Search

Cellular automata are a fundamental computational model with applications in mathematics, computer science, and physics. In this work, we explore the study of cellular automata to cases where the universe is a group, introducing the concept of \( \phi \)-cellular automata. We establish new theoretical results, including a generalized Uniform Curtis-Hedlund Theorem and linear \( \phi \)-cellular automata. Additionally, we define the covering map for \( \phi \)-cellular automata and investigate its properties. Specifically, we derive results for quotient covers when the universe of the automaton is a circulant graph. This work contributes to the algebraic and topological understanding of cellular automata, paving the way for future exploration of different types of covers and their applications to broader classes of graphs and dynamical systems.

This study provides a classification of disasters in terms of their causal parameters, introducing hypothetical cases of independent or hybrid AI-caused disasters. We overview the role of AI in disaster management, and possible ethical repercussions of the use of AI in intelligent disaster management - IDM. Next, we scrutinize certain ways of preventing or alleviating the ethical repercussions of AI use in disaster mismanagement, such as privacy breaches, biases, discriminations, etc. These include pre-design a priori, in-design, and post-design methods as well as regulations. We then discuss the government's role in preventing the ethical repercussions of AI use in IDM and identify and assess its deficits and challenges. We then discuss the advantages and disadvantages of pre-design or embedded ethics. Finally, we briefly consider the question of accountability and liability in AI-caused disasters.

Continual learning has been an active research area in machine learning, focusing on incrementally learning a sequence of tasks. A key challenge is catastrophic forgetting (CF), and most research efforts have been directed toward mitigating this issue. However, a significant gap remains between the accuracy achieved by state-of-the-art continual learning algorithms and the ideal or upper-bound accuracy achieved by training all tasks together jointly. This gap has hindered or even prevented the adoption of continual learning in applications, as accuracy is often of paramount importance. Recently, another challenge, termed inter-task class separation (ICS), was also identified, which spurred a theoretical study into principled approaches for solving continual learning. Further research has shown that by leveraging the theory and the power of large foundation models, it is now possible to achieve upper-bound accuracy, which has been empirically validated using both text and image classification datasets. Continual learning is now ready for real-life applications. This paper surveys the main research leading to this achievement, justifies the approach both intuitively and from neuroscience research, and discusses insights gained.

This study examines the growing use of Large Language Models (LLMs) in child-centered applications, highlighting safety and ethical concerns such as bias, harmful content, and cultural insensitivity. Despite their potential to enhance learning, there is a lack of standardized frameworks to mitigate these risks. Through a systematic literature review, we identify key parental and empirical concerns, including toxicity and ethical breaches in AI outputs. Moreover, to address these issues, this paper proposes a protection framework for safe Child-LLM interaction, incorporating metrics for content safety, behavioral ethics, and cultural sensitivity. The framework provides practical tools for evaluating LLM safety, offering guidance for developers, policymakers, and educators to ensure responsible AI deployment for children.

Computing molecular vibrational energies and wavefunctions using variational approaches is a computationally demanding task, with the primary bottleneck being the diagonalization of the Hamiltonian matrix. The achievable accuracy depends on the dimensionality and complexity of the vibrational problem, the number and quality of the utilized basis functions and on the choice of vibrational coordinates. Composing basis sets with normalizing flows is a newly emerged idea to improve their expressivity and subsequently reduce the computational effort of variational methods. This approach generates coordinates tailored to a given vibrational problem for a selected truncated basis. We illustrate that the optimized coordinates results in more accurate predictions and faster convergence when transferred across different basis-set truncations, without the need for re-optimization. In addition, we show that the optimized coordinates are transferable across isotopologues and across molecules with similar structural motifs.

Electrocardiogram (ECG)-based biometrics offer a promising method for user identification, combining intrinsic liveness detection with morphological uniqueness. However, elevated heart rates introduce significant physiological variability, posing challenges to pattern recognition systems and leading to a notable performance gap between resting and post-exercise conditions. Addressing this gap is critical for advancing ECG-based biometric systems for real-world applications. We propose DE-PADA, a Dual Expert model with Personalized Augmentation and Domain Adaptation, designed to enhance robustness across diverse physiological states. The model is trained primarily on resting-state data from the evaluation dataset, without direct exposure to their exercise data. To address variability, DE-PADA incorporates ECG-specific innovations, including heartbeat segmentation into the PQRS interval, known for its relative temporal consistency, and the heart rate-sensitive ST interval, enabling targeted feature extraction tailored to each region's unique characteristics. Personalized augmentation simulates subject-specific T-wave variability across heart rates using individual T-wave peak predictions to adapt augmentation ranges. Domain adaptation further improves generalization by leveraging auxiliary data from supplementary subjects used exclusively for training, including both resting and exercise conditions. Experiments on the University of Toronto ECG Database demonstrate the model's effectiveness. DE-PADA achieves relative improvements in post-exercise identification rates of 26.75% in the initial recovery phase and 11.72% in the late recovery phase, while maintaining a 98.12% identification rate in the sitting position. These results highlight DE-PADA's ability to address intra-subject variability and enhance the robustness of ECG-based biometric systems across diverse physiological states.

