Search

Real time vehicle detection is a challenging task for urban traffic surveillance. Increase in urbanization leads to increase in accidents and traffic congestion in junction areas resulting in delayed travel time. In order to solve these problems, an intelligent system utilizing automatic detection and tracking system is significant. But this becomes a challenging task at road intersection areas which require a wide range of field view. For this reason, fish eye cameras are widely used in real time vehicle detection purpose to provide large area coverage and 360 degree view at junctions. However, it introduces challenges such as light glare from vehicles and street lights, shadow, non-linear distortion, scaling issues of vehicles and proper localization of small vehicles. To overcome each of these challenges, a modified YOLOv5 object detection scheme is proposed. YOLOv5 is a deep learning oriented convolutional neural network (CNN) based object detection method. The proposed scheme for detecting vehicles in fish-eye images consists of a light-weight day-night CNN classifier so that two different solutions can be implemented to address the day-night detection issues. Furthurmore, challenging instances are upsampled in the dataset for proper localization of vehicles and later on the detection model is ensembled and trained in different combination of vehicle datasets for better generalization, detection and accuracy. For testing, a real world fisheye dataset provided by the Video and Image Processing (VIP) Cup organizer ISSD has been used which includes images from video clips of different fisheye cameras at junction of different cities during day and night time. Experimental results show that our proposed model has outperformed the YOLOv5 model on the dataset by 13.7% mAP @ 0.5.

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.

In the past two decades, Bangladesh experienced a substantial reduction in the prevalence of child labour, associated with improvements in school enrolment and completion. Despite progress, child labour persists in the country, also driven by household earning losses and school closures due to the COVID-19 pandemic. This report addresses a timely need for new research to help decision-makers and practitioners identify policy and programmatic actions that can support prevention and reduction of child labour, with a focus on the role of education. Drawing on quantitative secondary data analysis and qualitative primary data analysis, it offers an accessible and rigorous overview of recent trends and patterns in child labour and explores how these relate to children's schooling experiences. Implications of COVID-19 for education and labour, and the role of child marriage as a key related outcome, are also assessed. The report concludes with programmatic and research recommendations for further action. [This report was prepared by the Economic Research Group (ERG).]

One-class anomaly detection aims to detect objects that do not belong to a predefined normal class. In practice training data lack those anomalous samples; hence state-of-the-art methods are trained to discriminate between normal and synthetically-generated pseudo-anomalous data. Most methods use data augmentation techniques on normal images to simulate anomalies. However the best-performing ones implicitly leverage a geometric bias present in the benchmarking datasets. This limits their usability in more general conditions. Others are relying on basic noising schemes that may be suboptimal in capturing the underlying structure of normal data. In addition most still favour the image domain to generate pseudo-anomalies training models end-to-end from only the normal class and overlooking richer representations of the information. To overcome these limitations we consider frozen yet rich feature spaces given by pretrained models and create pseudo-anomalous features with a novel adaptive linear feature perturbation technique. It adapts the noise distribution to each sample applies decaying linear perturbations to feature vectors and further guides the classification process using a contrastive learning objective. Experimental evaluation conducted on both standard and geometric bias-free datasets demonstrates the superiority of our approach with respect to comparable baselines. The codebase is accessible via our public repository., Comment: Published in WACV 2025

Language is a cornerstone of cultural identity, yet globalization and the dominance of major languages have placed nearly 3,000 languages at risk of extinction. Existing AI-driven translation models prioritize efficiency but often fail to capture cultural nuances, idiomatic expressions, and historical significance, leading to translations that marginalize linguistic diversity. To address these challenges, we propose a multi-agent AI framework designed for culturally adaptive translation in underserved language communities. Our approach leverages specialized agents for translation, interpretation, content synthesis, and bias evaluation, ensuring that linguistic accuracy and cultural relevance are preserved. Using CrewAI and LangChain, our system enhances contextual fidelity while mitigating biases through external validation. Comparative analysis shows that our framework outperforms GPT-4o, producing contextually rich and culturally embedded translations, a critical advancement for Indigenous, regional, and low-resource languages. This research underscores the potential of multi-agent AI in fostering equitable, sustainable, and culturally sensitive NLP technologies, aligning with the AI Governance, Cultural NLP, and Sustainable NLP pillars of Language Models for Underserved Communities. Our full experimental codebase is publicly available at: https://github.com/ciol-researchlab/Context-Aware_Translation_MAS, Comment: Accepted in NAACL 2025 Workshop on Language Models for Underserved Communities (https://openreview.net/forum?id=RiCfefEHII)

One of the primary challenges in medical diagnostics is the accurate and efficient use of magnetic resonance imaging (MRI) for the detection of brain tumors. But the current machine learning (ML) approaches have two major limitations, data privacy and high latency. To solve the problem, in this work we propose a federated learning architecture for a better accurate brain tumor detection incorporating the YOLOv11 algorithm. In contrast to earlier methods of centralized learning, our federated learning approach protects the underlying medical data while supporting cooperative deep learning model training across multiple institutions. To allow the YOLOv11 model to locate and identify tumor areas, we adjust it to handle MRI data. To ensure robustness and generalizability, the model is trained and tested on a wide range of MRI data collected from several anonymous medical facilities. The results indicate that our method significantly maintains higher accuracy than conventional approaches.

Sharing of tabular data containing valuable but private information is limited due to legal and ethical issues. Synthetic data could be an alternative solution to this sharing problem, as it is artificially generated by machine learning algorithms and tries to capture the underlying data distribution. However, machine learning models are not free from memorization and may introduce biases, as they rely on training data. Producing synthetic data that preserves privacy and fairness while maintaining utility close to the real data is a challenging task. This research simultaneously addresses both the privacy and fairness aspects of synthetic data, an area not explored by other studies. In this work, we present PF-WGAN, a privacy-preserving, fair synthetic tabular data generator based on the WGAN-GP model. We have modified the original WGAN-GP by adding privacy and fairness constraints forcing it to produce privacy-preserving fair data. This approach will enable the publication of datasets that protect individual's privacy and remain unbiased toward any particular group. We compared the results with three state-of-the-art synthetic data generator models in terms of utility, privacy, and fairness across four different datasets. We found that the proposed model exhibits a more balanced trade-off among utility, privacy, and fairness.

