Processing Tasks Research Articles

DenseSeg: joint learning for semantic segmentation and landmark detection using dense image-to-shape representation.

Semantic segmentation and landmark detection are fundamental tasks of medical image processing, facilitating further analysis of anatomical objects. Although deep learning-based pixel-wise classification has set a new-state-of-the-art for segmentation, it falls short in landmark detection, a strength of shape-based approaches. In this work, we propose a dense image-to-shape representation that enables the joint learning of landmarks and semantic segmentation by employing a fully convolutional architecture. Our method intuitively allows the extraction of arbitrary landmarks due to its representation of anatomical correspondences. We benchmark our method against the state-of-the-art for semantic segmentation (nnUNet), a shape-based approach employing geometric deep learning and a convolutional neural network-based method for landmark detection. We evaluate our method on two medical datasets: one common benchmark featuring the lungs, heart, and clavicle from thorax X-rays, and another with 17 different bones in the paediatric wrist. While our method is on par with the landmark detection baseline in the thorax setting (error in mm of vs. ), it substantially surpassed it in the more complex wrist setting ( vs. ). We demonstrate that dense geometric shape representation is beneficial for challenging landmark detection tasks and outperforms previous state-of-the-art using heatmap regression. While it does not require explicit training on the landmarks themselves, allowing for the addition of new landmarks without necessitating retraining.

Reading words versus seeing font or handwriting style: a study of hemifield processing.

Tachistoscopic studies have established a right field advantage for the perception of visually presented words, which has been interpreted as reflecting a left hemispheric specialization. However, it is not clear whether this is driven by the linguistic task of word processing, or also occurs when processing properties such as the style and regularity of text. We had 23 subjects perform a tachistoscopic study while they viewed five-letter words in either computer font or handwriting. The task in one block was to respond if the word in the peripheral field matched a word just seen in the central field. In a second block with the same stimuli, the task was to respond if the style (handwriting or font) matched. We found a main effect of task: there was a right-field advantage for reading the word, but no field advantage for reporting the style of text. There was no effect of stimulus type and no interaction between task and stimulus type. We conclude that the field advantage for processing text is driven by the task, being specific for the processing the identity of the word and not the perception of the style of the text. We did not find evidence to support prior assertions that the type of text and its regularity influenced the field advantage during the word-reading task.

Quantifying Quantum Steering with Limited Resources: A Semi‐supervised Machine Learning Approach

AbstractQuantum steering, an intermediate quantum correlation lying between entanglement and nonlocality, has emerged as a critical quantum resource for a variety of quantum information processing tasks such as quantum key distribution and true randomness generation. The ability to detect and quantify quantum steering is crucial for these applications. Semi‐definite programming (SDP) has proven to be a valuable tool to quantify quantum steering. However, the challenge lies in the fact that the optimal measurement strategy is not priori known, making it time‐consuming to compute the steerable measure for any given quantum state. Furthermore, the utilization of SDP requires full information of the quantum state, necessitating quantum state tomography, which can be complex and resource‐consuming. In this work, the semi‐supervised self‐training model is used to estimate the steerable weight, a pivotal measure of quantum steering. The model can be trained using a limited amount of labeled data, thus reducing the time for labeling. The features are constructed by the probabilities derived by performing three sets of projective measurements under arbitrary local unitary transformations on the target states, circumventing the need for quantum tomography. The model demonstrates robust generalization capabilities and can achieve high levels of precision with limited resources.

The Effect of Free Weight Resistance Training on Cognitive Function Explored Through Eye Tracking: A Randomized Double-Blind Clinical Trial.

