We find that traditional GNNs are not well suited to learning on utility-scale power distribution graphs due to typical attributes of power distribution systems such as: their large size and low density, their heterophilic nature, and the long paths between nodes along which information must travel. Herein we outline a novel inductive GNN architecture which has been optimized for learning on power distribution graphs and which can pass information efficiently across the graph. We also demonstrate the performance of this algorithm by applying it to ComEd’s data as part of a practical use-case, and we benchmark our algorithm’s performance on this data versus other well-known GNN architectures. Submitted to IEEE PES General Meeting 2024

Due to the capability to perform participation factor analysis and oscillation origin location, the state-space model (SSM)-based eigenvalue method has been widely used for stability assessment of inverter-penetrated power systems. However, possible internal confidentiality of inverters impedes the derivation of their SSMs. In addition, conventional derivation procedure of system SSM can be tedious when complicated transmission network topology and various transmission cables are involved, which may result in a high-order system SSM. To this end, this article presents a black box-based incremental reduced-order modeling framework. The reduced-order SSMs of the inverters and transmission cables are extracted from their dq-domain admittance frequency responses and abc-domain impedance frequency responses, respectively, by the matrix fitting algorithm. Then, the SSM operators proposed in this article recursively assemble the fitted components’ SSMs in the similar manner as the impedance model operator-based recursive components’ impedance aggregation, while preserving the dynamics of individual components. Simulation results show that the presented state-space modeling framework can properly identify the state-space models of black-box devices at component modeling stage, simplify assembling procedure at subsystems/components integration stage, and release computational burden at system participation factor analysis stage.

The focus of our study is to predict RNA-small molecule binding sites, with the overarching goal of exploring potential applications in the field of RNA drug targets. In response to this challenge, we present the MultiModRLBP method, a novel approach that integrates multi-modal features through the application of deep learning algorithms.

Image analysis and compression We usually use Fourier transform, DCT transform and wavelet transform. The image transformation method based on weighted probability model is the new method described in this paper. We reasoned iterative formula of binary sequence-weighted probability model transformation versus inverse transformation, The encoding method of binary sequence transformation and inverse transformation are constructed. In the image transformation and inverse transformation experiment, yielded large number of duplicate values in the transformed data, which is suitable for the construction of a new image compression method. The inverse transform can reconstruct the image effectively, and has the obvious image edge annotation effect. This method can be used in image compression, image edge detection, image sharpening and intelligent recognition.

Non-fungible Tokens (NFTs) are emblematic of unique digital assets that offer a distinct proprietorship and value creation, whilst Self-sovereign Identity (SSI) imbues individuals with the capacity to govern their personal data and identifying information. The conceptualization of an NFT-based Self-sovereign Identity is still under contemplation within the scholarly community. Despite initial assertions by researchers concerning the potential advantages of integrating NFTs with Self-sovereign identity, the manifestation of systems based on this amalgamation has yet to materialize in pragmatic circumstances. This research paper explores the prospective benefits and impediments associated with the synthesis of Non-Fungible Tokens (NFTs) and Self-Sovereign Identity (SSI). It further unveils a generalized operation flow of an NFT-based SSI, the various iterations of NFTs that can be deployed in the realm of SSI, and an array of refined and expanded SSI principles specific to NFT-based SSI. The paper delves into the technical, legal, standardization, and governance challenges that might ensue from this amalgamation. This research paper accentuates the significance of tackling these obstacles to harness their potential for industry transformation and individual empowerment. Moreover, the paper examines prospective research and developmental trajectories, including technological progressions, potential reverberations on industries and societal structures, as well as the emergence of new business models and revenue streams. It also reiterates the importance of addressing these challenges to actualize the full potential of these emerging technologies. This research endeavor is a pioneering exploration in the realm of NFT-based Self-sovereign Identity.

This article presents a STEM learning platform focusing on renewable energy generation, energy storage, and simultaneous transmission of energy and data. These enabling technologies are classified already by teenagers as authentic, multidisciplinary, sustainable and future-oriented, which helps to stimulate their interest. Linking electric energy generation/storage/consumption and information transfer is done through the innovative concept of talkative power conversion. Students are not only provided with meaningful background information on the topics under investigation, but they also learn how to implement these concepts on a mixed hardware/software platform, which increases their motivation and understanding of STEM topics. The learning platform elaborated in this article is suitable for pupils at high school as well as undergraduate and graduate students in electrical engineering and related fields, since the level of difficulty is adjustable. Experiments are exemplified at a level suitable for undergraduate students in electrical engineering and information technologies after two years of study.

