Task Analysis Research Articles

Compact convolutional transformer for subject-independent motor imagery EEG-based BCIs

Motor imagery electroencephalography (EEG) analysis is crucial for the development of effective brain-computer interfaces (BCIs), yet it presents considerable challenges due to the complexity of the data and inter-subject variability. This paper introduces EEGCCT, an application of compact convolutional transformers designed specifically to improve the analysis of motor imagery tasks in EEG. Unlike traditional approaches, EEGCCT model significantly enhances generalization from limited data, effectively addressing a common limitation in EEG datasets. We validate and test our models using the open-source BCI Competition IV datasets 2a and 2b, employing a Leave-One-Subject-Out (LOSO) strategy to ensure subject-independent performance. Our findings demonstrate that EEGCCT not only outperforms conventional models like EEGNet in standard evaluations but also achieves better performance compared to other advanced models such as Conformer, Hybrid s-CViT, and Hybrid t-CViT, while utilizing fewer parameters and achieving an accuracy of 70.12%. Additionally, the paper presents a comprehensive ablation study that includes targeted data augmentation, hyperparameter optimization, and architectural improvements.

Automatic Negation Detection for Semantic Analysis in Arabic Hotel Reviews Through Lexical and Structural Features: A Supervised Classification

One significant challenge in sentiment analysis is the presence of negation, which reverses the meanings of sentences, transformingpositive statements into negative ones and impacting the sentiment conveyed in the text. This issue is particularly pronounced in Arabic, a language known for its complex morphology. Detecting negation is crucial for enhancing sentiment analysis performance and various natural language processing applications. This paper presents an approach for automatically detecting negation in user-generated Arabic hotel reviews through lexical and structural features. It comprises several stages: data collection, text pre-processing, feature extraction, supervised learning classification, and evaluation. The study employed multiple supervised classification techniques, including naïve Bayes, random forest, logistic regression, support vector machines, and deep learning, to analyse lexical and structural features extracted from the dataset. The results of the experiments yielded promising outcomes, demonstrating the feasibility of the approach for practical applications. The classifiers exhibited highly comparable performance in identifying negation, with only marginal deviations in their performance metrics. Notably, the deep learning classifier consistently emerged as the top performer, achieving an exceptionally high overall accuracy rate of 99.24 percent, surpassing established benchmarks in Arabic text processing and underscoring its potential for practical applications. These findings hold significant implications for advancing Arabic text processing, particularly in sentiment analysis and related NLP tasks. The high accuracy of 99.24 percent achieved by the deep learning classifier highlights its robustness in accurately detecting negation, a critical challenge in sentiment analysis. This classifier performance demonstrates the potential to be integrated into real-world applications, such as automated review systems and opinion mining tools, where accurate sentiment interpretation is essential.

Leveraging Advanced Machine Learning Algorithms for Enhanced Cyberattack Detection on U.S. Business Networks

Cyberattacks' rising volume and sophistication have made conventional security measures, such as firewalls, signature-based intrusion detection systems, and antivirus software, increasingly inadequate. The upsurge of cyber threats has been one of the most pressing predicaments for U.S. organizations in the digital age. With the increased dependence on internet-based forums, cloud computing, and interconnected networks, companies face an advancing number of extreme cyberattacks. The chief objective of this research project is to design and deploy proven machine learning methods to enhance the detection and combating of cyberattacks on U.S. organization networks. This research project retrieved a cyber-attack dataset from Kaggle.com, which had a collection of public datasets of cyber threats. This dataset was curated precisely, offering a realistic representation of cyber-attack scenarios, making it an ideal playground for various analytical tasks. The collection was classified as per the source of the relevant information, such as host-based datasets, network traffic datasets, malware or fraud reports, or a special section for datasets that can be classified according to a specific source. The dataset comprised numerous network traffic attributes such as source and destination IP addresses, ports, protocol, payload size, and attack labels. For this research project, three machine learning algorithms were used, namely: Logistic Regression, XG-Boost and Random Forest. This research project applied performance metrics such as accuracy, precision, recall, and F1 score for the performance of the classification models were considered. The result illustrated that the random forest model was far superior in accuracy compared to the logistic regression model; particularly, it had excellent accuracy. Through the use of advanced machine learning models, organizations will be in a position to devise more dynamic and intelligent security systems that evolve with the threat landscape. These intelligent systems monitor every kind of anomaly, malicious activity, and threat response with unparalleled effectiveness. The findings of this research project have significant implications for enhancing cybersecurity in U.S. organizational networks.