In this study, we investigated the impact of a 10-week free weight resistance training (RT) program on cognitive function in healthy young adults. In this randomized controlled trial, 18 participants were assigned to either an experimental or control group. We assessed cognitive function by using eye-tracking (ET) technology during text processing tasks. First-pass reading times (FPRTs) and total reading times (TRTs) were measured. Results revealed a significant three-way interaction between group, moment, and syntactic complexity in FPRTs, demonstrating training effects on cognitive processing. The experimental group showed a distinctive shift in processing patterns: from longer times in low complexity pre-intervention to increased times in high complexity post-intervention, particularly in early processing measures (FPRTs). Complementary analyses of strength improvements showed that increased strength was associated with enhanced attention allocation to complex structures and improved processing efficiency for simpler texts, suggesting RT's potential to modulate cognitive function.

Research Advanced in Sarcastic Detection based on Deep Learning

Sarcasm detection is an important task in natural language processing (NLP), which aims to identify ironic intentions in text or discourse. Unlike conventional narratives, satire often uses descriptions that are opposite to the literal meaning to convey humor or criticism, and it is widely used in various scenarios such as social media, comment sections, and forums. Accurately detecting satire is crucial for understanding users' true intentions, while remains an open issue due to the freedom of language expression. Compared to face-to-face communication with the extra tone, facial expressions, and body movements, or an article with background and contextual information, a single satirical comment can hardly provide information for the machine to make a correct judgment, which may mislead the model to recognize the emotions contained in the comment. This article aims to introduce the role of different features in machine learning and deep learning satire detection tasks based on current research in this field. In addition, this article discusses the problems of satire detection and looks forward to its future development direction

Resolving ambiguity in natural language for enhancement of aspect-based sentiment analysis of hotel reviews

In the ever-expanding digital landscape, the abundance of user-generated content on consumer platforms such as Booking and TripAdvisor offers a rich source of information for both travellers and hoteliers. Sentiment analysis, a fundamental research task of natural language processing (NLP) is used for mining sentiments and opinions within this vast reservoir of text reviews. A more specific type of sentiment analysis, i.e., aspect-based sentiment analysis (ABSA), is used when processing customer reviews is required. In ABSA, we aim to capture aspect-level sentiments and intricate relationships between various aspects within reviews. This article proposes a novel approach to ABSA by introducing a novel technique of word sense disambiguation (WSD) and integrating it with the Transformer architecture bidirectional encoder representations from Transformers (BERT) and graph convolutional networks (GCNs). The proposed approach resolves the intriguing ambiguities of the words and represents the review data as a complex graph structure, facilitating the modeling of intricate relationships between different aspects. The combination of bidirectional long short-term memory (BiLSTM) and GCN proves effective in capturing inter-dependencies among various aspects, providing a nuanced understanding of customer sentiments. The experiments are conducted on the RABSA dataset (an enhanced and richer hotel review data collection), and results demonstrate that our approach outperforms previous baselines, showcasing the effectiveness of integrating WSD in ABSA. Furthermore, an ablation study confirms the significant contribution of the WSD module to the overall performance. Moreover, we explore different similarity measures and find that cosine similarity yields the best results when identifying the real sense of a word in a given sentence using WordNet. The findings of our work and future work related to our work create lots of interest for people in the tourism and hospitality industry. This research gives another boost to the concept of the potential of NLP techniques in sentiment analysis. It emphasizes that if we combine the potential of NLP techniques along with state-of-the-art machine learning frameworks, we can shape the future of this field.

Security and Privacy Challenges of Large Language Models: A Survey

Large language models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLMs have become very popular tools in natural language processing (NLP) tasks, with the capability to analyze complicated linguistic patterns and provide relevant responses depending on the context. While offering significant advantages, these models are also vulnerable to security and privacy attacks, such as jailbreaking attacks, data poisoning attacks, and personally identifiable information (PII) leakage attacks. This survey provides a thorough review of the security and privacy challenges of LLMs, along with the application-based risks in various domains, such as transportation, education, and healthcare. We assess the extent of LLM vulnerabilities, investigate emerging security and privacy attacks against LLMs, and review potential defense mechanisms. Additionally, the survey outlines existing research gaps and highlights future research directions.

Self-Driving Microscopes: AI Meets Super-Resolution Microscopy.

