent geoapplication interactions. There is a lack of knowledge regarding how gaze interaction influences user performance (accuracy and efficiency), visual behavior, and cognitive workload in real-world map-reading settings. In this study, we adopted a low-cost eye tracker and dwell time method to implement a fundamental gaze-based map interaction: target (point, line and area) selection. We administered a comparative experiment in which 36 participants were asked to perform a series of map target selection tasks using gaze-based and mouse interactions. The results demonstrated that gaze-based map interaction is comparable to mouse in terms of overall efficiency. By evaluating the visual behavior of the participants, we found that mouse interaction exhibited heightened fixation frequency and larger saccade amplitude than gaze interaction. Although gaze-based map interaction frustrated participants more often, the overall cognitive workload was no different from that of mouse interaction. These differences between interaction modes were largely affected by task types but rarely dependent on target shapes or positions. Moreover, participants evaluated gaze interaction higher in terms of attractiveness, stimulation and novelty. These results are beneficial for map interaction researchers and developers.

The effects of slope-adaptive prosthetic feet on sloped gait performance and quality in unilateral transtibial prosthesis users: A scoping review.

In non-impaired human locomotion, sagittal-plane slope adaptation of the foot-ankle complex is a volitional function driven by neuromotor control to support upright posture and forward ambulation. Loss of this adaptation due to transtibial amputation can lead to instability and compensatory motions as most commercially-available prosthetic feet do not permit automatic slope adjustments. A selection of slope-adaptive feet (SAF) have been developed to promote biomimetic ankle motion while ambulating over slopes. This review evaluated the current literature to assess the effects of SAF prostheses on sloped gait performance in unilateral transtibial prosthesis users. Four databases (PubMed, Embase, CINAHL, IEEE Xplore) were searched on April 28, 2022, for relevant articles. Search keywords covered the general terms "transtibial," "amputation," "slope," "adaptive," and "gait", and included articles comparing a SAF prosthesis to a non-SAF prosthesis condition. Data were extracted for analysis and results were grouped according to outcomes to identify trends and aid interpretation of slope adaptation effects on gait. Of the 672 articles screened, 24 met the selection criteria and were included in this review, published between 2009 and 2022. The non-SAF condition included dynamic response feet and SAF prostheses with the adaptability function inactive. Outcomes included biomechanical variables (joint dynamics, gait symmetry, toe clearance), clinical outcome measures, and energy expenditure. All SAF demonstrated some form of foot-ankle slope gradient adaptability, but effects on other joint dynamics were inconsistent. Minimum toe clearance during incline and decline walking was greater when using SAF compared to non-SAF in all reporting studies. Results generally suggest improvements in gait quality, comfort, and safety with use of SAF compared to non-SAF during slope walking. However, variations in tested SAF and walking gradients across studies highlight the need for research to elucidate walking condition effects and advantages of specific designs. Slope-adaptive prosthetic feet may improve user gait quality and comfort and enhance gait safety by increasing minimum toe clearance. Patients who encounter slopes regularly should be considered as potential users of SAF if indicated appropriately.

Improving Performance of the Typical User in the Indoor Cooperative NOMA Millimeter Wave Networks with Presence of Walls

INTRODUCTION: The beyond 5G millimeter wave cellular network system is expecting to provide the high quality of service in indoor areas. OBJECTIVES: Due to the high density of obstacles, the cooperative communication technique is employed to improve the user's desired signal power by finding more than one appropriate station to serve that user. METHODS: While the conventional system utilizes additional equipment such as Reconfigurable Intelligent Surfaces (RIS) and relays to enable the cooperative features, the paper introduces a new network paradigm that utilizes the second nearest Base Station (BS) of the typical user as the Decode and Forward (DF) relay. Thus, depends on the success of decoding the message from the user' serving BS of the second nearest BS, the typical user can work with and without assistance from the relay whose operation follows the discipline of the power-domain NOMA technique. In the case of with relay assistance, the Maximum Ratio Combining technique is utilized by the typical user to combine the desired signals. RESULTS: To examine the performance of the proposed system, the Nakagami-m and the newly developed path loss model, which considers the density of walls and their properties, are adopted to derive the coverage probability of the user with and without relay assistance. The closed-form expressions of this performance metric are derived by Gauss quadrature and Welch-Satterthwaite approximation.

Learning-based personalisation of robot behaviour for robot-assisted therapy.