COMPARATOR REGRESSION ANALYSIS IN CONDITIONS OF FUZZY INITIAL DATA

Abstract. The canonical task of regression analysis consists in studying the problem of estimation and mathematical description of the influence caused by one or more independent variables (predictors, explanatory variables) on the dependent (explained) variable. The subject of comparator identification problem is a specific modification of the standard regression analysis problem in the case when, for some reason, it is not possible to measure values of the dependent, explained variable. However, the problem of reconstructing a regression polynomial can be solved if it is possible to qualitatively compare the results of experiments and rank them, for example, in the order of increasing. Taking into account the results of ranking the values of the explained variable in different experiments, a corresponding system of inequalities is formed. The purpose of the research consists in developing a method for mathematical processing of the resulting system of inequalities for analytical assessment of the level of influence of explanatory variables on the explained variable. The method for solving the problem is based on transforming a system of inequalities into a system of linear algebraic equations. A significant drawback of the known approach to solving this problem consists in the fact that the resulting system of linear algebraic equations is an underdetermined one (the number of unknowns in this system exceeds the number of equations). At the same time, the system has an infinite number of solutions, among which there may be an uncontrollable number of unacceptable ones. The exhaustive search method for finding acceptable solutions is futile. In this regard, the problem of developing a correct method of comparator identification remains relevant. Another difficulty that accompanies the actual procedure of comparator identification when solving practical problems consists in the fact that measurements of values of the controlled parameters are not accurate. The uncertainty that arises in the conditions of a small sample of initial data can be removed using the tools of fuzzy mathematics. It is assumed that, based on preliminary research, a mathematical description of the corresponding membership function can be obtained for each of the controlled parameters. As a result, effective approaches to solving emerging problems have been proposed, based on the use of developed optimization procedures in the conditions of a small sample of fuzzy initial data.

Research on A Task-Based Teaching Model for Cruise Ship Professional English

This paper aims to explore a task-based teaching model for cruise professional English. By analyzing the development of the cruise industry and the current status of cruise professional English teaching, it reveals the existing problems and challenges in teaching. Based on this, a task-based teaching model is constructed, and the theoretical basis, task analysis and design, and specific implementation steps of the model are elaborated. The effectiveness of the teaching model is verified through empirical research, and targeted teaching suggestions are proposed. This study aims to provide new ideas and methods for cruise professional English teaching to improve teaching quality and effectiveness.

Evaluating Convolutional Neural Network Architecture for Historical Topographic Hardcopy Maps Analysis: A Study on Training and Validation Accuracy Variation

Convolutional Neural Networks (CNN) are widely used for image analysis tasks, including object detection, segmentation, and recognition. Given the advanced capability, this study evaluates the effectiveness and performance of CNN architecture for analysing Historical Topographic Hardcopy Maps (HTHM) by assessing variations in training and validation accuracy. The lack of research specifically dedicated to CNN’s application in analysing topographic hardcopy maps presents an opportunity to explore and address the unique challenges associated with this domain. While existing studies have predominantly focused on satellite imagery, this study aims to uncover valuable insights, patterns, and characteristics inherent to HTHM through customised CNN approaches. This study utilises a standard CNN architecture and tests the model’s performance with different epoch settings (20, 40, and 60) using varying dataset sizes (288, 636, 1144, and 1716 images). The results indicate that the optimal operation point for training and validation accuracy is achieved at epoch 40. Beyond epoch 40, the widening gap between training and validation accuracy suggests overfitting. Hence, adding more epochs does not significantly improve accuracy beyond the optimum phase. The experiment also shows that the CNN model obtains a training accuracy of 98%, validation accuracy of 67%, and F1-score overall performance of 77%. The analysis demonstrates that the CNN model performs reasonably well in classifying instances from the HTHM dataset. These findings contribute to a better understanding of the strengths and limitations of the model, providing valuable insights for future research and refinement of classification approaches in the context of topographic hardcopy map analysis.

CTARR: A fast and robust method for identifying anatomical regions on CT images via atlas registration

Medical image analysis tasks often focus on regions or structures located in a particular location within the patient’s body. Often large parts of the image may not be of interest for the image analysis task. When using deep-learning based approaches, this causes an unnecessary increases the computational burden during inference and raises the chance of errors. In this paper, we introduce CTARR, a novel generic method for CT Anatomical Re- gion Recognition. The method serves as a pre-processing step for any deep learning-based CT image analysis pipeline by automatically identifying the pre-defined anatomical region that is relevant for the follow-up task and removing the rest. It can be used in (i) image segmentation to prevent false positives in anatomically implausible regions and speeding up the inference, (ii) image classification to produce image crops that are consistent in their anatomical context, and (iii) image registration by serving as a fast pre-registration step. Our proposed method is based on atlas registration and provides a fast and robust way to crop any anatomical region encoded as one or multiple bounding box(es) from any unlabeled CT scan of the brain, chest, abdomen and/or pelvis. We demonstrate the utility and robustness of the proposed method in the context of medical image segmentation by evaluating it on six datasets of public segmentation challenges. The foreground voxels in the regions of interest are preserved in the vast majority of cases and tasks (97.45-100%) while taking only fractions of a seconds to compute (0.1-0.21s) on a deep learning worksta- tion and greatly reducing the segmentation runtime (2.0-12.7x). Our code is available at <a href='https://github.com/ThomasBudd/ctarr'>https://github.com/ThomasBudd/ctarr</a>

