Search

With the increased use of the internet and social networks for online discussions, the spread of toxic and inappropriate content on social networking sites has also increased. Several studies have been conducted in different languages. However, there is less work done for South Asian languages for inappropriate content identification using deep learning techniques. In Urdu language, the spellings are not unique, and people write different common spellings for the same word, while mixing it other languages, like English in the text makes it more challenging, and limited research work is available to process such language with the finest algorithms. The use of attention layer with a deep learning model can help handling the long-term dependencies and increase its efficiency . To explore the effects of the attention layer, this study proposes attention-based Bidirectional GRU hybrid model for identifying inappropriate content in Urdu Unicode text language. Four different baseline deep learning models; LSTM, Bi-LSTM, GRU, and TCN, are used to compare the performance of the proposed model. The results of these models were compared based on evaluation metrics, dataset size, and impact of the word embedding layer. The pre-trained Urdu word2Vec embeddings were utilized for our case. Our proposed model BiGRU-A outperformed all other baseline models by yielding 84\% accuracy without using pre-trained word2Vec layer. From our experiments, we have established that the attention layer improves the model's efficiency, and pre-trained word2Vec embedding does not work well with an inappropriate content dataset.

Remote patient monitoring is crucial in modern healthcare, but current systems struggle with real-time analysis and prediction of vital signs. This paper presents a novel architecture combining deep learning with 5G network capabilities to enable real-time vital sign monitoring and prediction. The proposed system utilizes a hybrid CNN-LSTM model optimized for edge deployment, paired with 5G Ultra-Reliable Low-Latency Communication (URLLC) for efficient data transmission. The architecture achieves end-to-end latency of 14.4ms while maintaining 96.5% prediction accuracy across multiple vital signs. Our system shows significant improvements over existing solutions, reducing latency by 47% and increasing prediction accuracy by 4.2% compared to current state-of-the-art systems. Performance evaluations conducted over three months with data from 1000 patients validate the system's reliability and scalability in clinical settings. The results demonstrate that integrating deep learning with 5G technology can effectively address the challenges of real-time patient monitoring, leading to early detection of deteriorating conditions and improved clinical outcomes. This research establishes a framework for reliable, real-time vital sign monitoring and prediction in digital healthcare., Comment: 9 pages, 7 figures

Influence maximization in temporal social networks presents unique challenges due to the dynamic interactions that evolve over time. Traditional diffusion models often fall short in capturing the real-world complexities of active-inactive transitions among nodes, obscuring the true behavior of influence spread. In dynamic networks, nodes do not simply transition to an active state once; rather, they can oscillate between active and inactive states, with the potential for reactivation and reinforcement over time. This reactivation allows previously influenced nodes to regain influence potency, enhancing their ability to spread influence to others and amplifying the overall diffusion process. Ignoring these transitions can thus conceal the cumulative impact of influence, making it essential to account for them in any effective diffusion model. To address these challenges, we introduce the Continuous Persistent Susceptible-Infected Model with Reinforcement and Re-activation (cpSI-R), which explicitly incorporates active-inactive transitions, capturing the progressive reinforcement that makes nodes more potent spreaders upon reactivation. This model naturally leads to a submodular and monotone objective function, which supports efficient optimization for seed selection in influence maximization tasks. Alongside cpSI-R, we propose an efficient temporal snapshot sampling method, simplifying the analysis of evolving networks. We then adapt the prior algorithms of seed selection to our model and sampling strategy, resulting in reduced computational costs and enhanced seed selection efficiency. Experimental evaluations on diverse datasets demonstrate substantial improvements in performance over baseline methods, underscoring the effectiveness of cpSI-R for real-world temporal networks

Autonomous driving technology is progressing rapidly, largely due to complex End To End systems based on deep neural networks. While these systems are effective, their complexity can make it difficult to understand their behavior, raising safety concerns. This paper presents a new solution a Behavior Selector that uses multiple smaller artificial neural networks (ANNs) to manage different driving tasks, such as lane following and turning. Rather than relying on a single large network, which can be burdensome, require extensive training data, and is hard to understand, the developed approach allows the system to dynamically select the appropriate neural network for each specific behavior (e.g., turns) in real time. We focus on ensuring smooth transitions between behaviors while considering the vehicles current speed and orientation to improve stability and safety. The proposed system has been tested using the AirSim simulation environment, demonstrating its effectiveness., Comment: 7 pages, 8 figures