During robot-assisted therapy, a robot typically needs to be partially or fully controlled by therapists, for instance using a Wizard-of-Oz protocol; this makes therapeutic sessions tedious to conduct, as therapists cannot fully focus on the interaction with the person under therapy. In this work, we develop a learning-based behaviour model that can be used to increase the autonomy of a robot's decision-making process. We investigate reinforcement learning as a model training technique and compare different reward functions that consider a user's engagement and activity performance. We also analyse various strategies that aim to make the learning process more tractable, namely i) behaviour model training with a learned user model, ii) policy transfer between user groups, and iii) policy learning from expert feedback. We demonstrate that policy transfer can significantly speed up the policy learning process, although the reward function has an important effect on the actions that a robot can choose. Although the main focus of this paper is the personalisation pipeline itself, we further evaluate the learned behaviour models in a small-scale real-world feasibility study in which six users participated in a sequence learning game with an assistive robot. The results of this study seem to suggest that learning from guidance may result in the most adequate policies in terms of increasing the engagement and game performance of users, but a large-scale user study is needed to verify the validity of that observation.

Investigating Service Characteristics as Determinants of User Performance and Satisfaction in Saudi Arabia's Mobile Government Context

Investigating Service Characteristics as Determinants of User Performance and Satisfaction in Saudi Arabia's Mobile Government Context

Glaucoma Detection Using Explainable AI and Deep Learning

INTRODUCTION: Glaucoma is an incurable eye syndrome and the second leading reason of vision loss. A retinal scan is usually used to detect it. Glaucoma poses a challenge to predict in its nascent stages because the side effects of glaucoma are not recognized until the advanced stages of the disease are reached. Therefore, regular eye examinations are important and recommended. Manual glaucoma screening methods are labour-intensive and time-consuming processes. However, deep learning-based glaucoma detection methods reduce the need for manual work and improve accuracy and speed.
 OBJECTIVES: conduct a literature analysis of latest technical publications using various AI, Machine learning, and Deep learning methodologies for automated glaucoma detection.
 RESULTS: There are 329 Scopus articles on glaucoma detection using retinal images. The quantitative review presented state-of-art methods from different research publications and articles and the usage of a fundus image database for qualitative and quantitative analysis. This paper presents the execution of Explainable AI for Glaucoma prediction Analysis. Explainable AI (XAI) is artificial intelligence (AI) that allows humans to understand AI decisions and predictions. This contrasts with the machine learning “black box” concept, where even the designer cannot explain why the AI made certain decisions. XAI is committed to improving user performance. To provide reliable explanations for Glaucoma forecasting from unhealthy and diseased photos, XAI primarily employs an Adaptive Neuro-fuzzy Inference System (ANFIS).
 CONCLUSION: This article proposes and compares the performance metrics of ANFIS & SNN fuzzy layers, VGG19, AlexNet, ResNet, and MobileNet.

A K-Additive Fuzzy Logic Approach for Optimizing FCS Sizing and Enhanced User Satisfaction

Traditional electric vehicle (EV) charging methods can lead to extended waiting times for users, resulting in decreased travel efficiency and user satisfaction, therefore impacting overall convenience. Moreover, a limited number of charging stations can lead to congestion, exacerbating waiting times, while an excessive number of stations incurs inefficient costs and reduces utilization. While prior research has primarily focused on sizing and allocating charging stations to enhance user performance, there has been comparatively less emphasis on optimizing waiting times and determining the optimal number of charging stations, which is crucial from the EV user’s perspective. This study introduces a K-additive fuzzy logic algorithm to predict the average waiting time and the optimal number of charging stations. The K-additive fuzzy inference system (K-FIS) defines membership functions, expert rules, and a formulation for achieving the optimal solution. The proposed approach integrates uncertain and independent input parameters into weighted control variables, addressing the objective function to optimize EV waiting times and costs represented by the number of charging stations. The scheme utilizes both Type 1 and Type 2 membership functions, offering a detailed comparison. To validate its efficiency, the proposed scheme undergoes a comparative study against related state-of-the-art approaches.

Immersive virtual reality in orthopedic surgery as elective subject for medical students : First experiences in curricular teaching.

