Task Success Research Articles

Heuristic evaluation and end-user testing of a machine learning-based lower-limb exercise training system for management of knee pain in individuals aged 55 years or over

ObjectiveUsing machine learning techniques, we have developed an interactive exercise training system to assist individuals aged 55 years or over with knee pain to perform lower-limb exercises to improve their knee health. The system has three features: video-based exercise demonstrations, real-time feedback on exercise movements, and tracking of exercise performance and progress. The current study aimed to evaluate the design of the computer prototype of the system, and determine its usability and end users’ intention to use it (i.e., acceptance of it). MethodsHeuristic evaluation and end-user testing of the computer-based prototype system were conducted. Three human factors practitioners identified the design deficiencies, with reference to 64 design principles. In addition, 10 individuals with knee pain were recruited to use the prototype system to complete five tasks in the study laboratory. We recorded and examined the task success rate, number of requests for assistance, difficulties encountered during tasks, and perceptions of usability and acceptance. ResultsFour design deficiencies were identified, regarding recognition and recovery of errors, navigation, auditory perception, and help documentation. Most participants had difficulty in calibrating the camera and performing exercises. However, in general, the prototype system was perceived as usable and acceptable. ConclusionsThe use of heuristic evaluation and end-user testing revealed the capacity to systematically detect design deficiencies in interactive self-help systems, allowing for effective system adjustments. Moreover, our system shows potential for individuals managing knee pain, but conducting iterative usability testing is necessary to identify additional improvements. Furthermore, several design propositions have been submitted.

SB-Net: Synergizing CNN and LSTM networks for uncovering retrosynthetic pathways in organic synthesis

Retrosynthesis is vital in synthesizing target products, guiding reaction pathway design crucial for drug and material discovery. Current models often neglect multi-scale feature extraction, limiting efficacy in leveraging molecular descriptors. Our proposed SB-Net model, a deep-learning architecture tailored for retrosynthesis prediction, addresses this gap. SB-Net combines CNN and Bi-LSTM architectures, excelling in capturing multi-scale molecular features. It integrates parallel branches for processing one-hot encoded descriptors and ECFP, merging through dense layers. Experimental results demonstrate SB-Net’s superiority, achieving 73.6 % top-1 and 94.6 % top-10 accuracy on USPTO-50k data. Versatility is validated on MetaNetX, with rates of 52.8 % top-1, 74.3 % top-3, 79.8 % top-5, and 83.5 % top-10. SB-Net’s success in bioretrosynthesis prediction tasks indicates its efficacy. This research advances computational chemistry, offering a robust deep-learning model for retrosynthesis prediction. With implications for drug discovery and synthesis planning, SB-Net promises innovative and efficient pathways.

Reinforcement learning for encouraging cooperation in a multiagent system

Success in cooperative tasks may be compromised if cooperative stagnation and failure from information sharing occur. However, information sharing may require excessive memory. Other methods must be developed to encourage agents to take actions in accordance with the needs of the team. In this study, a method called the cooperative tendency model using Q-learning (CTM-Q) is proposed for a partial-communication multiagent team. Each agent maintains and records its tendency values (encouraging cooperation) and Q-values (encouraging goal-seeking) as input for a payoff function that is used to select actions. Each agent selects the action with the highest payoff value for the current state. The method improves learning performance, enabling agents to rapidly reach a consensus. In simulations, the proposed method accelerated learning for multiagent cooperative applications and outperformed competing methods in solution speed, convergence time, and stability.

To Abstract or Not to Abstract? A Comparative Study Evaluating the User Experience of Spreadsheet Programming with Sheet-Defined Functional Abstractions

