Real-time Processing Research Articles

The Impact of Intelligence Gathering, Risk Analysis, and Scenario Planning on Defense Policy Formulation

In the evolving landscape of global security, the integration of intelligence gathering, risk analysis, and scenario planning is paramount for effective defense policy formulation. This study aims to underscore the critical role of these elements in contemporary defense strategies. Employing qualitative research methods, particularly secondary data analysis, this research investigates the transformative impact of artificial intelligence (AI) and machine learning (ML) on threat assessments, the benefits and challenges of big data analytics in risk analysis, and the value of interdisciplinary perspectives in scenario planning. The findings reveal that AI and ML significantly enhance the accuracy and reliability of threat assessments by enabling real-time data processing and predictive analytics. However, challenges such as data privacy and algorithmic biases persist. Big data analytics offers substantial benefits in identifying and mitigating emerging threats but requires robust data management frameworks to address issues of data quality and integration. Additionally, scenario planning is highlighted as a strategic tool that enhances defense strategies by anticipating various future scenarios and enabling proactive measures. Furthermore, the integration of interdisciplinary perspectives in scenario planning fosters more robust and adaptable defense policies, ensuring a comprehensive approach to security challenges. In conclusion, the integration of advanced technologies and interdisciplinary methods in intelligence gathering, risk analysis, and scenario planning is crucial for developing resilient and adaptive defense policies.

Development and Evaluation of a New Algorithm for Real-Time Image Processing

When working with real-time images, creating and testing new methods is very important for making computers work faster and more accurately. This study describes a new method that is meant to solve problems in real-time picture processing applications by making them faster and better at what they do. It was created because of the need to deal with picture data that was getting more complicated in many areas, including autonomous systems, medical imaging, monitoring, and multimedia apps. Several new methods are built into the suggested program to help it reach its goals. To begin, it uses advanced parallel processing designs to speed up calculations without lowering their quality. The method cuts down on processing delays by making the best use of resources and job ordering. This makes it ideal for time-sensitive apps that need to make quick decisions based on real-time picture data. The algorithm also uses strong feature extraction techniques that are designed to work well with a wide range of picture traits and noise levels. This improves the algorithm's ability to work in a variety of settings, making sure it always works well in different working situations. Adaptive filtering mechanisms and advanced edge recognition algorithms are two important parts of the algorithm that work together to make it quick and easy to get useful information. A lot of testing was done to see how well the algorithm worked against the best available methods, using normal image processing datasets and real-life situations. A lot of attention was paid to performance measures like processing speed, accuracy in feature recognition, and computer economy. When compared to traditional methods, comparative research showed big gains in processing speed without sacrificing accuracy.

Modelling long-term operational dynamics of grid-connected hydro- photovoltaic hybrid systems

The development of variable renewable energy sources (VRESs), such as wind and solar photovoltaic (PV), has become a strategic choice for ensuring the security of electricity supplies and the decarbonization of power systems. The hybridization of hydropower with VRESs is an important measure for guaranteeing the smooth and cost-effective integration of VRESs into the power system. However, the highly variable weather- and climate-driven spatial and temporal fluctuations in VRES performance have significant potential to affect the optimal trajectory of hydropower operations. Therefore, it is essential to understand how hydropower responds to VRESs over long-term horizons, thereby allowing informed operation decisions to be made for hybrid generation systems (HGSs). In this study, a long- and short-term nested operation model is developed for hydropower operations considering PV integration. Specifically, the long-term model determines the day-by-day hydropower production over many years, and the short-term model simulates the day-ahead generation scheduling and real-time operation processes of the HGS. Performance metrics are established for evaluating the complementary operation in comparison with separate operation of hydropower and PV plants. China's two representative hydro-PV HGSs (Zhongyu and Longyangxia) are selected as case studies. The results indicate that the hybrid generation of hydropower and PV could, on average, increase total electricity generation by 11.33 %, reduce the load loss rate by 9.31 %, and decrease the PV curtailment rate by 36.60 %. However, hydro-PV hybridization may lead to an increase of 9.22 % in the water spillage rate and a decrease of 0.094 kWh/m3 in the water–electricity conversion coefficient. Therefore, hybrid generation of hydropower and PV could further enhance energy yield and supply reliability. Also, the importance of improving hydropower flexibility is highlighted.

