Autonomous Vehicle decisions rely on multimodal prediction models that account for multiple route options and the inherent uncertainty in human behavior. However, models can suffer from mode collapse, where only the most likely mode is predicted, posing significant safety risks. While existing methods employ various strategies to generate diverse predictions, they often overlook the diversity in interaction modes among agents. Additionally, traditional metrics for evaluating prediction models are dataset-dependent and do not evaluate inter-agent interactions quantitatively. To our knowledge, none of the existing metrics explicitly evaluates mode collapse. In this paper, we propose a novel evaluation framework that assesses mode collapse in joint trajectory predictions, focusing on safetycritical interactions. We introduce metrics for mode collapse, mode correctness, and coverage, emphasizing the sequential dimension of predictions. By testing four multi-agent trajectory prediction models, we demonstrate that mode collapse indeed happens. When looking at the sequential dimension, although prediction accuracy improves closer to interaction events, there are still cases where the models are unable to predict the correct interaction mode even just before the interaction mode becomes inevitable. We hope that our framework can help researchers gain new insights and advance the development of more consistent and accurate prediction models, thus enhancing the safety of autonomous driving systems.

In this paper, we present analytic solutions for explicit Model Predictive Control (EMPC) applied to the current control of Surface-mounted Permanent Magnet Synchronous Motor (SPMSM) drives. A key challenge in applying MPC to motor current control is solving the constrained optimization problem in real time. To address this, we develop an analytic procedure based on planar geometric projections to solve the problem efficiently. The correctness of our method is validated through comparisons with standard numerical solvers. Experimental results show that our algorithm can be implemented on low-cost hardware with rapid execution, supporting long prediction and control horizons while delivering fast dynamic response. These advantages make it suitable for both high-speed servo systems and budget-sensitive applications.

Optical flow is crucial for robotic visual perception, yet current methods primarily operate in a 2D format, capturing movement velocities only in horizontal and vertical dimensions. This limitation results in incomplete motion cues, such as missing regions of interest or detailed motion analysis of different regions, leading to delays in processing high-volume visual data in real-world settings. Here, we report a 3D neuromorphic optical flow method that leverages the time-domain processing capability of memristors to embed external motion features directly into hardware, thereby completing motion cues and dramatically accelerating the computation of movement velocities and subsequent task-specific algorithms. In our demonstration, this approach reduces visual data processing time by an average of 0.3 seconds while maintaining or improving the accuracy of motion prediction, object tracking, and object segmentation. Interframe visual processing is achieved for the first time in UAV scenarios. Furthermore, the neuromorphic optical flow algorithm's flexibility allows seamless integration with existing algorithms, ensuring broad applicability. These advancements open unprecedented avenues for robotic perception, without the trade-off between accuracy and efficiency.

Spam SMS often appears similar to legitimate (ham) messages but contains potential threats or malicious links designed to hack personal information such as bank account details, passport details, etc. Many mobile users have been affected because they unknowingly access spam messages and provide information through the link given, and they have lost a huge amount of money. Many industries are working on this to prevent such spam messages from entering the user's inbox using advanced machine or deep learning techniques. Any Artificial Intelligence technique requires enough data to train the model to perform better during real-time testing. Recently, there have been enough benchmark spam SMS datasets available for English; however, there are fewer for Indian languages. This paper provides an overview of an SMSDHL dataset comprising Dravidian languages-Tamil, Telugu, Kannada, and Malayalam with Hindi and English. The dataset can be utilized for various applications in Information Extraction, Information Retrieval, and Natural Language Processing (NLP).

To support the development of wearable medical devices for remote monitoring and treatment of cardiovascular diseases, we tackle the data scarcity problem that hinders the application of machine learning methods. We propose a self-supervised approach applied to cardiological signals, which benefits from existing datasets despite differences between them and inconsistencies within them. We develop a specific implementation: a diffusion autoencoder with a semantic encoder based on linear recurrent units, trained on ECG signals (various leads mixed together) without any annotations. The semantic encoder is evaluated as a feature extractor by measuring classification metrics of a logistic regression on a dataset not included in the self-supervised training. We obtain promising results and propose future directions.

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.

In today's Agile and DevOps-driven software development landscape, the need for rapid and accurate bug reporting is more critical than ever. This paper presents a nextgeneration automation tool powered by large language models and machine learning, aimed at innovating the bug reporting process. The tool automates every phase of bug reporting, from failure detection to severity assessment, duplicate detection, and report generation. By addressing the limitations of manual bug reporting such as inconsistency, scalability challenges, and time inefficiencies, the proposed solution enhances the software testing workflow. Initial findings demonstrate significant time savings, reduced manual errors, and improved collaboration between testers and developers. This work establishes a foundation for fully automated bug reporting, poised to accelerate software development cycles while maintaining high-quality standards.