This study explores the application of the VGG16 convolutional neural network for accurate fire detection, par- ticularly in forest fire scenarios, using images and videos. The urgency of timely fire detection, given the significant threats to life and property, underscores the importance of this research. Lever- aging transfer learning, VGG16 is fine-tuned with a comprehen- sive dataset, including forest fire data. The model demonstrates outstanding performance, with high accuracy in recognizing fire- related patterns, especially within forest landscapes. Key aspects of this research involve pre-trained weights, deep architecture, and data augmentation to enhance generalization. The proposed methodology not only provides an effective fire detection solution but also holds promise for applications in forest fire monitoring, where drones can offer critical imagery and data for improved situational awareness and response coordination.

This paper considers RIS enhanced D2D communications underlaying unmanned aerial vehicle (UAV) networks with non-orthogonal multiple access (NOMA). The objective is to maximize the sum rate of NOMA D2D communications by optimizing the power budget of D2D transmitter, NOMA power allocation coefficients of D2D receivers and passive beamforming of RIS while guaranteeing the quality of services of UAV user. Due to non-convexity, the optimization problem is intractable and challenging to handle. Therefore, it is solved in two parts using alternating optimization. Simulation results unviel the performance of the proposed RIS enhanced D2D communications scheme. Results demonstrate that the proposed scheme achieves 15\% and 27\% higher sum rates compared to the fixed power D2D and orthogonal D2D schemes.

As autonomous vehicles (AVs) advance, the integration of Large (Vision) Language Models (L(V)LMs) has emerged as a promising approach to enhance AV capabilities in perception, planning, decision-making, and data generation. However, the practical challenges of incorporating L(V)LMs into AV systems, including computational efficiency, real-time processing, and ethical considerations, remain underexplored. This survey aims to provide a comprehensive review of the current research on L(V)LM applications in AVs, focusing on four key areas: modular integration, end-to-end integration, data generation, and evaluation platforms. We systematically analyse 62 recent papers published before June 2024, detailing methodologies, models, datasets, and benchmarks used, while identifying common tradeoffs and limitations. Our findings highlight the potential of L(V)LMs to improve AV system performance but emphasise the need for further research in real-world integration, regulatory challenges, and V2X communication. This survey offers valuable insights and guidance for researchers and practitioners aiming to optimise L(V)LMs in autonomous vehicles.

Type 2 diabetes (T2D) is a common metabolic disorder that poses threat to human health. Blood glucose (BG) concentrations in T2D subjects can be influenced by various factors, such as stress, physical activity, and meal consumption. Obtaining personalized mathematical models for people with T2D can be beneficial for developing effective T2D management strategies, such as insulin dosing algorithms. However, fitting these models for T2D subjects can be challenging due to the limited data typically available during treatment, consisting of only Continuous Glucose Monitoring (CGM) readings and injected insulin amounts. To address this issue, we propose a stochastic jump diffusion model that incorporates the uncertainties from meal consumption behavior together with other disturbances. Additionally, we provide an inference strategy that enables us to estimate both physiological (e.g., insulin sensitivity) and behavioral (e.g., average number of meals per day) parameters using only CGM data and injected insulin amounts. We validate the proposed stochastic model and inference strategy with synthetic and clinical data, assessing their ability to estimate various parameters of the model and fit CGM data. The results demonstrate that our proposed method, along with the model, manages to estimates parameters with different interquartile range (IQR) values. Moreover, the model, in combination with the method, provide a good fit for CGM data, and demonstrates the ability to obtain estimates of unannounced meal times.