Time constraints on doctor patient interaction and restricted access to specialists under the managed care system led to increasingly referring to computers as a medical information source and a self-health-care management tool. However, research show that less than 40% of information seekers indicated that online information helped them to make a decision about their health. Searching multiple web sites that need basic computer skills, lack of interaction and no face to face interaction in most search engines and some social issues, led us to develop a specialized life-like agent that would overcome mentioned problems., Comment: 6 pages, 2 figures, 3rd International Conference on Machine Learning and Computing (ICMLC 2011): February 26-28, 2011, Singapore

Chiral-spin modes are collective excitations of a spin-orbit (SO) coupled system that lead to resonances in many observables. Here we identify resonances in "cross-response", i.e., electric-field induced magnetization and magnetic-field induced electric currents, known also as the Edelstein effect and its inverse, respectively. We show that the chiral-spin modes resonantly enhance the electrically induced magnetization. As specific examples, we consider a single-valley two-dimensional electron gas with Rashba or Dresselhaus SO coupling and a two-valley Dirac system with proximity-induced Rashba and valley-Zeeman SO couplings. We suggest an architecture for a spin-pumping experiment based on THz excitation of chiral-spin modes, which would demonstrate a resonant enhancement of charge-to-spin conversion.

The rapid evolution of cellular networks has introduced groundbreaking technologies, including large and distributed antenna arrays and reconfigurable intelligent surfaces in terrestrial networks (TNs), as well as aerial and space-based nodes in non-terrestrial networks (NTNs). These advancements enable applications beyond traditional communication, such as high-precision localization and sensing. While integrating TN and NTN enablers will lead to unparalleled opportunities for seamless global localization, such integration attempts are expected to face several challenges. To understand these opportunities and challenges, we first examine the distinctive characteristics of the key 6G enablers, evaluating their roles in localization from both technical and practical perspectives. Next, to identify developments driving TN-NTN localization, we review the latest standardization and industrial innovation progress. Finally, we discuss the opportunities and challenges of TN-NTN integration, illustrating its potential through two numerical case studies., Comment: 8 pages, 5 figures, submitted to IEEE Communications Standards Magazine: Special issue on Integrated Terrestrial and Non-Terrestrial Networks

Spin-orbit coupling in systems with broken inversion symmetry gives rise to the Edelstein effect, which is the induced spin polarization in response to an applied electric field or current, and the inverse Edelstein effect, which is the induced electric current in response to an oscillatory magnetic field or spin polarization. At the same time, an interplay between spin-orbit coupling and electron-electron interaction leads to a special type of collective excitations -- chiral-spin modes -- which are oscillations of spin polarization in the absence of a magnetic field. As a result, both Edelstein and inverse Edelstein effects exhibit resonances at the frequencies of spin-chiral collective modes. Here, we present a detailed study of the effect of electron correlation on the Edelstein and inverse Edelstein effects in a single-valley two-dimensional electron gas and a multi-valley Dirac system with proximity-induced spin-orbit coupling. While the chiral-spin modes involve both in-plane and out-of-plane oscillations of spins, we show that only the in-plane modes are responsible for the above resonances. In the multi-valley system, electron correlation splits the in-plane modes into two. We also study the spectral weight distribution between the two resonances over a large parameter space of intra- and inter-valley interactions.

Satellites are highly vulnerable to adversarial glitches or high-energy radiation in space, which could cause faults on the onboard computer. Various radiation- and fault-tolerant methods, such as error correction codes (ECC) and redundancy-based approaches, have been explored over the last decades to mitigate temporary soft errors on software and hardware. However, conventional ECC methods fail to deal with hard errors or permanent faults in the hardware components. This work introduces a detection- and response-based countermeasure to deal with partially damaged processor chips. It recovers the processor chip from permanent faults and enables continuous operation with available undamaged resources on the chip. We incorporate digitally-compatible delay-based sensors on the target processor's chip to reliably detect the incoming radiation or glitching attempts on the physical fabric of the chip, even before a fault occurs. Upon detecting a fault in one or more components of the processor's arithmetic logic unit (ALU), our countermeasure employs adaptive software recompilations to resynthesize and substitute the affected instructions with instructions of still functioning components to accomplish the task. Furthermore, if the fault is more widespread and prevents the correct operation of the entire processor, our approach deploys adaptive hardware partial reconfigurations to replace and reroute the failed components to undamaged locations of the chip. To validate our claims, we deploy a high-energy near-infrared (NIR) laser beam on a RISC-V processor implemented on a 28~nm FPGA to emulate radiation and even hard errors by partially damaging the FPGA fabric. We demonstrate that our sensor can confidently detect the radiation and trigger the processor testing and fault recovery mechanisms. Finally, we discuss the overhead imposed by our countermeasure., Comment: 9 pages, 10 figures, Workshop on the Security of Space and Satellite Systems

The use of Sentinel-2 images to compute Normalized Difference Water Index (NDWI) has many applications, including water body area detection. However, cloud cover poses significant challenges in this regard, which hampers the effectiveness of Sentinel-2 images in this context. In this paper, we present a deep learning model that can generate NDWI given Sentinel-1 images, thereby overcoming this cloud barrier. We show the effectiveness of our model, where it demonstrates a high accuracy of 0.9134 and an AUC of 0.8656 to predict the NDWI. Additionally, we observe promising results with an R2 score of 0.4984 (for regressing the NDWI values) and a Mean IoU of 0.4139 (for the underlying segmentation task). In conclusion, our model offers a first and robust solution for generating NDWI images directly from Sentinel-1 images and subsequent use for various applications even under challenging conditions such as cloud cover and nighttime.