Environment perception is a fundamental part of the dynamic driving task executed by Autonomous Driving Systems (ADS). Artificial Intelligence (AI)-based approaches have prevailed over classical techniques for realizing the environment perception. Current safety-relevant standards for automotive systems, International Organization for Standardization (ISO) 26262 and ISO 21448, assume the existence of comprehensive requirements specifications. These specifications serve as the basis on which the functionality of an automotive system can be rigorously tested and checked for compliance with safety regulations. However, AI-based perception systems do not have complete requirements specification. Instead, large datasets are used to train AI-based perception systems. This paper presents a function monitor for the functional runtime monitoring of a two-folded AI-based environment perception for ADS, based respectively on camera and LiDAR sensors. To evaluate the applicability of the function monitor, we conduct a qualitative scenario-based evaluation in a controlled laboratory environment using a model car. The evaluation results then are discussed to provide insights into the monitor's performance and its suitability for real-world applications., Comment: 9 pages, 8 figures

A $\Gamma$-Besicovitch set is a set which contains a rotated copy of $\Gamma$ in every direction. Our main result is the construction of a non-trivial $1$-rectifiable set $\Gamma$ in the plane, for which there exists a 1-dimensional $\Gamma$-Besicovitch set., Comment: 16 pages, 2 figures

Deep learning holds tremendous potential in healthcare for uncovering hidden patterns within extensive clinical datasets, aiding in the diagnosis of various diseases. Parkinson's disease (PD) is a neurodegenerative condition characterized by the deterioration of brain function. In the initial stages of PD, automatic diagnosis poses a challenge due to the similarity in behavior between individuals with PD and those who are healthy. Our objective is to propose an effective model that can aid in the early detection of Parkinson's disease. We employed the VGRF gait signal dataset sourced from Physionet for distinguishing between healthy individuals and those diagnosed with Parkinson's disease. This paper introduces a novel deep learning architecture based on the LSTM network for automatically detecting freezing of gait episodes in Parkinson's disease patients. In contrast to conventional machine learning algorithms, this method eliminates manual feature engineering and proficiently captures prolonged temporal dependencies in gait patterns, thereby improving the diagnosis of Parkinson's disease. The LSTM network resolves the issue of vanishing gradients by employing memory blocks in place of self-connected hidden units, allowing for optimal information assimilation. To prevent overfitting, dropout and L2 regularization techniques have been employed. Additionally, the stochastic gradient-based optimizer Adam is used for the optimization process. The results indicate that our proposed approach surpasses current state-of-the-art models in FOG episode detection, achieving an accuracy of 97.71%, sensitivity of 99%, precision of 98%, and specificity of 96%. This demonstrates its potential as a superior classification method for Parkinson's disease detection.

Context: The advent of Large Language Model-driven tools like ChatGPT offers software engineers an interactive alternative to community question-answering (CQA) platforms like Stack Overflow. While Stack Overflow provides benefits from the accumulated crowd-sourced knowledge, it often suffers from unpleasant comments, reactions, and long waiting times. Objective: In this study, we assess the efficacy of ChatGPT in providing solutions to software engineering questions by analyzing its performance specifically against human solutions. Method: We empirically analyze 2564 Python and JavaScript questions from StackOverflow that were asked between January 2022 and December 2022. We parse the questions and answers from Stack Overflow, then collect the answers to the same questions from ChatGPT through API, and employ four textual and four cognitive metrics to compare the answers generated by ChatGPT with the accepted answers provided by human subject matter experts to find out the potential reasons for which future knowledge seekers may prefer ChatGPT over CQA platforms. We also measure the accuracy of the answers provided by ChatGPT. We also measure user interaction on StackOverflow over the past two years using three metrics to determine how ChatGPT affects it. Results: Our analysis indicates that ChatGPT's responses are 66% shorter and share 35% more words with the questions, showing a 25% increase in positive sentiment compared to human responses. ChatGPT's answers' accuracy rate is between 71 to 75%, with a variation in response characteristics between JavaScript and Python. Additionally, our findings suggest a recent 38% decrease in comment interactions on Stack Overflow, indicating a shift in community engagement patterns. A supplementary survey with 14 Python and JavaScript professionals validated these findings.