Discovering vaccines: the trial tale.

This paper reviews the importance of vaccine trials to public health. Vaccines are developed to build immunity to disease, which have helped to completely eliminate smallpox, and reduced incidence of polio and measles. A variety of breakthroughs made many years ago, such as the smallpox vaccine by Edward Jenner and the discoveries by Louis Pasteur, also set the stage for modern international immunization programs. A few events, such as the licensing of the polio vaccine and the passage of the Vaccination Assistance Act helped to improve the study of vaccines. In particular, vaccine trials may be RCTs, cluster trials, or cohort studies. The sample sizes will depend on the objectives, which would include the primary and secondary endpoints. The population under study and the geographical location also affect the trial design. Preclinical evaluation is usually the starting point of vaccine trials, where the safety and efficacy are researched on animal models or cell cultures. Animal models are selected based on their similarity to the target disease. Safety is checked in Phase I, efficacy in Phase II, and both in Phase III. Phase IV is a post-marketing surveillance of the vaccine's safety in real life. Regulatory bodies play a very vital role in ensuring that vaccines adhere to a very high standard of safety and efficacy, such as the FDA, as required. Ethical considerations, such as informed consent and the rights of participants, are innate and are implemented and enforced through laws, regulations, and ethical committees. Vaccine studies vary from the drug studies as it is focused on preventing illness in healthy patients as opposed to cure of diseases in drug trials. The dramatic development in vaccine research was driven by recent pandemics, with parallel processing and data collection in real time. Clinical trials of the vaccine are a foundation stone of public health in the reduction of sickness, offering immunity to diseases, and continuing the fight against infectious diseases. The present review is aimed at describing vaccine trials and their important aspects.

Crossmodal sensory neurons based on high-performance flexible memristors for human-machine in-sensor computing system

Constructing crossmodal in-sensor processing system based on high-performance flexible devices is of great significance for the development of wearable human-machine interfaces. A bio-inspired crossmodal in-sensor computing system can perform real-time energy-efficient processing of multimodal signals, alleviating data conversion and transmission between different modules in conventional chips. Here, we report a bio-inspired crossmodal spiking sensory neuron (CSSN) based on a flexible VO2 memristor, and demonstrate a crossmodal in-sensor encoding and computing system for wearable human-machine interfaces. We demonstrate excellent performance in the VO2 memristor including endurance (>1012), uniformity (0.72% for cycle-to-cycle variations and 3.73% for device-to-device variations), speed (<30 ns), and flexibility (bendable to a curvature radius of 1 mm). A flexible hardware processing system is implemented based on the CSSN, which can directly perceive and encode pressure and temperature bimodal information into spikes, and then enables the real-time haptic-feedback for human-machine interaction. We successfully construct a crossmodal in-sensor spiking reservoir computing system via the CSSNs, which can achieve dynamic objects identification with a high accuracy of 98.1% and real-time signal feedback. This work provides a feasible approach for constructing flexible bio-inspired crossmodal in-sensor computing systems for wearable human-machine interfaces.