Virtualization in 5G and beyond networks allows the creation of virtual networks, or network slices, tailored to meet the requirements of various applications. However, this flexibility introduces several challenges for infrastructure providers (InPs) in slice admission control (AC) and resource allocation. To maximize revenue, InPs must decide in real-time whether to admit new slice requests (SRs) given slices' revenues, limited infrastructure resources, unknown relationship between resource allocation and Quality of Service (QoS), and the unpredictability of future SRs. To address these challenges, this paper introduces a novel data-driven framework for 5G slice admission control that offers a guaranteed upper bound on the competitive ratio, i.e., the ratio between the revenue obtained by an oracle solution and that of the online solution. The proposed framework leverages a pricing function to dynamically estimate resources' pseudo-prices that reflect resource scarcity. Such prices are further coupled with a resource allocation algorithm, which leverages a machine-learned slice model and employs a primal-dual algorithm to determine the minimum-cost resource allocation. The resource cost is then compared with the offered revenue to admit or reject a SR. To demonstrate the efficacy of our framework, we train the data-driven slice model using real traces collected from our 5G testbed. Our results show that our novel approach achieves up to 42% improvement in the empirical competitive ratio, i.e., ratio between the optimal and the online solution, compared to other benchmark algorithms.

The ground-state spin of optically active defects in hexagonal boron nitride (hBN) offers a promising platform for quantum information applications, such as qubits for quantum computing and nanoscale sensing. A key characteristic of a qubit is its decoherence time, as its duration and controllability are critical for practical applications in quantum technologies. In this work, we investigate the electron spin dephasing time of the negatively charged boron vacancies, $V_{B}$ centers, in the hBN lattice by considering the dipolar hyperfine as well as spin-phonon interactions. We employ an approximate method based on the Holstein-Primakoff transformation to take into account a large number of nuclear spins and Debye model to consider the effect of lattice phonons. We show that, in the presence of the dipolar hyperfine interactions, Hahn-echo coherence time of the $V_{B}$ electron spin is approximately $30\: \mathrm{\mu s}$ at room temperature. Our results provide a step forward in understanding the $V_{B}$ defect decoherence in the hBN, which might be used for quantum information applications.

In the rapidly evolving field of quantum computing, niobium nitride (NbN) superconductors have emerged as integral components due to their unique structural properties, including a high superconducting transition temperature (Tc), exceptional electrical conductivity, and compatibility with advanced device architectures. This study investigates the impact of high-temperature annealing and high-dose gamma irradiation on the structural and superconducting properties of NbN films grown on GaN via reactive DC magnetron sputtering. The as-deposited cubic {\delta}-NbN (111) films exhibited a high-intensity XRD peak, high Tc of 12.82K, and an atomically flat surface. Annealing at 500 and 950 {\deg}C for varying durations revealed notable structural and surface changes. High-resolution STEM indicated improved local ordering, while AFM showed reduced surface roughness after annealing. XPS revealed a gradual increase in the Nb/N ratio with higher annealing temperatures and durations. High-resolution XRD and STEM analyses showed lattice constant modifications in {\delta}-NbN films, attributed to residual stress changes following annealing. Additionally, XRD phi-scans revealed sixfold symmetry in NbN films due to rotational domains relative to GaN. While Tc remained stable after annealing at 500 {\deg}C, increasing the annealing temperature to 950 {\deg}C degraded Tc to ~8K and reduced the residual resistivity ratio from 0.85 in as-deposited films to 0.29 after 30 minutes. The effects of gamma radiation (5 Mrad (Si)) were also studied, demonstrating minimal changes to crystallinity and superconducting performance, indicating excellent radiation resilience. These findings highlight the potential of NbN superconductors for integration into advanced quantum devices and their suitability for applications in radiation-intensive environments such as space, satellites, and nuclear power plants.

The Internet of Things (IoT) and mobile technology have significantly transformed healthcare by enabling real-time monitoring and diagnosis of patients. Recognizing medical-related human activities (MRHA) is pivotal for healthcare systems, particularly for identifying actions that are critical to patient well-being. However, challenges such as high computational demands, low accuracy, and limited adaptability persist in Human Motion Recognition (HMR). While some studies have integrated HMR with IoT for real-time healthcare applications, limited research has focused on recognizing MRHA as essential for effective patient monitoring. This study proposes a novel HMR method for MRHA detection, leveraging multi-stage deep learning techniques integrated with IoT. The approach employs EfficientNet to extract optimized spatial features from skeleton frame sequences using seven Mobile Inverted Bottleneck Convolutions (MBConv) blocks, followed by ConvLSTM to capture spatio-temporal patterns. A classification module with global average pooling, a fully connected layer, and a dropout layer generates the final predictions. The model is evaluated on the NTU RGB+D 120 and HMDB51 datasets, focusing on MRHA, such as sneezing, falling, walking, sitting, etc. It achieves 94.85% accuracy for cross-subject evaluations and 96.45% for cross-view evaluations on NTU RGB+D 120, along with 89.00% accuracy on HMDB51. Additionally, the system integrates IoT capabilities using a Raspberry Pi and GSM module, delivering real-time alerts via Twilios SMS service to caregivers and patients. This scalable and efficient solution bridges the gap between HMR and IoT, advancing patient monitoring, improving healthcare outcomes, and reducing costs.

Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning pre-trained models, which can have large weight and activation outlier values that make lower-precision optimization difficult. To address this, we present HALO, a novel quantization-aware training approach for Transformers that enables accurate and efficient low-precision training by combining 1) strategic placement of Hadamard rotations in both forward and backward passes, which mitigate outliers, 2) high-performance kernel support, and 3) FSDP integration for low-precision communication. Our approach ensures that all large matrix multiplications during the forward and backward passes are executed in lower precision. Applied to LLAMA-family models, HALO achieves near-full-precision-equivalent results during fine-tuning on various tasks, while delivering up to 1.41x end-to-end speedup for full fine-tuning on RTX 4090 GPUs. HALO efficiently supports both standard and parameterefficient fine-tuning (PEFT). Our results demonstrate the first practical approach to fully quantized LLM fine-tuning that maintains accuracy in 8-bit precision, while delivering performance benefits. Code is available at \url{https://github.com/IST-DASLab/HALO}., Comment: 13 pages, 6 figures

This study introduces AGGA, a dataset comprising 80 academic guidelines for the use of Generative AIs (GAIs) and Large Language Models (LLMs) in academic settings, meticulously collected from official university websites. The dataset contains 188,674 words and serves as a valuable resource for natural language processing tasks commonly applied in requirements engineering, such as model synthesis, abstraction identification, and document structure assessment. Additionally, AGGA can be further annotated to function as a benchmark for various tasks, including ambiguity detection, requirements categorization, and the identification of equivalent requirements. Our methodologically rigorous approach ensured a thorough examination, with a selection of universities that represent a diverse range of global institutions, including top-ranked universities across six continents. The dataset captures perspectives from a variety of academic fields, including humanities, technology, and both public and private institutions, offering a broad spectrum of insights into the integration of GAIs and LLMs in academia., Comment: arXiv admin note: text overlap with arXiv:2406.18842, arXiv:2501.00959

Parkinson's disease (PD), the second most common neurodegenerative disorder, is characterized by dopaminergic neuron loss and the accumulation of abnormal synuclein. PD presents both motor and non-motor symptoms that progressively impair daily functioning. The severity of these symptoms is typically assessed using the MDS-UPDRS rating scale, which is subjective and dependent on the physician's experience. Additionally, PD shares symptoms with other neurodegenerative diseases, such as progressive supranuclear palsy (PSP) and multiple system atrophy (MSA), complicating accurate diagnosis. To address these diagnostic challenges, we propose a machine learning-based system for differential diagnosis of PD, PSP, MSA, and healthy controls (HC). This system utilizes a kinematic feature-based hierarchical feature extraction and selection approach. Initially, 18 kinematic features are extracted, including two newly proposed features: Thumb-to-index vector velocity and acceleration, which provide insights into motor control patterns. In addition, 41 statistical features were extracted here from each kinematic feature, including some new approaches such as Average Absolute Change, Rhythm, Amplitude, Frequency, Standard Deviation of Frequency, and Slope. Feature selection is performed using One-way ANOVA to rank features, followed by Sequential Forward Floating Selection (SFFS) to identify the most relevant ones, aiming to reduce the computational complexity. The final feature set is used for classification, achieving a classification accuracy of 66.67% for each dataset and 88.89% for each patient, with particularly high performance for the MSA and HC groups using the SVM algorithm. This system shows potential as a rapid and accurate diagnostic tool in clinical practice, though further data collection and refinement are needed to enhance its reliability.

This paper introduces IGGA, a dataset of 160 industry guidelines and policy statements for the use of Generative AIs (GAIs) and Large Language Models (LLMs) in industry and workplace settings, collected from official company websites, and trustworthy news sources. The dataset contains 104,565 words and serves as a valuable resource for natural language processing tasks commonly applied in requirements engineering, such as model synthesis, abstraction identification, and document structure assessment. Additionally, IGGA can be further annotated to function as a benchmark for various tasks, including ambiguity detection, requirements categorization, and the identification of equivalent requirements. Our methodologically rigorous approach ensured a thorough examination, with a selection of reputable and influential companies that represent a diverse range of global institutions across six continents. The dataset captures perspectives from fourteen industry sectors, including technology, finance, and both public and private institutions, offering a broad spectrum of insights into the integration of GAIs and LLMs in industry.

The rise of Generative AI (GAI) and Large Language Models (LLMs) has transformed industrial landscapes, offering unprecedented opportunities for efficiency and innovation while raising critical ethical, regulatory, and operational challenges. This study conducts a text-based analysis of 160 guidelines and policy statements across fourteen industrial sectors, utilizing systematic methods and text-mining techniques to evaluate the governance of these technologies. By examining global directives, industry practices, and sector-specific policies, the paper highlights the complexities of balancing innovation with ethical accountability and equitable access. The findings provide actionable insights and recommendations for fostering responsible, transparent, and safe integration of GAI and LLMs in diverse industry contexts.