We study robust and efficient distributed algorithms for building and maintaining distributed data structures in dynamic Peer-to-Peer (P2P) networks. P2P networks are characterized by a high level of dynamicity with abrupt heavy node \emph{churn} (nodes that join and leave the network continuously over time). We present a novel algorithm that builds and maintains with high probability a skip list for $poly(n)$ rounds despite $\mathcal{O}(n/\log n)$ churn \emph{per round} ($n$ is the stable network size). We assume that the churn is controlled by an oblivious adversary (that has complete knowledge and control of what nodes join and leave and at what time and has unlimited computational power, but is oblivious to the random choices made by the algorithm). Moreover, the maintenance overhead is proportional to the churn rate. Furthermore, the algorithm is scalable in that the messages are small (i.e., at most $polylog(n)$ bits) and every node sends and receives at most $polylog(n)$ messages per round. Our algorithm crucially relies on novel distributed and parallel algorithms to merge two $n$-elements skip lists and delete a large subset of items, both in $\mathcal{O}(\log n)$ rounds with high probability. These procedures may be of independent interest due to their elegance and potential applicability in other contexts in distributed data structures. To the best of our knowledge, our work provides the first-known fully-distributed data structure that provably works under highly dynamic settings (i.e., high churn rate). Furthermore, they are localized (i.e., do not require any global topological knowledge). Finally, we believe that our framework can be generalized to other distributed and dynamic data structures including graphs, potentially leading to stable distributed computation despite heavy churn.

This research investigates the use of artificial intelligence and machine learning techniques to predict the toxicity of nanoparticles, a pressing concern due to their pervasive use in various industries and the inherent challenges in assessing their biological interactions. Employing models such as Decision Trees, Random Forests, and XGBoost, the study focuses on analyzing physicochemical properties like size, shape, surface charge, and chemical composition to determine their influence on toxicity. Our findings highlight the significant role of oxygen atoms, particle size, surface area, dosage, and exposure duration in affecting toxicity levels. The use of machine learning allows for a nuanced understanding of the intricate patterns these properties form in biological contexts, surpassing traditional analysis methods in efficiency and predictive power. These advancements aid in developing safer nanomaterials through computational chemistry, reducing reliance on costly and time-consuming experimental methods. This approach not only enhances our understanding of nanoparticle behavior in biological systems but also streamlines the safety assessment process, marking a significant stride towards integrating computational techniques in nanotoxicology., Comment: 20 pages, 14 figures. Presented at the International Conference on Nanotechnology and Smart Materials 2024. Includes supplementary material

This review explores the synthesis, characterization, and therapeutic applications of zinc oxide nanoparticles (ZnO NPs) in the treatment of diabetes mellitus. The study delves into both chemical and green synthesis methods, comparing their impacts on nanoparticle properties. Key characterization techniques such as XRD, FTIR, UV-Vis spectroscopy, and SEM confirm the crystalline structure, optical properties, and morphology of the nanoparticles. ZnO NPs demonstrate significant biological activities, including antibacterial, anti-inflammatory, and antidiabetic effects. These nanoparticles show promise in improving glucose regulation, enhancing insulin sensitivity, and boosting glucose uptake in cells. Despite these benefits, the potential toxicity and long-term effects of ZnO NPs warrant further investigation. Future research should focus on optimizing synthesis methods and conducting comprehensive studies to fully exploit ZnO NPs' potential in diabetes management and other biomedical applications., Comment: 21 pages, 1 figure. Includes comprehensive review of synthesis methods and biological evaluations of ZnO nanoparticles in diabetes treatment