Ternary shandite compounds with the general formula T3M2X2 (T = Ni, Co, Rh or Pd; M = Sn, In or Pb and X = S or Se) have emerged as a large pool of topological semimetals. This family of compounds hosts different topological phases for various combinations of T, M and X. This paper reports the observation of quantum oscillations under the high magnetic fields in Ni3In2S2-xSex single crystals. Angular dependence of oscillation frequency suggests an evolution of the Fermi surface from three-dimensional to two-dimensional on Se substitution for S in Ni3In2S2. The effective mass obtained for each composition by fitting the oscillation amplitude with the Lifshitz-Kosevich formula, shows no significant change, suggesting that the topological phase might be relatively robust against enhanced SOC upon Se doping in Ni3In2S2., Comment: 23 pages, 6 figures

Software projects thrive on the involvement and contributions of individuals from different backgrounds. However, toxic language and negative interactions can hinder the participation and retention of contributors and alienate newcomers. Proactive moderation strategies aim to prevent toxicity from occurring by addressing conversations that have derailed from their intended purpose. This study aims to understand and predict conversational derailment leading to toxicity on GitHub. To facilitate this research, we curate a novel dataset comprising 202 toxic conversations from GitHub with annotated derailment points, along with 696 non-toxic conversations as a baseline. Based on this dataset, we identify unique characteristics of toxic conversations and derailment points, including linguistic markers such as second-person pronouns, negation terms, and tones of Bitter Frustration and Impatience, as well as patterns in conversational dynamics between project contributors and external participants. Leveraging these empirical observations, we propose a proactive moderation approach to automatically detect and address potentially harmful conversations before escalation. By utilizing modern LLMs, we develop a conversation trajectory summary technique that captures the evolution of discussions and identifies early signs of derailment. Our experiments demonstrate that LLM prompts tailored to provide summaries of GitHub conversations achieve 69% F1-Score in predicting conversational derailment, strongly improving over a set of baseline approaches.

We investigate the impact of quantum well (QW) thickness on efficiency loss in c-plane InGaN/GaN LEDs using a small-signal electroluminescence (SSEL) technique. Multiple mechanisms related to efficiency loss are independently examined, including injection efficiency, carrier density vs. current density relationship, phase space filling (PSF), quantum confined stark effect (QCSE), and Coulomb enhancement. An optimal QW thickness of around 2.7 nm in these InGaN/GaN LEDs was determined for quantum wells having constant In composition. Despite better control of deep-level defects and lower carrier density at a given current density, LEDs with thin QWs still suffer from an imbalance of enhancement effects on the radiative and intrinsic Auger-Meitner recombination coefficients. The imbalance of enhancement effects results in a decline in internal quantum efficiency (IQE) and radiative efficiency with decreasing QW thickness at low current density in LEDs with QW thicknesses below 2.7 nm. We also investigate how LED modulation bandwidth varies with quantum well thickness, identifying the key trends and their implications for device performance., Comment: 15 pages, 6 figures

The quality of the silicon-oxide interface plays a crucial role in fabricating reproducible silicon spin qubits. In this work we characterize interface quality by performing mobility measurements on silicon Hall bars. We find a peak electron mobility of nearly $40,000\,\text{cm}^2/\text{Vs}$ in a device with a $21\,\text{nm}$ oxide layer, and a peak hole mobility of about $2,000\,\text{cm}^2/\text{Vs}$ in a device with $8\,\text{nm}$ oxide, the latter being the highest recorded mobility for a p-type silicon MOSFET. Despite the high device quality, we note an order-of-magnitude difference in mobility between electrons and holes. By studying additional n-type and p-type devices with identical oxides, and fitting to transport theory, we show that this mobility discrepancy is due to valence band nonparabolicity. The nonparabolicity endows holes with a density-dependent transverse effective mass ranging from $0.6m_0$ to $0.7m_0$, significantly larger than the usually quoted bend-edge mass of $0.22m_0$. Finally, we perform magnetotransport measurements to extract momentum and quantum scattering lifetimes.

The MEDVQA-GI challenge addresses the integration of AI-driven text-to-image generative models in medical diagnostics, aiming to enhance diagnostic capabilities through synthetic image generation. Existing methods primarily focus on static image analysis and lack the dynamic generation of medical imagery from textual descriptions. This study intends to partially close this gap by introducing a novel approach based on fine-tuned generative models to generate dynamic, scalable, and precise images from textual descriptions. Particularly, our system integrates fine-tuned Stable Diffusion and DreamBooth models, as well as Low-Rank Adaptation (LORA), to generate high-fidelity medical images. The problem is around two sub-tasks namely: image synthesis (IS) and optimal prompt production (OPG). The former creates medical images via verbal prompts, whereas the latter provides prompts that produce high-quality images in specified categories. The study emphasizes the limitations of traditional medical image generation methods, such as hand sketching, constrained datasets, static procedures, and generic models. Our evaluation measures showed that Stable Diffusion surpasses CLIP and DreamBooth + LORA in terms of producing high-quality, diversified images. Specifically, Stable Diffusion had the lowest Fr\'echet Inception Distance (FID) scores (0.099 for single center, 0.064 for multi-center, and 0.067 for combined), indicating higher image quality. Furthermore, it had the highest average Inception Score (2.327 across all datasets), indicating exceptional diversity and quality. This advances the field of AI-powered medical diagnosis. Future research will concentrate on model refining, dataset augmentation, and ethical considerations for efficiently implementing these advances into clinical practice

This paper presents the concept, design, channel modeling, beamforming algorithm, prototype fabrication, and experimental measurement of an electromagnetically reconfigurable fluid antenna system (ER-FAS), in which each FAS array element features electromagnetic (EM) reconfigurability. Unlike most existing FAS works that investigate spatial reconfigurability, the proposed ER-FAS enables direct control over the EM characteristics of each element, allowing for dynamic radiation pattern reconfigurability. Specifically, a novel ER-FAS architecture leveraging software-controlled fluidics is proposed, and corresponding wireless channel models are established. A low-complexity greedy beamforming algorithm is developed to jointly optimize the analog phase shift and the radiation state of each array element. The accuracy of the ER-FAS channel model and the effectiveness of the beamforming algorithm are validated through (i) full-wave EM simulations and (ii) numerical spectral efficiency evaluations. Simulation results confirm that the proposed ER-FAS significantly enhances spectral efficiency compared to conventional antenna arrays. To further validate this design, we fabricate hardware prototypes for both the ER-FAS element and array, using Galinstan liquid metal alloy, fluid silver paste, and software-controlled fluidic channels. The simulation results are experimentally verified through prototype measurements conducted in an anechoic chamber. Additionally, indoor communication trials are conducted via a pair of software-defined radios which demonstrate superior received power and bit error rate performance of the ER-FAS prototype. This work presents the first demonstration of a liquid-based ER-FAS in array configuration for enhancing communication systems.