Investigation of Acoustic Voice Characteristics of Individuals Diagnosed with Muscle Tension Dysphonia.

Muscle tension dysphonia (MTD) is a functional voice condition that causes irregular and imbalanced laryngeal and paralaryngeal muscle activation. Our study aimed to examine the acoustic characteristics of patients with MTD and reveal the differences between genders. The study retrospectively reviewed the acoustic examination findings from the files of patients diagnosed with MTD during evaluations in the laryngology outpatient clinic at a tertiary reference hospital between 2015 and 2022. The parameters assessed in prolonged vowel phonation analysis were fundamental frequency (F0), jitter, shimmer, noise-to-harmonic-to-ratio, and soft phonation index; in the counting task analysis, they were intensity, frequency, and semitone. Gender differences in acoustic measurements obtained during prolonged vowel phonation and counting tasks were also examined. The study included 80 individuals diagnosed with MTD. Although all parameters in the acoustic analysis of/a/ phonation were increased, differences were statistically significant only in the F0 and jitter parameters between females and males (p≤0.05). In the analysis of the counting task, the mean and minimum F0 parameters were significantly higher in females than in males (p=0.000). The mean dB level was decreased, particularly in the counting task, but the results for the intensity parameter did not differ significantly between genders (p>0.05). The values in the acoustic voice analysis parameters of patients with MTD were determined. These acoustic parameters are thought to guide the clinician in evaluating voice and determining voice therapy goals for MTD patients.

Large language model-based optical network log analysis using LLaMA2 with instruction tuning

The optical network encompasses numerous devices and links, generating a significant volume of logs. Analyzing these logs is significant for network optimization, failure diagnosis, and health monitoring. However, the large-scale and diverse formats of optical network logs present several challenges, including the high cost and difficulty of manual processing, insufficient semantic understanding in existing analysis methods, and the strict requirements for data security and privacy. Generative artificial intelligence (GAI) with powerful language understanding and generation capabilities has the potential to address these challenges. Large language models (LLMs) as a concrete realization of GAI are well-suited for analyzing DCI logs, replacing human experts and enhancing accuracy. Additionally, LLMs enable intelligent interactions with network administrators, automating tasks and improving operational efficiency. Moreover, fine-tuning with open-source LLMs protects data privacy and enhances log analysis accuracy. Therefore, we introduce LLMs and propose a log analysis method with instruction tuning using LLaMA2 for log parsing, anomaly detection and classification, anomaly analysis, and report generation. Real log data extracted from the field-deployed network was used to design and construct instruction tuning datasets. We utilized the dataset for instruction tuning and demonstrated and evaluated the effectiveness of the proposed scheme. The results indicate that this scheme improves the performance of log analysis tasks, especially a 14% improvement in exact match rate for log parsing, a 13% improvement in F1-score for anomaly detection and classification, and a 23% improvement in usability for anomaly analysis, compared with the best baselines.

Diffusion MRI with Machine Learning

Abstract Diffusion-weighted magnetic resonance imaging (dMRI) of the brain offers unique capabilities including noninvasive probing of tissue microstructure and structural connectivity. It is widely used for clinical assessment of disease and injury, and for neuroscience research. Analyzing the dMRI data to extract useful information for medical and scientific purposes can be challenging. The dMRI measurements may suffer from strong noise and artifacts, and may exhibit high inter-session and inter-scanner variability in the data, as well as inter-subject heterogeneity in brain structure. Moreover, the relationship between measurements and the phenomena of interest can be highly complex. Recent years have witnessed increasing use of machine learning methods for dMRI analysis. This manuscript aims to assess these efforts, with a focus on methods that have addressed data preprocessing and harmonization, microstructure mapping, tractography, and white matter tract analysis. We study the main findings, strengths, and weaknesses of the existing methods and suggest topics for future research. We find that machine learning may be exceptionally suited to tackle some of the difficult tasks in dMRI analysis. However, for this to happen, several shortcomings of existing methods and critical unresolved issues need to be addressed. There is a pressing need to improve evaluation practices, to increase the availability of rich training datasets and validation benchmarks, as well as model generalizability, reliability, and explainability concerns.