This paper focuses on developing a generalized ghost dark energy model $f\mathcal{(Q,T)}$ through the correspondence scheme for a non-interacting scenario involving pressureless matter and a power-law scale factor. We analyze the cosmological implications of our model using the equation of state parameter, $\omega_{GGDE}-\omega'_{GGDE}$ and the $r-s$ planes. We also examine stability of the model by considering squared speed of sound parameter. The equation of state parameter shows the phantom era, while the squared speed of sound indicates a stable generalized ghost dark energy model throughout the cosmic evolution. The $\omega_{GGDE}-\omega'_{GGDE}$ plane depicts a freezing region, whereas the $r-s$ plane corresponds to the Chaplygin gas model. We conclude that our results are consistent with the current observational data., Comment: 30 pages, 6 figures. arXiv admin note: text overlap with arXiv:2405.04548

Autonomous embedded systems (e.g., robots) typically necessitate intelligent computation with low power/energy processing for completing their tasks. Such requirements can be fulfilled by embodied neuromorphic intelligence with spiking neural networks (SNNs) because of their high learning quality (e.g., accuracy) and sparse computation. Here, the employment of event-based data is preferred to ensure seamless connectivity between input and processing parts. However, state-of-the-art SNNs still face a long training time to achieve high accuracy, thereby incurring high energy consumption and producing a high rate of carbon emission. Toward this, we propose FastSpiker, a novel methodology that enables fast SNN training on event-based data through learning rate enhancements targeting autonomous embedded systems. In FastSpiker, we first investigate the impact of different learning rate policies and their values, then select the ones that quickly offer high accuracy. Afterward, we explore different settings for the selected learning rate policies to find the appropriate policies through a statistical-based decision. Experimental results show that our FastSpiker offers up to 10.5x faster training time and up to 88.39% lower carbon emission to achieve higher or comparable accuracy to the state-of-the-art on the event-based automotive dataset (i.e., NCARS). In this manner, our FastSpiker methodology paves the way for green and sustainable computing in realizing embodied neuromorphic intelligence for autonomous embedded systems., Comment: To appear at the 18th International Conference on Control, Automation, Robotics and Vision (ICARCV), December 2024, Dubai, UAE

The present work explores different evolutionary phases of isotropically homogeneous and flat cosmos filled with dust fluid in non-minimally coupled gravity. We consider different models of this gravity to discuss the presence of symmetry generators together with conserved integrals using Nother Gauge symmetry scheme. In most of the cases, we obtain temporal and scaling symmetries that yield conservation of energy and linear momentum, respectively. In the absence of contracted Ricci and energy-momentum tensors, we obtain maximum symmetries but none of them correspond to any standard symmetry or conservation law. We formulate exact solutions and construct graphical analysis of standard cosmological parameters. We observe realistic nature of new models via squared speed of sound, viability conditions suggested by Dolgov-Kawasaki instability and state-finder parameters. We investigate the behavior of fractional densities and check the compatibility with Planck 2018 observational data. The new models are stable and viable preserving compatibility with $\Lambda$CDM and Chaplygin gas models. It is concluded that most of the solutions favor accelerated cosmic expansion., Comment: 31 pages, 11 figures

With the recent advances of large language models (LLMs), it is no longer infeasible to build an automated debate system that helps people to synthesise persuasive arguments. Previous work attempted this task by integrating multiple components. In our work, we introduce an argument mining dataset that captures the end-to-end process of preparing an argumentative essay for a debate, which covers the tasks of claim and evidence identification (Task 1 ED), evidence convincingness ranking (Task 2 ECR), argumentative essay summarisation and human preference ranking (Task 3 ASR) and metric learning for automated evaluation of resulting essays, based on human feedback along argument quality dimensions (Task 4 SQE). Our dataset contains 14k examples of claims that are fully annotated with the various properties supporting the aforementioned tasks. We evaluate multiple generative baselines for each of these tasks, including representative LLMs. We find, that while they show promising results on individual tasks in our benchmark, their end-to-end performance on all four tasks in succession deteriorates significantly, both in automated measures as well as in human-centred evaluation. This challenge presented by our proposed dataset motivates future research on end-to-end argument mining and summarisation. The repository of this project is available at https://github.com/HaoBytes/ArgSum-Datatset, Comment: Published on ACL 2024 Findings