Purpose: This study delves deep into systematically integrating AI, Blockchain, and IoT within manufacturing, guided by Lean Six Sigma (LSS) philosophy, aiming to promote higher precision, human safety, sustainability, reduced errors, and wastage while maintaining minimal human involvement. Design/methodology/approach: The study rigorously studies cases of the manufacturing industry integrating these concepts into real industrial or experimental setups and discusses their potential implications. It explores the step-by-step integration, control, and regulation of intricate manufacturing aspects. Findings: Artificial Intelligence is beneficial for real-time regulation and prompt corrective measures during manufacturing operations. The Internet of Things provides real-time feedback, ensuring synchronization between teams and departments to maintain flaw detection and correction. Blockchain offers security and transparency in task performance, supply chain management, and payments, resulting in a seamless and efficient manufacturing experience. Originality: This study is not a mere overview or surface-level juxtaposition of Industry 5.0 concepts. It offers a comprehensive analysis of the holistic integration of advanced technologies within manufacturing, linking developments to sustainable manufacturing. It provides new insights and perspectives not discussed in current literature found in databases like Scopus and Web of Science. Research limitations/implications: The study encourages ongoing research and development to meet modern economic needs and environmental challenges. It emphasizes that the integration is not the endpoint, but continuous improvement (kaizen) should prevail. Practical implications: This study serves as an authoritative source of information for the scientific community to further advancements in the field, guiding them to develop evidence-based opinions. Social implications: The findings support the vision of sustainable digital manufacturing, promoting economic efficiency and environmental sustainability, crucial for the current and future industrial landscape.

In the rapidly advancing landscape of System-on-Chips (SoCs), achieving appropriate levels of functional safety compliance has become a fundamental concern. With SoCs serving critical roles in applications such as automotive, industrial, and consumer electronics, a unified approach to navigate different functional safety standards can help save time and speed up time to market. By reusing the fundamental principles of ISO 26262 and IEC 61508, this article presents a unified framework tailored specifically for advanced multi-domain SoCs. This framework seeks to streamline safety compliance efforts while enhancing overall system safety resilience for various applications.

A document by Van-Vi Vo . Click on the document to view its contents.

With a global energy system in rapid transformation from fossil fuels, Green Hydrogen is one of few solutions to hard-to-abate emissions within industry. While most hydrogen projects are in a planning phase, the Ovako hydrogen facility in Hofors, with a scrap-based Electric Arc Furnace process, was inaugurated in September 2023. This project studies wider system benefits of the electrolyser such as power grid support, oxygen byproduct, providing hydrogen to external actors, and district heating. This is analysed both with current capacity and in regards to possible future development. Replacing fossil fuel with hydrogen produced by an atmospheric alkaline electrolyser is an indirect electrification with the potential to decrease Green House Gas emissions. Industry-wide electrification increases the demand for electricity, affecting all existing users. Therefore, system benefits and sector couplings such as enabling ancillary services to the grid, producing low-marginal cost hydrogen for hydrogen-powered trucks, and using waste heat for district heating, are important to ascertain system-wide improvements.

In the dynamic world of financial markets, investors and traders alike seek tools and methodologies that can provide insights into potential price movements and help them make informed decisions. Technical analysis stands at the forefront of such methodologies, offering a systematic approach to interpreting historical price data and identifying trends and patterns that may guide future market behavior.

Electronic parts in space inevitably subject to radiation effects leading to the degradation of electronic performance or even failure, so radiation performance of an electronic part must be assessed to ensure it work normally in space. At present, to assess the ion radiation effects on a semiconductor device is directly through irradiation tests. However, due to the scarcity of cyclotron resources, the test time is difficult to appoint and the cost is huge. Due to schedule and budget constraints, it is also impossible to conduct irradiation tests on all semiconductor devices in actual space missions. Therefore, assessment of the radiation effects on semiconductor devices through irradiation tests has caused difficulties. Radiation susceptibility of semiconductor device is determined by the design topology and fabrication technology, and the irradiation test data shows that similar semiconductor devices has similar radiation susceptibility, so a method to assess the radiation effects on semiconductor devices base on similarity theory is proposed at first time in this paper. This assessing method does not require irradiation testing and does not require separate sampling. It has the virtues of easy implementation, quick response and low cost, providing an efficient method of assessing radiation effects on semiconductor devices.

This paper considers resource allocation for a high-throughput satellite communications system operating in geostationary earth orbit. The main contributions of this paper include the design, development, and testing of three beamforming algorithms, each using a different paradigm for candidate beam collection and evaluation, but the same integer programming model for optimizing the selection of the beams to be used from a set of candidate beams.

This paper discusses 2d malware image  detection and classifying with AI based Model using  Machine Learning. It aims to use previous data and learn  and train automatically to identify and classify malware  families. Results are based on several parameters.