Hirschsprung's disease (HD) is a congenital birth defect diagnosed by identifying the lack of ganglion cells within the colon's muscularis propria, specifically within the myenteric plexus regions. There may be advantages for quantitative assessments of histopathology images of the colon, such as counting the ganglion and assessing their spatial distribution; however, this would be time-intensive for pathologists, costly, and subject to inter- and intra-rater variability. Previous research has demonstrated the potential for deep learning approaches to automate histopathology image analysis, including segmentation of the muscularis propria using convolutional neural networks (CNNs). Recently, Vision Transformers (ViTs) have emerged as a powerful deep learning approach due to their self-attention. This study explores the application of ViTs for muscularis propria segmentation in calretinin-stained histopathology images and compares their performance to CNNs and shallow learning methods. The ViT model achieved a DICE score of 89.9% and Plexus Inclusion Rate (PIR) of 100%, surpassing the CNN (DICE score of 89.2%; PIR of 96.0%) and k-means clustering method (DICE score of 80.7%; PIR 77.4%). Results assert that ViTs are a promising tool for advancing HD-related image analysis., Comment: To be published in the CMBEC47/ACCES26 Joint Conference

The integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) opens new avenues for addressing complex challenges in multimodal content analysis, particularly in biased news detection. This study introduces VLBias, a framework that leverages state-of-the-art LLMs and VLMs to detect linguistic and visual biases in news content. We present a multimodal dataset comprising textual content and corresponding images from diverse news sources. We propose a hybrid annotation framework that combines LLM-based annotations with human review to ensure high-quality labeling while reducing costs and enhancing scalability. Our evaluation compares the performance of state-of-the-art SLMs and LLMs for both modalities (text and images) and the results reveal that while SLMs are computationally efficient, LLMs demonstrate superior accuracy in identifying subtle framing and text-visual inconsistencies. Furthermore, empirical analysis shows that incorporating visual cues alongside textual data improves bias detection accuracy by 3 to 5%. This study provides a comprehensive exploration of LLMs, SLMs, and VLMs as tools for detecting multimodal biases in news content and highlights their respective strengths, limitations, and potential for future applications, Comment: Under review

Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation (ICS). Despite numerous proposed methods, these issues remain persistent obstacles. This paper proposes a novel CIL method, called Kernel Linear Discriminant Analysis (KLDA), that can effectively avoid CF and ICS problems. It leverages only the powerful features learned in a foundation model (FM). However, directly using these features proves suboptimal. To address this, KLDA incorporates the Radial Basis Function (RBF) kernel and its Random Fourier Features (RFF) to enhance the feature representations from the FM, leading to improved performance. When a new task arrives, KLDA computes only the mean for each class in the task and updates a shared covariance matrix for all learned classes based on the kernelized features. Classification is performed using Linear Discriminant Analysis. Our empirical evaluation using text and image classification datasets demonstrates that KLDA significantly outperforms baselines. Remarkably, without relying on replay data, KLDA achieves accuracy comparable to joint training of all classes, which is considered the upper bound for CIL performance. The KLDA code is available at https://github.com/salehmomeni/klda.

Parkinson's disease (PD) is a progressive neurological disorder that impairs movement control, leading to symptoms such as tremors, stiffness, and bradykinesia. Many researchers analyzing handwriting data for PD detection typically rely on computing statistical features over the entirety of the handwriting task. While this method can capture broad patterns, it has several limitations, including a lack of focus on dynamic change, oversimplified feature representation, lack of directional information, and missing micro-movements or subtle variations. Consequently, these systems face challenges in achieving good performance accuracy, robustness, and sensitivity. To overcome this problem, we proposed an optimized PD detection methodology that incorporates newly developed dynamic kinematic features and machine learning (ML)-based techniques to capture movement dynamics during handwriting tasks. In the procedure, we first extracted 65 newly developed kinematic features from the first and last 10% phases of the handwriting task rather than using the entire task. Alongside this, we also reused 23 existing kinematic features, resulting in a comprehensive new feature set. Next, we enhanced the kinematic features by applying statistical formulas to compute hierarchical features from the handwriting data. This approach allows us to capture subtle movement variations that distinguish PD patients from healthy controls. To further optimize the feature set, we applied the Sequential Forward Floating Selection method to select the most relevant features, reducing dimensionality and computational complexity. Finally, we employed an ML-based approach based on ensemble voting across top-performing tasks, achieving an impressive 96.99\% accuracy on task-wise classification and 99.98% accuracy on task ensembles, surpassing the existing state-of-the-art model by 2% for the PaHaW dataset.

Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating any parameters. However, incrementally learning each new task in ICL necessitates adding training examples from each class of the task to the prompt, which hampers scalability as the prompt length increases. This issue not only leads to excessively long prompts that exceed the input token limit of the underlying LLM but also degrades the model's performance due to the overextended context. To address this, we introduce InCA, a novel approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without CF. The ECL is built incrementally to pre-select a small subset of likely classes for each test instance. By restricting the ICL prompt to only these selected classes, InCA prevents prompt lengths from becoming excessively long, while maintaining high performance. Experimental results demonstrate that InCA significantly outperforms existing CL baselines, achieving substantial performance gains.

Knee osteoporosis weakens the bone tissue in the knee joint, increasing fracture risk. Early detection through X-ray images enables timely intervention and improved patient outcomes. While some researchers have focused on diagnosing knee osteoporosis through manual radiology evaluation and traditional machine learning using hand-crafted features, these methods often struggle with performance and efficiency due to reliance on manual feature extraction and subjective interpretation. In this study, we propose a computer-aided diagnosis (CAD) system for knee osteoporosis, combining transfer learning with stacked feature enhancement deep learning blocks. Initially, knee X-ray images are preprocessed, and features are extracted using a pre-trained Convolutional Neural Network (CNN). These features are then enhanced through five sequential Conv-RELU-MaxPooling blocks. The Conv2D layers detect low-level features, while the ReLU activations introduce non-linearity, allowing the network to learn complex patterns. MaxPooling layers down-sample the features, retaining the most important spatial information. This sequential processing enables the model to capture complex, high-level features related to bone structure, joint deformation, and osteoporotic markers. The enhanced features are passed through a classification module to differentiate between healthy and osteoporotic knee conditions. Extensive experiments on three individual datasets and a combined dataset demonstrate that our model achieves 97.32%, 98.24%, 97.27%, and 98.00% accuracy for OKX Kaggle Binary, KXO-Mendeley Multi-Class, OKX Kaggle Multi-Class, and the combined dataset, respectively, showing an improvement of around 2% over existing methods.