We propose a novel mechanism for real-time (human-in-the-loop) feedback focused on false positive reduction to enhance anomaly detection models. It was designed for the lightweight deployment of a behavioral network anomaly detection model. This methodology is easily integrable to similar domains that require a premium on throughput while maintaining high precision. In this paper, we introduce Retrieval Augmented Anomaly Detection, a novel method taking inspiration from Retrieval Augmented Generation. Human annotated examples are sent to a vector store, which can modify model outputs on the very next processed batch for model inference. To demonstrate the generalization of this technique, we benchmarked several different model architectures and multiple data modalities, including images, text, and graph-based data., Comment: 6 pages, 3 figures. 2 tables, accepted at ISDFS 2025

A novel implementation of the traditional node-to-node Coulomb contact-friction problem is presented that utilizes run-time parameter updates on conventional elasto-plastic elements. The two-noded elements are defined by an independent uniaxial force-deformation (or constitutive) relation in each degree of freedom. The location of the two nodes may or may not be coincident. A parameter is a pointer to a value (nodal geometry, element property, material property, etc.) in the finite element domain that can be controlled by the user. Parameters that control the frictional interface normal and tangential responses are updated based on contact detection, and eliminate the need for adding new source code to the finite element library of a given software. The run-time algorithm for updating both an elastic and elasto-plastic force-deformation element to achieve a penalty-based contact-friction model is presented. Static and dynamic cases were investigated for a two-noded unit process and compared with the results obtained from closed-form solutions. Multiple interface elements were then used for the sliding, tipping, and rocking responses of a rigid block on rigid foundation. Finally, several case studies were investigated, and the findings were compared with the experimental results or solutions from the literature. The proposed friction-contact implementation can be deployed in larger finite element models, and parameter updates facilitate implementation of a wider array of friction models by changing only the constitutive model.

The broadcast nature of the wireless medium and openness of wireless standards, e.g., 3GPP releases 16-20, invite adversaries to launch various active and passive attacks on cellular and other wireless networks. This work identifies one such loose end of wireless standards and presents a novel passive attack method enabling an eavesdropper (Eve) to localize a line of sight wireless user (Bob) who is communicating with a base station or WiFi access point (Alice). The proposed attack involves two phases. In the first phase, Eve performs modulation classification by intercepting the downlink channel between Alice and Bob. This enables Eve to utilize the publicly available modulation and coding scheme (MCS) tables to do pesudo-ranging, i.e., the Eve determines the ring within which Bob is located, which drastically reduces the search space. In the second phase, Eve sniffs the uplink channel, and employs multiple strategies to further refine Bob's location within the ring. Towards the end, we present our thoughts on how this attack can be extended to non-line-of-sight scenarios, and how this attack could act as a scaffolding to construct a malicious digital twin map., Comment: 7 pages, 4 figures, submitted to IEEE for possible publication

Nowadays, DeepSeek, ChatGPT, and Google Gemini are the most trending and exciting Large Language Model (LLM) technologies for reasoning, multimodal capabilities, and general linguistic performance worldwide. DeepSeek employs a Mixture-of-Experts (MoE) approach, activating only the parameters most relevant to the task at hand, which makes it especially effective for domain-specific work. On the other hand, ChatGPT relies on a dense transformer model enhanced through reinforcement learning from human feedback (RLHF), and then Google Gemini actually uses a multimodal transformer architecture that integrates text, code, and images into a single framework. However, by using those technologies, people can be able to mine their desired text, code, images, etc, in a cost-effective and domain-specific inference. People may choose those techniques based on the best performance. In this regard, we offer a comparative study based on the DeepSeek, ChatGPT, and Gemini techniques in this research. Initially, we focus on their methods and materials, appropriately including the data selection criteria. Then, we present state-of-the-art features of DeepSeek, ChatGPT, and Gemini based on their applications. Most importantly, we show the technological comparison among them and also cover the dataset analysis for various applications. Finally, we address extensive research areas and future potential guidance regarding LLM-based AI research for the community.

Efficient exploration is essential for intelligent systems interacting with their environment, but existing language models often fall short in scenarios that require strategic information gathering. In this paper, we present PAPRIKA, a fine-tuning approach that enables language models to develop general decision-making capabilities that are not confined to particular environments. By training on synthetic interaction data from different tasks that require diverse strategies, PAPRIKA teaches models to explore and adapt their behavior on a new task based on environment feedback in-context without more gradient updates. Experimental results show that models fine-tuned with PAPRIKA can effectively transfer their learned decision-making capabilities to entirely unseen tasks without additional training. Unlike traditional training, our approach's primary bottleneck lies in sampling useful interaction data instead of model updates. To improve sample efficiency, we propose a curriculum learning strategy that prioritizes sampling trajectories from tasks with high learning potential. These results suggest a promising path towards AI systems that can autonomously solve novel sequential decision-making problems that require interactions with the external world., Comment: Project Website: https://paprika-llm.github.io