In this paper, an adaptive Super Twisting Algorithm (STA) based Second Order Sliding Mode Controller (SOSMC) design using a novel Gated Recurrent Unit (GRU) blended Redial Basis Function Neural Network (RBFNN) structure is proposed. In this GRU blended RBFNN structure, the GRU is placed in 1st hidden layer and the RBF is placed in the 2nd hidden layer to enhance the estimation of unknown function f (x) of the nonlinear dynamical system. The estimated function is used to design an adaptive STA of the SOSMC with adaptive laws for updating STA gains. The closed loop asymptotic stability and finite time convergence of the system is also ensured using the Lyapunov theory. Finally, the controller is implemented on two link Robotic Arm with serial flexible joints to show the performance and efficacy. The experimental results exhibit an excellent tracking performance and robustness of the controller.

Hardware design for radio frequency devices often demands the use of full-wave electromagnetic (EM) field-solvers to extract scattering parameters (S-parameters) for systems that contain discontinuities throughout their printed circuit boards (PCBs) and substrate packages. Using EM field-solvers not only requires extensive EM knowledge during the setup phase, but also demands considerable computational resources. Previously, machine learning (ML) and neural network (NN) models have been used to solve EM fields; however, they tend to use design parameters as input rather than the structure's geometry. Parametric analysis is beneficial when the solution space is well bounded, but it is more desirable to develop the capability of feeding generic and arbitrary geometry into a machine learning model for rapid S-parameter extraction. This work presents an algorithm for converting a subsection of hardware geometry designed with an electronic design automation (EDA) tool into a dataset suitable for training and validating machine learning models including fully connected NNs and convolutional NNs (CNNs).

Contributions: This paper presents an innovative course curriculum designed to bridge the gap between electric circuit knowledge and control engineering principles. The curriculum emphasizes hands-on learning through op-amp circuit design projects, fostering a deeper understanding of both theoretical concepts and practical applications. Background: Traditional educational approaches often treat electric circuits and control systems as separate disciplines, hindering students' ability to grasp the interconnectedness of these fields. This disconnect can impede the holistic understanding required for effective circuit design and feedback control system development. Intended Outcomes: The proposed course aims to equip students with a comprehensive understanding of op-amp circuit design principles, proficiency in analyzing and optimizing frequency responses and bandwidth using techniques like zero-pole placement, the ability to translate theoretical knowledge into practical applications in industrial settings, and a stronger appreciation for the synergistic relationship between electric circuits and control engineering. Application Design:The course features a series of three illustrative examples that progressively introduce students to selecting resistor and capacitor values to achieve desired DC gains and frequency responses, analyzing feedback loops using open-loop transfer functions and zero-pole placement techniques for bandwidth optimization, and designing controller architectures for industrial applications by applying the principles learned in previous exercises. Findings: Through student engagement and project implementation, the course demonstrates a significant improvement in students' understanding of both circuit design and control engineering concepts. The hands-on approach fosters deeper comprehension, practical skills, and a more integrated perspective on these interconnected disciplines.

We present an alternative approach to optical tactile sensor design that uses a non-camera-based sensing principle that we term light vector (LiVec) sensing. We propose to present a poster that provides an overarching summary of our work on this design concept to date. Namely, we will review: (i) a proof-of-principle single-element design; (ii) the LiVec Finger design, which consists of an array of sensing elements arranged in a finger pad shape; (iii) work-in-progress toward designs using flexible printed circuit boards to achieve non-planar sensor designs.

A modification is proposed to the conventional magnetic reluctance circuit (MRC) in which a dependent MMF source, which is a function of an output current, is replaced by a passive element, an inductor. This eases the analysis and simulation of the MRC by breaking the closed feedback loop between the output current and the resulting dependent MMF source. The proposed approach is verified by simulations which show an excellent match between the classical and modified MRCs.

The paper considers monostatic ISAC transceivers relying on in-band full-duplex (IBFD) capability to achieve simultaneous sensing and communication. These systems transmit a waveform for both communication and sensing and receive target echoes and incoming communication signals from other nodes. The major challenge is self-interference cancellation (SIC), suppressing interference from the leaked transmitted signal for both sensing and communications and the mutual interference between the echo for sensing and incoming signals for communication. This paper proposes an advanced joint analog and twostage digital SIC structure to address this challenge, enabling simultaneous communication and sensing in IBFD ISAC systems. The analog SIC structure leverages an analog least mean square (ALMS) loop with specific design constraints to preserve the integrity of sensing signals. A sample-and-hold mechanism is employed to avoid ALMS weighting coefficient variation caused by the strong reflected sensing signal and uplink communication signal. The novel two-stage digital SIC first cancels residual self-interference for sensing and then mitigates echo sensing signals for communication. Doppler effects in the echo signals are compensated during the second stage to ensure effective suppression of sensing signals and accurate retrieval of communication signals. Simulation results validate the proposed approach, showcasing its strong communication and sensing performance and robust SIC capabilities.