Heart disease is a leading cause of premature death worldwide, particularly among middle-aged and older adults, with men experiencing a higher prevalence. According to the World Health Organization (WHO), non-communicable diseases, including heart disease, account for 25\% (17.9 million) of global deaths, with over 43,204 annual fatalities in Bangladesh. However, the development of heart disease detection (HDD) systems tailored to the Bangladeshi population remains underexplored due to the lack of benchmark datasets and reliance on manual or limited-data approaches. This study addresses these challenges by introducing new, ethically sourced HDD dataset, BIG-Dataset and CD dataset which incorporates comprehensive data on symptoms, examination techniques, and risk factors. Using advanced machine learning techniques, including Logistic Regression and Random Forest, we achieved a remarkable testing accuracy of up to 96.6\% with Random Forest. The proposed AI-driven system integrates these models and datasets to provide real-time, accurate diagnostics and personalized healthcare recommendations. By leveraging structured datasets and state-of-the-art machine learning algorithms, this research offers an innovative solution for scalable and effective heart disease detection, with the potential to reduce mortality rates and improve clinical outcomes.

Shape completion, a crucial task in 3D computer vision, involves predicting and filling the missing regions of scanned or partially observed objects. Current methods expect known pose or canonical coordinates and do not perform well under varying rotations, limiting their real-world applicability. We introduce ESCAPE (Equivariant Shape Completion via Anchor Point Encoding), a novel framework designed to achieve rotation-equivariant shape completion. Our approach employs a distinctive encoding strategy by selecting anchor points from a shape and representing all points as a distance to all anchor points. This enables the model to capture a consistent, rotation-equivariant understanding of the object's geometry. ESCAPE leverages a transformer architecture to encode and decode the distance transformations, ensuring that generated shape completions remain accurate and equivariant under rotational transformations. Subsequently, we perform optimization to calculate the predicted shapes from the encodings. Experimental evaluations demonstrate that ESCAPE achieves robust, high-quality reconstructions across arbitrary rotations and translations, showcasing its effectiveness in real-world applications without additional pose estimation modules.

We systematically investigated the growth of Si-doped $\beta$-Ga$_2$O$_3$ films using LPCVD system, achieving high electron mobilities of 162 cm$^2$/V.s and 149 cm$^2$/V.s at carrier concentrations of $1.51 \times 10^{17}$ cm$^{-3}$ and $1.15 \times 10^{17}$ cm$^{-3}$, respectively, for homoepitaxial (010) $\beta$-Ga$_2$O$_3$ films grown on $\beta$-Ga$_2$O$_3$ substrates and heteroepitaxial (-201) $\beta$-Ga$_2$O$_3$ films grown on off-axis c-sapphire substrates with 6{\deg} miscut, representing the highest mobilities reported for LPCVD-grown $\beta$-Ga$_2$O$_3$ materials. Carrier concentrations were precisely tuned by varying SiCl$_4$ flow rates at a growth temperature of 1000{\deg}C, resulting in concentrations ranging from $1.15 \times 10^{17}$ to $1.19 \times 10^{19}$ cm$^{-3}$, as confirmed by both Hall and C-V measurements. The films exhibited high crystalline quality, confirmed by high-resolution XRD and Raman spectroscopy, indicating phase purity and structural integrity. Surface morphologies characterized by FESEM and AFM imaging showed a strong correlation between carrier concentrations and surface smoothness, with lower concentrations resulting in reduced RMS roughness. SIMS analysis revealed uniform Si incorporation, with low carbon, hydrogen, and chlorine impurities below detection limits, indicating high purity of the films. A high low-temperature peak mobility exceeding 843 cm$^2$/V$\cdot$s was achieved for (-201) $\beta$-Ga$_2$O$_3$ films at 80 K, highlighting the high purity and low compensation of these films. These findings emphasize the potential of LPCVD growth system for producing high-purity $\beta$-Ga$_2$O$_3$ films with thickness ranging between ~2.3-11.7 $\mu$m and faster growth rates (~4.7-17 $\mu$m/hr), promising transport properties, controllable doping, and scalability for developing high power vertical devices.