Electric load forecasting is essential for power management and stability in smart grids. This is mainly achieved via advanced metering infrastructure, where smart meters (SMs) record household energy data. Traditional machine learning (ML) methods are often employed for load forecasting but require data sharing which raises data privacy concerns. Federated learning (FL) can address this issue by running distributed ML models at local SMs without data exchange. However, current FL-based approaches struggle to achieve efficient load forecasting due to imbalanced data distribution across heterogeneous SMs. This paper presents a novel personalized federated learning (PFL) method for high-quality load forecasting in metering networks. A meta-learning-based strategy is developed to address data heterogeneity at local SMs in the collaborative training of local load forecasting models. Moreover, to minimize the load forecasting delays in our PFL model, we study a new latency optimization problem based on optimal resource allocation at SMs. A theoretical convergence analysis is also conducted to provide insights into FL design for federated load forecasting. Extensive simulations from real-world datasets show that our method outperforms existing approaches in terms of better load forecasting and reduced operational latency costs., Comment: arXiv admin note: text overlap with arXiv:2411.10619

This paper presents a novel knowledge distillation neural architecture leveraging efficient transformer networks for effective image classification. Natural images display intricate arrangements encompassing numerous extraneous elements. Vision transformers utilize localized patches to compute attention. However, exclusive dependence on patch segmentation proves inadequate in sufficiently encompassing the comprehensive nature of the image. To address this issue, we have proposed an inner-outer transformer-based architecture, which gives attention to the global and local aspects of the image. Moreover, The training of transformer models poses significant challenges due to their demanding resource, time, and data requirements. To tackle this, we integrate knowledge distillation into the architecture, enabling efficient learning. Leveraging insights from a larger teacher model, our approach enhances learning efficiency and effectiveness. Significantly, the transformer-in-transformer network acquires lightweight characteristics by means of distillation conducted within the feature extraction layer. Our featured network's robustness is established through substantial experimentation on the MNIST, CIFAR10, and CIFAR100 datasets, demonstrating commendable top-1 and top-5 accuracy. The conducted ablative analysis comprehensively validates the effectiveness of the chosen parameters and settings, showcasing their superiority against contemporary methodologies. Remarkably, the proposed Transformer-in-Transformer Network (TITN) model achieves impressive performance milestones across various datasets: securing the highest top-1 accuracy of 74.71% and a top-5 accuracy of 92.28% for the CIFAR100 dataset, attaining an unparalleled top-1 accuracy of 92.03% and top-5 accuracy of 99.80% for the CIFAR-10 dataset, and registering an exceptional top-1 accuracy of 99.56% for the MNIST dataset.

The autonomous AI agents using large language models can create undeniable values in all span of the society but they face security threats from adversaries that warrants immediate protective solutions because trust and safety issues arise. Considering the many-shot jailbreaking and deceptive alignment as some of the main advanced attacks, that cannot be mitigated by the static guardrails used during the supervised training, points out a crucial research priority for real world robustness. The combination of static guardrails in dynamic multi-agent system fails to defend against those attacks. We intend to enhance security for LLM-based agents through the development of new evaluation frameworks which identify and counter threats for safe operational deployment. Our work uses three examination methods to detect rogue agents through a Reverse Turing Test and analyze deceptive alignment through multi-agent simulations and develops an anti-jailbreaking system by testing it with GEMINI 1.5 pro and llama-3.3-70B, deepseek r1 models using tool-mediated adversarial scenarios. The detection capabilities are strong such as 94\% accuracy for GEMINI 1.5 pro yet the system suffers persistent vulnerabilities when under long attacks as prompt length increases attack success rates (ASR) and diversity metrics become ineffective in prediction while revealing multiple complex system faults. The findings demonstrate the necessity of adopting flexible security systems based on active monitoring that can be performed by the agents themselves together with adaptable interventions by system admin as the current models can create vulnerabilities that can lead to the unreliable and vulnerable system. So, in our work, we try to address such situations and propose a comprehensive framework to counteract the security issues., Comment: 18 pages, 7 figures

Centralized electronic health record repositories are critical for advancing disease surveillance, public health research, and evidence-based policymaking. However, developing countries face persistent challenges in achieving this due to fragmented healthcare data sources, inconsistent record-keeping practices, and the absence of standardized patient identifiers, limiting reliable record linkage, compromise data interoperability, and limit scalability-obstacles exacerbated by infrastructural constraints and privacy concerns. To address these barriers, this study proposes a scalable, privacy-preserving clinical data warehouse, NCDW, designed for heterogeneous EHR integration in resource-limited settings and tested with 1.16 million clinical records. The framework incorporates a wrapper-based data acquisition layer for secure, automated ingestion of multisource health data and introduces a soundex algorithm to resolve patient identity mismatches in the absence of unique IDs. A modular data mart is designed for disease-specific analytics, demonstrated through a dengue fever case study in Bangladesh, integrating clinical, demographic, and environmental data for outbreak prediction and resource planning. Quantitative assessment of the data mart underscores its utility in strengthening national decision-support systems, highlighting the model's adaptability for infectious disease management. Comparative evaluation of database technologies reveals NoSQL outperforms relational SQL by 40-69% in complex query processing, while system load estimates validate the architecture's capacity to manage 19 million daily records (34TB over 5 years). The framework can be adapted to various healthcare settings across developing nations by modifying the ingestion layer to accommodate standards like ICD-11 and HL7 FHIR, facilitating interoperability for managing infectious diseases (i.e., COVID, tuberculosis).

This paper studies the radio resource management (RRM) for the uplink (UL) of a cellular system with codebook-based hybrid beamforming. We consider the often neglected but highly practical multi-channel case with fewer radio frequency chains in the base station than user equipment (UEs) in the cell, assuming one RF chain per UE. As for any UL RRM, a per-time slot solution is needed as the allocation of power to subchannels by a UE can only be done once it knows which subchannels it has been allocated. The RRM in this system comprises beam selection, user selection and power allocation, three steps that are intricately coupled and we will show that the order in which they are performed does impact performance and so does the amount of coupling that we take into account. Specifically, we propose 4 online sequential solutions with different orders in which the steps are called and of different complexities, i.e., different levels of coupling between the steps. Our extensive numerical campaign for a mmWave system shows how a well-designed heuristic that takes some level of couplings between the steps can make the performance exceedingly better than a benchmark., Comment: This paper has been accepted by 2025 IEEE International Conference on Communications (ICC): Mobile and Wireless Networks Symposium

