Search

A tensor-based formula for solving the linear system involving Kronecker sum is proposed. It is shown that the linear system involving Kronecker sum of matrices is directly related to the matrix and tensor forms of Sylvester equation. The new tensor-based formula indicates that a Sylvester tensor equation has a unique solution if the sum of spectra of the matrices does not contain zero. As an application, we solve the discretized Poisson equation on a rectangular domain and Dirichlet boundary conditions. In 2d, we show that both the new formula and the fast Poisson solver based on diagonalization have the same cost $\mathcal {O}(n^{3/2})$. In 3d, the new formula has the cost $\mathcal {O}(n^{4/3})$ while cyclic reduction and successive over-relaxation methods have a complexity of $\mathcal {O}(n^{3/2})$.

Accurate modeling is essential in integer-valued real phenomena, including the distribution of entire data, zero-inflated (ZI) data, and discrete exceedances. The Poisson and Negative Binomial distributions, along with their ZI variants, are considered suitable for modeling the entire data distribution, but they fail to capture the heavy tail behavior effectively alongside the bulk of the distribution. In contrast, the discrete generalized Pareto distribution (DGPD) is preferred for high threshold exceedances, but it becomes less effective for low threshold exceedances. However, in some applications, the selection of a suitable high threshold is challenging, and the asymptotic conditions required for using DGPD are not always met. To address these limitations, extended versions of DGPD are proposed. These extensions are designed to model one of three scenarios: first, the entire distribution of the data, including both bulk and tail and bypassing the threshold selection step; second, the entire distribution along with ZI; and third, the tail of the distribution for low threshold exceedances. The proposed extensions offer improved estimates across all three scenarios compared to existing models, providing more accurate and reliable results in simulation studies and real data applications., Comment: 17 pages, Figures 8, tables 3

Personalized Federated Learning (pFL) holds immense promise for tailoring machine learning models to individual users while preserving data privacy. However, achieving optimal performance in pFL often requires a careful balancing act between memory overhead costs and model accuracy. This paper delves into the trade-offs inherent in pFL, offering valuable insights for selecting the right algorithms for diverse real-world scenarios. We empirically evaluate ten prominent pFL techniques across various datasets and data splits, uncovering significant differences in their performance. Our study reveals interesting insights into how pFL methods that utilize personalized (local) aggregation exhibit the fastest convergence due to their efficiency in communication and computation. Conversely, fine-tuning methods face limitations in handling data heterogeneity and potential adversarial attacks while multi-objective learning methods achieve higher accuracy at the cost of additional training and resource consumption. Our study emphasizes the critical role of communication efficiency in scaling pFL, demonstrating how it can significantly affect resource usage in real-world deployments.

In recent years, financial analysts have been trying to develop models to predict the movement of a stock price index. The task becomes challenging in vague economic, social, and political situations like in Pakistan. In this study, we employed efficient models of machine learning such as long short-term memory (LSTM) and quantum long short-term memory (QLSTM) to predict the Karachi Stock Exchange (KSE) 100 index by taking monthly data of twenty-six economic, social, political, and administrative indicators from February 2004 to December 2020. The comparative results of LSTM and QLSTM predicted values of the KSE 100 index with the actual values suggested QLSTM a potential technique to predict stock market trends.

Hyperentangled states are highly efficient and resource economical. This is because they enhance the quantum information encoding capabilities due to the correlated engagement of more than one degree of freedom of the same quantum entity while keeping the physical resources at their minimum. Therefore, initially the photonic hyperentangled states have been explored extensively but the generation and respective manipulation of the atomic counterpart states are still limited to only few proposals. In this work, we propose a new and feasible scheme to engineer the atomic hyperentangled cluster and ring graph states invoking cavity QED technique for applicative relevance to quantum biology and quantum communications utilizing the complex quantum networks. These states are engineered using both external quantized momenta states and energy levels of neutral atoms under off-resonant and resonant Atomic Bragg Diffraction (ABD) technique. The study of dynamical capacity and potential efficiency have certainly enhanced the range of usefulness of these states. In order to assess the operational behavior of such states when subjected to a realistic noise environment has also been simulated, demonstrating long enough sustainability of the proposed states. Moreover, experimental feasibility of the proposed scheme has also been elucidated under the prevailing cavity-QED research scenario., Comment: Submitted to Physica Scripta

This work investigates how the theoretically calculated particle ratios and freeze-out parameters for a multi-component hot and dense non-ideal hadron resonance gas system, formed during the pre freeze-out stage in ultra-relativistic nucleus-nucleus collisions, are affected by van der Waals type interactions, incorporating both repulsive and attractive interactions among hadrons. The baryons (antibaryons) are treated as hard incompressible objects. Using this theoretical approach, we analyze experimental particle ratios involving like-mass as well as unlike-mass hadrons. We also try to understand the existence of horn-like structures seen in the ratios of strange particles to pion as a function of the collision energy. Using information about the dependence of experimental particle ratios on $\sqrt{s_{NN}}$ over a wide range of collision energies, we have extracted several model freeze-out parameters and examined their dependence on $\sqrt{s_{NN}}$ The correlation between the $\bar{p}/p$ and $K^-/K^+$ ratios is also examined., Comment: 15 pages, 19 Figures

