Search

Federated Learning (FL) is a distributed learning technique that maintains data privacy by providing a decentralized training method for machine learning models using distributed big data. This promising Federated Learning approach has also gained popularity in bioinformatics, where the privacy of biomedical data holds immense importance, especially when patient data is involved. Despite the successful implementation of Federated learning in biological sequence analysis, rigorous consideration is still required to improve accuracy in a way that data privacy should not be compromised. Additionally, the optimal integration of federated learning, especially in protein sequence analysis, has not been fully explored. We propose a deep feed-forward neural network-based enhanced federated learning method for protein sequence classification to overcome these challenges. Our method introduces novel enhancements to improve classification accuracy. We introduce dynamic weighted federated learning (DWFL) which is a federated learning-based approach, where local model weights are adjusted using weighted averaging based on their performance metrics. By assigning higher weights to well-performing models, we aim to create a more potent initial global model for the federated learning process, leading to improved accuracy. We conduct experiments using real-world protein sequence datasets to assess the effectiveness of DWFL. The results obtained using our proposed approach demonstrate significant improvements in model accuracy, making federated learning a preferred, more robust, and privacy-preserving approach for collaborative machine-learning tasks., Comment: Accepted at SIMBig 2024

In this research, we define two concepts; random matrix and mean square stability. Studying the stability of solutions for perturbed random differential systems is included. Partial moments of the second order were verified, which determines the stability conditions of the studied systems, ensuring stability through Lyapunov functions. The differential equations that determine Lyapunov functions were obtained. The necessary conditions for Lyapunov matrices to ensure asymptotic stability were established.

In this study, we investigate the performance of the sparse identification of nonlinear dynamics (SINDy) algorithm and the neural ordinary differential equations (ODEs) in identification of the underlying mechanisms of open ocean Lagrangian drifter hydrodynamics with possible applications in coastal and port hydrodynamic processes. With this motivation we employ two different Lagrangian drifter datasets acquired by National Oceanic and Atmospheric Administration (NOAA)'s surface buoys with proper World Meteorological Organization (WMO) numbers. In the SINDy approach, the primary goal is to identify the drifter paths of buoys using ordinary differential equation sets with a minimal number of sparse coefficients. In the neural ODE approach, the goal is to identify the derivative of the hidden state of a neural network (NN). Using the acquired data, we examine the applicability of the SINDy and the neural ODE algorithms in identification of the drifter trajectories comparatively. We propose that while both of the algorithms may give acceptable results for open ocean, the SINDy-based algorithmic approach can predict the Lagrangian drifter paths more accurately and consistently at least for the datasets investigated and parameters selected. A discussion of our findings with potential applications in search and rescue missions in the open ocean, their limitations and applicability are also presented.

Hybrid Rebeca is introduced for modeling asynchronous event-based Cyber-Physical Systems (CPSs). In this work, we extend Hybrid Rebeca to allow the modeling of non-deterministic time behavior. We provide a set of rules to define the semantic model of Hybrid Rebeca models in terms of Time Transition Systems which represents an over-approximation of the reachable states of a Hybrid Rebeca model. Then, we adapt the reachability analysis algorithm of Flow$^*$ for Hybrid Rebeca models leveraging our semantic rules. This improves the analysis significantly because the previous technique relied on the reachability analysis of hybrid automata by deriving a monolithic hybrid automaton from a given Hybrid Rebeca model, leading to a huge hybrid automaton. We illustrate the applicability of our approach through a case study.

