Task Analysis Research Articles

Do domain-specific protein language models outperform general models on immunology-related tasks?

Deciphering the antigen recognition capabilities by T-cell and B-cell receptors (antibodies) is essential for advancing our understanding of adaptive immune system responses. In recent years, the development of protein language models (PLMs) has facilitated the development of bioinformatic pipelines where complex amino acid sequences are transformed into vectorized embeddings, which are then applied to a range of downstream analytical tasks. With their success, we have witnessed the emergence of domain-specific PLMs tailored to specific proteins, such as immune receptors. Domain-specific models are often assumed to possess enhanced representation capabilities for targeted applications, however, this assumption has not been thoroughly evaluated. In this manuscript, we assess the efficacy of both generalist and domain-specific transformer-based embeddings in characterizing B and T-cell receptors. Specifically, we assess the accuracy of models that leverage these embeddings to predict antigen specificity and elucidate the evolutionary changes that B cells undergo during an immune response. We demonstrate that the prevailing notion of domain-specific models outperforming general models requires a more nuanced examination. We also observe remarkable differences between generalist and domain-specific PLMs, not only in terms of performance but also in the manner they encode information. Finally, we observe that the choice of the size and the embedding layer in PLMs are essential model hyperparameters in different tasks. Overall, our analyzes reveal the promising potential of PLMs in modeling protein function while providing insights into their information-handling capabilities. We also discuss the crucial factors that should be taken into account when selecting a PLM tailored to a particular task.

Negation handling for sentiment analysis task: approaches and performance analysis

Negation plays an essential role in sentiment analysis within natural language processing (NLP). Its integration involves two key aspects: identifying the scope of negation and incorporating this information into the sentiment model. Before delving into scope detection, the specific negation cue must be identified, with explicit and implicit negation cues being the two main types. Various methodologies, such as rule-based, machine learning, and hybrid approaches, address the negation scope detection challenge. Strategies for leveraging negation information in sentiment models encompass heuristic polarity modification, feature space augmentation, end-to-end approach, and hierarchical multi-task learning. Notably, there is a need for more studies addressing implicit negation cue detection, even within the state-of-the-art bidirectional encoder representation for transformers (BERT) approach. Some studies have employed reinforcement learning and hybrid techniques to address the implicit negation problem. Further exploration, particularly through a hybrid and multi-task learning approach, is warranted to make potential contributions to the nuanced challenges of handling negation in sentiment analysis, especially in complex sentence structures.

Combining unsupervised and supervised learning in microscopy enables defect analysis of a full 4H-SiC wafer

AbstractDetecting and analyzing various defect types in semiconductor materials is an important prerequisite for understanding the underlying mechanisms and tailoring the production processes. Analysis of microscopy images that reveal defects typically requires image analysis tasks such as segmentation and object detection. With the permanently increasing amount of data from experiments, handling these tasks manually becomes more and more impossible. In this work, we combine various image analysis and data mining techniques to create a robust and accurate, automated image analysis pipeline for extracting the type and position of all defects in a microscopy image of a KOH-etched 4H-SiC wafer. Graphical abstract

A Survey of Adversarial Attacks: An Open Issue for Deep Learning Sentiment Analysis Models

In recent years, the use of deep learning models for deploying sentiment analysis systems has become a widespread topic due to their processing capacity and superior results on large volumes of information. However, after several years’ research, previous works have demonstrated that deep learning models are vulnerable to strategically modified inputs called adversarial examples. Adversarial examples are generated by performing perturbations on data input that are imperceptible to humans but that can fool deep learning models’ understanding of the inputs and lead to false predictions being generated. In this work, we collect, select, summarize, discuss, and comprehensively analyze research works to generate textual adversarial examples. There are already a number of reviews in the existing literature concerning attacks on deep learning models for text applications; in contrast to previous works, however, we review works mainly oriented to sentiment analysis tasks. Further, we cover the related information concerning generation of adversarial examples to make this work self-contained. Finally, we draw on the reviewed literature to discuss adversarial example design in the context of sentiment analysis tasks.