Communication networks are evolving from solely emphasizing communication to facilitating multiple functionalities. In this regard, integrated sensing, communication, and powering (ISCAP) provides an efficient way of enabling data transmission, radar sensing, and wireless power transfer simultaneously. Such a multi-functional network requires a multi-functional architectural solution. Toward this end, sensor-aided zero-energy reconfigurable intelligent surfaces (SAZE-RISs) offer an energy-efficient solution for ISCAP by meeting the requirements of the end users as well as supplying power for the RIS. This paper explores the use of SAZE-RIS within the ISCAP framework. First, we present the general system architecture, operational protocols, and main application scenarios for employing SAZE-RIS in ISCAP. Next, we discuss methods for managing the conflicting requirements of communication, sensing, and powering within ISCAP and the role of SAZE-RIS in this process. We then provide a detailed case study complete with simulation results, offering valuable insights into the design choices and tradeoffs that come into play when adopting this technology. Furthermore, we discuss the related challenges and open research avenues, highlighting areas that require further exploration to fully realize the potential of SAZE-RIS within this ISCAP framework., Comment: Accepted for publication in IEEE Network

The landscape of software developer learning resources has continuously evolved, with recent trends favoring engaging formats like video tutorials. The emergence of Large Language Models (LLMs) like ChatGPT presents a new learning paradigm. While existing research explores the potential of LLMs in software development and education, their impact on developers' learning and solution-seeking behavior remains unexplored. To address this gap, we conducted a survey targeting software developers and computer science students, gathering 341 responses, of which 268 were completed and analyzed. This study investigates how AI chatbots like ChatGPT have influenced developers' learning preferences when acquiring new skills, exploring technologies, and resolving programming issues. Through quantitative and qualitative analysis, we explore whether AI tools supplement or replace traditional learning resources such as video tutorials, written tutorials, and Q&A forums. Our findings reveal a nuanced view: while video tutorials continue to be highly preferred for their comprehensive coverage, a significant number of respondents view AI chatbots as potential replacements for written tutorials, underscoring a shift towards more interactive and personalized learning experiences. Additionally, AI chatbots are increasingly considered valuable supplements to video tutorials, indicating their growing role in the developers' learning resources. These insights offer valuable directions for educators and the software development community by shedding light on the evolving preferences toward learning resources in the era of ChatGPT., Comment: International Conference on Software Maintenance and Evolution (ICSME 2024)

In recent times, a considerable number of research studies have been carried out to address the issue of Missing Value Imputation (MVI). MVI aims to provide a primary solution for datasets that have one or more missing attribute values. The advancements in Artificial Intelligence (AI) drive the development of new and improved machine learning (ML) algorithms and methods. The advancements in ML have opened up significant opportunities for effectively imputing these missing values. The main objective of this article is to conduct a comprehensive and rigorous review, as well as analysis, of the state-of-the-art ML applications in MVI methods. This analysis seeks to enhance researchers' understanding of the subject and facilitate the development of robust and impactful interventions in data preprocessing for Data Analytics. The review is performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) technique. More than 100 articles published between 2014 and 2023 are critically reviewed, considering the methods and findings. Furthermore, the latest literature is examined to scrutinize the trends in MVI methods and their evaluation. The accomplishments and limitations of the existing literature are discussed in detail. The survey concludes by identifying the current gaps in research and providing suggestions for future research directions and emerging trends in related fields of interest.

Machine learning (ML) has become a ubiquitous tool across various domains of data mining and big data analysis. The efficacy of ML models depends heavily on high-quality datasets, which are often complicated by the presence of missing values. Consequently, the performance and generalization of ML models are at risk in the face of such datasets. This paper aims to examine the nuanced impact of missing values on ML workflows, including their types, causes, and consequences. Our analysis focuses on the challenges posed by missing values, including biased inferences, reduced predictive power, and increased computational burdens. The paper further explores strategies for handling missing values, including imputation techniques and removal strategies, and investigates how missing values affect model evaluation metrics and introduces complexities in cross-validation and model selection. The study employs case studies and real-world examples to illustrate the practical implications of addressing missing values. Finally, the discussion extends to future research directions, emphasizing the need for handling missing values ethically and transparently. The primary goal of this paper is to provide insights into the pervasive impact of missing values on ML models and guide practitioners toward effective strategies for achieving robust and reliable model outcomes.

