We propose a novel approach to active neuromorphic sensing to rapidly focus and artificially generate contrast to improve event-based space imaging. Space imaging is the collection of timely and accurate visual data of objects in the space environment and is essential for space-based operations and infrastructure. Recently, neuromorphic event-based vision sensors have been demonstrated as effective space imaging sensors with their high-speed contrast-driven operation. We demonstrate the performance of variable focus liquid lens driven artificial contrast generation as an active sensing technique. We demonstrate an improvement to the performance of an event-based space imaging system by cycling rapidly through an optical power range to incidentally pass through and detect an optimal focus range at each oscillation. We show that our approach can improve an event-based space imaging system's source detection, sensitivity, noise filtering, and localisation error. Furthermore, we demonstrate a solution to the critical problem of accurately and rapidly focusing the event-based camera for space imaging. By improving the performance of event-based space imaging systems, this sensor's unique capabilities can be further leveraged in critical space imaging applications such as international space traffic management efforts, and other optical domains as a new approach to difficult target detection problems.

Course evaluation is a critical component in higher education pedagogy. It not only serves to identify limitations in existing course designs and provide a basis for curricular innovation, but also to offer quantitative insights for university administrative decision-making. Traditional evaluation methods, primarily comprising student surveys, instructor self-assessments, and expert reviews, often encounter challenges, including inherent subjectivity, feedback delays, inefficiencies, and limitations in addressing innovative teaching approaches. Recent advancements in large language models (LLMs) within artificial intelligence (AI) present promising new avenues for enhancing course evaluation processes. This study explores the application of LLMs in automated course evaluation from multiple perspectives and conducts rigorous experiments across 100 courses at a major university in China. The findings indicate that: (1) LLMs can be an effective tool for course evaluation; (2) their effectiveness is contingent upon appropriate fine-tuning and prompt engineering; and (3) LLM-generated evaluation results demonstrate a notable level of rationality and interpretability.

Predicting the future trajectories of agents in dynamic, multi-agent environments remains a fundamental challenge, especially when models lack interpretability, an essential factor for safety-critical applications like autonomous driving. We propose the Scene-level Trajectory Prediction Transformer (STPT), a novel framework that integrates diffusion-based generative modeling with Kan network mechanisms to capture both spatial and temporal dynamics of agent-environment interactions. STPT leverages a recursive diffusion process that refines trajectory predictions over multiple time steps, explicitly accounting for uncertainty and inter-agent dependencies. Importantly, we introduce a Shapley value-based feature attribution technique tailored for diffusion models, quantifying the global and scenario-specific importance of features such as traffic signals and lane geometry at every stage of the prediction process. Extensive evaluations on benchmark datasets demonstrate that STPT not only surpasses state-of-the-art trajectory prediction methods in accuracy but also sets a new standard in real-time interpretability, making it particularly suited for deployment in safety-critical systems requiring both precision and accountability.

The cascading of power modules can generate multilevel voltage output to enhance power transmission capacity and quality. However, conventional cascaded converters need excessively high numbers of modules for high quality due to the only linear increase of levels with modules. Modules whose voltages following a decreasing sequence, e.g., a binary geometric progression (1, ½, ¼, …), imitate analog-digital conversion and generate very fine output shapes through a linear combination of modules with finer and finer steps. However, the use of modules with decreasing voltages rapidly reduces the energy content per module and typically requires dedicated module designs for every module voltage level. Thus, the large voltage differences thwart the initial goal of a uniform, modular, and readily scalable circuit. Furthermore, keeping this balance with very different voltages and energy contents in the same string becomes challenging, while modules with smaller voltages need to switch by orders of magnitude faster than larger ones. Active or diode-enabled parallel modes that simplified balancing and increased utilization in conventional cascaded circuits appear not helpful across the large voltage differences. This paper proposes a novel asymmetric converter design featuring a very different sequence of module voltages, an optimal low-cost control scheme, and accurate sensorless module-voltage regulation. The circuit does not operate any module below half the highest-voltage module (dc link voltage). Compared to previously suggested asymmetric cascaded circuits, modules will have significantly closer rated voltages, yet their voltages never decay to negligible values at higher voltage levels. The proposed tighter rated voltage range allows for a uniform module design with fully interchangeable modules. The reduced voltage difference between neighboring modules exponentially reduces the total size and dimensions of the inductors required to limit the balancing current. Moreover, we introduce an optional pseudo-parallel mode for efficient module-to-module energy exchange. Simulations using MATLAB/Simulink and a hardware prototype confirm the effectiveness of this approach.