Feedback-based quantum algorithms have recently emerged as potential methods for approximating the ground states of Hamiltonians. One such algorithm, the feedback-based algorithm for quantum optimization (FALQON), is specifically designed to solve quadratic unconstrained binary optimization problems. Its extension, the feedback-based algorithm for quantum optimization with constraints (FALQON-C), was introduced to handle constrained optimization problems with equality and inequality constraints. In this work, we extend the feedback-based quantum algorithms framework to address a broader class of constraints known as invalid configuration (IC) constraints, which explicitly prohibit specific configurations of decision variables. We first present a transformation technique that converts the constrained optimization problem with invalid configuration constraints into an equivalent unconstrained problem by incorporating a penalizing term into the cost function. Then, leaning upon control theory, we propose an alternative method tailored for feedback-based quantum algorithms that directly tackles IC constraints without requiring slack variables. Our approach introduces a new operator that encodes the optimal feasible solution of the constrained optimization problem as its ground state. Then, a controlled quantum system based on the Lyapunov control technique is designed to ensure convergence to the ground state of this operator. Two approaches are introduced in the design of this operator to address IC constraints: the folded spectrum approach and the deflation approach. These methods eliminate the need for slack variables, significantly reducing the quantum circuit depth and the number of qubits required. We show the effectiveness of our proposed algorithms through numerical simulations.

In this paper, we propose an efficient implementation of deep policy gradient method (PGM) for optimal control problems in continuous time. The proposed method has the ability to manage the allocation of computational resources, number of trajectories, and complexity of architecture of the neural network. This is, in particular, important for continuous-time problems that require a fine time discretization. Each step of this method focuses on a different time scale and learns a policy, modeled by a neural network, for a discretized optimal control problem. The first step has the coarsest time discretization. As we proceed to other steps, the time discretization becomes finer. The optimal trained policy in each step is also used to provide data for the next step. We accompany the multi-scale deep PGM with a theoretical result on allocation of computational resources to obtain a targeted efficiency and test our methods on the linear-quadratic stochastic optimal control problem., Comment: 20 pages, 4 figures

Van der Waals (vdW) magnets, with their two-dimensional (2D) atomic structures, provide a unique platform for exploring magnetism at the nanoscale. Although there have been numerous reports on their diverse quantum properties, the emergent interfacial magnetism--artificially created at the interface between two layered magnets--remains largely unexplored. This work presents observations of such emergent interfacial magnetism at the ferromagnet/antiferromagnet interface in a vdW heterostructure. We report the discovery of an intermediate Hall resistance plateau in the anomalous Hall loop, indicative of emergent interfacial antiferromagnetism fostered by the heterointerface. This plateau can be stabilized and further manipulated under varying pressures but collapses under high pressures over 10 GPa. Our theoretical calculations reveal that charge transfer at the interface is pivotal in establishing the interlayer antiferromagnetic spin-exchange interaction. This work illuminates the previously unexplored emergent interfacial magnetism at a vdW interface comprised of a ferromagnetic metal and an antiferromagnetic insulator, and highlights its gradual evolution under increasing pressure. These findings enrich the portfolio of emergent interfacial magnetism and support further investigations on vdW magnetic interfaces and the development of next-generation spintronic devices., Comment: Accepted by ACS Nano; 42 pages, 5 main figures, 8 supporting figures

In this paper, we introduce MASQRAD (Multi-Agent Strategic Query Resolution and Diagnostic tool), a transformative framework for query resolution based on the actor-critic model, which utilizes multiple generative AI agents. MASQRAD is excellent at translating imprecise or ambiguous user inquiries into precise and actionable requests. This framework generates pertinent visualizations and responses to these focused queries, as well as thorough analyses and insightful interpretations for users. MASQRAD addresses the common shortcomings of existing solutions in domains that demand fast and precise data interpretation, such as their incapacity to successfully apply AI for generating actionable insights and their challenges with the inherent ambiguity of user queries. MASQRAD functions as a sophisticated multi-agent system but "masquerades" to users as a single AI entity, which lowers errors and enhances data interaction. This approach makes use of three primary AI agents: Actor Generative AI, Critic Generative AI, and Expert Analysis Generative AI. Each is crucial for creating, enhancing, and evaluating data interactions. The Actor AI generates Python scripts to generate data visualizations from large datasets within operational constraints, and the Critic AI rigorously refines these scripts through multi-agent debate. Finally, the Expert Analysis AI contextualizes the outcomes to aid in decision-making. With an accuracy rate of 87\% when handling tasks related to natural language visualization, MASQRAD establishes new benchmarks for automated data interpretation and showcases a noteworthy advancement that has the potential to revolutionize AI-driven applications., Comment: Accepted for publication in IEEE Transactions on Artificial Intelligence

We present the first catalog of fast radio burst (FRB) host galaxies from CHIME/FRB Outriggers, selected uniformly in the radio and the optical by localizing 81 new bursts to 2'' x ~60'' accuracy using CHIME and the KKO Outrigger, located 66 km from CHIME. Of the 81 localized bursts, we use the Probabilistic Association of Transients to their Hosts (PATH) algorithm to securely identify 21 new FRB host galaxies, and compile spectroscopic redshifts for 19 systems, 15 of which are newly obtained via spectroscopic observations. The most nearby source is FRB 20231229A, at a distance of 90 Mpc. One burst in our sample is from a previously reported repeating source in a galaxy merger (FRB 20190303A). Three new FRB host galaxies (FRBs 20230203A, 20230703A, and 20231206A) are found towards X-ray and optically selected galaxy clusters, potentially doubling the sample of known galaxy cluster FRBs. A search for radio counterparts reveals that FRB 20231128A is associated with a luminous persistent radio source (PRS) candidate with high significance ($P_{cc} \sim 10^{-2}$). If its compactness is confirmed, it would be the nearest known compact PRS at $z = 0.1079$. Our catalog significantly increases the statistics of the Macquart relation at low redshifts ($z < 0.2$). In the near future, the completed CHIME/FRB Outriggers array will produce hundreds of FRBs localized with very long baseline interferometry (VLBI). This will significantly expand the known sample and pave the way for future telescopes relying on VLBI for FRB localization., Comment: 27 pages, 10 figures