The integration of Machine Learning (ML) with super-resolution microscopy represents a transformative advancement in biomedical research. Recent advances in ML, particularly deep learning (DL), have significantly enhanced image processing tasks, such as denoising and reconstruction. This review explores the growing potential of automation in super-resolution microscopy, focusing on how DL can enable autonomous imaging tasks. Overcoming the challenges of automation, particularly in adapting to dynamic biological processes and minimizing manual intervention, is crucial for the future of microscopy. Whilst still in its infancy, automation in super-resolution can revolutionize drug discovery and disease phenotyping leading to similar breakthroughs as have been recognized in this year's Nobel Prizes for Physics and Chemistry.

Phonological and speech motor abilities in children with childhood apraxia of speech

ABSTRACT Childhood apraxia of speech (CAS) is a motor speech disorder in which the precision and consistency of speech sounds are impaired due to deficits in motor planning and programming. The literature on CAS suggests that the clinical features of CAS cannot be limited to one level of speech processing and that a more comprehensive understanding of how all levels involved in speech production are part of a complex system is needed. The aim of this study was to investigate the relationship between phonological and speech motor abilities in children with CAS and to determine the extent to which speech motor performance accounts for phonological processing in children with CAS. Croatian children with CAS (n = 30) and typically developing children (n = 28) aged 5–7 years participated in this study. Behavioural measures representing different aspects of the speech production chain were created taking into account the inevitable overlap of linguistic and motor processes underlying each task. The results showed that children with CAS performed significantly worse on all measured tasks. Spearman correlation analysis revealed positive relationships between the speech motor tasks and the expressive and receptive phonological processing tasks. A hierarchical regression analysis showed that both receptive phonological processing and speech motor performance contribute significantly to expressive phonological processing in children with CAS, with monosyllabic MRR emerging as a significant predictor. These results emphasise the interconnectedness of phonological and speech motor skills in CAS and provide valuable insights for assessment and intervention.

Unified noise estimation and denoising algorithm with filters and neural networks for denoising satellite images

ABSTRACT Recent studies have demonstrated a rising trend in the utilization of multispectral and hyperspectral image de-noising, which is crucial for improving the visual quality of images and facilitating more efficient image processing tasks. Despite significant advancements in image denoising research, removing noise without distorting the image remains a challenging task. This paper addresses these limitations of multispectral satellite images and performs denoising of multispectral images by integrating noise estimates with a hybrid denoising framework that combines the benefits of two distinct approaches to image processing. Integrating filtering with Wavelet decomposition yields a denoising solution that is more robust and accurate than either technique could achieve on its own. Experiments on multispectral images from Sentinel-2 demonstrate the applicability and generalization of the proposed method in real-life scenarios. The comparative analysis indicates that this method significantly outperforms existing techniques, thereby demonstrating its superior performance.

KalmanFormer: using transformer to model the Kalman Gain in Kalman Filters.

Tracking the hidden states of dynamic systems is a fundamental task in signal processing. Recursive Kalman Filters (KF) are widely regarded as an efficient solution for linear and Gaussian systems, offering low computational complexity. However, real-world applications often involve non-linear dynamics, making it challenging for traditional Kalman Filters to achieve accurate state estimation. Additionally, the accurate modeling of system dynamics and noise in practical scenarios is often difficult. To address these limitations, we propose the KalmanFormer, a hybrid model-driven and data-driven state estimator. By leveraging data, the KalmanFormer promotes the performance of state estimation under non-linear conditions and partial information scenarios. The proposed KalmanFormer integrates classical Kalman Filter with a Transformer framework. Specifically, it utilizes the Transformer to learn the Kalman Gain directly from data without requiring prior knowledge of noise parameters. The learned Kalman Gain is then incorporated into the standard Kalman Filter workflow, enabling the system to better handle non-linearities and model mismatches. The hybrid approach combines the strengths of data-driven learning and model-driven methodologies to achieve robust state estimation. To evaluate the effectiveness of KalmanFormer, we conducted numerical experiments in both synthetic and real-world dataset. The results demonstrate that KalmanFormer outperforms the classical Extended Kalman Filter (EKF) in the same settings. It achieves superior accuracy in tracking hidden states, demonstrating resilience to non-linearities and imprecise system models.