Spreadsheets are a widespread functional programming paradigm that offer liveness and directness of interaction. However, spreadsheets are notoriously error-prone and difficult to debug. To overcome this limitation and improve the expressive power of spreadsheets, we propose an extension to the spreadsheet paradigm in the form of sheet-defined lambdas – user-defined functions that abstract computations on the sheet. This concept was developed and deployed in our web-based spreadsheet application named Lattice. We evaluate this approach through a user study which compared the user experience of programming in a spreadsheet with and without lambdas, as well as the difference in performance between learner (N = 12) and experienced (N = 12) programmers. The study measured participant task performance (task time, success rate and number of errors) and the quality of their user experience of using Lattice (video recordings of use, interviews and questionnaire responses). Our findings indicate that programming with lambdas is not only more efficient than writing formulas in a conventional way, but also provides a rewarding hedonic experience. However, we found that learners perceived the concept of functional abstractions with lambdas as difficult to comprehend; while experienced programmers noted potential utilitarian advantages that aid in managing the complexity of a spreadsheet program. The results obtained in this work contribute to a better understanding of human-spreadsheet interaction and can inform the future design of user-friendly computational systems.

A Hybrid Genetic Algorithm for Ground Station Scheduling Problems

In recent years, the substantial growth in satellite data transmission tasks and volume, coupled with the limited availability of ground station hardware resources, has exacerbated conflicts among missions and rendered traditional scheduling algorithms inadequate. To address this challenge, this paper introduces an improved tabu genetic hybrid algorithm (ITGA) integrated with heuristic rules for the first time. Firstly, a constraint satisfaction model for satellite data transmission tasks is established, considering multiple factors such as task execution windows, satellite–ground visibility, and ground station capabilities. Leveraging heuristic rules, an initial population of high-fitness chromosomes is selected for iterative refinement. Secondly, the proposed hybrid algorithm iteratively evolves this population towards optimal solutions. Finally, the scheduling plan with the highest fitness value is selected as the best strategy. Comparative simulation experimental results demonstrate that, across four distinct scenarios, our algorithm achieves improvements in the average task success rate ranging from 1.5% to 19.8% compared to alternative methods. Moreover, it reduces the average algorithm execution time by 0.5 s to 28.46 s and enhances algorithm stability by 0.8% to 27.7%. This research contributes a novel approach to the efficient scheduling of satellite data transmission tasks.

An effectual recommendation model using hybrid learning models for early detection of Alzheimer’s disease

Alzheimer’s disease (AD) is a neurodegenerative disorder that affects millions of individuals worldwide, causing progressive cognitive decline. Early prediction and diagnosis the AD accurately is crucial for effective intervention and treatment. In this study, we propose a comprehensive framework for AD prediction using various techniques, including preprocessing and denoising with Multilayer Perceptron (MLP) and Ant Colony Optimization (ACO), segmentation using U-Net, and classification with Spatial Pyramid Pooling Network (SPPNet). Furthermore, we employ Convolutional Neural Network (CNN) with SPPNet for training and develop a chatbot for recommendation based on MRI data input. The preprocessing and denoising techniques play a vital role in enhancing the quality of the input data. MLP is utilized for preprocessing, where it effectively handles feature extraction and noise reduction. ACO is employed for denoising, optimizing the data to improve the signal-to-noise ratio, and enhancing the overall performance of subsequent stages. For accurate segmentation of brain regions, we employ the U-Net architecture, which has shown remarkable success in medical image segmentation tasks. U-Net effectively identifies the regions of interest, aiding in subsequent classification stages. The classification phase utilizes SPPNet, a deep learning model known for its ability to capture spatial information at multiple scales. SPPNet extracts features from segmented brain regions, enabling robust classification of AD and non-AD cases. To enhance the training process, we employ CNN with SPPNet, leveraging the power of convolutional layers to capture intricate patterns and improve predictive accuracy. The CNN-SPPNet model is trained on a large dataset of MRI scans, enabling it to learn complex representations and make accurate predictions. Hence the proposed work can be integrated with a chatbot that takes MRI data as input and provides recommendations based on the predicted AD probability. Experimental evaluation shows that the combination of preprocessing, denoising, segmentation, and classification offers a comprehensive solution for accurate and efficient AD diagnosis and management.

Smartwatch-Based Interventions for People With Dementia: User-Centered Design Approach.