This paper studies the reconstruction criterion in the framework of $f(Q,T)$ gravity using ghost dark energy model, where $Q$ represents the non-metricity and $T$ is the trace of energy-momentum tensor. In this regard, the correspondence scenario for a non-interacting scheme is used to construct the ghost dark energy $f(Q,T)$ model. We consider the flat Friedmann-Robertson-Walker universe with power-law scale factor and pressure-less matter. We investigate the behavior of equation of state parameter and examine the stability of ghost dark energy model via squared speed of sound parameter. The equation of state parameter depicts the phantom era, while the squared speed of sound reveals stable ghost dark energy model for the entire cosmic evolutionary paradigm. Finally, we study the cosmography of the $\omega_{GDE}-\omega'_{GDE}$ and $r-s$ planes that correspond to freezing region and Chaplygin gas model, respectively. It is concluded that the reconstructed ghost dark energy model represents the evolution of the cosmos for suitable choices of the parametric values., Comment: 34 pages, 6 figures

Autonomous Driving (AD) systems are considered as the future of human mobility and transportation. Solving computer vision tasks such as image classification and object detection/segmentation, with high accuracy and low power/energy consumption, is highly needed to realize AD systems in real life. These requirements can potentially be satisfied by Spiking Neural Networks (SNNs). However, the state-of-the-art works in SNN-based AD systems still focus on proposing network models that can achieve high accuracy, and they have not systematically studied the roles of SNN parameters when used for learning event-based automotive data. Therefore, we still lack understanding of how to effectively develop SNN models for AD systems. Toward this, we propose a novel methodology to systematically study and analyze the impact of SNN parameters considering event-based automotive data, then leverage this analysis for enhancing SNN developments. To do this, we first explore different settings of SNN parameters that directly affect the learning mechanism (i.e., batch size, learning rate, neuron threshold potential, and weight decay), then analyze the accuracy results. Afterward, we propose techniques that jointly improve SNN accuracy and reduce training time. Experimental results show that our methodology can improve the SNN models for AD systems than the state-of-the-art, as it achieves higher accuracy (i.e., 86%) for the NCARS dataset, and it can also achieve iso-accuracy (i.e., ~85% with standard deviation less than 0.5%) while speeding up the training time by 1.9x. In this manner, our research work provides a set of guidelines for SNN parameter enhancements, thereby enabling the practical developments of SNN-based AD systems., Comment: To appear at the 18th International Conference on Control, Automation, Robotics and Vision (ICARCV), December 2024, Dubai, UAE

Large language models (LLMs) have increased interest in vision language models (VLMs), which process image-text pairs as input. Studies investigating the visual understanding ability of VLMs have been proposed, but such studies are still preliminary because existing datasets do not permit a comprehensive evaluation of the fine-grained visual linguistic abilities of VLMs across multiple languages. To further explore the strengths of VLMs, such as GPT-4V \cite{openai2023GPT4}, we developed new datasets for the systematic and qualitative analysis of VLMs. Our contribution is four-fold: 1) we introduced nine vision-and-language (VL) tasks (including object recognition, image-text matching, and more) and constructed multilingual visual-text datasets in four languages: English, Japanese, Swahili, and Urdu through utilizing templates containing \textit{questions} and prompting GPT4-V to generate the \textit{answers} and the \textit{rationales}, 2) introduced a new VL task named \textit{unrelatedness}, 3) introduced rationales to enable human understanding of the VLM reasoning process, and 4) employed human evaluation to measure the suitability of proposed datasets for VL tasks. We show that VLMs can be fine-tuned on our datasets. Our work is the first to conduct such analyses in Swahili and Urdu. Also, it introduces \textit{rationales} in VL analysis, which played a vital role in the evaluation.