In this paper, the symbol error rate performance analysis is provided for a pilot-aided simultaneous communication and tracking (PASCAT) system. In specific, we employ multiple drones to actively transmit signals to a BS, which is responsible for continuously monitoring the location of drones over time and decoding the symbols transmitted from the drones. It is found that the estimated location parameters at a given moment during tracking follow Gaussian distributions with means equal to actual values and variances equal to root mean square error (RMSE). Afterwards, the obtained location information is employed for informing the channel information, which is then used to preprocess the received signal before decoding by using the maximum ratio combining (MRC) technique. The average symbol error rate (SER) is also evaluated over the distribution of the estimated location parameters and an approximate value for the average SER is obtained by using a Taylor approximation with fast convergence. The result indicates that there is a cooperation relationship between the RMSE of the estimated location parameters and the average SER. In addition, the effect of the number of pilot signals is analysed as well. By employing more pilots, it is found that both communication and sensing functionalities are enhanced. Furthermore, the SER performance of our PASCAT system is similar to that of maximum likelihood detection (MLD) when a number of pilot signals are employed, which demonstrates the efficiency of the PASCAT system. In the end, all results are validated by using Monte Carlo simulations., Comment: 13 pages, 9 figures

Software engineering (SE) chatbots are increasingly gaining attention for their role in enhancing development processes. At the core of chatbots are the Natural Language Understanding platforms (NLUs), which enable them to comprehend and respond to user queries. Before deploying NLUs, there is a need to train them with labeled data. However, acquiring such labeled data for SE chatbots is challenging due to the scarcity of high-quality datasets. This challenge arises because training SE chatbots requires specialized vocabulary and phrases not found in typical language datasets. Consequently, chatbot developers often resort to manually annotating user queries to gather the data necessary for training effective chatbots, a process that is both time-consuming and resource-intensive. Previous studies propose approaches to support chatbot practitioners in annotating users' posed queries. However, these approaches require human intervention to generate rules, called labeling functions (LFs), that identify and categorize user queries based on specific patterns in the data. To address this issue, we propose an approach to automatically generate LFs by extracting patterns from labeled user queries. We evaluate the effectiveness of our approach by applying it to the queries of four diverse SE datasets (namely AskGit, MSA, Ask Ubuntu, and Stack Overflow) and measure the performance improvement gained from training the NLU on the queries labeled by the generated LFs. We find that the generated LFs effectively label data with AUC scores of up to 85.3%, and NLU's performance improvement of up to 27.2% across the studied datasets. Furthermore, our results show that the number of LFs used to generate LFs affects the labeling performance. We believe that our approach can save time and resources in labeling users' queries, allowing practitioners to focus on core chatbot functionalities., Comment: Submitted to IEEE Transactions on Software Engineering for review

In this paper, we report the long-range and wireless interrogation of multiple chipless sensors from the isoline processing of three-dimensional polarimetric radar images. A Frequency-Modulated Continuous-Wave Radar operating at 24 GHz is used for the indoor interrogation of four sensors in the basement of a Laboratory. In such cluttered environment, the proposed radar image processing based on isolines computation allows the wireless measurement range of sensors up to 5.8m.

In a mixture experiment, we study the behavior and properties of $m$ mixture components, where the primary focus is on the proportions of the components that make up the mixture rather than the total amount. Mixture-amount experiments are specialized types of mixture experiments where both the proportions of the components in the mixture and the total amount of the mixture are of interest. Such experiments consider the total amount of the mixture as a variable. In this paper, we consider an Order-of-Addition (OofA) mixture-amount experiment in which the response depends on both the mixture amounts of components and their order of addition. Full Mixture OofA designs are constructed to maintain orthogonality between the mixture-amount model terms and the effects of the order of addition. These designs enable the estimation of mixture-component model parameters and the order-of-addition effects. The G-efficiency criterion assesses how well the design supports precise and unbiased estimation of the model parameters. The Fraction of Design Space (FDS) plot is used to provide a visual assessment of the prediction capabilities of a design across the entire design space., Comment: 12 pages figures 2 tables 5

STImulated Raman Adiabatic Passage (STIRAP) is a powerful technique for robust state transfer capabilities in quantum systems. This method, however encounters challenges for its implementation as a gate in qubit-subspace due to its sensitivity to initial states. By incorporating single-photon detuning into the protocol, the sensitivity to the initial state can effectively be mitigated, enabling STIRAP to operate as a gate. In this study, we experimentally demonstrate the implementation of robust $\pi$ and $\pi$/2 rotations in a dual-rail qubit formed by two strongly coupled fixed-frequency transmon qubits. We achieve state preparation fidelity in excess of 0.98 using such rotations. Our analysis reveals these gates exhibit significant resilience to errors. Furthermore, our numerical calculations confirm that these gates can achieve fidelity levels in excess of 0.999. This work suggest a way for realizing quantum gates which are robust against minor drifts in pulse or system parameters.