Applying MLP-Mixer and gMLP to Human Activity Recognition.

The development of deep learning has led to the proposal of various models for human activity recognition (HAR). Convolutional neural networks (CNNs), initially proposed for computer vision tasks, are examples of models applied to sensor data. Recently, high-performing models based on Transformers and multi-layer perceptrons (MLPs) have also been proposed. When applying these methods to sensor data, we often initialize hyperparameters with values optimized for image processing tasks as a starting point. We suggest that comparable accuracy could be achieved with fewer parameters for sensor data, which typically have lower dimensionality than image data. Reducing the number of parameters would decrease memory requirements and computational complexity by reducing the model size. We evaluated the performance of two MLP-based models, MLP-Mixer and gMLP, by reducing the values of hyperparameters in their MLP layers from those proposed in the respective original papers. The results of this study suggest that the performance of MLP-based models is positively correlated with the number of parameters. Furthermore, these MLP-based models demonstrate improved computational efficiency for specific HAR tasks compared to representative CNNs.

A Review on Inverse Kinematics, Control and Planning for Robotic Manipulators With and Without Obstacles via Deep Neural Networks

Robotic manipulators are highly valuable tools that have become widespread in the industry, as they can achieve great precision and velocity in pick and place as well as processing tasks. However, to unlock their complete potential, some problems such as inverse kinematics (IK) need to be solved: given a Cartesian target, a method is needed to find the right configuration for the robot to reach that point. Another issue that needs to be addressed when dealing with robotic manipulators is the obstacle avoidance problem. Workspaces are usually cluttered and the manipulator should be able to avoid colliding with objects that could damage it, as well as with itself. Two alternatives exist to do this: a controller can be designed that computes the best action for each moment given the manipulator’s state, or a sequence of movements can be planned to be executed by the robot. Classical approaches to all these problems, such as numeric or analytical methods, can produce precise results but take a high computation time and do not always converge. Learning-based methods have gained considerable attention in tackling the IK problem, as well as motion planning and control. These methods can reduce the computational cost and provide results for every situation avoiding singularities. This article presents a literature review of the advances made in the past five years in the use of Deep Neural Networks (DNN) for IK with regard to control and planning with and without obstacles for rigid robotic manipulators. The literature has been organized in several categories depending on the type of DNN used to solve the problem. The main contributions of each reference are reviewed and the best results are presented in summary tables.

Veracity‐Oriented Context‐Aware Large Language Models–Based Prompting Optimization for Fake News Detection

Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE–FND framework, context‐aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity‐oriented context‐aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self‐adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero‐shot and few‐shot experiments using GPT‐3.5‐turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE–FND framework, even surpassing advanced GPT‐4.0 and human performance in certain scenarios. To support further LLM–based FND, we have made our approach’s code publicly available on GitHub (our CAPE–FND code: https://github.com/albert-jin/CAPE-FND [Accessed on 2024.09]).

Pythagorean Neutrosophic Bonferroni Mean Based Machine Learning Model for Data Analytics and Sentiment Classification of Product Reviews