Virtual reality (VR) simulators have been introduced for skills training in various medical disciplines to create an approximately realistic environment without the risk of patient harm and have improved to more immersive VR (iVR) simulators at affordable costs. There is evidence that training on VR simulators improves technical skills but its use in orthopedic training programs and especially in curricular teaching sessions for medical students are currently not well established. The aim of this study was to describe the implementation of aVR operating theater as an elective course for undergraduate medical students and to evaluate its effect on student learning. An elective course for 12students was implemented during the summer semester of 2023. Using Oculus Quest2 headsets (Reality Labs, Meta Platforms, USA) and controllers and the PrecisionOS platform, they were able to train five different surgical procedures. The courses were accompanied by weekly topic discussions and instructional videos. Students were assigned to two groups: group VR vs. group non-VR. The groups were switched after 5 weeks. User feedback and performance development (theoretical and procedural surgical knowledge) after VR training were assessed using three questionnaires. The students highly appreciated the implementation of VR training into their curriculum and 91% stated that they would opt for further VR training. All students stated that VR training improved their understanding of surgical procedures and that it should be obligatory in surgical training for undergraduate medical students. After 5 weeks of training, students in the VR group achieved significantly better results (100 out of maximum 180 points) than the non-VR group (70points, p = 0.0495) in procedural surgical knowledge. After completion of the VR training the VR group achieved 106 points and the non-VR group 104 points (p = 0.8564). The procedural knowledge for non-VR group after 5 weeks significantly improved after VR training from 70to 106 points (p = 0.0087). The iVR can be easily integrated into the curriculum of medical students and is highly appreciated by the participants. The iVR statistically improves the procedural knowledge of surgical steps compared to conventional teaching methods. Further implementation of iVR training in curricular teaching of medical students should be considered.

Effects of In-Exercise Carbohydrate Supplementation on Prolonged High-Intensity Exercise Performance in Oral Contraceptive Users.

To examine the impact of oral contraceptive (OC) phases on performance, physiological, and subjective responses to prolonged, intensive exercise when carbohydrate (CHO) stores are reduced. Ten well-trained female cyclists using monophasic OC completed 4 identical trials (>150min) under conditions of in-trial 60-g·h-1 CHO supplementation (CHO+) or placebo (CHO-) during the sugar- (SUG) and active-pill (ACT) phases of their OC cycle. Each trial comprised two 400-kcal time trials (TT) separated by 1hour of submaximal cycling at first ventilatory threshold. Change in completion time from TT1 to TT2 was minimized in CHO+ compared with CHO- (4.06 [2.55] vs 6.08 [5.33]min; P = .019, effect size = -0.36). An interaction effect of OC and CHO was observed for time to complete TT (P = .006), mean TT power (P = .002), mean TT heart rate (P = .002), and posttrial emotional balance (P = .020) and negative emotional state (P = .033). In ACT, mean TT power and heart rate were higher in CHO+ when compared with CHO-, resulting in faster TTs in CHO+ and improved posttrial emotional well-being. When CHO was not supplemented, TT power and heart rate were higher in SUG when compared with ACT, resulting in faster TTs in SUG and improved posttrial emotional balance. CHO depletion during ACT negatively influenced TT performance and emotional well-being when compared with SUG. Irrespective of OC pill phase, CHO supplementation should be prioritized to sustain performance and improve postexercise recovery-stress balance.

Intelligent Reflecting Surface Assisted Secure Computation of Wireless Powered MEC System

The integration of mobile edge computing (MEC) and wireless power transfer (WPT) can effectively improve the computing ability and energy sustainability of energy-constrained wireless devices in the Internet of Things (IoT) networks. Intelligent reflecting surface (IRS) has recently emerged as an effective technique to improve the performance of wireless systems by intelligently reconfiguring wireless environments. This paper studies the exploitation of IRS to improve the secure computation performance of WPT-MEC systems with a passive eavesdropper. A wireless access point (AP) first charge multiple users with the emitted energy signals, and then the users perform local computing and partial offloading to complete their computation tasks with the harvested energy in the presence of an eavesdropper, where the local computing can be executed during the whole process of WPT and offloading. Meanwhile, deploying IRS can improve the energy capture and secure offloading performance of the users. We maximize the secure computation task bits of users by jointly optimizing the AP energy transmit beamforming, the IRS phase shifts, the transmit power, users' offloading time, and the local computation frequency of users, which are tangled with each other. An iterative optimal algorithm is developed to solve this non-convex problem by combining Taylor expansion method, semidefinite relaxation (SDR) algorithm, the Lagrange duality theory and Karush-Kuhn-Tucker (KKT) conditions. The numerical results show that the proposed scheme can effectively increase the secure computation task bits compared with other benchmark schemes, especially for the maximum transmit power of AP, the improvement is above 45 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> .