Assistive technologies can help people living with dementia maintain their everyday activities. Nevertheless, there is a gap between the potential and use of these materials. Involving future users may help close this gap, but the impact on people with dementia is unclear. We aimed to determine if user-centered development of smartwatch-based interventions together with people with dementia is feasible. In addition, we evaluated the extent to which user feedback is plausible and therefore helpful for technological improvements. We examined the interactions between smartwatches and people with dementia or people with mild cognitive impairment. All participants were prompted to complete 2 tasks (drinking water and a specific cognitive task). Prompts were triggered using a smartphone as a remote control and were repeated up to 3 times if participants failed to complete a task. Overall, 50% (20/40) of the participants received regular prompts, and 50% (20/40) received intensive audiovisual prompts to perform everyday tasks. Participants' reactions were observed remotely via cameras. User feedback was captured via questionnaires, which included topics like usability, design, usefulness, and concerns. The internal consistency of the subscales was calculated. Plausibility was also checked using qualitative approaches. Participants noted their preferences for particular functions and improvements. Patients struggled with rating using the Likert scale; therefore, we assisted them with completing the questionnaire. Usability (mean 78 out of 100, SD 15.22) and usefulness (mean 9 out of 12) were rated high. The smartwatch design was appealing to most participants (31/40, 76%). Only a few participants (6/40, 15%) were concerned about using the watch. Better usability was associated with better cognition. The observed success and self-rated task comprehension were in agreement for most participants (32/40, 80%). In different qualitative analyses, participants' responses were, in most cases, plausible. Only 8% (3/40) of the participants were completely unaware of their irregular task performance. People with dementia can have positive experiences with smartwatches. Most people with dementia provided valuable information. Developing assistive technologies together with people with dementia can help to prioritize the future development of functional and nonfunctional features.

Enhancing Medical Image Retrieval with UMLS-Integrated CNN-Based Text Indexing.

In recent years, Convolutional Neural Network (CNN) models have demonstrated notable advancements in various domains such as image classification and Natural Language Processing (NLP). Despite their success in image classification tasks, their potential impact on medical image retrieval, particularly in text-based medical image retrieval (TBMIR) tasks, has not yet been fully realized. This could be attributed to the complexity of the ranking process, as there is ambiguity in treating TBMIR as an image retrieval task rather than a traditional information retrieval or NLP task. To address this gap, our paper proposes a novel approach to re-ranking medical images using a Deep Matching Model (DMM) and Medical-Dependent Features (MDF). These features incorporate categorical attributes such as medical terminologies and imaging modalities. Specifically, our DMM aims to generate effective representations for query and image metadata using a personalized CNN, facilitating matching between these representations. By using MDF, a semantic similarity matrix based on Unified Medical Language System (UMLS) meta-thesaurus, and a set of personalized filters taking into account some ranking features, our deep matching model can effectively consider the TBMIR task as an image retrieval task, as previously mentioned. To evaluate our approach, we performed experiments on the medical ImageCLEF datasets from 2009 to 2012. The experimental results show that the proposed model significantly enhances image retrieval performance compared to the baseline and state-of-the-art approaches.

Neighbors selective Graph Convolutional Network for homophily and heterophily

Graph Convolutional Networks (GCNs) gain remarkable success in graph-related tasks under homophily graph assumption—most connected nodes have the same label. However, this assumption is fragile since heterophily is common in real-world networks, where most linked nodes have different labels. Some methods address heterophily using graph-level weighted combinations of multi-hop neighbor representations. However, they introduce noise and irrelevant information from two aspects: (1) higher-order neighborhoods may include more neighbors with different labels than those with the same label; (2) graph-level weighted combination fails to capture distinct node properties. To address these issues, firstly, a Neighborhood Distribution-induced Similarity (NDS) measure is developed to identify potential similar neighbors for nodes. Secondly, a node-level fusion mechanism Selective-Neighbors Gated Unit (SNGU) is designed to adaptively aggregate potential neighbors, first-hop neighbors, and the node itself by learning distinct weights for nodes. By combining the above two designs, this work proposes a novel Neighbors Selective Graph Convolutional Network (NSGCN), which allows nodes to selectively receive relevant neighbor information for better node representations, effectively modeling homophily and heterophily. Experiments on 10 widely used real-world datasets with varying properties demonstrate the superiority of the NSGCN, surpassing a strong baseline with an absolute increase of 9.83% in classification accuracy. The code is available at https://github.com/GGA23/NSGCN.