Exploring the development of ‘understanding’ in high-level youth soccer players

ABSTRACT Background Developing understanding, and tactical understanding in particular, is an important goal for coaches in high-level youth sport. Deeper understanding can be associated with metacognition, which in soccer, is suggestive of players who can outwit the opponent by strategising. Although attractive, however, the construct is difficult to operationalise and hence, is seen as a challenging area, albeit a crucial one. Purposes This study tested how one team of under 13–14 academy players’ depth of understanding changed using a mixed methods approach with data collection over 18-months. Methods Players’ (n = 10) experienced a metacognitive coaching method, Digital Video Game Design (DVGD) throughout the study duration. Testing occurred on four occasions using Applied Cognitive Task Analysis (ACTA) to elicit how player thinking when playing evolved, combined with a Game Understanding (GU) comparative rating scale. In parallel, players’ coaches (n = 3) completed quantitative measurement of GU. Quantitative data analysis employed a repeated measures ANOVA whilst. Qualitative analysis of ACTA interviews used a deductive framework focussed on metacognitive skills and strategy. Findings Players’ depth of understanding significantly improved during and post exposure to the metacognitive coaching method. Post the initial intervention, understanding showed further improvements at a steady but not significant rate. Qualitative findings indicated that players’ metacognition became more sophisticated, with a particular improvement in strategising based on team mates and opponent’s capabilities. The most dominant metacognitive skills were planning and problem setting, whilst information gathering was least deployed. Conclusions Results show that young players are capable of rapidly developing metacognitive skills and strategy. Sports should upskill their coach education workforce to enhance their understanding of metacognition and its role within GU.

X-LoRA: Mixture of low-rank adapter experts, a flexible framework for large language models with applications in protein mechanics and molecular design

We report a mixture of expert strategy to create fine-tuned large language models using a deep layer-wise token-level approach based on low-rank adaptation (LoRA). Starting with a set of pre-trained LoRA adapters, our gating strategy uses the hidden states to dynamically mix adapted layers, allowing the resulting X-LoRA model to draw upon different capabilities and create never-before-used deep layer-wise combinations to solve tasks. The design is inspired by the biological principles of universality and diversity, where neural network building blocks are reused in different hierarchical manifestations. Hence, the X-LoRA model can be easily implemented for any existing large language model without a need for modifications of the underlying structure. We develop a tailored X-LoRA model that offers scientific capabilities, including forward/inverse analysis tasks and enhanced reasoning capability, focused on biomaterial analysis, protein mechanics, and design. The impact of this work includes access to readily expandable and adaptable models with strong domain knowledge and the capability to integrate across areas of knowledge. Featuring experts in biology, mathematics, reasoning, bio-inspired materials, mechanics and materials, chemistry, protein biophysics, mechanics, and quantum-mechanics based molecular properties, we conduct a series of physics-focused case studies. We examine knowledge recall, protein mechanics forward/inverse tasks, protein design, adversarial agentic modeling including ontological knowledge graph construction, and molecular design. The model is capable not only of making quantitative predictions of nanomechanical properties of proteins or quantum mechanical molecular properties but also reasoning over the results and correctly predicting likely mechanisms that explain distinct molecular behaviors.

Anticipating Trends and Innovations for A Sustainable Automotive Industrial Revolution

Graph classification aims to predict the label associated with a graph and is an important graph analytic task with widespread applications. Recently, graph neural networks (GNNs) have achieved state-of-the-art results on purely supervised graph classification by virtue of the powerful representation ability of neural networks. However, almost all of them ignore the fact that graph classification usually lacks reasonably sufficient labelled data in practical scenarios due to the inherent labelling difficulty caused by the high complexity of graph data. The existing semi-supervised GNNs typically focus on the task of node classification and are incapable of dealing with graph classification. To tackle the challenging but practically useful scenario, we propose a novel and general semi-supervised GNN framework for graph classification, which takes full advantage of a slight amount of labelled graphs and abundant unlabelled graph data. In our framework, we train two GNNs as complementary views for collaboratively learning high-quality classifiers using both labelled and unlabelled graphs. To further exploit the view itself, we constantly select pseudo-labelled graph examples with high confidence from its own view for enlarging the labelled graph dataset and enhancing predictions on graphs. Furthermore, the proposed framework is investigated on two specific implementation regimes with a few labelled graphs and the extremely few labelled graphs, respectively. Extensive experimental results demonstrate the effectiveness of our proposed semi-supervised GNN framework for graph classification on several benchmark datasets

Dependency-aware deep generative models for multitasking analysis of spatial omics data.

Spatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations. spaVAE introduces a hybrid embedding combining a Gaussian process prior with a Gaussian prior to explicitly capture spatial correlations among spots. It then optimizes the parameters of deep neural networks to approximate the distributions underlying the SRT data. With the approximated distributions, spaVAE can contribute to several analytical tasks that are essential for SRT data analysis, including dimensionality reduction, visualization, clustering, batch integration, denoising, differential expression, spatial interpolation, resolution enhancement and identification of spatially variable genes. Moreover, we have extended spaVAE to spaPeakVAE and spaMultiVAE to characterize spatial ATAC-seq (assay for transposase-accessible chromatin using sequencing) data and spatial multi-omics data, respectively.

Advancements in Korean Emotion Classification: A Comparative Approach Using Attention Mechanism

Recently, the analysis of emotions in social media has been considered a significant NLP task in digital and social-media-driven environments due to their pervasive influence on communication, culture, and consumer behavior. In particular, the task of Aspect-Based Emotion Analysis (ABEA), which involves analyzing the emotions of various targets within a single sentence, has drawn attention to understanding complex and sophisticated human language. However, ABEA is a challenging task in languages with limited data and complex linguistic properties, such as Korean, which follows spiral thought patterns and has agglutinative characteristics. Therefore, we propose a Korean Target-Attention-Based Emotion Classifier (KOTAC) designed to utilize target information by unveiling emotions buried within intricate Korean language patterns. In the experiment section, we compare various methods of utilizing and representing vectors of target information for the attention mechanism. Specifically, our final model, KOTAC, shows a performance enhancement on the MTME (Multiple Targets Multiple Emotions) samples, which include multiple targets and distinct emotions within a single sentence, achieving a 0.72% increase in F1 score over a baseline model without effective target utilization. This research contributes to the development of Korean language models that better reflect syntactic features by innovating methods to not only obtain but also utilize target-focused representations.

Identification and Classification of Bilingual Language using Natural Language Processing

This paper presents an efficient approach to language detection and sentiment analysis using Naive Bayes classifiers. The research involves training classifiers on a diverse dataset of text samples in multiple languages. Our method employs vectorization techniques and separate classifiers for language detection and sentiment analysis tasks. Experimental results demonstrate the effectiveness of the classifiers, with high accuracy in identifying the language and sentiment of input text. The approach showcases notable efficiency in processing language detection and sentiment analysis, addressing the growing need for automated text processing solutions. The findings have implications for various domains, including customer feedback analysis, market research, and opinion Mining

Can LLMs Answer Investment Banking Questions? Using Domain-Tuned Functions to Improve LLM Performance on Knowledge-Intensive Analytical Tasks

Large Language Models (LLMs) can increase the productivity of general-purpose knowledge work, but accuracy is a concern, especially in professional settings requiring domain-specific knowledge and reasoning. To evaluate the suitability of LLMs for such work, we developed a benchmark of 16 analytical tasks representative of the investment banking industry. We evaluated LLM performance without special prompting, with relevant information provided in the prompt, and as part of a system giving the LLM access to domain-tuned functions for information retrieval and planning. Without access to functions, state-of-the-art LLMs performed poorly, completing two or fewer tasks correctly. Access to appropriate domain-tuned functions yielded dramatically better results, although performance was highly sensitive to the design of the functions and the structure of the information they returned. The most effective designs yielded correct answers on 12 out of 16 tasks. Our results suggest that domain-specific functions and information structures, by empowering LLMs with relevant domain knowledge and enabling them to reason in domain-appropriate ways, may be a powerful means of adapting LLMs for use in demanding professional settings.

A One-Step Methodology for Identifying Concrete Pathologies Using Neural Networks—Using YOLO v8 and Dataset Review

Pathologies in concrete structures can be visually evidenced on the concrete surface, such as by fissures or cracks, fragmentation of part of the concrete, concrete efflorescence, corrosion stains on the concrete surface, or exposed steel bars, the latter two occurring in reinforced concrete. Therefore, these pathologies can be analyzed via the images of concrete structures. This article proposes a methodology for visually inspecting concrete structures using deep neural networks. This method makes it possible to speed up the detection task and increase its effectiveness by saving time in preparing the identifications to be analyzed and eliminating or reducing errors, such as those resulting from human errors caused by the execution of tedious, repetitive analysis tasks. The methodology was tested to analyze its accuracy. The neural network architecture used for detection was YOLO, versions 4 and 8, which was tested to analyze the gain with migration to a more recent version. The dataset for classification was Ozgnel, which was trained with YOLO version 8, and the detection dataset was CODEBRIM. The use of a dedicated classification dataset allows for a better-trained network for this function and results in the elimination of false positives in the detection stage. The classification achieved 99.65% accuracy.