To handle incomplete and indeterminate data, neutrosophic logicsetprobability was recognized. The neutrosophic falsehood, truth, and indeterminacy modules show symmetry as the truth and the falsehood appear the similar and perform in a symmetrical method with esteem to the indeterminacy module which aids as a line of the symmetry. Soft set is a general mathematical device to deal with uncertainty. Sentiment analysis (SA) is the foremost task of natural language processing (NLP), where judgments, opinions, thoughts, or attitudes toward an exact subject are removed. Web is a rich foundation of information and unstructured covering numerous text documents with reviews and opinions. The detection of sentiment will be useful for governments, discrete business groups, and decision-makers. With this motivation, this study develops a Data Analytics Framework for Sentiment Classification Using Pythagorean Neutrosophic Bonferroni Mean (DAFSC-PNBM) technique on Product Reviews. The presented DAFSC-PNBM technique mainly aims to determine the nature of sentiments based on product reviews. Primarily, data preprocessing is performed to increase the product review qualities. For the word embedding process, word2vec model is used. Besides, the DAFSC-PNBM model uses the Pythagorean Neutrosophic Bonferroni Mean (PNBM) technique for classification. To enhance the SA performance of the PNBM model, the grey wolf optimizer (GWO) model has been applied as a hyperparameter tune process. The experimentation outcome analysis of the DAFSC-PNBM method occurs and the outcomes are investigated under several features. The experimental study indicated the improvement of the DAFSC-PNBM method across the modern techniques

A Cost-Minimized Task Migration Assignment Mechanism in Blockchain Based Edge Computing System

Background: Cloud computing is usually introduced to execute computing intensive tasks for data processing and data mining. As a supplement to cloud computing, edge computing is provided as a new paradigm to effectively reduce processing latency, energy consumption cost and bandwidth consumption for time-sensitive tasks or resource-sensitive tasks. To better meet such requirements during task assignment in edge computing systems, an intelligent task migration assignment mechanism based on blockchain is proposed, which jointly considers the factors of resource allocation, resource control and credit degree. Methods: In this paper, an optimization problem is firstly constructed to minimize the total cost of completing all tasks under constraints of delay, energy consumption, communication, and credit degree. Here, the terminal node mines computing resources from edge nodes to complete task migration. An incentive method based on blockchain is provided to mobilize the activity of terminal nodes and edge nodes, and to ensure the security of the transaction during migration. The designed allocation rules ensure the fairness of rewards for successfully mining resource. To solve the optimization problem, an intelligent migration algorithm that utilizes a dual “actor-reviewer” neural network on inverse gradient update is proposed which makes the training process more stable and easier to converge. Results: Compared to the existing two benchmark mechanisms, the extensive simulation results indicate that the proposed mechanism based on neural network can converge at a faster speed and achieve the minimal total cost. Conclusion: To satisfy the requirements of delay and energy consumption for computing intensive tasks in edge computing scenarios, an intelligent, blockchain based task migration assignment mechanism with joint resource allocation and control is proposed. To realize this mechanism effectively, a dual “actor-reviewer” neural network algorithm is designed and executed.

Effective data visualization strategies in untargeted metabolomics.

Covering: 2014 to 2023 for metabolomics, 2002 to 2023 for information visualizationLC-MS/MS-based untargeted metabolomics is a rapidly developing research field spawning increasing numbers of computational metabolomics tools assisting researchers with their complex data processing, analysis, and interpretation tasks. In this article, we review the entire untargeted metabolomics workflow from the perspective of information visualization, visual analytics and visual data integration. Data visualization is a crucial step at every stage of the metabolomics workflow, where it provides core components of data inspection, evaluation, and sharing capabilities. However, due to the large number of available data analysis tools and corresponding visualization components, it is hard for both users and developers to get an overview of what is already available and which tools are suitable for their analysis. In addition, there is little cross-pollination between the fields of data visualization and metabolomics, leaving visual tools to be designed in a secondary and mostly ad hoc fashion. With this review, we aim to bridge the gap between the fields of untargeted metabolomics and data visualization. First, we introduce data visualization to the untargeted metabolomics field as a topic worthy of its own dedicated research, and provide a primer on cutting-edge visualization research into data visualization for both researchers as well as developers active in metabolomics. We extend this primer with a discussion of best practices for data visualization as they have emerged from data visualization studies. Second, we provide a practical roadmap to the visual tool landscape and its use within the untargeted metabolomics field. Here, for several computational analysis stages within the untargeted metabolomics workflow, we provide an overview of commonly used visual strategies with practical examples. In this context, we will also outline promising areas for further research and development. We end the review with a set of recommendations for developers and users on how to make the best use of visualizations for more effective and transparent communication of results.