Cost-aware task offloading in vehicular edge computing: A Stackelberg game approach

With the popularity of vehicular communication systems and mobile edge vehicle networking, intelligent transportation applications arise in Internet of Vehicles (IoVs), which are latency-sensitive, computation-intensive, and requiring sufficient computing and communication resources. To satisfy the requirements of these applications, computation offloading emerges as a new paradigm to utilize idle resources on vehicles to cooperatively complete tasks. However, there exist several obstacles for realizing successful task offloading among vehicles. For one thing, extra cost such as communication overhead and energy consumption occurs when a task is offloaded on a service vehicle, it is unlikely to expect the service vehicle will contribute its resources without any reward. For another, since there are many vehicles around, both user vehicles and service vehicles are trying to strike a balance between cost and profit, through matching the perfect service/user vehicles and settled with optimal offloading plan that is beneficial to all parties. To solve these issues, this work focuses on the design of effective incentive mechanisms to stimulate vehicles with idle resources to actively participate in the offloading process. A fuzzy logic-based dynamic pricing strategy is proposed to accurately evaluate the cost of a vehicle for processing the task, which provides insightful guidance for finding the optimal offloading decision. Meanwhile, the competitive and cooperation relations among vehicles are thoroughly investigated and modeled as a two-stage Stackelberg game. Particularly, this work emphasizes the social attributes of vehicles and their effect on the offloading decision making process, multiple key properties such as the willingness of UV to undertake the task locally, the reputation of UV and the satisfaction of SV for the allocated task proportion, are carefully integrated in the design of the optimization problem. A distributed algorithm with applicable complexity is proposed to solve the problem and to find the optimal task offloading strategy. Extensive simulations are conducted on real-world scenarios and results show that the proposed mechanism achieves significant performance advantages in terms of vehicles' utilities, cost, completion delay under varied network and channel environment, which justifies the effectiveness and efficiency of this work.

Multiobjective Evolutionary Generative Adversarial Network Compression for Image Translation

Generative Adversarial Networks (GANs) have achieved remarkable success in image translation tasks. However, its prohibitive computational overhead has been a major hurdle for deployment on resource constrained platforms. Due to the training instability and the complicated network architecture, existing model acceleration techniques cannot appropriately handle the GAN compression problem. To cope with these difficulties, we propose a multi-objective evolutionary algorithm to compress GAN models in the context of image translation tasks, which is termed as MEGC. Particularly, the conflict between the computational cost of the GAN model and the quality of generated image is explicitly modeled as a two-objective optimization problem, and the evolved Pareto set is utilized to guide the sampling process during supernet training, which can in turn divert the focus of the supernet training to well-performing compact subnets. Besides, an evaluation-free strategy is introduced to facilitate exploration in the search space while incurring no extra computational cost. Based on the above design, the proposed MEGC eliminates the requirement of subnet searching in the post-processing procedure. Experiments on image translation tasks under paired and unparied settings demonstrate the effectiveness of the proposed MEGC on reducing the computational cost of GANs while improving the quality of generated images compared to those of the full models.

Learning Graph Representations Through Learning and Propagating Edge Features.

Graph convolutional networks have achieved considerable success in various graph domain tasks. Recently, numerous types of graph convolutional networks have been developed. A typical rule for learning a node's feature in these graph convolutional networks is to aggregate node features from the node's local neighborhood. However, in these models, the interrelation information between adjacent nodes is not well-considered. This information could be helpful to learn improved node embeddings. In this article, we present a graph representation learning framework that generates node embeddings through learning and propagating edge features. Instead of aggregating node features from a local neighborhood, we learn a feature for each edge and update a node's representation by aggregating local edge features. The edge feature is learned from the concatenation of the edge's starting node feature, the input edge feature, and the edge's end node feature. Unlike node feature propagation-based graph networks, our model propagates different features from a node to its neighbors. In addition, we learn an attention vector for each edge in aggregation, enabling the model to focus on important information in each feature dimension. By learning and aggregating edge features, the interrelation between a node and its neighboring nodes is integrated in the aggregated feature, which helps learn improved node embeddings in graph representation learning. Our model is evaluated on graph classification, node classification, graph regression, and multitask binary graph classification on eight popular datasets. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