Edge crossings in geometric graphs are sometimes undesirable as they could lead to unwanted situations such as collisions in motion planning and inconsistency in VLSI layout. Short geometric structures such as shortest perfect matchings, shortest spanning trees, shortest spanning paths, and shortest spanning cycles on a given point set are inherently noncrossing. However, the longest such structures need not be noncrossing. In fact, it is intuitive to expect many edge crossings in various geometric graphs that are longest. Recently, \'Alvarez-Rebollar, Cravioto-Lagos, Mar\'in, Sol\'e-Pi, and Urrutia (Graphs and Combinatorics, 2024) constructed a set of points for which the longest perfect matching is noncrossing. They raised several challenging questions in this direction. In particular, they asked whether the longest spanning path, on any finite set of points in the plane, must have a pair of crossing edges. They also conjectured that the longest spanning cycle must have a pair of crossing edges. In this paper, we give a negative answer to the question and also refute the conjecture. We present a framework for constructing arbitrarily large point sets for which the longest perfect matchings, the longest spanning paths, and the longest spanning cycles are noncrossing., Comment: 19 pages, 8 figures, GD 2024

Predicting time-dependent dynamics of complex systems governed by non-linear partial differential equations (PDEs) with varying parameters and domains is a challenging task motivated by applications across various fields. We introduce a novel family of neural operators based on our Graph Fourier Neural Kernels, designed to learn solution generators for nonlinear PDEs in which the highest-order term is diffusive, across multiple domains and parameters. G-FuNK combines components that are parameter- and domain-adapted with others that are not. The domain-adapted components are constructed using a weighted graph on the discretized domain, where the graph Laplacian approximates the highest-order diffusive term, ensuring boundary condition compliance and capturing the parameter and domain-specific behavior. Meanwhile, the learned components transfer across domains and parameters using our variant Fourier Neural Operators. This approach naturally embeds geometric and directional information, improving generalization to new test domains without need for retraining the network. To handle temporal dynamics, our method incorporates an integrated ODE solver to predict the evolution of the system. Experiments show G-FuNK's capability to accurately approximate heat, reaction diffusion, and cardiac electrophysiology equations across various geometries and anisotropic diffusivity fields. G-FuNK achieves low relative errors on unseen domains and fiber fields, significantly accelerating predictions compared to traditional finite-element solvers.

The rapid expansion of video content across a variety of industries, including social media, education, entertainment, and surveillance, has made video summarization an essential field of study. The current work is a survey that explores the various approaches and methods created for video summarizing, emphasizing both abstractive and extractive strategies. The process of extractive summarization involves the identification of key frames or segments from the source video, utilizing methods such as shot boundary recognition, and clustering. On the other hand, abstractive summarization creates new content by getting the essential content from the video, using machine learning models like deep neural networks and natural language processing, reinforcement learning, attention mechanisms, generative adversarial networks, and multi-modal learning. We also include approaches that incorporate the two methodologies, along with discussing the uses and difficulties encountered in real-world implementations. The paper also covers the datasets used to benchmark these techniques. This review attempts to provide a state-of-the-art thorough knowledge of the current state and future directions of video summarization research.

Time synchronization is a critical component in network operation and management, and it is also required by Ultra-Reliable, Low-Latency Communications (URLLC) in next-generation wireless systems such as those of 5G, 6G, and Open RAN. In this context, we design and implement AraSync as an end-to-end time synchronization system in the ARA wireless living lab to enable advanced wireless experiments and applications involving stringent time constraints. We make use of Precision Time Protocol (PTP) at different levels to achieve synchronization accuracy in the order of nanoseconds. Along with fiber networks, AraSync enables time synchronization across the AraHaul wireless x-haul network consisting of long-range, high-capacity mmWave and microwave links. In this paper, we present the detailed design and implementation of AraSync, including its hardware and software components and the PTP network topology. Further, we experimentally characterize the performance of AraSync from spatial and temporal dimensions. Our measurement and analysis of the clock offset and mean path delay show the impact of the wireless channel and weather conditions on the PTP synchronization accuracy., Comment: 8 pages, 10 figures, accepted in ACM WiNTECH 2024 (The 18th ACM Workshop on Wireless Network Testbeds, Experimental evaluation & Characterization 2024)

We explore the velocity distributions in a vibrated binary granular gas system, focusing on how these distributions are influenced by the coefficient of restitution (CoR) and the inelasticity of particle collisions. Through molecular dynamics simulations, we examine the system's behavior for a range of CoR values below unity: specifically, 0.80, 0.85, 0.90, and 0.95. We track the evolution of velocity distributions as the system approaches a non-equilibrium steady state. Our findings reveal a clear departure from the classical Maxwell-Boltzmann distribution, with increasing deviations as CoR decreases, indicating non-equipartition of energy between the two particle types. This behavior underscores the intricate dynamics inherent in inelastic collisions and highlights the significance of particle inelasticity in determining the system's velocity distributions. These results provide insight into non-equilibrium statistical mechanics and have implications for real-world applications where granular materials are subject to external vibrations.

Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers more experience, it should learn the layout of its environment and remember where objects are, allowing it to complete new tasks more efficiently. To enable such rapid adaptation to new tasks, we present ReLIC, a new approach for in-context reinforcement learning (RL) for embodied agents. With ReLIC, agents are capable of adapting to new environments using 64,000 steps of in-context experience with full attention while being trained through self-generated experience via RL. We achieve this by proposing a novel policy update scheme for on-policy RL called "partial updates'' as well as a Sink-KV mechanism that enables effective utilization of a long observation history for embodied agents. Our method outperforms a variety of meta-RL baselines in adapting to unseen houses in an embodied multi-object navigation task. In addition, we find that ReLIC is capable of few-shot imitation learning despite never being trained with expert demonstrations. We also provide a comprehensive analysis of ReLIC, highlighting that the combination of large-scale RL training, the proposed partial updates scheme, and the Sink-KV are essential for effective in-context learning. The code for ReLIC and all our experiments is at https://github.com/aielawady/relic

We introduce Temporal Attention-enhanced Variational Graph Recurrent Neural Network (TAVRNN), a novel framework for analyzing the evolving dynamics of neuronal connectivity networks in response to external stimuli and behavioral feedback. TAVRNN captures temporal changes in network structure by modeling sequential snapshots of neuronal activity, enabling the identification of key connectivity patterns. Leveraging temporal attention mechanisms and variational graph techniques, TAVRNN uncovers how connectivity shifts align with behavior over time. We validate TAVRNN on two datasets: in vivo calcium imaging data from freely behaving rats and novel in vitro electrophysiological data from the DishBrain system, where biological neurons control a simulated environment during the game of pong. We show that TAVRNN outperforms previous baseline models in classification, clustering tasks and computational efficiency while accurately linking connectivity changes to performance variations. Crucially, TAVRNN reveals that high game performance in the DishBrain system correlates with the alignment of sensory and motor subregion channels, a relationship not evident in earlier models. This framework represents the first application of dynamic graph representation of electrophysiological (neuronal) data from DishBrain system, providing insights into the reorganization of neuronal networks during learning. TAVRNN's ability to differentiate between neuronal states associated with successful and unsuccessful learning outcomes, offers significant implications for real-time monitoring and manipulation of biological neuronal systems., Comment: 31 pages, 6 figures, 4 supplemental figures, 4 tables, 8 supplemental tables

Layered material $\beta$-IrSn$_4$ ($I4_1/acd$, $D^{20}_{4h}$, #142), whose electron bands have symmetry-enforced Dirac points, was investigated using high-quality single crystals. It exhibits a pronounced linear field-dependence of magnetoresistance (LMR), which cannot be explained by currently existing models. Structures in the field-angle dependence of magnetoresistance and Hall resistivity are attributable to the Fermi surface topology; the presence of open orbits is inferred. At the superconducting (SC) transition, the specific-heat jump exhibits a significant increase in applied fields, revealing the type-I SC nature. This feature is attributable to the high Fermi velocity of linearly dispersive multibands. To clarify the mechanism of the puzzling LMR, investigations into the topological nature of those multibands in applied fields are highly desired.

Climate change has led to an increase in the frequency and severity of extreme weather events, posing significant challenges for power distribution systems. In response, this work presents a planning approach in order to enhance the resilience of distribution systems against climatic hazards. The framework systematically addresses uncertainties during extreme events, including weather variability and line damage. Key strategies include line hardening, backup diesel generators, and sectionalizers to strengthen resilience. We model spatio-temporal dynamics and costs through a hybrid model integrating stochastic processes with deterministic elements. A two-stage stochastic mixed-integer linear approach is developed to optimize resilience investments against load loss, generator operations, and repairs. Case studies on the IEEE 15-bus benchmark system and a realistic distribution grid model in Riyadh, Saudi Arabia demonstrate enhanced system robustness as well as cost efficiency of 10% and 15%, respectively., Comment: CIRED Chicago Workshop 2024: Resilience of Electric Distribution Systems

Reduced-scale experiments offer a controlled and safe environment for studying the effects of blasts on structures. Traditionally, these experiments rely on the detonation of solid or gaseous explosive mixtures, with only limited understanding of alternative explosive sources. This paper presents a detailed investigation of the blasts produced by exploding aluminum wires for generating shock waves of controlled energy levels. We meticulously design our experiments to ensure a precise quantification of the underlying uncertainties and conduct comprehensive parametric studies. We drawn practical relationships of the blast intensity with respect to the stand-off distance and the stored energy levels. The analysis demonstrates self-similarity of blasts with respect to the conventional concept of the scaled distance, a desirable degree of sphericity of the generated shock waves, and high repeatability. Finally, we quantify the equivalence of the reduced-scale blasts from exploding wires with high explosives, including TNT. This experimental setup and the present study demonstrate the high degree of robustness and effectiveness of exploding aluminum wires as a tool for controlled blast generation and reduced-scale structural testing.

