This paper presents an extensive review of the recent advancements in gait analysis using machine learning (ML) techniques, focusing on its application for detecting and treating genu valgum, a condition characterized by inward angling of the knees. The integration of various technologies such as wearable sensors, motion capture systems, and sophisticated ML algorithms has significantly enhanced the classification and prediction of abnormal gait patterns, aiding clinicians in assessing genu valgum and developing personalized treatment plans. However, challenges persist regarding model interpretability, dataset diversity, and the variability of realworld conditions. This paper highlights future directions for research, emphasizing the need for advanced algorithms, larger datasets, and improved integration of wearable sensors for realtime gait analysis.

This study aims to explore the integration of historical weather data with machine learning methods for better rainfall forecasting in Bangladesh. It has the potential to identify rainfall early by observing their prediction on preventing natural disasters. Weather forecasting protects human lives and property but often struggles with manual, error-prone calculations due to the complex data involved. This research combines weather forecasting with machine learning techniques to improve the accuracy and precision of predictions. The main goal is to develop an accurate prediction system of rainfall forecasting in Bangladesh for the future. The model training data set is from historical meteorologic records of Bangladesh. After neatly hyper-tuning the Random Forest model, we achieve some impressive RMSE metrics. The results are compared with a baseline model, Randomized Search CV, using different evaluation metrics such as MAE, MSLE, and RMSLE, etc., and the observations of significantly better performance is observable. An extensive analysis of machine learning techniques was performed in the domain of rainfall prediction. Among all the tried models, the Random Forest model gave perfect predictions, as noted by its MSE of 12245.52 and absolute error value of 64.25. Furthermore, there was excellent precision of 95% and recall 92%, respectively, for the classification of wet days, corresponding to a total accuracy score of 91%. Based on the above result, we can conclude that the Random Forest model is both robust and promising for rainfall prediction problems. Various models such as Linear Regression, Support Vector Regressor, Decision Tree, K-Nearest Neighbors, AdaBoost, XG Boost, Ridge, Linear SVR and MLP Regressor showed variations in prediction accuracies and errors. Nevertheless, the Random Forest came out as a better choice in this case, showing its superiority.

Structural Health Monitoring (SHM) is vital to guarantee the early identification of any deterioration in bridge structures and to prevent unexpected collapses. As structures degrade, one of the most efficient techniques in SHM is vibrationbased damage diagnosis, which evaluates damage through analysing the dynamic features of structures. Identification of bridge deterioration may be done by measuring the vibration response caused by cars crossing a bridge. This paper proposes a unique Vehicle-Bridge Interaction (VBI)-based damage detection method to assess the bridge's condition.First, the method's foundations of theory are studied. A half-car dynamic model represents the vehicle and its suspension system, while the Finite Element Method is used to describe the bridge superstructure. The equations of motion for the bridge and the vehicle are obtained, respectively, using the mode superposition technique, D'Alembert's principle, and the finite element method. After that, the Newmark-beta approach is used to solve the linked dynamic issue. The roughness of the bridge road surface is taken into consideration during the examination.The proposed method for determining bridge damage is based on an analysis of the pitching rotation of a passing vehicle. The three main theoretical elements of this response are the bridge natural frequency, the vehicle frequency, and a pseudo-frequency component related to the vehicle speed. The Empirical Mode Decomposition (EMD) approach dissects the signal into its constituent parts, or intrinsic mode functions. A recommended damage detection method makes use of the intrinsic mode functions (IMFs) corresponding to the vehicle speed component of the response obtained from the passing vehicle. Through the study, it is observed that the proposed technique is capable of effectively identifying various damage cases considered in this research.

The capacity of modern artificial intelligence systems to interpret and respond to intricate human language patterns has introduced significant advancements across diverse domains. However, maintaining contextual coherence over extended and semantically complex interactions remains an area of considerable challenge. The concept of Dynamic Semantic Bridging (DSB) introduces a highly novel approach designed to address this limitation through a recalibration mechanism that enhances contextual alignment within large language models (LLMs). By dynamically adapting to semantic shifts within evolving dialogues, DSB enables LLMs to retain thematic continuity, thereby advancing their ability to respond consistently to complex, multi-turn exchanges. The architectural design of DSB integrates a layered, dual-channel approach to contextual embedding, supporting selective prioritization of both primary and secondary context components within each interaction. Experiments reveal that DSB markedly improves coherence scores and contextual accuracy across varied datasets, with a reduction in semantic drift over long-form conversations, ultimately enhancing the interpretative precision of LLMs. Findings from this study highlight the transformative implications of DSB in applications where context-sensitive responses are essential, positioning DSB as a foundational advancement for improving the adaptability and coherence of LLMs in real-world deployments.