Robust differential expression testing for single-cell CRISPR screens at low multiplicity of infection.

Single-cell CRISPR screens (perturb-seq) link genetic perturbations to phenotypic changes in individual cells. The most fundamental task in perturb-seq analysis is to test for association between a perturbation and a count outcome, such as gene expression. We conduct the first-ever comprehensive benchmarking study of association testing methods for low multiplicity-of-infection (MOI) perturb-seq data, finding that existing methods produce excess false positives. We conduct an extensive empirical investigation of the data, identifying three core analysis challenges: sparsity, confounding, and model misspecification. Finally, we develop an association testing method - SCEPTRE low-MOI - that resolves these analysis challenges and demonstrates improved calibration and power.

Microblog sentiment analysis method using BTCBMA model in Spark big data environment

Abstract Microblogs are currently one of the most well-liked social platforms in China, and sentiment analysis of microblog texts can help further analyze the realization of their media value; however, the current task of sentiment analysis based on microblog information suffers from low accuracy due to the large size and high redundancy of microblog data, a microblog sentiment analysis method using Bidirectional Encoder Representation from Transformers (BERT)–Text Convolutional Neural Network (TextCNN)–Bidirectional Gate Recurrent Unit (BiGRU)–Multihead-Attention model in Spark big data environment is proposed. First, the Chinese pre-trained language model BERT is used to convert the input data into dynamic character-level word vectors; then, TextCNN is used to effectively obtain local features such as keywords and pool the filtered features; then, BiGRU is introduced to quickly capture more comprehensive semantic information; finally, a multi-headed attention mechanism is implemented to emphasize the most significant features in order to accomplish the sentiment classification of microblog information task precisely. By comparing the existing advanced models, the proposed model demonstrates an improvement of at least 4.99% and 0.05 in accuracy and F1-score evaluation indexes, respectively. This enhancement significantly enhances the accuracy of microblog sentiment analysis tasks and aids pertinent authorities in comprehending the inclination of individual’s attitude toward hot topics. Furthermore, it facilitates a prompt prediction of topic trends, enabling them to guide public opinion accordingly.

An event-scene cooperative analysis network with dual-stream attention convolution module and soft parameter-sharing

Sound event detection (SED) and acoustic scene classification (ASC) are critical tasks in computational environmental sound scene analysis. Both exhibit significant potential across diverse applications, including urban environment detection, smart home integration, and anomaly monitoring. Considering the intricate relationship between acoustic scenes and sound events, researchers have proposed a joint analysis method for SED and ASC tasks using multi-task learning (MTL). However, conventional MTL-based methods rely mainly on a hard parameter-sharing mechanism, which restricts information flow and collaborative learning among tasks during training. To address this issue, this paper proposes a novel MTL method for SED that employs a soft parameter-sharing mechanism to explore the intrinsic correlation between acoustic scenes and sound events. A cross-stitch mechanism is introduced in this study to facilitate soft parameter-sharing between the SED and ASC tasks by employing scene information to improve the performance of the SED tasks and ensure training efficiency. Furthermore, a dual-stream attention convolution module (DACM) is designed to capture global and local contextual information through parallel branches of attention and convolution. To evaluate the performance of the proposed method in SED tasks, we tested two datasets: the TUT Acoustic Scenes 2016/2017 and TUT Sound Events 2016/2017 datasets and the synthetic sound scene datasets. Experimental results indicate that the proposed MTL method outperforms state-of-the-art approaches, demonstrating that acoustic scene information can improve the performance of SED tasks.

Federated Learning for Exploiting Annotators’ Disagreements in Natural Language Processing

Abstract The annotation of ambiguous or subjective NLP tasks is usually addressed by various annotators. In most datasets, these annotations are aggregated into a single ground truth. However, this omits divergent opinions of annotators, hence missing individual perspectives. We propose FLEAD (Federated Learning for Exploiting Annotators’ Disagreements), a methodology built upon federated learning to independently learn from the opinions of all the annotators, thereby leveraging all their underlying information without relying on a single ground truth. We conduct an extensive experimental study and analysis in diverse text classification tasks to show the contribution of our approach with respect to mainstream approaches based on majority voting and other recent methodologies that also learn from annotator disagreements.