This paper introduces a real-time Vehicle Collision Avoidance System (V-CAS) designed to enhance vehicle safety through adaptive braking based on environmental perception. V-CAS leverages the advanced vision-based transformer model RT-DETR, DeepSORT tracking, speed estimation, brake light detection, and an adaptive braking mechanism. It computes a composite collision risk score based on vehicles' relative accelerations, distances, and detected braking actions, using brake light signals and trajectory data from multiple camera streams to improve scene perception. Implemented on the Jetson Orin Nano, V-CAS enables real-time collision risk assessment and proactive mitigation through adaptive braking. A comprehensive training process was conducted on various datasets for comparative analysis, followed by fine-tuning the selected object detection model using transfer learning. The system's effectiveness was rigorously evaluated on the Car Crash Dataset (CCD) from YouTube and through real-time experiments, achieving over 98% accuracy with an average proactive alert time of 1.13 seconds. Results indicate significant improvements in object detection and tracking, enhancing collision avoidance compared to traditional single-camera methods. This research demonstrates the potential of low-cost, multi-camera embedded vision transformer systems to advance automotive safety through enhanced environmental perception and proactive collision avoidance mechanisms., Comment: Accepted at ICMLA 2024

Evaluating datasets in data marketplaces, where the buyer aim to purchase valuable data, is a critical challenge. In this paper, we introduce an innovative task-agnostic data valuation method called PriArTa which is an approach for computing the distance between the distribution of the buyer's existing dataset and the seller's dataset, allowing the buyer to determine how effectively the new data can enhance its dataset. PriArTa is communication-efficient, enabling the buyer to evaluate datasets without needing access to the entire dataset from each seller. Instead, the buyer requests that sellers perform specific preprocessing on their data and then send back the results. Using this information and a scoring metric, the buyer can evaluate the dataset. The preprocessing is designed to allow the buyer to compute the score while preserving the privacy of each seller's dataset, mitigating the risk of information leakage before the purchase. A key feature of PriArTa is its robustness to common data transformations, ensuring consistent value assessment and reducing the risk of purchasing redundant data. The effectiveness of PriArTa is demonstrated through experiments on real-world image datasets, showing its ability to perform privacy-preserving, augmentation-robust data valuation in data marketplaces.

Current work includes a study of the very rare case called intruder nuclear levels, where there are only seven nuclei in nature. Such cases occur when the first excited state is . The current study included only three nuclei: . The nuclear model used to explore and investigate nuclei in this work is the second interacting boson. The experimental data and theoretical values obtained were in good agreement, indicating this model's success in calculating such anomalies. The main reason for the presence of these levels in other than their natural locations expected according to the IBM model is that they have a double subshell closure. The values of the electric quadrupole transitions, magnetic dipole transitions and zero transitions estimated were in acceptable agreement with experimental data.

Recent advancements in Large Language Models (LLMs) have renewed interest in automatic programming language translation. Encoder-decoder transformer models, in particular, have shown promise in translating between different programming languages. However, translating between a language and its high-performance computing (HPC) extensions remains underexplored due to challenges such as complex parallel semantics. In this paper, we introduce CodeRosetta, an encoder-decoder transformer model designed specifically for translating between programming languages and their HPC extensions. CodeRosetta is evaluated on C++ to CUDA and Fortran to C++ translation tasks. It uses a customized learning framework with tailored pretraining and training objectives to effectively capture both code semantics and parallel structural nuances, enabling bidirectional translation. Our results show that CodeRosetta outperforms state-of-the-art baselines in C++ to CUDA translation by 2.9 BLEU and 1.72 CodeBLEU points while improving compilation accuracy by 6.05%. Compared to general closed-source LLMs, our method improves C++ to CUDA translation by 22.08 BLEU and 14.39 CodeBLEU, with 2.75% higher compilation accuracy. Finally, CodeRosetta exhibits proficiency in Fortran to parallel C++ translation, marking it, to our knowledge, as the first encoder-decoder model for this complex task, improving CodeBLEU by at least 4.63 points compared to closed-source and open-code LLMs.