AxLaM: energy-efficient accelerator design for language models for edge computing.

Modern language models such as bidirectional encoder representations from transformers have revolutionized natural language processing (NLP) tasks but are computationally intensive, limiting their deployment on edge devices. This paper presents an energy-efficient accelerator design tailored for encoder-based language models, enabling their integration into mobile and edge computing environments. A data-flow-aware hardware accelerator design for language models inspired by Simba, makes use of approximate fixed-point POSIT-based multipliers and uses high bandwidth memory (HBM) in achieving significant improvements in computational efficiency, power consumption, area and latency compared to the hardware-realized scalable accelerator Simba. Compared to Simba, AxLaM achieves a ninefold energy reduction, 58% area reduction and 1.2 times improved latency, making it suitable for deployment in edge devices. The energy efficiency of AxLaN is 1.8 TOPS/W, 65% higher than FACT, which requires pre-processing of the language model before implementing it on the hardware.This article is part of the theme issue 'Emerging technologies for future secure computing platforms'.

Soft cosine and extended cosine adaptation for pre-trained language model semantic vector analysis

Semantic textual analysis is a natural language processing task that has enjoyed several research contributions towards solving diverse real-life problems. Vector comparison is a core subtask in semantic textual similarity analysis. A plethora of solutions including recent state-of-the-art transformer-based pre-trained language models for transfer learning have focused on using only cosine similarity for embedding evaluation in downstream tasks and ignored other vector comparison methods. To investigate the relative performance of some such ignored measures, this work proposes novel adaptations for soft cosine and extended cosine vector measures. We investigate their performance against the conventional cosine measure, distance-weighted cosine, vector similarity measure, negative Manhattan, and Euclidean distances on downstream semantic textual similarity tasks, under same conditions, for the first time in literature. Adopting transformer-based Universal sentence encoder, SBERT, SRoBERTa, SimCSE, and ST5 for text encoding; the performances of the adapted measures are evaluated on diverse real world datasets using Pearson, Spearman, accuracy and F1 evaluation metrics. Results obtained show that the adapted measures significantly surpass previously reported state-of-the-art cosine similarity-based correlations in several test cases considered.

UNCA: A Neutrosophic-Based Framework for Robust Clustering and Enhanced Data Interpretation

Accurately representing the complex linkages and inherent uncertainties included in huge datasets is still a major difficulty in the field of data clustering. We address these issues with our proposed Unified Neutrosophic Clustering Algorithm (UNCA), which combines a multifaceted strategy with Neutrosophic logic to improve clustering performance. UNCA starts with a full-fledged similarity examination via a λ-cutting matrix that filters meaningful relationships between each two points of data. Then, we initialize centroids for Neutrosophic K-Means clustering, where the membership values are based on their degrees of truth, indeterminacy and falsity. The algorithm then integrates with a dynamic network visualization and MST (Minimum Spanning Tree) so that a visual interpretation of the relationships between the clusters can be clearly represented. UNCA employs Single-Valued Neutrosophic Sets (SVNSs) to refine cluster assignments, and after fuzzifying similarity measures, guarantees a precise clustering result. The final step involves solidifying the clustering results through defuzzification methods, offering definitive cluster assignments. According to the performance evaluation results, UNCA outperforms conventional approaches in several metrics: it achieved a Silhouette Score of 0.89 on the Iris Dataset, a Davies-Bouldin Index of 0.59 on the Wine Dataset, an Adjusted Rand Index (ARI) of 0.76 on the Digits Dataset, and a Normalized Mutual Information (NMI) of 0.80 on the Customer Segmentation Dataset. These results demonstrate how UNCA enhances interpretability and resilience in addition to improving clustering accuracy when contrasted with Fuzzy C-Means (FCM), Neutrosophic C-Means (NCM), as well as Kernel Neutrosophic C-Means (KNCM). This makes UNCA a useful tool for complex data processing tasks.