Data heterogeneity among Federated Learning (FL) users poses a significant challenge, resulting in reduced global model performance. The community has designed various techniques to tackle this issue, among which Knowledge Distillation (KD)-based techniques are common. While these techniques effectively improve performance under high heterogeneity, they inadvertently cause higher accuracy degradation under model poisoning attacks (known as attack amplification). This paper presents a case study to reveal this critical vulnerability in KD-based FL systems. We show why KD causes this issue through empirical evidence and use it as motivation to design a hybrid distillation technique. We introduce a novel algorithm, Hybrid Knowledge Distillation for Robust and Accurate FL (HYDRA-FL), which reduces the impact of attacks in attack scenarios by offloading some of the KD loss to a shallow layer via an auxiliary classifier. We model HYDRA-FL as a generic framework and adapt it to two KD-based FL algorithms, FedNTD and MOON. Using these two as case studies, we demonstrate that our technique outperforms baselines in attack settings while maintaining comparable performance in benign settings., Comment: Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

Rapid urbanization in megacities around the world, like Dhaka, has caused numerous transportation challenges that need to be addressed. Emerging technologies of deep learning and artificial intelligence can help us solve these problems to move towards Intelligent Transportation Systems (ITS) in the city. The government of Bangladesh recognizes the integration of ITS to ensure smart mobility as a vital step towards the development plan "Smart Bangladesh Vision 2041", but faces challenges in understanding ITS, its effects, and directions to implement. A vehicle detection system can pave the way to understanding traffic congestion, finding mobility patterns, and ensuring traffic surveillance. So, this paper proposes a fine-tuned object detector, the YOLOv9 model to detect native vehicles trained on a Bangladesh-based dataset. Results show that the fine-tuned YOLOv9 model achieved a mean Average Precision (mAP) of 0.934 at the Intersection over Union (IoU) threshold of 0.5, achieving state-of-the-art performance over past studies on Bangladesh-based datasets, shown through a comparison. Later, by suggesting the model to be deployed on CCTVs (closed circuit television) on the roads, a conceptual technique is proposed to process the vehicle detection model output data in a graph structure creating a vehicle detection system in the city. Finally, applications of such vehicle detection system are discussed showing a framework on how it can solve further ITS research questions, to provide a rationale for policymakers to implement the proposed vehicle detection system in the city., Comment: 16 pages, 10 figures

Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The current state-of-the-art VPR methods rely on VLAD aggregation, which can be trained to learn a weighted contribution of features through their soft assignment to cluster centers. However, this process has two key limitations. Firstly, the feature-to-cluster weighting does not account for over-represented repetitive structures within a cluster, e.g., shadows or window panes; this phenomenon is also referred to as the `burstiness' problem, classically solved by discounting repetitive features before aggregation. Secondly, feature to cluster comparisons are compute-intensive for state-of-the-art image encoders with high-dimensional local features. This paper addresses these limitations by introducing VLAD-BuFF with two novel contributions: i) a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training, and ii) Fast Feature aggregation by reducing local feature dimensions specifically through PCA-initialized learnable pre-projection. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall. Through additional qualitative studies, we show how our proposed weighting method effectively downweights the non-distinctive features. Source code: https://github.com/Ahmedest61/VLAD-BuFF/., Comment: Presented at ECCV 2024; Includes supplementary; 29 pages; 7 figures

Several studies have discussed the impact different optimization techniques in the context of time series forecasting across different Neural network architectures. This paper examines the effectiveness of Adam and Nesterov's Accelerated Gradient (NAG) optimization techniques on LSTM and GRU neural networks for time series prediction, specifically stock market time-series. Our study was done by training LSTM and GRU models with two different optimization techniques - Adam and Nesterov Accelerated Gradient (NAG), comparing and evaluating their performance on Apple Inc's closing price data over the last decade. The GRU model optimized with Adam produced the lowest RMSE, outperforming the other model-optimizer combinations in both accuracy and convergence speed. The GRU models with both optimizers outperformed the LSTM models, whilst the Adam optimizer outperformed the NAG optimizer for both model architectures. The results suggest that GRU models optimized with Adam are well-suited for practitioners in time-series prediction, more specifically stock price time series prediction producing accurate and computationally efficient models. The code for the experiments in this project can be found at https://github.com/AhmadMak/Time-Series-Optimization-Research Keywords: Time-series Forecasting, Neural Network, LSTM, GRU, Adam Optimizer, Nesterov Accelerated Gradient (NAG) Optimizer, Comment: 12 pages, 6 figures

The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, Li et al. (2021) proposed the tilted empirical risk as a non-linear risk metric for machine learning applications such as classification and regression problems. In this work, we examine the generalization error of the tilted empirical risk. In particular, we provide uniform and information-theoretic bounds on the tilted generalization error, defined as the difference between the population risk and the tilted empirical risk, with a convergence rate of $O(1/\sqrt{n})$ where $n$ is the number of training samples. Furthermore, we study the solution to the KL-regularized expected tilted empirical risk minimization problem and derive an upper bound on the expected tilted generalization error with a convergence rate of $O(1/n)$., Comment: 49 pages