A General Method for Resampling Autocorrelated Spatial Data

AbstractComparing spatial data sets is a ubiquitous task in data analysis, however the presence of spatial autocorrelation means that standard estimates of variance will be wrong and tend to over‐estimate the statistical significance of correlations and other observations. While there are a number of existing approaches to this problem, none are ideal, requiring detailed analytical calculations, which are hard to generalize or detailed modeling of the data generating process, which may not be straightforward. In this work we propose an approach based on permuting or resampling at fixed spatial autocorrelation, measured by Moran's I, in order to generate a null model that accounts for spatial dependence. Testing on real and synthetic data, we find that, as long as the spatial autocorrelation is not too strong, this approach works just as well as if we knew the data generating process exactly and allows us to compute P‐values with the correct Type‐I error rate.

Redefining retinal vessel segmentation: empowering advanced fundus image analysis with the potential of GANs

Retinal vessel segmentation is a critical task in fundus image analysis, providing essential insights for diagnosing various retinal diseases. In recent years, deep learning (DL) techniques, particularly Generative Adversarial Networks (GANs), have garnered significant attention for their potential to enhance medical image analysis. This paper presents a novel approach for retinal vessel segmentation by harnessing the capabilities of GANs. Our method, termed GANVesselNet, employs a specialized GAN architecture tailored to the intricacies of retinal vessel structures. In GANVesselNet, a dual-path network architecture is employed, featuring an Auto Encoder-Decoder (AED) pathway and a UNet-inspired pathway. This unique combination enables the network to efficiently capture multi-scale contextual information, improving the accuracy of vessel segmentation. Through extensive experimentation on publicly available retinal datasets, including STARE and DRIVE, GANVesselNet demonstrates remarkable performance compared to traditional methods and state-of-the-art deep learning approaches. The proposed GANVesselNet exhibits superior sensitivity (0.8174), specificity (0.9862), and accuracy (0.9827) in segmenting retinal vessels on the STARE dataset, and achieves commendable results on the DRIVE dataset with sensitivity (0.7834), specificity (0.9846), and accuracy (0.9709). Notably, GANVesselNet achieves remarkable performance on previously unseen data, underscoring its potential for real-world clinical applications. Furthermore, we present qualitative visualizations of the generated vessel segmentations, illustrating the network’s proficiency in accurately delineating retinal vessels. In summary, this paper introduces GANVesselNet, a novel and powerful approach for retinal vessel segmentation. By capitalizing on the advanced capabilities of GANs and incorporating a tailored network architecture, GANVesselNet offers a quantum leap in retinal vessel segmentation accuracy, opening new avenues for enhanced fundus image analysis and improved clinical decision-making.

Brexit references in UK financial disclosure discourse (2015-2017): a corpus study

Major political events become a dominant topic of the discussions in the countries involved, and various actors, often other than political parties, take a stance towards them. The withdrawal of the UK from the European Union as a result of the 2016 UK referendum was one of those, and a quite polarised atmosphere from supporters of both sides was observed in the UK and the rest of Europe since the referendum was announced in 2015. Based on the impact of the Brexit on the economy, this study focused into the financial domain of the UK, and the ways that UK financial services referred towards it in their financial disclosures before, during and just after the referendum. For that purpose, I collected the 2015, 2016 and 2017 annual reports from five UK-based financial companies (Barclays, HSBC, Lloyds, Royal Bank of Scotland and Santander UK), and I used thematic keywords to identify all the texts referring to the 2016 UK referendum, its outcome, and the response of the financial services to the exiting process of the UK from the European Union. This set of texts composed the Brexit-related data set, in which different analytical tasks were performed. I explored the context in which the thematic keywords are found, compared statistically the three yearly subsets of the corpus, and searched the significant words of the subset in terms of their keyness strength. This case study revealed that the discourse around a major political event such as Brexit cannot be considered as neutral or objective, and that financial companies clearly expressed negative opinion regarding the 2016 referendum and the UK’s decision to exit the European Union.