Alzheimer’s Disease Diagnosis via SVM-Driven Classification of Structural MRI Data

Abstract: In this study we introduce an automated system designed to classify Alzheimers disease (AD) using MRI brain scans. Our technique employs support vector machine (SVM) classification to effectively differentiate between AD patients and older adults without the disease by analyzing brain MRI images. The process includes dividing 2D T1 weighted MR images into regions of interest and extracting gray matter characteristics, from each region. By leveraging SVMs reliability and proven success in classification tasks along with the principle of minimizing risks our research showcases performance in generalizing results. This SVM based approach shows promise in distinguishing AD affected brains from ones presenting a valuable opportunity, for enhancing medical analysis and interpretation of MRI findings.

SKATE : Successive Rank-based Task Assignment for Proactive Online Planning

SKATE : Successive Rank-based Task Assignment for Proactive Online Planning

Success in the Natural Detection Task is influenced by only a few factors generally believed to affect dogs’ olfactory performance

Research into dogs' olfactory ability is growing rapidly. However, generalising based on scientific results is challenging, because research has been typically conducted on a few specially trained subjects of a few breeds tested in different environmental conditions. We investigated the effects of temperature and humidity (outdoors), age, test location, sex, neutering status, and repeated testing (outdoors and indoors) on the olfactory performance of untrained family dogs (N = 411) of various breeds. We employed the Natural Detection Task with three difficulty levels, from which we derived two performance metrics: Top Level and Success Score. Temperature (0–25 °C) and humidity (18–90%) did not affect olfactory performance. Young adult dogs surpassed other age groups in reaching the Top Level. Sex and neutering status showed no discernible influence on Top Level and Success Score. Dogs performed better in both metrics when tested indoors compared to outdoors. In the test–retest procedure no significant learning effect was observed. We confirmed on untrained companion dogs that olfactory performance declines with age and rejected some factors that have been previously hypothesised to significantly affect dogs’ olfactory success. The influence of the testing environment was notable, emphasising the need to consider various factors in understanding dogs' olfactory capabilities.

Indoor Localization and Path Planning of Mobile Disinfection and Epidemic Prevention Robot

Introduction: In response to the challenge of autonomous localization and navigation for mobile disinfection robots in unknown environments during the COVID-19 pandemic based on the existing patent technology of mobile robots, a localization and navigation approach combining the Cartographer-Simultaneous Localization and Mapping (SLAM) algorithm, an improved A* algorithm, and the Dynamic Window Approach (DWA) has been proposed, enabling effective disinfection and prevention work. Method: First, a comprehensive analysis of two laser SLAM algorithm frameworks, Gmapping- SLAM and Cartographer-SLAM, was conducted, which determined the Cartographer algorithm as the optimal SLAM algorithm for the mobile disinfection robot due to its superior performance. Second, an improved A* algorithm was developed based on its principles and integrated with the DWA algorithm for optimal path planning. Result: Simulation and prototype experiments demonstrated that the proposed approach effectively solved the autonomous localization and navigation challenges faced by mobile disinfection robots in unknown environments, enabling successful disinfection and prevention tasks. Conclusion: The proposed approach has the potential to lead to new patent applications in this field.

The essence of motivation in learning English as a foreign or second language

This research paper investigates recent studies on the role of motivation in second or foreign language acquisition. Motivation is identified as a critical determinant of success or failure in complex tasks. The paper offers academic definitions of motivation, categorizes different types of motivation, and revisits prior research on its significance in language learning. It also outlines the essential requirements and key aspects of motivation. The literature review underscores the pivotal role of motivation in learning English as a second or foreign language, revealing that motivation significantly enhances language learning outcomes. The findings emphasize that fostering motivation is essential for achieving effective and successful language acquisition. This comprehensive examination provides valuable insights into how motivation can be leveraged to improve language learning processes and outcomes. Keywords: English as a foreign language; impact; motivation; second language.