Modern multicore System-on-Chips (SoCs) feature hardware monitoring mechanisms that measure total power consumption. However, these aggregate measurements are often insufficient for fine-grained thermal and power management. This paper presents an enhanced Clustering Blind Power Identification (ICBPI) approach, designed to improve the sensitivity and robustness of the traditional Blind Power Identification (BPI) method. BPI estimates the power consumption of individual cores and models the thermal behavior of an SoC using only thermal sensor data and total power measurements. The proposed ICBPI approach refines BPI's initialization process, particularly improving the non-negative matrix factorization (NNMF) step, which is critical to the accuracy of BPI. ICBPI introduces density-based spatial clustering of applications with noise (DBSCAN) to better align temperature and power consumption data, thereby providing more accurate power consumption estimates. We validate the ICBPI method through two key tasks. The first task evaluates power estimation accuracy across four different multicore architectures, including a heterogeneous processor. Results show that ICBPI significantly enhances accuracy, reducing error rates by 77.56% compared to the original BPI and by 68.44% compared to the state-of-the-art BPISS method. The second task focuses on improving the detection and localization of malicious thermal sensor attacks in heterogeneous processors. The results demonstrate that ICBPI enhances the security and robustness of multicore SoCs against such attacks.

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in some respects, agents are often remarkably brittle to minor visual variations in control-irrelevant factors such as the background or camera viewpoint. In this paper, we present theDeepMind Control Visual Benchmark (DMC-VB), a dataset collected in the DeepMind Control Suite to evaluate the robustness of offline RL agents for solving continuous control tasks from visual input in the presence of visual distractors. In contrast to prior works, our dataset (a) combines locomotion and navigation tasks of varying difficulties, (b) includes static and dynamic visual variations, (c) considers data generated by policies with different skill levels, (d) systematically returns pairs of state and pixel observation, (e) is an order of magnitude larger, and (f) includes tasks with hidden goals. Accompanying our dataset, we propose three benchmarks to evaluate representation learning methods for pretraining, and carry out experiments on several recently proposed methods. First, we find that pretrained representations do not help policy learning on DMC-VB, and we highlight a large representation gap between policies learned on pixel observations and on states. Second, we demonstrate when expert data is limited, policy learning can benefit from representations pretrained on (a) suboptimal data, and (b) tasks with stochastic hidden goals. Our dataset and benchmark code to train and evaluate agents are available at: https://github.com/google-deepmind/dmc_vision_benchmark., Comment: NeurIPS 2024 Datasets and Benchmarks Track. Dataset available at: https://github.com/google-deepmind/dmc_vision_benchmark

With robots increasingly collaborating with humans in everyday tasks, it is important to take steps toward robotic systems capable of understanding the environment. This work focuses on scene understanding to detect pick and place tasks given initial and final images from the scene. To this end, a dataset is collected for object detection and pick and place task detection. A YOLOv5 network is subsequently trained to detect the objects in the initial and final scenes. Given the detected objects and their bounding boxes, two methods are proposed to detect the pick and place tasks which transform the initial scene into the final scene. A geometric method is proposed which tracks objects' movements in the two scenes and works based on the intersection of the bounding boxes which moved within scenes. Contrarily, the CNN-based method utilizes a Convolutional Neural Network to classify objects with intersected bounding boxes into 5 classes, showing the spatial relationship between the involved objects. The performed pick and place tasks are then derived from analyzing the experiments with both scenes. Results show that the CNN-based method, using a VGG16 backbone, outscores the geometric method by roughly 12 percentage points in certain scenarios, with an overall success rate of 84.3%., Comment: Conference Paper, ICEE 2024, 7 pages, 5 figures

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries to extract information about a model's training dataset by exploiting access to model parameters during or after training. In this work, we study privacy attacks in the gray-box setting, where the attacker has only limited access - in terms of view and actions - to the model. The findings of our investigation provide new insights for the development of privacy-preserving collaborative learning solutions. We deploy SmartCryptNN, a framework that tailors homomorphic encryption to protect the portions of the model posing higher privacy risks. Our solution offers a trade-off between privacy and efficiency, which varies based on the extent and selection of the model components we choose to protect. We explore it on dense neural networks, where through extensive evaluation of diverse datasets and architectures, we uncover instances where a favorable sweet spot in the trade-off can be achieved by safeguarding only a single layer of the network. In one of such instances, our approach trains ~4 times faster compared to fully encrypted solutions, while reducing membership leakage by 17.8 times compared to plaintext solutions., Comment: 19 pages, 7 figures, in submission

Real-life medical data is often multimodal and incomplete, fueling the growing need for advanced deep learning models capable of integrating them efficiently. The use of diverse modalities, including histopathology slides, MRI, and genetic data, offers unprecedented opportunities to improve prognosis prediction and to unveil new treatment pathways. Contrastive learning, widely used for deriving representations from paired data in multimodal tasks, assumes that different views contain the same task-relevant information and leverages only shared information. This assumption becomes restrictive when handling medical data since each modality also harbors specific knowledge relevant to downstream tasks. We introduce DRIM, a new multimodal method for capturing these shared and unique representations, despite data sparsity. More specifically, given a set of modalities, we aim to encode a representation for each one that can be divided into two components: one encapsulating patient-related information common across modalities and the other, encapsulating modality-specific details. This is achieved by increasing the shared information among different patient modalities while minimizing the overlap between shared and unique components within each modality. Our method outperforms state-of-the-art algorithms on glioma patients survival prediction tasks, while being robust to missing modalities. To promote reproducibility, the code is made publicly available at https://github.com/Lucas-rbnt/DRIM