Artificial General Intelligence (AGI) requires an infrastructure, for algebraically expressing composable structures and operations, built on powerful abstractions. In a well-trained system built on these principles, learning to make appropriate algebraic substitutions would be sufficient to make intelligent responses. The power of Category Theory (CT) to dynamically compose appropriate granular units of computations and Homotopy Type Theory (HoTT) to help with semantics and validate the compositions, is necessary for this. This paper describes the roles CT and HoTT could play in providing a mathematical foundation for implementing a framework suggested by the Subjective Emergence of Objective Minds (SEOM) model developed earlier by the author. The paper concludes by observing that insights derived here, regarding Deep Neural Networks (DNN) and other related approaches to artificial intelligence, are necessary to put us on the correct path to AGI.

The unprecedented demand for seamless multimedia services necessitates novel approaches to optimize caching and computing. This paper presents an innovative framework using digital twin (DT) technology to create a dynamic, virtual representation of multimedia service infrastructure, enabling real-time optimization for user-centric applications. By leveraging DT's predictive capabilities and integrating them with advanced caching and computing strategies, the proposed system improves resource allocation, reduces latency, and enhances Quality of Experience (QoE) for users. Our simulation results demonstrate significant performance improvements over traditional approaches, establishing the potential of DT-based systems in next-generation multimedia services.

A pure weight-based test case generator for context-free grammars is introduced, where weights are set for each rule and used as unique driver to identify which one to apply during the derivation process; we demonstrate why static flat weights generally cannot work whereas, introducing a simple penalty mechanism, a dynamic weight-based approach is always able to produce random but finite sentences; then, looking at the source grammar from an original perspective, we proceed towards the definition of constraints through which, while still guaranteeing the convergence of the derivation, static but balanced weights can be identified: balanced weights own the interesting capability to drive the generation of an inexhaustible number of extremely random, structurally complex but finite sentences by an automatic test case generator having a dramatically simple derivation logic. Thereafter, we illustrate how to design a weight-based system which, by exploiting the characteristics of balanced weights, can be easily configured to produce sentences that address any specific coverage metric, including those not having a definite generative strategy yet. A complete example of the application of the balanced concept and the weight-based system is then included and experimental results are eventually shown.

In this paper, we discuss the manufacture and testing of a modular snake inspired robot, designed with the specific objective of minimising actuation requirements to enable serpentine movement, whilst still permitting dorso-ventral motion. To achieve this, we use ball gears to increase the range of motion at joints that are connected to the robotic snake body by linkages. While we use different motors to enable both dorso-ventral and lateral kinematics, the research presented here focusses on the lateral (serpentine) kinematics. The serpentine kinetics of the robotic snake are mapped for both linear and non-linear trajectories. We find that despite our robot's use of simple actuation mechanisms, serpentine movements leading to forward motion are possible. The paper instigates new scope for the use of ball gear mechanics to simplify serpentine movement in modular robots, whilst still permitting dorso-ventral kinematics through the same joints.

The increasing complexity of user interactions requires language models that can dynamically adapt to complex contextual cues. Adaptive Contextual Synthesis (ACS) introduces a multi-layered framework that enhances semantic alignment by recalibrating responses in real-time according to the intricacies of input prompts. Through integrating adaptive feedback loops and probabilistic adjustments, ACS refines the coherence and relevance of generated text, addressing limitations in existing models' contextual adaptability. Empirical evaluations demonstrate that ACS significantly improves semantic precision and user satisfaction, showing its potential to advance the development of more contextually aware language models.

The fifth-generation new radio coding techniques, such as low-density parity-check (LDPC) codes, have made significant progress. However, their limitations in the low error floor region prevent them from meeting the stringent bit error rate (BER) targets required for sixth-generation (6G) communications. 6G aims to support services with BER as low as 10 −9 , providing the reliability needed for mission-critical applications. his is particularly crucial for ultra-reliable lowlatency communication. In this paper, we present a two-stage decoding method that combines the strengths of layered LDPC decoding and federated transfer learning (FTL). The layered LDPC decoding stage effectively handles the challenging waterfall region, reducing errors during the initial decoding process. In addition, the FTL model adapts to mitigate the error floor and accelerate its decline. This combination achieves lower error rates and faster performance improvements, reducing the need for retransmissions and enhancing overall system efficiency.