In recent years, increasing model complexity and improvements in self-attention mechanisms have enabled language models to perform remarkably well on tasks involving human language understanding and generation. However, limitations in preserving context over long sequences continue to present challenges, as models often struggle to retain coherence across extended discourse. The introduction of the Trans-Contextual Embedding (TCE) Mechanism provides a novel approach to addressing these challenges through a context-aware embedding layer integrated into transformer architectures, uniquely designed to maintain semantic depth and logical continuity. Through incorporating TCE into the initial embedding layer, the model achieves improved contextual coherence by dynamically weighting contextual relevance, leading to more accurate representation of complex, interdependent text elements. A series of experiments evaluated the TCE Mechanism on various opensource models, with results indicating a marked improvement in context continuity, semantic density, and reduced error rates, suggesting the applicability of TCE in a range of complex language tasks. Furthermore, the model achieved these improvements with minimal increase in computational overhead, presenting TCE as a scalable option for enhancing LLM capabilities in real-world applications. These findings lay foundational insights into context preservation mechanisms, positioning TCE as a significant advancement for the development of sophisticated and contextually robust language models.

The increasing life expectancy is contributing to a rapidly aging global population, which leads to higher risk of injuries and reduced physical activity. Biosensor applications provide a promising direction for promoting healthy aging by enabling continuous health monitoring and early detection of potential issues. However, current research on biosensor applications often focusing on specific sensor modalities without fully exploring the integration of advanced large language models (LLMs). To fill the gap, we present a comprehensive survey summarizing the current state of LLMs achievements for biosensor application, providing valuable insights for researchers in the field. We begin by providing common challenges in biosensor modalities and the current deep learning techniques. Subsequently, we examine current LLMs systems employed in biosensor applications. Finally, we identify some key challenges and propose potential research directions to advance the application of LLMs systems in biosensor area.

Cybersecurity threats have escalated rapidly in recent years, with ransomware posing one of the most critical challenges to digital infrastructures globally. Traditional detection mechanisms, while effective against known threats, often lack the adaptability needed to address the fast-evolving tactics employed by ransomware attackers. The RansomGuard framework introduces a transformative, multi-layered approach to ransomware detection, integrating Dynamic Encryption Pattern Analysis (DEPA), Real-Time Behavior Profiling (RBP), and Heuristic Risk Scoring (HRS) to achieve unprecedented levels of accuracy and reliability. By employing adaptive analytical techniques, RansomGuard effectively distinguishes between benign and malicious activities, minimizing false positives and optimizing detection speed. Extensive evaluation across diverse ransomware families demonstrates RansomGuard's ability to achieve high detection rates while maintaining computational efficiency, ensuring its suitability for real-time deployment in dynamic and resourceconstrained environments. This study not only showcases a novel solution to the challenges associated with ransomware detection but also sets a new standard for cybersecurity frameworks aimed at proactive threat mitigation, positioning RansomGuard as a critical advancement in ransomware defense strategies.

The increasing complexity and diversity of natural language inputs have posed significant challenges to the contextual understanding capabilities of contemporary language models. Dynamic Pattern Alignment (DPA) emerges as a novel approach that dynamically aligns detected semantic patterns within input data with the model's internal representations, thereby enhancing semantic transfer and context-aware processing. This study presents a comprehensive examination of DPA's integration into an open-source language model, detailing the algorithmic framework and modifications to the model architecture. An automated testing environment was employed to evaluate performance gains and context consistency, utilizing diverse datasets and standardized preprocessing techniques. The experimental results demonstrate that DPA significantly improves semantic retention across contextually dynamic inputs, reduces computational load, and enhances response times. Comparative analyses with baseline models demonstrate DPA's superiority in semantic transfer and contextual relevance. These findings suggest that DPA offers a promising advancement in the development of context-aware language models, with potential applications extending beyond the current scope.