Superparamagnetic iron-oxide nanoparticles (SPIONs) are promising probes for biomedical imaging, but the heterogeneity of their magnetic properties is difficult to characterize with existing methods. Here, we perform widefield imaging of the stray magnetic fields produced by hundreds of isolated ~30-nm SPIONs using a magnetic microscope based on nitrogen-vacancy centers in diamond. By analyzing the SPION magnetic field patterns as a function of applied magnetic field, we observe substantial field-dependent transverse magnetization components that are typically obscured with ensemble characterization methods. We find negligible hysteresis in each of the three magnetization components for nearly all SPIONs in our sample. Most SPIONs exhibit a sharp Langevin saturation curve, enumerated by a characteristic polarizing applied field, B_c. The B_c distribution is highly asymmetric, with a standard deviation (1.4 mT) that is larger than the median (0.6 mT). Using time-resolved magnetic microscopy, we directly record SPION N\'eel relaxation, after switching off a 31 mT applied field, with a temporal resolution of ~60 ms that is limited by the ring-down time of the electromagnet coils. For small bias fields B_{hold}=1.5-3.5 mT, we observe a broad range of SPION N\'eel relaxation times--from milliseconds to seconds--that are consistent with an exponential dependence on B_{hold}. Our time-resolved diamond magnetic microscopy study reveals rich SPION sample heterogeneity and may be extended to other fundamental studies of nanomagnetism., Comment: Main text: 9 pages, 5 figures. Entire manuscript including Appendices: 31 pages, 24 figures

Tight and essentially tight modules generalize weakly injective modules. Essential tightness requires embeddings to be essential. This restriction makes the two notions totally different. In this note, we investigate cases when those two notions are the same. Moreover, we look at the cases when essentiallity is imposed only on one of the embeddings rather than both. This allows defining a special class of tight and essentially tight modules and a generalization of both.

This paper introduces a new application named ArPA for Arabic kids who have trouble with pronunciation. Our application comprises two key components: the diagnostic module and the therapeutic module. The diagnostic process involves capturing the child's speech signal, preprocessing, and analyzing it using different machine learning classifiers like K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Decision Trees as well as deep neural network classifiers like ResNet18. The therapeutic module offers eye-catching gamified interfaces in which each correctly spoken letter earns a higher avatar level, providing positive reinforcement for the child's pronunciation improvement. Two datasets were used for experimental evaluation: one from a childcare centre and the other including Arabic alphabet pronunciation recordings. Our work uses a novel technique for speech recognition using Melspectrogram and MFCC images. The results show that the ResNet18 classifier on speech-to-image converted data effectively identifies mispronunciations in Arabic speech with an accuracy of 99.015\% with Mel-Spectrogram images outperforming ResNet18 with MFCC images.

Quantization-aware training (QAT) schemes have been shown to achieve near-full precision accuracy. They accomplish this by training a quantized model for multiple epochs. This is computationally expensive, mainly because of the full precision backward pass. On the other hand, post-training quantization (PTQ) schemes do not involve training and are therefore computationally cheap, but they usually result in a significant accuracy drop. We address these challenges by proposing EfQAT, which generalizes both schemes by optimizing only a subset of the parameters of a quantized model. EfQAT starts by applying a PTQ scheme to a pre-trained model and only updates the most critical network parameters while freezing the rest, accelerating the backward pass. We demonstrate the effectiveness of EfQAT on various CNNs and Transformer-based models using different GPUs. Specifically, we show that EfQAT is significantly more accurate than PTQ with little extra compute. Furthermore, EfQAT can accelerate the QAT backward pass between 1.44-1.64x while retaining most accuracy., Comment: 12 pages, 5 figures

Post-traumatic stress disorder (PTSD) is a significant mental health challenge that affects individuals exposed to traumatic events. Early detection and effective intervention for PTSD are crucial, as it can lead to long-term psychological distress if untreated. Accurate detection of PTSD is essential for timely and targeted mental health interventions, especially in disaster-affected populations. Existing research has explored machine learning approaches for classifying PTSD, but many face limitations in terms of model performance and generalizability. To address these issues, we implemented a comprehensive preprocessing pipeline. This included data cleaning, missing value treatment using the SimpleImputer, label encoding of categorical variables, data augmentation using SMOTE to balance the dataset, and feature scaling with StandardScaler. The dataset was split into 80\% training and 20\% testing. We developed an ensemble model using a majority voting technique among several classifiers, including Logistic Regression, Support Vector Machines (SVM), Random Forest, XGBoost, LightGBM, and a customized Artificial Neural Network (ANN). The ensemble model achieved an accuracy of 96.76\% with a benchmark dataset, significantly outperforming individual models. The proposed method's advantages include improved robustness through the combination of multiple models, enhanced ability to generalize across diverse data points, and increased accuracy in detecting PTSD. Additionally, the use of SMOTE for data augmentation ensured better handling of imbalanced datasets, leading to more reliable predictions. The proposed approach offers valuable insights for policymakers and healthcare providers by leveraging predictive analytics to address mental health issues in vulnerable populations, particularly those affected by disasters.

Continuous Integration/Continuous Deployment (CI/CD) is fundamental for advanced software development, supporting faster and more efficient delivery of code changes into cloud environments. However, security issues in the CI/CD pipeline remain challenging, and incidents (e.g., DDoS, Bot, Log4j, etc.) are happening over the cloud environments. While plenty of literature discusses static security testing and CI/CD practices, only a few deal with network traffic pattern analysis to detect different cyberattacks. This research aims to enhance CI/CD pipeline security by implementing anomaly detection through AI (Artificial Intelligence) support. The goal is to identify unusual behaviour or variations from network traffic patterns in pipeline and cloud platforms. The system shall integrate into the workflow to continuously monitor pipeline activities and cloud infrastructure. Additionally, it aims to explore adaptive response mechanisms to mitigate the detected anomalies or security threats. This research employed two popular network traffic datasets, CSE-CIC-IDS2018 and CSE-CIC-IDS2017. We implemented a combination of Convolution Neural Network(CNN) and Long Short-Term Memory (LSTM) to detect unusual traffic patterns. We achieved an accuracy of 98.69% and 98.30% and generated log files in different CI/CD pipeline stages that resemble the network anomalies affected to address security challenges in modern DevOps practices, contributing to advancing software security and reliability., Comment: 10 pages