We propose SGS-GNN, a novel supervised graph sparsifier that learns the sampling probability distribution of edges and samples sparse subgraphs of a user-specified size to reduce the computational costs required by GNNs for inference tasks on large graphs. SGS-GNN employs regularizers in the loss function to enhance homophily in sparse subgraphs, boosting the accuracy of GNNs on heterophilic graphs, where a significant number of the neighbors of a node have dissimilar labels. SGS-GNN also supports conditional updates of the probability distribution learning module based on a prior, which helps narrow the search space for sparse graphs. SGS-GNN requires fewer epochs to obtain high accuracies since it learns the search space of subgraphs more effectively than methods using fixed distributions such as random sampling. Extensive experiments using 33 homophilic and heterophilic graphs demonstrate the following: (i) with only 20% of edges retained in the sparse subgraphs, SGS-GNN improves the F1-scores by a geometric mean of 4% relative to the original graph; on heterophilic graphs, the prediction accuracy is better up to 30%. (ii) SGS-GNN outperforms state-of-the-art methods with improvement in F1-scores of 4-7% in geometric mean with similar sparsities in the sampled subgraphs, and (iii) compared to sparsifiers that employ fixed distributions, SGS-GNN requires about half the number of epochs to converge.

Brain tumors require an assessment to ensure timely diagnosis and effective patient treatment. Morphological factors such as size, location, texture, and variable appearance complicate tumor inspection. Medical imaging presents challenges, including noise and incomplete images. This research article presents a methodology for processing Magnetic Resonance Imaging (MRI) data, encompassing techniques for image classification and denoising. The effective use of MRI images allows medical professionals to detect brain disorders, including tumors. This research aims to categorize healthy brain tissue and brain tumors by analyzing the provided MRI data. Unlike alternative methods like Computed Tomography (CT), MRI technology offers a more detailed representation of internal anatomical components, making it a suitable option for studying data related to brain tumors. The MRI picture is first subjected to a denoising technique utilizing an Anisotropic diffusion filter. The dataset utilized for the models creation is a publicly accessible and validated Brain Tumour Classification (MRI) database, comprising 3,264 brain MRI scans. SMOTE was employed for data augmentation and dataset balancing. Convolutional Neural Networks(CNN) such as ResNet152V2, VGG, ViT, and EfficientNet were employed for the classification procedure. EfficientNet attained an accuracy of 98%, the highest recorded.

The solid-state reaction was used to synthesize CoO2 nanostructured material. Cobalt nitrate tetrahydrate and sodium oxide (NaOH) were combined to produce CoO2 nanostructured material. The three synthesized working electrodes were each tested individually, using 3 M KOH as the electrolyte. The CV analysis of a three-electrode system revealed redox peaks, indicating Faradaic processes. The estimated specific capacitances of CoO2, CoO2 (250oC), CoO2 (300oC) nanostructured material at scan rates of (10) mVs-1 is (223, 348, and 473) Fg-1. The diffraction peaks at 2{\theta} = 26.264o, 33.527o, 37.579, 51.264 and 54.367o correspond respectively to the diffraction planes of 111, 112, 200, 211, and 311 of CoO2 nanostructured material. The annealing temperature, which affects the bandgap, can influence the size, shape, and crystallinity of nanostructures. For the unannealed material, the energy bandgap of CoO2 is 2.00 eV, whereas for the annealed material it ranges from 1.77 to 1.86 eV., Comment: 16 pages, 6 figures

Germanium quantum dots in strained $\text{Ge}/\text{Si}_{1-x}\text{Ge}_{x}$ heterostructures exhibit fast and coherent hole qubit control in experiments. In this work, we theoretically and numerically address the effects of random alloy disorder and gate-induced strain on the operation of planar Ge hole spin qubits. Electrical operation of hole quantum dot spin qubits is enabled by the strong Rashba spin-orbit coupling (SOC) originating from the intrinsic SOC in the Ge valence band as well as from the structural inversion asymmetry inherent in the underlying 2D hole gas. We use the atomistic valence force field (VFF) method to compute the strain due to random alloy disorder, and thermal expansion models in COMSOL Multiphysics to obtain the strain from a realistic gate-stack of planar hole quantum dot confinement. Recently, spin-orbit coupling terms $\propto k$ have been shown to be induced by strain inhomogeneity. Our hybrid approach to realistic device modeling suggests that strain inhomogeneity due to both random alloy disorder and gate-induced strain make a strong contribution to the linear-$k$ Dresselhaus spin-orbit coupling, which eventually dominates hole spin EDSR; and there exist specific in-plane orientations of the global magnetic field $\mathbf{B}$ and the microwave drive $\mathbf{\tilde{E}}_{\text{ac}}$ for maximum EDSR Rabi frequency of the hole spin qubit. The current model including strain inhomogeneity accurately predicts the EDSR Rabi frequency to be $\!\sim\!100$ MHz for typical electric and magnetic fields in experiments, which represents at least an order of magnitude improvement in accuracy over phenomenological models assuming uniform uniaxial strain. State-of-the-art atomistic tight binding calculations via nano-electronic modeling (NEMO3D) are in agreement with the $\mathbf{k}{\cdot}\mathbf{p}$ description.

Embedded Field-Programmable Gate Arrays (eFPGAs) allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget compared with traditional FPGA platforms. However, the limited eFPGA logic and memory significantly constrain compute capabilities and model size. As such, ML application deployment on eFPGAs is in direct contrast with the most recent FPGA approaches developing architecture-specific implementations and maximizing throughput over resource frugality. This paper focuses on the opposite side of this trade-off: the proposed eFPGA accelerator focuses on minimizing resource usage and allowing flexibility for on-field recalibration over throughput. This allows for runtime changes in model size, architecture, and input data dimensionality without offline resynthesis. This is made possible through the use of a bitwise compressed inference architecture of the Tsetlin Machine (TM) algorithm. TM compute does not require any multiplication operations, being limited to only bitwise AND, OR, NOT, summations and additions. Additionally, TM model compression allows the entire model to fit within the on-chip block RAM of the eFPGA. The paper uses this accelerator to propose a strategy for runtime model tuning in the field. The proposed approach uses 2.5x fewer Look-up-Tables (LUTs) and 3.38x fewer registers than the current most resource-fugal design and achieves up to 129x energy reduction compared with low-power microcontrollers running the same ML application., Comment: Accepted as a full paper by the 2025 EDGE AI FOUNDATION Austin