Hidden Markov Models (HMMs) are fundamental tools for modeling sequential data, yet traditional methods for evaluation and estimation often struggle with computational inefficiency, especially when applied to large datasets. In such cases, the evaluation of sequence likelihoods becomes imprecise, impairing the performance of the Baum-Welch algorithm, which relies on these likelihood calculations to propose transition and emission matrices. In this work, we present two innovative techniques aimed at improving computational efficiency in these processes. For model evaluation, we introduce a non-parametric, sample-based method that can be used to compare likelihoods using small, randomly sampled segments of data, thereby reducing computational load while preserving statistical integrity. For parameter estimation, we leverage a novel mathematical relationship between transition and emission matrices and observed transitions, which constrains the search space and eliminates the need for iterative likelihood computations. Results from Monte Carlo simulations demonstrate that our methods substantially enhance computational performance without compromising accuracy.

Preprocessing methods are important in enhancing prediction performance for time-series administrative data. This study underscores the importance of preprocessing methods by comparing two data representation techniques, that can be used with sliding window techniques for time-series administrative healthcare data, for use with gated recurrent unit (GRU) networks. The first method uses a sequence event representation and the second employs a sequence matrix representation. The evaluation was conducted through a retrospective administrative healthcare data case study to predict multiple outcomes. The target outcomes were the first instances of healthcare encounters indicating homelessness or police interaction that appeared in the healthcare data. Results reveal that the GRU combined with sequence matrix representation and sliding window outperformed the sequence of events with the sliding window by over 20% in the area under the curve (AUC) and sensitivity for both outcomes. Given the data used in this analysis, sequence matrix representation was superior to sequence event representation while using GRU models. The results remained consistent across the evaluation in real-world clinical frameworks using two trigger methods for prediction time, such as the sliding window and clinical demand window structures.

Understanding speech in noisy environments remains a critical challenge for hearing-loss intervention development. Advancement in methods for enhancing speech recognition necessitate extensive datasets for training and testing algorithms. The majority of speech corpora focus on individual utterances, dyadic interactions and scripted recordings (e.g. of phonetically balanced sentences), despite the fact that much of our social communication occurs in dynamic, small group interactions. This paper presents a systematic review of existing speech corpora that encompass both audio and visual recordings of small group conversations. In doing so, we examine the currently available data for testing and evaluating computational audio-visual speech enhancement models. The available datasets for testing speech enhancement techniques are varied and often specific to set use cases. This results in restrictions in technology development due to limitations imposed by the available training and testing databases. There is a need to develop a corpus of audio-visual multi-talker speech that can be used to train audio-visual speech enhancement technology and further cognitive hearing-related research. Existing audio-visual corpora are typically confined to the specific paradigms for which they were collected. Studies utilising speech with various types and levels of background noise generally achieve this by combining datasets containing utterances or dialogue with databases of background noise. Existing 2 available datasets do not incorporate free-flowing speech between multiple talkers whilst also accounting for differing listening environments and hearing abilities. No database exists to computationally explore the needs and preferences of hearing aid users in typical situations such as conversations in social environments or while navigating busy events. We propose the generation of a new dataset containing audio and visual information from multiple talkers interacting spontaneously in a variety of sound environments. Such a corpus would provide audiovisual data of free-flowing conversations to evaluate and fine-tune technological developments in realistic scenarios. Such evaluation data is necessary to develop speech enhancement models that will be able to cope with the complex demands of hearing in the real world.

This research explores the application of data analytics, specifically Microsoft Power BI, to optimize processes within the chemical and manufacturing industries. By analyzing large volumes of production data from a PVC (polyvinyl chloride) manufacturing plant, we aimed to identify trends, anomalies, and opportunities for improvement.The study involved collecting, cleaning, and transforming production data, including process temperature, flow rate, torque, tool wear, energy consumption, and failure types. This data was then loaded into Power BI, where it was analyzed and visualized to gain insights into the manufacturing process.Through data-driven analysis, we were able to identify critical relationships between process variables and product quality. For instance, we observed that variations in voltage and temperature can significantly impact product quality and energy consumption. By monitoring these variables and making timely adjustments, it is possible to optimize production processes, reduce energy costs, and minimize product defects.The findings of this research demonstrate the potential of data analytics to revolutionize industrial processes. By leveraging the power of Power BI, organizations can harness the value of their data to achieve significant improvements in efficiency, productivity, and overall performance.