The modern era always looks into advancements in technology. Design and topology of interconnection networks play a mutual role in development of technology. Analysing the topological properties and characteristics of an interconnection network is not an easy task. Graph theory helps in solving this task analytically and efficiently through the use of numerical parameters known as distance based topological descriptors. These descriptors have considerable applications in various fields of computer science, chemistry, biology, etc. This paper deals with the evaluation of topological descriptors for an n-dimensional multistage interconnection network, the benes network,BB(n). Also, a new variant of interconnection network is derived from the benes network, named as augmented benes network and denoted as BB^* (n). The topological descriptors for the benes derived network are also determined in this work. Further, the benes network and augmented benes network undergoes a comparative analysis based on few network parameters, which helps to understand the efficiency of newly derived benes network. A broadcasting algorithm for the augmented benes network is also provided.

We present an advanced approach to medical question-answering (QA) services, using fine-tuned Large Language Models (LLMs) to improve the accuracy and reliability of healthcare information. Our study focuses on optimizing models like LLaMA-2 and Mistral, which have shown great promise in delivering precise, reliable medical answers. By leveraging comprehensive datasets, we applied fine-tuning techniques such as rsDoRA+ and ReRAG. rsDoRA+ enhances model performance through a combination of decomposed model weights, varied learning rates for low-rank matrices, and rank stabilization, leading to improved efficiency. ReRAG, which integrates retrieval on demand and question rewriting, further refines the accuracy of the responses. This approach enables healthcare providers to access fast, dependable information, aiding in more efficient decision-making and fostering greater patient trust. Our work highlights the potential of fine-tuned LLMs to significantly improve the quality and accessibility of medical information services, ultimately contributing to better healthcare outcomes for all., Comment: 8 pages, 10 figures, accepted and to be published in the proceedings of 2024 IEEE International Conference on Data Mining Workshops (ICDMW)

While recent advances in deep learning (DL) for surgical scene segmentation have yielded promising results on single-center and single-imaging modality data, these methods usually do not generalize well to unseen distributions or modalities. Even though human experts can identify visual appearances, DL methods often fail to do so when data samples do not follow a similar distribution. Current literature addressing domain gaps in modality changes has focused primarily on natural scene data. However, these methods cannot be directly applied to endoscopic data, as visual cues in such data are more limited compared to natural scenes. In this work, we exploit both style and content information in images by performing instance normalization and feature covariance mapping techniques to preserve robust and generalizable feature representations. Additionally, to avoid the risk of removing salient feature representations associated with objects of interest, we introduce a restitution module within the feature-learning ResNet backbone that retains useful task-relevant features. Our proposed method shows a 13.7% improvement over the baseline DeepLabv3+ and nearly an 8% improvement over recent state-of-the-art (SOTA) methods for the target (different modality) set of the EndoUDA polyp dataset. Similarly, our method achieved a 19% improvement over the baseline and 6% over the best-performing SOTA method on the EndoUDA Barrett's esophagus (BE) dataset., Comment: The paper was accepted at Machine Learning in Medical Imaging (MLMI) workshop at MICCAI 2024 in Marrakesh

Medical image analysis has emerged as an essential element of contemporary healthcare, facilitating physicians in achieving expedited and precise diagnosis. Recent breakthroughs in deep learning, a subset of artificial intelligence, have markedly revolutionized the analysis of medical pictures, improving the accuracy and efficiency of clinical procedures. Deep learning algorithms, especially convolutional neural networks (CNNs), have demonstrated remarkable proficiency in autonomously learning features from multidimensional medical pictures, including MRI, CT, and X-ray scans, without the necessity for manual feature extraction. These models have been utilized across multiple medical disciplines, including pathology, radiology, ophthalmology, and cardiology, where they aid in illness detection, classification, and segmentation tasks......