One of the key issues contributing to inefficiency in Puskesmas is the time-consuming nature of doctor-patient interactions. Doctors need to conduct thorough consultations, which include diagnosing the patient's condition, providing treatment advice, and transcribing detailed notes into medical records. In regions with diverse linguistic backgrounds, doctors often have to ask clarifying questions, further prolonging the process. While diagnosing is essential, transcription and summarization can often be automated using AI to improve time efficiency and help doctors enhance care quality and enable early diagnosis and intervention. This paper proposes a solution using a localized large language model (LLM) to transcribe, translate, and summarize doctor-patient conversations. We utilize the Whisper model for transcription and GPT-3 to summarize them into the ePuskemas medical records format. This system is implemented as an add-on to an existing web browser extension, allowing doctors to fill out patient forms while talking. By leveraging this solution for real-time transcription, translation, and summarization, doctors can improve the turnaround time for patient care while enhancing the quality of records, which become more detailed and insightful for future visits. This innovation addresses challenges like overcrowded facilities and the administrative burden on healthcare providers in Indonesia. We believe this solution will help doctors save time, provide better care, and produce more accurate medical records, representing a significant step toward modernizing healthcare and ensuring patients receive timely, high-quality care, even in resource-constrained settings.

Crop field boundaries are foundational datasets for agricultural monitoring and assessments but are expensive to collect manually. Machine learning (ML) methods for automatically extracting field boundaries from remotely sensed images could help realize the demand for these datasets at a global scale. However, current ML methods for field instance segmentation lack sufficient geographic coverage, accuracy, and generalization capabilities. Further, research on improving ML methods is restricted by the lack of labeled datasets representing the diversity of global agricultural fields. We present Fields of The World (FTW) -- a novel ML benchmark dataset for agricultural field instance segmentation spanning 24 countries on four continents (Europe, Africa, Asia, and South America). FTW is an order of magnitude larger than previous datasets with 70,462 samples, each containing instance and semantic segmentation masks paired with multi-date, multi-spectral Sentinel-2 satellite images. We provide results from baseline models for the new FTW benchmark, show that models trained on FTW have better zero-shot and fine-tuning performance in held-out countries than models that aren't pre-trained with diverse datasets, and show positive qualitative zero-shot results of FTW models in a real-world scenario -- running on Sentinel-2 scenes over Ethiopia.

Solar photovoltaic (PV) modules are prone to damage during manufacturing, installation and operation which reduces their power conversion efficiency. This diminishes their positive environmental impact over the lifecycle. Continuous monitoring of PV modules during operation via unmanned aerial vehicles is essential to ensure that defective panels are promptly replaced or repaired to maintain high power conversion efficiencies. Computer vision provides an automatic, non-destructive and cost-effective tool for monitoring defects in large-scale PV plants. We review the current landscape of deep learning-based computer vision techniques used for detecting defects in solar modules. We compare and evaluate the existing approaches at different levels, namely the type of images used, data collection and processing method, deep learning architectures employed, and model interpretability. Most approaches use convolutional neural networks together with data augmentation or generative adversarial network-based techniques. We evaluate the deep learning approaches by performing interpretability analysis on classification tasks. This analysis reveals that the model focuses on the darker regions of the image to perform the classification. We find clear gaps in the existing approaches while also laying out the groundwork for mitigating these challenges when building new models. We conclude with the relevant research gaps that need to be addressed and approaches for progress in this field: integrating geometric deep learning with existing approaches for building more robust and reliable models, leveraging physics-based neural networks that combine domain expertise of physical laws to build more domain-aware deep learning models, and incorporating interpretability as a factor for building models that can be trusted. The review points towards a clear roadmap for making this technology commercially relevant., Comment: 31 pages, 14 figures

We consider families $A(t)$ of self-adjoint operators with symmetry that causes the spectral flow of the family to vanish. We study the secondary $\mathbb{Z}_2$-valued spectral flow of such families. We prove an analog of the Atiyah-Singer-Robbin-Salamon theorem, showing that this secondary spectral flow of $A(t)$ is equal to the secondary $\mathbb{Z}_2$-valued index of the suspension operator $\frac{d}{dt}+A(t)$. Applying this result, we show that the graded secondary spectral flow of a symmetric family of Toeplitz operators on a complete Riemannian manifold equals the secondary index of a certain Callias-type operator. In the case of a pseudo-convex domain, this leads to an odd version of the secondary Boutet de Monvel's index theorem for Toeplitz operators. When this domain is simply a unit disc in the complex plane, we recover the bulk-edge correspondence for the Graf-Porta module for 2D topological insulators of type AII., Comment: 27 pages