Recent years have seen transformative progress in machine comprehension and generation of human language, but maintaining thematic coherence and contextual continuity over extended interactions remains a significant hurdle. This paper introduces a novel framework for response generation, the Contextual Relevance Transfer (CRT) enabled by Continuity-Based Response Generation (CBRG), designed to address these challenges by retaining relevance and coherence across multiturn exchanges. CRT and CBRG work in tandem to embed context-specific relevance patterns into large language model architectures, thereby supporting more fluid and thematically aligned interactions. By implementing CRT within an opensource LLM, this research evaluates the capacity for CBRG to facilitate continuity without sacrificing computational efficiency, employing context-sensitive filters, adaptive protocols, and recursive relevance loops. Empirical results illustrate notable advancements in multi-turn coherence, sentiment alignment, and topic transition smoothness, showing CBRG's effectiveness in minimizing response degeneration and supporting a more cohesive user experience. Experimental benchmarks confirm that CBRG not only achieves high continuity scores but also demonstrates reduced response latency, making it viable for realtime conversational applications. The insights offered here reveal the potential for contextually aware frameworks like CBRG to redefine interaction quality in intelligent language-based systems, presenting new possibilities for applications requiring sustained engagement and thematic accuracy.

Conventional attention mechanisms, particularly those applied in Transformer architectures, have achieved remarkable success across various domains, including natural language processing, computer vision, and multimodal data integration. However, these methods often focus primarily on intra-cluster relationships, limiting their capacity to effectively capture inter-cluster dependencies that are essential in data with complex, heterogeneous structures. To address this gap, we propose a novel approach utilizing energy-based attention mechanisms to enhance inter-cluster interactions. Our study introduces and evaluates several energy well configurations, including Gaussian, Lorentzian, and softmax exponential models, which are tailored to adjust attentional focus dynamically across clusters. This work demonstrates that energy-based inter-cluster attention mechanisms not only improve interpretability but also outperform traditional attention in both accuracy and computational efficiency. Experimental results on text and image datasets confirm the efficacy of our approach, making it a promising alternative to standard attention mechanisms in neural networks.

The complexity and variation inherent in the tasks processed through language models increasingly demand that such systems not only retain semantic coherence but also adapt responsively to diverse contextual shifts across prompts. In response to this challenge, Neural Modulation for Dynamic Semantic Convergence (NMDSC) introduces an innovative neural architecture enhancement designed to enable on-the-fly adjustments to the language model's interpretative pathways. NMDSC accomplishes this through embedding modulation gates at strategic points within the model's intermediate layers, which recalibrate neural pathways dynamically, ensuring responses remain aligned with the semantic demands of changing prompts. Such modulation allows the model to maintain interpretative continuity and thematic relevance, particularly when handling complex or contextually complex inputs. Experimental implementation of NMDSC within an open-source language model showcased substantial advancements in response adaptability and coherence, with quantifiable improvements observed across various performance metrics and qualitative dimensions. Detailed assessments revealed that the NMDSC-enabled model exhibited enhanced semantic alignment and reduced error rates when responding to prompts with complex thematic requirements. The findings emphasize NMDSC's capacity to improve language model functionality, offering a scalable framework that enriches context-sensitive language generation, ultimately fostering more refined, consistent, and reliable interpretative outcomes across varied application scenarios. This approach to modular neural modulation thus positions NMDSC as a forward-looking solution to the adaptive challenges faced in current-generation language modeling tasks.

In practice, many mechanical systems are underactuated, such as naval vessels, cranes, and helicopters, to reduce energy consumption and enhance flexibility. However, compounded by strong nonlinearity arising from state coupling, the underactuated nature and high-order unavailable states pose great challenges to motion control (particularly for unactuated states lacking independent actuators or kinematic constraints). In this paper, an adaptive controller based on fully-actuated system methods is proposed, together with a general and extensible analysis method. Firstly, a group of high-order auxiliary variables, consisting of actuated/unactuated states, their derivatives, and proportional-differential terms, are designed to rearrange the nonlinear underactuated system as a high-order linear fullyactuated system without any linearization operations. The asymptotic convergence of auxiliary variables theoretically eliminates the steady-state errors of actuated/unactuated states together. For high-order unmeasurable variables, they are recovered by the constructed neural network observer to estimate high-order dynamics, which avoids discontinuous robust terms and improves the accuracy of compensation/positioning. Motivated by the inherent features and advantages of fully-actuated systems, this paper proposes the first fully-actuated system-based continuous adaptive controller for a class of underactuated robots. Moreover, it is convenient to extend the proposed controller to handle more practical problems, such as state delay, without the need to re-conduct Lyapunov-based analysis. In addition to complete theoretical frames, this paper also provides several experimental validation.Remark:  This paper was first submitted to an IEEE Transactions journal on Mar. 28, 2024. It has been revised and submitted on Oct. 02, 2024.  Currently, this paper is under review.