Ensuring the cyber resiliency of IEC 61850-based Substation Automation Systems (SAS) is critical for reliable grid operations. This work presents a comprehensive analysis of the performance and security of traditional networking and Software-Defined Networking (SDN) for IEC 61850-based SAS. By leveraging SDN's flow control, proactive traffic engineering, and deny-by-default policies, this study highlights its advantages over traditional networking in critical Operational Technology (OT) applications. Three novel factors for cyber resiliency metrics-network performance, protocol-specific attackability, traffic containment, are proposed, culminating in a unified resiliency score. Experimental evaluations using an enhanced real-time Hardware-in-the-Loop (HIL) testbed, includes GOOSE spoofing, DNP3 Denial-of-Service attacks, and network failovers. Results demonstrates SDN's ability to mitigate impact of cyber threats, enhanced network performance, and reduced attack surface. The findings also indicates the significance of adopting SDN at the process bus for scenarios, if full SDN deployment is not feasible. Additionally, this work provides a metric-based approach to evaluate and compare OT network resiliency across various possible configurations.

Reconfigurable Intelligent Surfaces (RIS) represent transformative technologies for next-generation wireless communications, offering advanced control over electromagnetic wave propagation. While RIS have been extensively studied, Stacked Intelligent Metasurfaces (SIM), which extend the RIS concept to multilayered systems, present significant modeling and optimization challenges. This work addresses these challenges by introducing an optimization framework for SIM that, unlike previous approaches, is based on a comprehensive model without relying on specific assumptions, allowing for broader applicability of the results. We first present a model based on multi-port network theory for characterizing a general electromagnetic collaborative object (ECO) and derive a general framework for ECO optimization. We then introduce the SIM as an ECO with a specific architecture, providing insights into SIM optimization for various architectures and discussing the complexity in each case. Finally, we analyze the impact of commonly used assumptions, demonstrating that employing a complete model-one that does not rely on the unilateral hypothesis and accounts for mutual coupling among SIM elements-can yield better performance, using the realization of a 2D DFT as a case study.

The problem of robust quickest change detection (QCD) in non-stationary processes under a multi-stream setting is studied. In classical QCD theory, optimal solutions are developed to detect a sudden change in the distribution of stationary data. Most studies have focused on single-stream data. In non-stationary processes, the data distribution both before and after change varies with time and is not precisely known. The multi-dimension data even complicates such issues. It is shown that if the non-stationary family for each dimension or stream has a least favorable law (LFL) or distribution in a well-defined sense, then the algorithm designed using the LFLs is robust optimal. The notion of LFL defined in this work differs from the classical definitions due to the dependence of the post-change model on the change point. Examples of multi-stream non-stationary processes encountered in public health monitoring and aviation applications are provided. Our robust algorithm is applied to simulated and real data to show its effectiveness.

The long-term drift is well known as one of the most challenging issues regarding gas sensing and applications involving electronic noses, undermining the reliability and accuracy of these systems over time, as the pattern recognition models lose their capability of performing gas discrimination. In this work, we adopt a probabilistic view of the drift problem. This perspective yields a novel univariate scheme for drift compensation, which is grounded on probabilistic modelling. The potential usefulness of the proposed approach is highlighted through experimental results on the gas classification task, which reveal a superior and more stable performance when compared to traditional component correction multivariate methods. Besides its stable performance, the proposed method also presents several desired attributes, such as computational simplicity, continuous adaptability and suitability for online applications. The experiments were conducted using a dataset lasting 7 months, comprising measurements from three different gases at different concentration levels in an array containing 17 polymeric sensors.

In this paper, we present latest advancements in Ambient IoT (A-IoT) research within 3GPP and explore the challenges of introducing Ambient IoT technology into 3GPP system. We also propose key design directions for both current and future 3GPP releases. The diverse use cases, device types, design targets, and topologies of A-IoT poses significant design challenges due to the factors such as energy harvesting, need for low cost, power, and complexity. Additionally, mechanisms differ from existing 3GPP technologies. We introduce feasible high level design directions, including waveform, modulation, multiplexing, duty-cycled monitoring, random access, continuous wave (CW) interference cancellation, and proximity determination.