Hyperspectral imaging (HSI) captures spatial and spectral data, enabling analysis of features invisible to conventional systems. The technology is vital in fields such as weather monitoring, food quality control, counterfeit detection, healthcare diagnostics, and extending into defense, agriculture, and industrial automation at the same time. HSI has advanced with improvements in spectral resolution, miniaturization, and computational methods. This study provides an overview of the HSI, its applications, challenges in data fusion and the role of deep learning models in processing HSI data. We discuss how integration of multimodal HSI with AI, particularly with deep learning, improves classification accuracy and operational efficiency. Deep learning enhances HSI analysis in areas like feature extraction, change detection, denoising unmixing, dimensionality reduction, landcover mapping, data augmentation, spectral construction and super resolution. An emerging focus is the fusion of hyperspectral cameras with large language models (LLMs), referred as highbrain LLMs, enabling the development of advanced applications such as low visibility crash detection and face antispoofing. We also highlight key players in HSI industry, its compound annual growth rate and the growing industrial significance. The purpose is to offer insight to both technical and non-technical audience, covering HSI's images, trends, and future directions, while providing valuable information on HSI datasets and software libraries., Comment: 39 Pages, 22 figures, 20 tables

Point spread function (PSF) engineering has been pivotal in the remarkable progress made in high-resolution imaging in the last decades. However, the diversity in PSF structures attainable through existing engineering methods is limited. Here, we report universal PSF engineering, demonstrating a method to synthesize an arbitrary set of spatially varying 3D PSFs between the input and output volumes of a spatially incoherent diffractive processor composed of cascaded transmissive surfaces. We rigorously analyze the PSF engineering capabilities of such diffractive processors within the diffraction limit of light and provide numerical demonstrations of unique imaging capabilities, such as snapshot 3D multispectral imaging without involving any spectral filters, axial scanning or digital reconstruction steps, which is enabled by the spatial and spectral engineering of 3D PSFs. Our framework and analysis would be important for future advancements in computational imaging, sensing and diffractive processing of 3D optical information., Comment: 16 Pages, 5 Figures

Millions of new pieces of malicious software (i.e., malware) are introduced each year. This poses significant challenges for antivirus vendors, who use machine learning to detect and analyze malware, and must keep up with changes in the distribution while retaining knowledge of older variants. Continual learning (CL) holds the potential to address this challenge by reducing the storage and computational costs of regularly retraining over all the collected data. Prior work, however, shows that CL techniques, which are designed primarily for computer vision tasks, fare poorly when applied to malware classification. To address these issues, we begin with an exploratory analysis of a typical malware dataset, which reveals that malware families are diverse and difficult to characterize, requiring a wide variety of samples to learn a robust representation. Based on these findings, we propose $\underline{M}$alware $\underline{A}$nalysis with $\underline{D}$iversity-$\underline{A}$ware $\underline{R}$eplay (MADAR), a CL framework that accounts for the unique properties and challenges of the malware data distribution. Through extensive evaluation on large-scale Windows and Android malware datasets, we show that MADAR significantly outperforms prior work. This highlights the importance of understanding domain characteristics when designing CL techniques and demonstrates a path forward for the malware classification domain., Comment: 13 pages, 12 figures, 7 tables

Multiferroic perovskites that exhibit room temperature magnetization and polarization have immense potential in the next generation of magneto-electric and spintronic memory devices. In this work, the magnetic and ferroelectric properties of Bismuth Ferrite, BiFeO3 (BFO) nanoparticles (NPs) were enhanced through simultaneous A and B site Ca and Cr co-substitution. Novel compositions of Bi0.97Ca0.03CrxFe1-xO3 (x=0, 0.01, 0.03, 0.05) were synthesized using the sol-gel route and annealed at 550 degrees Celcius. Rietveld Refinement of XRD patterns confirmed high phase purity, while SEM analysis revealed a decreasing trend in average particle size with increasing dopant concentration. Hysteresis loops showed enhanced magnetic properties as particle size approached the spin cycloid wavelength (around 62 nm), disrupting the intrinsic antiferromagnetic ordering of BFO. Moreover, the presence of exchange bias in the NPs was linked to the formation of core-shell structure. Temperature dependent magnetization studies showed an increase in N\'eel temperature upon Ca substitution. XPS analysis confirmed that Bi0.97Ca0.03FeO3 samples exhibited the highest oxygen vacancy concentration, while Fe3+ remained the dominant oxidation state across all compositions. Ferroelectric polarization loop measurements showed enhanced remanent polarization in doped samples, with leakage linked to oxygen vacancies and extrinsic microstructural effects., Comment: Mehedi Hasan Prince, Abrar Daiyan, Troyee Mitra Aishi contributed equally to this work. Paper undergoing review in Ceramics International

In the growing terrain of the Internet of Things (IoT), it is vital that networks are secure to protect against a range of cyber threats. Based on the strong machine learning framework, this study proposes novel lightweight ensemble approaches for improving multi-class attack detection of IoT devices. Using the large CICIoT 2023 dataset with 34 attack types distributed amongst 10 attack categories, we systematically evaluated the performance of a wide variety of modern machine learning methods with the aim of establishing the best-performing algorithmic choice to secure IoT applications. In particular, we explore approaches based on ML classifiers to tackle the biocharges characterized by the challenging and heterogeneous nature of attack vectors in IoT environments. The method that performed best was the Decision Tree, with an accuracy of 99.56% and an F1 score of 99.62%, showing that this model is capable of accurately and reliably detecting threats.The Random Forest model was the next best-performing model with 98.22% and an F1 score of 98.24%, suggesting that ML methods are quite effective in a situation of high-dimensional data. Our results highlight the potential for using ML classifiers in bolstering security for IoT devices and also serve as motivations for future investigations targeting scalable, keystroke-based attack detection systems. We believe that our method provides a new path to develop complex machine learning algorithms for low-resource IoT devices, balancing both accuracy and time efficiency needs. In summary, these contributions enrich the state of the art of the IoT security literature, laying down solid ground and guidelines for the deployment of smart, adaptive security in IoT settings., Comment: Accepted in an international conference