This paper presents, to our knowledge, a new approach in developing integrated pure heralded single-photon sources based on the interplay between the spontaneous four-wave mixing and sum-frequency generation parametric processes. We introduce a comprehensive quantum model to exploit this interplay in AlGaAs and LiNbO$_3$ nanophotonic waveguides. The developed model is used to assess the performance of the sources based on the photon-pair generation and the associated spectral purity. We find that this approach can remarkably improve the spectral purity of low-pure generated photon pairs, relaxing the restrictions on the structure design and the used pump wavelength. In addition, it overcomes the current hurdles in implementing on-chip photon detectors operating at room temperature, paving the way for advanced applications in integrated quantum photonics and information processing.

Objectives: Age and gender estimation is crucial for various applications, including forensic investigations and anthropological studies. This research aims to develop a predictive system for age and gender estimation in living individuals, leveraging dental measurements such as Coronal Height (CH), Coronal Pulp Cavity Height (CPCH), and Tooth Coronal Index (TCI). Methods: Machine learning models were employed in our study, including Cat Boost Classifier (Catboost), Gradient Boosting Machine (GBM), Ada Boost Classifier (AdaBoost), Random Forest (RF), eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGB), and Extra Trees Classifier (ETC), to analyze dental data from 862 living individuals (459 males and 403 females). Specifically, periapical radiographs from six teeth per individual were utilized, including premolars and molars from both maxillary and mandibular. A novel ensemble learning technique was developed, which uses multiple models each tailored to distinct dental metrics, to estimate age and gender accurately. Furthermore, an explainable AI model has been created utilizing SHAP, enabling dental experts to make judicious decisions based on comprehensible insight. Results: The RF and XGB models were particularly effective, yielding the highest F1 score for age and gender estimation. Notably, the XGB model showed a slightly better performance in age estimation, achieving an F1 score of 73.26%. A similar trend for the RF model was also observed in gender estimation, achieving a F1 score of 77.53%. Conclusions: This study marks a significant advancement in dental forensic methods, showcasing the potential of machine learning to automate age and gender estimation processes with improved accuracy.

We investigate the measurement incompatibility of continuous-variable systems with infinite-dimensional Hilbert spaces under the influence of pure losses, a fundamental noise source in quantum optics, and a significant challenge for long-distance quantum communication. We show that loss channels with transmissivities less than $1/n$ make any set of $n$ measurements compatible. Additionally, we design a set of measurements that remains incompatible even under extreme losses, where the number of measurements in the set increases with the amount of loss. These measurements rely on on-off photodetectors and linear optics, making them feasible for implementation under realistic laboratory conditions. Furthermore, we demonstrate that no loss channel can break the incompatibility of all measurements. As a result, quantum steering remains achievable in the presence of pure loss., Comment: In the new version we add a new analytical result: Measurement incompatibility (and therefore steering) never breaks under pure loss

In recent years, advanced artificial intelligence technologies, such as ChatGPT, have significantly impacted various fields, including education and research. Developed by OpenAI, ChatGPT is a powerful language model that presents numerous opportunities for students and educators. It offers personalized feedback, enhances accessibility, enables interactive conversations, assists with lesson preparation and evaluation, and introduces new methods for teaching complex subjects. However, ChatGPT also poses challenges to traditional education and research systems. These challenges include the risk of cheating on online exams, the generation of human-like text that may compromise academic integrity, a potential decline in critical thinking skills, and difficulties in assessing the reliability of information generated by AI. This study examines both the opportunities and challenges ChatGPT brings to education from the perspectives of students and educators. Specifically, it explores the role of ChatGPT in helping students develop their subjective skills. To demonstrate its effectiveness, we conducted several subjective experiments using ChatGPT, such as generating solutions from subjective problem descriptions. Additionally, surveys were conducted with students and teachers to gather insights into how ChatGPT supports subjective learning and teaching. The results and analysis of these surveys are presented to highlight the impact of ChatGPT in this context.

Cells operate in part by compartmentalizing chemical reactions. For example, recent work has shown that chromatin, the material that contains the cell's genome, can auto-regulate its structure by utilizing reaction products (proteins, RNA) to compartmentalize biomolecules via liquid-liquid phase separation (LLPS). Here, we develop a model biomolecular system that permits quantitative investigation of such dynamics, particularly by coupling a phase-separating system of DNA nanostars to an in vitro transcription reaction. The DNA nanostars' sequence is designed such that they self-assemble into liquid droplets only in the presence of a transcribed single-stranded RNA linker. We find that nanostar droplets form with a substantial delay and non-linear response to the kinetics of RNA synthesis. In addition, we utilize the compartments generated by the phase-separation process to engineer an activator/repressor network, where the transcription reaction activates the formation of droplets, and then droplets suppress the transcription reaction by segregating transcription components inside them. Our work on transcription-driven liquid-liquid phase separation constitutes a robust and programmable platform to explore non-equilibrium reaction-phase transition dynamics and could also provide a foundation to understand the dynamics of transcriptional condensate assembly in cells.