Dynamic and Integrated Security Model in Inter Cloud for Image Classification

Cloud computing has transformed software and database accessibility, utilizing the Internet and server hosting. However, security risks arise, including malware attacks and website hacking. To address these challenges, deep learning models like ResNet50 have been developed. Trained on encrypted images, ResNet50 enhances the speed and accuracy of image recognition, enabling the identification of hidden data without decryption. Despite inter-cloud communication issues, cloud servers prioritize data security, user privacy, and integrity maintenance. The ResNet50 model exhibits impressive performance, achieving 99.5%accuracy and precision-recall scores of 99.5% and 99.5% using the ImageNet Dataset. Cloud computing offers significant advantages, but data security remains a critical concern. Encrypted image recognition powered by deep learning models offers efficient and private solutions. Cloud providers continually strive to improve inter-cloud communication, ensuring comprehensive protection for data and system integrity. The remarkable capabilities of ResNet50 highlight its potential in encrypted image analysis tasks.

Design and Manufacturing of a Pin on Disk Tribometer

This paper presents the design and manufacturing of a pin on disk tribometer aimed at performing friction and wear testing as accurate as a professional tribometer at a lower cost. Since friction is an important part of our lives and its application varies greatly in size, environment and other factors, testing can be expensive. Tribometers are instruments where these conditions can be simulated experimentally. They are manufactured by various companies abroad and are imported to Turkey. For this reason, the cost of these instruments is very high. The design of the proposed tribometer prioritizes portability and low cost of manufacturing. The manufacturing process of the various parts are discussed in detail. The tribometer was manufactured in the ATILIM University manufacturing laboratories within a tight budget using CNC machining. The instrument has the full capability to adjust the load, testing radius, motor speed, and the duration of the test before starting the experiments. To handle the electronics and data gathering within the instrument, Arduino boards and software are utilized. Real-time data streaming is made possible for data analysis tasks both during and after the experiments. The paper also provides the results of experiments that are obtained from the newly developed tribometer and comparisons with a mass produced, professional tribometer. The experiments are conducted with the same type of samples and with the same parameters. The proposed tribometer provides researchers with easily accessible friction data that is within close range to what they would get from a professional tribometer.

V4RIN: visual analysis of regional industry network with domain knowledge.

The regional industry network (RIN) is a type of financial network derived from industry networks that possess the capability to describe the connections between specific industries within a particular region. For most investors and financial analysts lacking extensive experience, the decision-support information provided by industry networks may be too vague. Conversely, RINs express more detailed and specific industry connections both within and outside the region. As RIN analysis is domain-specific and current financial network analysis tools are designed for generalized analytical tasks and cannot be directly applied to RINs, new visual analysis approaches are needed to enhance information exploration efficiency. In this study, we collaborated with domain experts and proposed V4RIN, an interactive visualization analysis system that integrates predefined domain knowledge and data processing methods to support users in uploading custom data. Through multiple views in the system panel, users can comprehensively explore the structure, geographical distribution, and spatiotemporal variations of the RIN. Two case studies were conducted and a set of expert interviews with five domain experts to validate the usability and reliability of our system.

Application and challenges of layers of protection analysis (LOPA) in mining processes: Insights into benefits and limitations

AbstractLayers of protection analysis (LOPA) is a semiquantitative technique widely used in process industries for assessing hazardous scenarios and supporting risk‐informed decision making. It provides a balance between the simplicity of qualitative analysis and the detail of quantitative analysis. This paper discusses the authors' experiences with the application of LOPA in the mining and metals (M&M) industry, combined with traditional methods like HAZOP and HAZID, to identify risks. Several of LOPA's limitations became evident, and scenarios involving human factors, natural events, and asset integrity were excluded from analysis. Certain M&M processes, often complex and heavily reliant on manual operations, pose unique challenges to LOPA's effectiveness due to difficulties in isolating independent protection layers: for example, those involving induction furnaces where overheat scenarios can lead to explosive phase transitions upon contact with water and molten metal. Despite these challenges, the advantages of LOPA, such as enhanced understanding of protection layers and fostering effective safety improvements, are significant. The paper anticipates continued use of LOPA within the company, complemented by safety critical task analysis to manage human errors and enhance safety controls in critical situations.