The advancement of concrete 3D printing (C3DP) technology has revolutionized the construction industry, offering unique opportunities for innovation and efficiency. At the heart of this process lies a comprehensive digital chain that integrates various stages, from initial design to post-processing. This article provides an overview of this digital chain, explaining each crucial step. The chain begins with design, utilizing Design for Additive Manufacturing (DFAM) concept and parametric modeling to create optimized structures. Path generation follows, determining the precise toolpath for extruding concrete layers. Simulations, both numerical and analytical, ensure the design's integrity and feasibility. Several articles have addressed parametric modeling, process and numerical simulation, and the post-processing phase. However, none has proposed an updated methodology for the workflow. This study aims to propose a robust digital chain for C3DP technology, using one platform (3Dexperience) and seamless data transfer between applications. These steps provide insights into the structural performance of printed components, enabling necessary adjustments and optimizations. In essence, the digital chain coordinates a seamless workflow that transforms digital designs into concrete structures, unlocking the full potential of C3DP and paving the way for innovative and efficient construction., Comment: Digital Concrete 2024 - Supplementary Proceedings, Sep 2024, Munich, France

For a graph $\mathbb{Q}=(\mathbb{V},\mathbb{E})$, the transformation graphs are defined as graphs with vertex set being $\mathbb{V(Q)} \cup \mathbb{E(Q)}$ and edge set is described following certain conditions. In comparison to the structure descriptor of the original graph $\mathbb{Q}$, the topological descriptor of its transformation graphs displays distinct characteristics related to structure. Thus, a compound's transformation graphs descriptors can be used to model a variety of structural features of the underlying chemical. In this work, the concept of transformation graphs are extended giving rise to novel class of graphs, the $(r,s)$- generalised transformation graphs, whose vertex set is union of $r$ copies of $\mathbb{V(Q)}$ and $s$ copies of $\mathbb{E(Q)}$, where, $r, s \in N$ and the edge set are defined under certain conditions. Further, these class of graphs are analysed with the help of first Zagreb index. Mainly, there are eight transformation graphs based on the criteria for edge set, but under the concept of $(r,s)$- generalised transformation graphs, infinite number of graphs can be described and analysed.

We present a refined approach to biomedical question-answering (QA) services by integrating large language models (LLMs) with Multi-BERT configurations. By enhancing the ability to process and prioritize vast amounts of complex biomedical data, this system aims to support healthcare professionals in delivering better patient outcomes and informed decision-making. Through innovative use of BERT and BioBERT models, combined with a multi-layer perceptron (MLP) layer, we enable more specialized and efficient responses to the growing demands of the healthcare sector. Our approach not only addresses the challenge of overfitting by freezing one BERT model while training another but also improves the overall adaptability of QA services. The use of extensive datasets, such as BioASQ and BioMRC, demonstrates the system's ability to synthesize critical information. This work highlights how advanced language models can make a tangible difference in healthcare, providing reliable and responsive tools for professionals to manage complex information, ultimately serving the broader goal of improved care and data-driven insights., Comment: 10 pages, 12 figures, accepted and to be published in the proceedings of 2024 IEEE International Conference on Data Mining Workshops (ICDMW)

Applying deep learning (DL) for annotating surgical instruments in robot-assisted minimally invasive surgeries (MIS) represents a significant advancement in surgical technology. This systematic review examines 48 studies that and advanced DL methods and architectures. These sophisticated DL models have shown notable improvements in the precision and efficiency of detecting and segmenting surgical tools. The enhanced capabilities of these models support various clinical applications, including real-time intraoperative guidance, comprehensive postoperative evaluations, and objective assessments of surgical skills. By accurately identifying and segmenting surgical instruments in video data, DL models provide detailed feedback to surgeons, thereby improving surgical outcomes and reducing complication risks. Furthermore, the application of DL in surgical education is transformative. The review underscores the significant impact of DL on improving the accuracy of skill assessments and the overall quality of surgical training programs. However, implementing DL in surgical tool detection and segmentation faces challenges, such as the need for large, accurately annotated datasets to train these models effectively. The manual annotation process is labor-intensive and time-consuming, posing a significant bottleneck. Future research should focus on automating the detection and segmentation process and enhancing the robustness of DL models against environmental variations. Expanding the application of DL models across various surgical specialties will be essential to fully realize this technology's potential. Integrating DL with other emerging technologies, such as augmented reality (AR), also offers promising opportunities to further enhance the precision and efficacy of surgical procedures., Comment: 57 pages, 9 figures, Published in Artificial Intelligence Reviews journal