An Imaging-Compatible Oral Retractor System for Transoral Robotic Surgery.

This study aimed to develop and validate a Computed Tomography (CT)/Magnetic Resonance Imaging(MRI)-compatible polymer oral retractor system to enable intraoperative image guidance for transoral robotic surgery (TORS). The retractor was designed based on standard-of-care metallic retractors and 3D (three-dimensional) printed with carbon fiber composite and nylon. The system was comprehensively evaluated in bench-top and cadaveric experiments in terms of its ability to enable intraoperative CT/MR images during TORS, functionality including surgical exposure and working volume, usability, compatibility with da Vinci surgical systems, feasibility for disinfection or sterilization, and robustness over an extended period of time. The polymer retractor system enabled the acquisition of high-resolution and artifact-free intraoperative CT/MR images during TORS. With an inter-incisive distance of 42.55mm and a working volume of 200.09cm3, it provided surgical exposure comparable to standard-of-care metallic retractors. The system proved intuitive and compatible with da Vinci S, Xi, and Single Port systems, enabling successful mock surgical tasks performed by surgeons and residents. The retractor components could be effectively disinfected or sterilized for clinical use without significant compromise in material strength, with STERRAD considered the optimal method. Throughout a 2h mock procedure, the retractor system showed minimal displacements (<1.5mm) due to surrounding tissue deformation, with insignificant device deformation. The 3D-printed polymer retractor system successfully enabled artifact-free intraoperative CT/MR imaging in TORS for the first time and demonstrated feasibility for clinical use. This breakthrough opens the door to surgical navigation with intraoperative image guidance in TORS, offering the potential to significantly improve surgical outcomes and patients' quality of life.

MDCNet: Long-term time series forecasting with mode decomposition and 2D convolution

Long-term time series forecasting is widely used in various real-world applications, such as weather, traffic, energy, healthcare, etc. Recently, time series decomposition techniques have been adopted in many mainstream forecasting models, such as the prevalent Transformer-based models, to help capture sophisticated temporal patterns and achieve success in several benchmark tasks. However, conventional decomposition algorithms are often based on simple operations or limited to specific fields, and therefore are not effective and applicable enough, especially for complex time series. In this paper, we propose Mode Decomposition and 2D Convolutional Network (MDCNet), a structure-simple yet effective forecasting architecture based on a more effective decomposition method and a multi-frequency time series feature extraction network with multi-scale 2D convolution. Specifically, we first introduce a Variational Mode Decomposition Block to discover intricate time patterns, which decompose time series into trend components and stationary modal components at different main frequencies. Then, we design a Trend Prediction Block and an Intrinsic Mode Functions Prediction Block to capture global correlation and hidden dependencies within different main frequencies, respectively. Furthermore, a Frequency Enhancement Module is designed to further reduce the impact of noise in long-term time series. Experiments on eight benchmark datasets show that MDCNet significantly reduces the error of the previous state-of-the-art method by 15.1% and 11.5% for multivariate and univariate time series, respectively.

Structure enhanced prototypical alignment for unsupervised cross-domain node classification

Graph Neural Networks (GNNs) have demonstrated remarkable success in graph node classification task. However, their performance heavily relies on the availability of high-quality labeled data, which can be time-consuming and labor-intensive to acquire for graph-structured data. Therefore, the task of transferring knowledge from a label-rich graph (source domain) to a completely unlabeled graph (target domain) becomes crucial. In this paper, we propose a novel unsupervised graph domain adaptation framework called Structure Enhanced Prototypical Alignment (SEPA), which aims to learn domain-invariant representations on non-IID (non-independent and identically distributed) data. Specifically, SEPA captures class-wise semantics by constructing a prototype-based graph and introduces an explicit domain discrepancy metric to align the source and target domains. The proposed SEPA framework is optimized in an end-to-end manner, which could be incorporated into various GNN architectures. Experimental results on several real-world datasets demonstrate that our proposed framework outperforms recent state-of-the-art baselines with different gains.