Real World Assets (RWAs) have emerged as a pivotal concept in the transformation of global financial markets, driven by blockchain technology and the process of tokenization. By digitizing physical assets and traditional financial instruments, tokenization enhances liquidity, accessibility, and efficiency in financial transactions. Escrow mechanisms, particularly those enabled by blockchain-based smart contracts, play a crucial role in ensuring the secure and transparent transfer and management of these tokenized assets. This article examines the connection between RWAs and escrow mechanisms, exploring foundational concepts, types, and advantages of tokenizing RWAs, as well as the functions and innovations of escrow mechanisms in this context. The paper analyzes the synergies between tokenization and escrow services, discusses practical applications and case studies, and addresses the comprehensive challenges and risks involved. Finally, it offers future perspectives on technological advancements, regulatory developments, market growth, and collaborative ecosystem development in the integration of RWAs and escrow mechanisms.

Recently, Nature-Inspired Algorithms (NIAs) have received significant attention in the literature reviews and applications. This algorithmic family mimics nature-based processes to tackle complex optimization problems. Many problems in the industry, science, medicine, and engineering are becoming optimization problem challenges. More than 500 algorithms have been proposed till today to tackle specific problems in the different articles. Many researchers call these algorithms novel; these algorithms will be explaining in this study. New taxonomy and classification would be described. It has been found that nature-based algorithms have some problems and time complexity limits that could lead to a new direction for them in the future. This research would be used to study and understand the time complexity and parameter affection the computation time of recently developed nature-based algorithms for multi-modal problems and applications.

The 3rd Generation Partnership Project (3GPP) specification for the physical layer procedures of the uplink control channels within the fifth generation (5G) New Radio (NR) has defined several formats, flexible configurations, and user/data multiplexing options to allow for quick and efficient uplink control information (UCI) transfer for a variety of different network requirements. Such varied formats, configurations and multiplexing across users in a network inevitably translates to complications in the design and implementation of receivers at the NR base station (the next generation node-B or gNB). The specification details associated with different UCI formats, multiplexing rules with other channels and users are quite complicated, especially for the UCI over PUSCH (physical uplink shared data channel) multiplexing feature. Understanding all the design details of UCI physical layer procedures are critical towards building an efficient gNB uplink control receiver. The 3GPP 5G-NR specifications are in general dense and concise, and the information can often be convoluted or distributed across several documents with key design details or motivations omitted for brevity making the physical layer procedures difficult to understand. In this paper, all the design details associated with UCI channels in 5G-NR specifications are carefully unwrapped. The contributions of the paper are three folds. First, the design details and justifications associated with uplink control channels are presented along with signal generation details. Secondly, receiver design aspects of UCI short formats are discussed, and the practical aspects of the UCI receiver implementation are presented. Lastly, a novel UCI over PUSCH receiver implementation which leverages transmitter code flow is proposed. The work in this paper is of significant value to researchers and system engineers looking to design and build uplink control receiver algorithms as part of 5G NR radio access systems.

The widespread use of social media platforms like Twitter and Facebook has enabled people of all ages to share their thoughts and experiences, leading to an immense accumulation of user-generated content. However, alongside the benefits, these platforms also face the challenge of managing hate speech and offensive content, which can undermine rational discourse and threaten democratic values. As a result, there is a growing need for automated methods to detect and mitigate such content, especially given the complexity of conversations that may require contextual analysis across multiple languages, including code-mixed languages like Hinglish, German-English, and Bangla. We participated in the English task where we have to classify English tweets into two categories namely Hate and Offensive and Non Hate-Offensive. In this work, we experiment with state-of-the-art large language models like GPT-3.5 Turbo via prompting to classify tweets into Hate and Offensive or Non Hate-Offensive. In this study, we evaluate the performance of a classification model using Macro-F1 scores across three distinct runs. The Macro-F1 score, which balances precision and recall across all classes, is used as the primary metric for model evaluation. The scores obtained are 0.756 for run 1, 0.751 for run 2, and 0.754 for run 3, indicating a high level of performance with minimal variance among the runs. The results suggest that the model consistently performs well in terms of precision and recall, with run 1 showing the highest performance. These findings highlight the robustness and reliability of the model across different runs.

Signal transform and new time series representations are crucial for advancing signal processing techniques. This letter introduces the consensus-based signal transform (CBST), a method to represent a time series as a weighted undirected graph, a linear combination of base graphs. Within CBST, each graph's topology is determined by maximizing the collective frequency response, measured by the rate of change in the state variables of all nodes in response to an input signal. The state variables are updated using a linear distributed consensus protocol, which filters different input time series frequency components. The resulting graph topology resonates with specific frequencies. Base graphs are produced for each dominant frequency, and their weighted sum forms the graph representation of the input time series. Mathematical analysis and examples demonstrate the CBST's validity and potential applications, offering a new perspective on signal processing.