Achieving deterministic control over the properties of low-dimensional materials with nanoscale precision is a long-sought goal. Mastering this capability has a transformative impact on the design of multifunctional electrical and optical devices. Here, we present an ion-assisted synthetic technique that enables precise control over the material composition and energy landscape of two-dimensional (2D) atomic crystals. Our method transforms binary transition metal dichalcogenides (TMDs), like MoSe$_2$, into ternary MoS$_{2\alpha}$Se$_{2(1-{\alpha}})$ alloys with systematically adjustable compositions, ${\alpha}$. By piecewise assembly of the lateral, compositionally modulated MoS$_{2\alpha}$Se$_{2(1-{\alpha})}$ segments within 2D atomic layers, we present a synthetic pathway towards the realization of multi-compositional designer materials. Our technique enables the fabrication of complex structures with arbitrary boundaries, dimensions as small as 30 nm, and fully customizable energy landscapes. Our optical characterizations further showcase the potential for implementing tailored optoelectronics in these engineered 2D crystals., Comment: 22 pages, 5 Figures

Coding theory plays a crucial role in ensuring data integrity and reliability across various domains, from communication to computation and storage systems. However, its reliance on trust assumptions for data recovery poses significant challenges, particularly in emerging decentralized systems where trust is scarce. To address this, the game of coding framework was introduced, offering insights into strategies for data recovery within incentive-oriented environments. The focus of the earliest version of the game of coding was limited to scenarios involving only two nodes. This paper investigates the implications of increasing the number of nodes in the game of coding framework, particularly focusing on scenarios with one honest node and multiple adversarial nodes. We demonstrate that despite the increased flexibility for the adversary with an increasing number of adversarial nodes, having more power is not beneficial for the adversary and is not detrimental to the data collector, making this scheme sybil-resistant. Furthermore, we outline optimal strategies for the data collector in terms of accepting or rejecting the inputs, and characterize the optimal noise distribution for the adversary.

Automating the design of microstrip antennas has been an active area of research for the past decade. By leveraging machine learning techniques such as Genetic Algorithms (GAs) or, more recently, Deep Neural Networks (DNNs), a number of work have demonstrated the possibility of producing non-trivial antenna geometries that can be efficient in terms of area utilization or be used in complex multi-frequency-band scenarios. However, both GAs and DNNs are notoriously compute-expensive, often requiring hour-long run times in order to produce new antenna geometries. In this paper, we propose to explore the novel use of Cross-Entropy optimization as a Monte-Carlo sampling technique for optimizing the geometry of patch antennas given a target $S_{11}$ scattering parameter curve that a user wants to obtain. We compare our proposed Uniform Cross-Entropy (UCE) method against other popular Monte-Carlo optimization techniques such as Gaussian Processes, Forest optimization and baseline random search approaches. We demonstrate that the proposed UCE technique outperforms the competing methods while still having a reasonable compute complexity, taking around 16 minutes to converge. Finally, our code is released as open-source with the hope of being useful to future research.

Error accumulation is an essential component of the Top-$k$ sparsification method in distributed gradient descent. It implicitly scales the learning rate and prevents the slow-down of lateral movement, but it can also deteriorate convergence. This paper proposes a novel sparsification algorithm called regularized Top-$k$ (RegTop-$k$) that controls the learning rate scaling of error accumulation. The algorithm is developed by looking at the gradient sparsification as an inference problem and determining a Bayesian optimal sparsification mask via maximum-a-posteriori estimation. It utilizes past aggregated gradients to evaluate posterior statistics, based on which it prioritizes the local gradient entries. Numerical experiments with ResNet-18 on CIFAR-10 show that at $0.1\%$ sparsification, RegTop-$k$ achieves about $8\%$ higher accuracy than standard Top-$k$., Comment: To appear in Proc. IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2024