Visual Design and Evaluation of Public Space Scene Based on Virtual Reality Technology

Public space scenes are being transformed by virtual reality (VR) technology, offering immersive and interactive experiences that redefine how people engage with their surroundings. Through VR simulations, users can explore and interact with virtual public spaces in ways that were previously impossible. From virtual parks and plazas to digital replicas of iconic landmarks, VR technology allows users to experience the ambiance and atmosphere of public spaces from the comfort of their own homes. Moreover, VR enables designers and planners to experiment with different layouts, amenities, and features, facilitating participatory design processes and community engagement. This paper presents a visual design and evaluation framework for public space scenes using virtual reality (VR) technology, enhanced by Virtual Parallel Edge Hashing Computing (VPE-HC). The framework aims to optimize the design and user experience of public spaces by leveraging VR technology to create immersive and interactive simulations. Through simulated experiments and empirical validations, the effectiveness of the VPE-HC-enhanced VR-based design and evaluation process is evaluated. Results demonstrate significant improvements in user satisfaction, engagement, and usability compared to traditional design methods. For instance, users interacting with public space scenes designed using VPE-HC reported a 40% increase in perceived safety and a 25% improvement in overall satisfaction ratings. Additionally, the framework enabled designers to optimize spatial layouts and amenities based on real-time user feedback and performance data, leading to more effective and user-centric design solutions. These findings underscore the potential of VPE-HC in enhancing the visual design and evaluation of public space scenes based on VR technology, facilitating more inclusive and user-friendly urban environments.

Intelligent Talent Recommendation Algorithm for College Students for the Future Job Market

An intelligent talent recommendation algorithm is a sophisticated system that utilizes advanced data analysis techniques and machine learning algorithms to match individuals with suitable job opportunities or educational programs. By analyzing a wide range of data points such as skills, qualifications, work experience, and preferences, these algorithms can generate personalized recommendations tailored to each individual's unique profile and career goals. Moreover, intelligent talent recommendation algorithms continuously learn and improve over time, refining their recommendations based on user feedback and performance data. This paper presents an intelligent talent recommendation algorithm tailored for college students preparing for the future job market, utilizing Ranking Hidden Chain Deep Learning (RHC-DL). The algorithm aims to provide personalized recommendations by analysing students' skills, qualifications, interests, and career aspirations. Through simulated experiments and empirical validations, the efficacy of the RHC-DL-enhanced recommendation algorithm is evaluated. Results demonstrate significant improvements in recommendation accuracy and relevance compared to traditional methods. For instance, students using the RHC-DL algorithm reported a 40% increase in job offer acceptance rates and a 30% improvement in job satisfaction levels. Additionally, the algorithm adapts and learns from user interactions, continuously refining its recommendations based on real-time feedback.

Design of Visual Communication Experience Based on Virtual Reality Technology

Visual communication experiences have been revolutionized by virtual reality (VR) technology, offering users immersive and captivating interactions with digital content. Through VR headsets and immersive environments, users can engage with visual content in unprecedented ways, feeling as though they are physically present within the digital space. Whether exploring virtual art galleries, immersive storytelling experiences, or interactive visualizations, VR technology provides users with a sense of presence and agency, enhancing their connection to the content. Furthermore, VR enables creators to design highly engaging and interactive visual experiences that transcend traditional media formats, allowing for innovative storytelling techniques and immersive narratives. This paper presents the design of a novel visual communication experience leveraging virtual reality (VR) technology enhanced by Multi-Spectral Multi-Point Co-Ordination (MSMPC). The proposed design aims to create immersive and engaging visual experiences that transcend traditional media formats. Through simulated experiments and empirical validations, the effectiveness of the MSMPC-enhanced VR-based visual communication experience is evaluated. Results demonstrate significant improvements in user engagement, immersion, and satisfaction compared to conventional approaches. The users interacting with the MSMPC-enhanced VR experience reported a 40% increase in immersion levels and a 25% improvement in overall satisfaction ratings. Additionally, the design enabled creators to optimize visual storytelling techniques based on real-time user feedback and performance data, leading to more impactful and effective communication. These findings highlight the potential of MSMPC in enhancing visual communication experiences based on VR technology, paving the way for innovative and immersive storytelling in various domains.

A Study on Innovative Design Approaches for Implementing an Intelligent ICT-Based Smart Highway

This research, conducted over a three-year period starting from 2020, was a collaborative project between practitioners in the field of VE design and the Korea Expressway Corporation, aimed at innovating the design VE project to construct an intelligent ICT-based smart highway and enhancing highway driving performance and customer satisfaction.&#x0D; The research included R&amp;D support for payment and management systems integrated with IOT technology, the application of the developed prototype at highway sites, and analysis of user performance evaluation. Based on the Innovation Work Roadmap of the Korea Expressway Corporation, the research process involved collaboration between a public participation group and an expert group, considering the technical feasibility of data-based ICT technology through the National Idea VE Contest.&#x0D; The final VE design results were implemented at the Seongnam tollgate site with budget support from relevant departments, followed by a satisfaction survey. It is expected that the continuous contributions to achieving an ESG society, such as the increase in the number of customers using the tolling zone equipped with smart upgrades, along with their satisfaction rate, and the reduction in carbon emissions and total settlement time of highway users, will be sustained.