Gastrointestinal (GI) tract cancers account for a substantial portion of the global cancer burden, where early diagnosis is critical for improved management and patient outcomes. The complex aetiologies and overlapping symptoms across GI cancers often delay diagnosis, leading to suboptimal treatment strategies. Cancer-related queries are crucial for timely diagnosis, treatment, and patient education, as access to accurate, comprehensive information can significantly influence outcomes. However, the complexity of cancer as a disease, combined with the vast amount of available data, makes it difficult for clinicians and patients to quickly find precise answers. To address these challenges, we leverage large language models (LLMs) such as GPT-3.5 Turbo to generate accurate, contextually relevant responses to cancer-related queries. Pre-trained with medical data, these models provide timely, actionable insights that support informed decision-making in cancer diagnosis and care, ultimately improving patient outcomes. We calculate two metrics: A1 (which represents the fraction of entities present in the model-generated answer compared to the gold standard) and A2 (which represents the linguistic correctness and meaningfulness of the model-generated answer with respect to the gold standard), achieving maximum values of 0.546 and 0.881, respectively.

A document by Maria Elena Valcher. Click on the document to view its contents.

Data scaling is an essential and extensively performed operation in the field of image processing and deep learning. It is used to handle data of varying magnitude and reconstructing tensors in neural networks. While executing such operations in real time, the pre and post processing of data onthe-fly during data transfer reduces memory accesses and delivers ready-to-use data to respective cache, hence playing a vital role in improving the system performance. This paper proposes SCALER, a novel scaling hardware accelerator, aimed at scaling the data in image and NPU Cell [1] formats, on-thefly. It can be configured to scale different types of data-formats, wide range of scaling ratios (both, upscaling and downscaling) and different interpolations namely, Nearest Neighbor, Bilinear Interpolation and Half Pixel Center. This paper also illustrates a scenario where SCALER is integrated inside a DMA which caters to NPU subsystem and supports multiple data transfer paths. SCALER supports on-the-fly processing by overlapping the data fetching and pre-processing time. The current architecture is designed to achieve a maximum throughput of 25.6GBps in real time at 800MHz. Keeping a generic base architecture for multiple data-formats and without any image size restriction, SCALER aims improving performance of DSP/NPU applications and reducing power consumption.

This paper explores enhancements in Adaptive Cruise Control (ACC) using Frequency Modulated Continuous Wave (FMCW) radar to optimize performance in varied environmental clutter conditions, including rain, fog, and insect interference. By implementing Constant False Alarm Rate (CFAR) algorithms, the study reduces clutter impact, enhancing radar accuracy for both range and velocity measurements of multiple targets. Results demonstrate that CFAR integration mitigates errors in velocity and distance estimation, particularly under adverse conditions, supporting ACC reliability over a range of up to 200 meters. This study underscores the effectiveness of advanced clutter rejection in improving safety and functionality in ACC systems for real-world applications.

Myocardial Infarction (MI), commonly referred to as a heart attack, remains a significant challenge in early detection, compounded by the vulnerability of medical data to privacy breaches. This article introduces MI-System, a pioneering framework aimed at facilitating early MI diagnosis through an advanced industrial cyber-physical system (ICPS) coupled with robust privacy-preserving mechanisms. The system is built around a custom-developed Internet of Medical Things (IoMT) device and a state-of-theart security model. MI-System integrates three key layers: 1) the user layer, which gathers photoplethysmography (PPG) signal data via an IoMT device and Smartwatch; 2) the client Layer, where local processing and feature extraction takes place with stringent privacy safeguards; and 3) the cloud layer, which leverages a Federated Learning (FL)based architecture to maintain the integrity of raw data while securing the classification model through differential privacy (DP) and a secure aggregation framework that synchronizes model updates from client devices. To further protect the aggregation process in the FL scheme, an innovative secure, and privacy-focused asynchronous aggregation framework is proposed. In comprehensive realworld trials involving 813 tests across 794 participants, MI-System achieved a remarkably accuracy of high accuracy of 93.51% from the IoMT device, and smartwatches via Android app 94.27%, with minimal latency. This breakthrough enhances MI detection and sets new standards for privacy in smart healthcare, positioning it as a promising candidate for clinical integration worldwide.