Intelligent transportation systems (ITS) are characterized by wired or wireless communication among different entities, such as vehicles, roadside infrastructure, and traffic management infrastructure. These communications demand different levels of security, depending on how sensitive the data is. The national ITS reference architecture (ARC-IT) defines three security levels, i.e., high, moderate, and low-security levels, based on the different security requirements of ITS applications. In this study, we present a generalized approach to secure ITS communications using a standardized key encapsulation mechanism, known as Kyber, designed for post-quantum cryptography (PQC). We modified the encryption and decryption systems for ITS communications while mapping the security levels of ITS applications to the three versions of Kyber, i.e., Kyber-512, Kyber-768, and Kyber-1024. Then, we conducted a case study using a benchmark fault-enabled chosen-ciphertext attack to evaluate the security provided by the different Kyber versions. The encryption and decryption times observed for different Kyber security levels and the total number of iterations required to recover the secret key using the chosen-ciphertext attack are presented. Our analyses show that higher security levels increase the time required for a successful attack, with Kyber-512 being breached in 183 seconds, Kyber-768 in 337 seconds, and Kyber-1024 in 615 seconds. In addition, attack time instabilities are observed for Kyber-512, 768, and 1024 under 5,000, 6,000, and 8,000 inequalities, respectively. The relationships among the different Kyber versions, and the respective attack requirements and performances underscore the ITS communication security Kyber could provide in the PQC era.

Layer-wise preconditioning methods are a family of memory-efficient optimization algorithms that introduce preconditioners per axis of each layer's weight tensors. These methods have seen a recent resurgence, demonstrating impressive performance relative to entry-wise ("diagonal") preconditioning methods such as Adam(W) on a wide range of neural network optimization tasks. Complementary to their practical performance, we demonstrate that layer-wise preconditioning methods are provably necessary from a statistical perspective. To showcase this, we consider two prototypical models, linear representation learning and single-index learning, which are widely used to study how typical algorithms efficiently learn useful features to enable generalization. In these problems, we show SGD is a suboptimal feature learner when extending beyond ideal isotropic inputs $\mathbf{x} \sim \mathsf{N}(\mathbf{0}, \mathbf{I})$ and well-conditioned settings typically assumed in prior work. We demonstrate theoretically and numerically that this suboptimality is fundamental, and that layer-wise preconditioning emerges naturally as the solution. We further show that standard tools like Adam preconditioning and batch-norm only mildly mitigate these issues, supporting the unique benefits of layer-wise preconditioning.

Distributed Denial of Service (DDoS) attacks make the challenges to provide the services of the data resources to the web clients. In this paper, we concern to study and apply different Machine Learning (ML) techniques to separate the DDoS attack instances from benign instances. Our experimental results show that forward and backward data bytes of our dataset are observed more similar for DDoS attacks compared to the data bytes for benign attempts. This paper uses different machine learning techniques for the detection of the attacks efficiently in order to make sure the offered services from web servers available. This results from the proposed approach suggest that 97.1% of DDoS attacks are successfully detected by the Support Vector Machine (SVM). These accuracies are better while comparing to the several existing machine learning approaches.

Significant losses in terms of life and property occur from road traffic accidents, which are often caused by drunk and drowsy drivers. Reducing accidents requires effective detection of alcohol impairment and drowsiness as well as real-time driver monitoring. This paper aims to create an Internet of Things (IoT)--enabled Drowsiness Driver Safety Alert System with Real-Time Monitoring Using Integrated Sensors Technology. The system features an alcohol sensor and an IR sensor for detecting alcohol presence and monitoring driver eye movements, respectively. Upon detecting alcohol, alarms and warning lights are activated, the vehicle speed is progressively reduced, and the motor stops within ten to fifteen seconds if the alcohol presence persists. The IR sensor monitors prolonged eye closure, triggering alerts, or automatic vehicle stoppage to prevent accidents caused by drowsiness. Data from the IR sensor is transmitted to a mobile phone via Bluetooth for real-time monitoring and alerts. By identifying driver alcoholism and drowsiness, this system seeks to reduce accidents and save lives by providing safer transportation.

The integration of Large Language Models (LLMs) such as GitHub Copilot, ChatGPT, Cursor AI, and Codeium AI into software development has revolutionized the coding landscape, offering significant productivity gains, automation, and enhanced debugging capabilities. These tools have proven invaluable for generating code snippets, refactoring existing code, and providing real-time support to developers. However, their widespread adoption also presents notable challenges, particularly in terms of security vulnerabilities, code quality, and ethical concerns. This paper provides a comprehensive analysis of the benefits and risks associated with AI-powered coding tools, drawing on user feedback, security analyses, and practical use cases. We explore the potential for these tools to replicate insecure coding practices, introduce biases, and generate incorrect or non-sensical code (hallucinations). In addition, we discuss the risks of data leaks, intellectual property violations and the need for robust security measures to mitigate these threats. By comparing the features and performance of these tools, we aim to guide developers in making informed decisions about their use, ensuring that the benefits of AI-assisted coding are maximized while minimizing associated risks.

We present a theory for the relaxation time of the octupole order parameter in nanoscale chiral antiferromagnets (AFMs) coupled to thermal baths and spin injection sources. Using stochastic spin dynamics simulations, we demonstrate that the octupole moment relaxes through two distinct mechanisms$-$escape over a barrier and precessional dephasing$-$as the barrier for octupole fluctuations is lowered relative to the thermal energy. Notably, the octupole moment relaxes orders of magnitude faster than the typical dipolar order parameters, reaching picosecond timescales. By combining Langer's theory with an effective low-energy description of octupole dynamics in chiral AFMs, we derive analytical expressions for the relaxation times. We find that relaxation in chiral AFMs parallels dipole relaxation in XY magnets, with exchange fields serving the role of the dipole fields. Further, by drawing on the analogy between order parameter dynamics in XY magnets under spin injection and current-biased Josephson junctions, we propose a new scheme for electrically tuning the octupole relaxation times. Our work offers fundamental insights for the development of next-generation spintronic devices that harness octupole order parameters for information encoding, especially in octupole-based probabilistic computing.