2D metal halide perovskites have enabled significant stability improvements in perovskite devices, particularly in resistance to moisture. However, some 2D perovskites are even more susceptible to photooxidation compared to 3D perovskites. This is particularly true for more commonly investigated Ruddlesden-Popper (RP) perovskites that exhibit increased susceptibility to photoinduced degradation compared to Dion-Jacobson (DJ) perovskites. Comparisons between different RP and DJ perovskites reveal that this phenomenon cannot be explained by commonly proposed differences in superoxide ion generation, interlayer distance and lattice structural rigidity differences. Instead, the resistance to photooxidation of DJ perovskites can be attributed to decreased likelihood of double deprotonation events (compared to single deprotonation events in RP perovskites) required for the loss of organic cations and the perovskite decomposition. Consequently, DJ perovskites are less susceptible to oxidative degradation (both photo- and electrochemically induced), which leads to improved operational stability of solar cells based on these materials., Comment: Main text: 19 pages, 6 figures, supplementary information: 62 pages, 47 figures

Frequent monitoring is necessary to stratify individuals based on their likelihood of developing gastrointestinal (GI) cancer precursors. In clinical practice, white-light imaging (WLI) and complementary modalities such as narrow-band imaging (NBI) and fluorescence imaging are used to assess risk areas. However, conventional deep learning (DL) models show degraded performance due to the domain gap when a model is trained on one modality and tested on a different one. In our earlier approach, we used a superpixel-based method referred to as "SUPRA" to effectively learn domain-invariant information using color and space distances to generate groups of pixels. One of the main limitations of this earlier work is that the aggregation does not exploit structural information, making it suboptimal for segmentation tasks, especially for polyps and heterogeneous color distributions. Therefore, in this work, we propose an approach for style-content disentanglement using instance normalization and instance selective whitening (ISW) for improved domain generalization when combined with SUPRA. We evaluate our approach on two datasets: EndoUDA Barrett's Esophagus and EndoUDA polyps, and compare its performance with three state-of-the-art (SOTA) methods. Our findings demonstrate a notable enhancement in performance compared to both baseline and SOTA methods across the target domain data. Specifically, our approach exhibited improvements of 14%, 10%, 8%, and 18% over the baseline and three SOTA methods on the polyp dataset. Additionally, it surpassed the second-best method (EndoUDA) on the Barrett's Esophagus dataset by nearly 2%.

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.

Background: This study aimed to evaluate and compare the performance of classical machine learning models (CMLs) and large language models (LLMs) in predicting mortality associated with COVID-19 by utilizing a high-dimensional tabular dataset. Materials and Methods: We analyzed data from 9,134 COVID-19 patients collected across four hospitals. Seven CML models, including XGBoost and random forest (RF), were trained and evaluated. The structured data was converted into text for zero-shot classification by eight LLMs, including GPT-4 and Mistral-7b. Additionally, Mistral-7b was fine-tuned using the QLoRA approach to enhance its predictive capabilities. Results: Among the CML models, XGBoost and RF achieved the highest accuracy, with F1 scores of 0.87 for internal validation and 0.83 for external validation. In the LLM category, GPT-4 was the top performer with an F1 score of 0.43. Fine-tuning Mistral-7b significantly improved its recall from 1% to 79%, resulting in an F1 score of 0.74, which was stable during external validation. Conclusion: While LLMs show moderate performance in zero-shot classification, fine-tuning can significantly enhance their effectiveness, potentially aligning them closer to CML models. However, CMLs still outperform LLMs in high-dimensional tabular data tasks., Comment: Code is available at: https://github.com/mohammad-gh009/Large-Language-Models-vs-Classical-Machine-learning and https://github.com/Sdamirsa/Tehran_COVID_Cohort. The datasets are available from the corresponding author on reasonable request (sdamirsa@ymail.com)