An applied cognitive task analysis investigation of professional judgement and decision-making in a small group of high-level, UK-based caving instructors

ABSTRACT The professional judgement and decision-making processes of adventure sports coaches’ leadership practice is a growing area of research. However, the PJDM and underpinning epistemology of caving instructors has recived limited research focus. The decision-making practice of professionals working in complex and constrained environments has significant transferability to domains such as rescue and emergency services. Consequently, this paper investigates the leadership practice of a purposive sample of 3 UK based caving instructors, utilising an Applied Cognitive Task Analysis to access expert cognition. The study aimed specifically to examine the decision-making processes of this sub-group of outdoor professionals who work in difficult, multifaceted and demanding environments. Results supported and built upon previous work in adventure sports, specifically in confirming the complexity of judgement and decision-making underground. In particular, decision-making creates high cognitive loads because of environmental factors inherent in extended caving journeys. Loads are assuaged by the application of heuristics and planning, but naturalistic decision-making processes remain numerous and multifaceted. Findings have implications for National Governing Body instructor training programme design, with particular reference to the development of decision-making expertise in complex environments.

Challenges of Translating Idiomatic Expressions: A Cross-Linguistic Analysis at a University in Hanoi, Vietnam

This study investigates the challenges students face when translating idiomatic expressions between English and Vietnamese and explores how linguistic and cultural factors influence the translation process. Utilizing a combination of translation task analysis and focus group discussions, the research reveals that students frequently rely on literal translations, resulting in inaccurate or nonsensical outcomes due to their inability to grasp the figurative meanings of idioms. Cultural mismatches, particularly the absence of equivalent expressions in Vietnamese, further complicate translation efforts, leading to significant misunderstandings. Additionally, linguistic barriers, such as syntactic differences between English and Vietnamese, hinder students' ability to produce natural and accurate translations of idiomatic expressions. The findings emphasize the critical role of cultural knowledge and syntactic flexibility in effective idiomatic translation. To address these challenges, the study recommends that translation training programs place greater emphasis on idiomatic understanding and cross-cultural competence. This study contributes to the growing body of literature on idiomatic translation by highlighting the interplay of linguistic and cultural factors and suggesting strategies to enhance translation accuracy.

Enhancing Learning Interest in the Collaborative Learning Practitioner Lecture: Training on Determining the Viscosity of Palm Kernel Oil (PKO)

This study aims to determine the effects in physical chemistry class with the workshop sessions on measuring PKO viscosity by CV. Bina Agro Mandiri. The effects are evaluated through the enhancing of student's learning interest in the Physical Chemistry II class in Chemistry Program of the Islamic University of Indonesia, which presents a good avenue for this investigation. The study was conducted by classroom, practical and online action. The data were analyzed using a pie chart. Findings showed that the implementation of the practical was able to increase the student's learning interests. Through case analysis tasks, students participate significantly in the teaching-learning process.

Estimation of Lower Limb Joint Angles Using sEMG Signals and RGB-D Camera.

Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST’s capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.

Development and Validation of a Laparoscopic Sacrocolpopexy Training Model.

Proper training is necessary to develop the highly specialized skills required to safely perform laparoscopic sacrocolpopexy. Currently, there is no validated training model for laparoscopic sacrocolpopexy that includes dissection of the presacral space, both vaginal and presacral mesh attachments, and peritoneal closure. This study aimed to create a procedure specific hierarchical task analysis for laparoscopic sacrocolpopexy and then develop and validate a corresponding laparoscopic sacrocolpopexy pelvic training model for the simulation environment. This was an observational simulation study that was divided into 5 phases: (1) development of hierarchical task analysis, (2) model construction, (3) participant recruitment and simulation testing, (4) reliability and validity testing, and (5) creation of a standard passing performance measure. Construct, face, and content validity were established for this model. According to the participating experts, the model was able to replicate the steps of presacral dissection, anterior vaginal and sacral mesh attachment, and peritoneal closure. Thirteen trainees and 5 experts completed the simulation, and all "agreed" or "strongly agreed" that the model seemed useful for improving suturing technique and learning the procedure. Additionally, a passing performance measure was determined through contrasting groups methodology. We developed a novel, reusable, and validated training model that can be utilized as a training resource for the many critical skills necessary to safely and efficiently perform laparoscopic sacrocolpopexy.

Network mutual information measures for graph similarity

A wide range of tasks in network analysis, such as clustering network populations or identifying anomalies in temporal graph streams, require a measure of the similarity between two graphs. To provide a meaningful data summary for downstream scientific analyses, the graph similarity measures used for these tasks must be principled, interpretable, and capable of distinguishing meaningful overlapping network structure from statistical noise at different scales of interest. Here we derive a family of graph mutual information measures that satisfy these criteria and are constructed using only fundamental information theoretic principles. Our measures capture the information shared among networks according to different encodings of their structural information, with our mesoscale mutual information measure allowing for network comparison under any specified network coarse-graining. We test our measures in a range of applications on real and synthetic network data, finding that they effectively highlight intuitive aspects of network similarity across scales in a variety of systems.