Energy efficiency assessment in advanced driver assistance systems with real-time image processing on custom Xilinx DPUs

Energy efficiency assessment in advanced driver assistance systems with real-time image processing on custom Xilinx DPUs

An edge computing and distributed ledger technology architecture for secure and efficient transportation

Intelligent Transportation Systems (ITS) faces significant challenges in achieving its goal of sustainable and efficient transportation. These challenges include real-time data processing bottlenecks caused by high communication latency and security vulnerabilities related to centralized data storage. We propose a novel architecture that leverages Edge Computing and Distributed Ledger Technology (DLT) to address these concerns. Edge computing pushes cloud services, such as vehicles and roadside units, closer to the data source. This strategy reduces latency and network congestion. DLT provides a secure, decentralized platform for storing and sharing ITS data. Its tamper-proof nature ensures data integrity and prevents unauthorized access. Our architecture utilizes these technologies to create a decentralized platform for ITS data management. This platform facilitates secure processing, storage, and data exchange from various sources in the transportation network. This paper delves deeper into the architecture, explaining its essential components and functionalities. Additionally, we explore its potential applications and benefits for ITS. We describe a case study focusing on a data marketplace system for connected vehicles to assess the architecture’s effectiveness. The simulation results show an average latency reduction of 83.35% for publishing and 87.57% for purchasing datasets compared to the cloud architecture. Additionally, transaction processing speed improved by 18.73% and network usage decreased by 96.67%. The proposed architecture also achieves up to 99.61% reduction in mining centralization.

A Single-Pixel Event Photoactive Device for Real-Time, In-Sensor Spatiotemporal Optical Information Processing.

The increasing demand for energy-efficient, sophisticated optical sensing technologies in various applications, from machine vision to optical communication, highlights the necessity for innovations in spatiotemporal information sensing and processing at a nearly single-pixel scale. Traditional methods, including multi-pixel photodetector arrays and event-based camera systems, often fail to provide rapid, real-time detection and processing of dynamic events within the sensor. This shortcoming is particularly notable in handling high-dimensional spatiotemporal data, where the dependency on sequential data input and external processing tools leads to latency, reduced throughput, and heightened energy consumption, thereby impeding real-time parallel data processing capabilities. Here, a carrier-selective, single-pixel, position-sensitive planar photoactive device that integrates spatiotemporal event sensing with inherent short-term memory capabilities is introduced. The proof-of-concept single-pixel event photoactive device enables in-sensor spatiotemporal parallel optical information processing, efficiently managing multibit (>4 bit) data simultaneously and facilitating ultrafast (≈0.4µs) recognition of input patterns with low energy consumption (25 femtojoules). Additionally, by adjusting the operating speed from continuous to pulsed light illumination, the sensor array can detect trajectories and absolute position of events, offering in-sensor optical flow detection. This single-pixel event photodetector marks significant advancement toward developing compact, energy-efficient, ultrafast sensors suitable for a wide range of in sensor-based photonic applications.

From Near-Sensor to In-Sensor: A State-of-the-Art Review of Embedded AI Vision Systems.

In modern cyber-physical systems, the integration of AI into vision pipelines is now a standard practice for applications ranging from autonomous vehicles to mobile devices. Traditional AI integration often relies on cloud-based processing, which faces challenges such as data access bottlenecks, increased latency, and high power consumption. This article reviews embedded AI vision systems, examining the diverse landscape of near-sensor and in-sensor processing architectures that incorporate convolutional neural networks. We begin with a comprehensive analysis of the critical characteristics and metrics that define the performance of AI-integrated vision systems. These include sensor resolution, frame rate, data bandwidth, computational throughput, latency, power efficiency, and overall system scalability. Understanding these metrics provides a foundation for evaluating how different embedded processing architectures impact the entire vision pipeline, from image capture to AI inference. Our analysis delves into near-sensor systems that leverage dedicated hardware accelerators and commercially available components to efficiently process data close to their source, minimizing data transfer overhead and latency. These systems offer a balance between flexibility and performance, allowing for real-time processing in constrained environments. In addition, we explore in-sensor processing solutions that integrate computational capabilities directly into the sensor. This approach addresses the rigorous demand constraints of embedded applications by significantly reducing data movement and power consumption while also enabling in-sensor feature extraction, pre-processing, and CNN inference. By comparing these approaches, we identify trade-offs related to flexibility, power consumption, and computational performance. Ultimately, this article provides insights into the evolving landscape of embedded AI vision systems and suggests new research directions for the development of next-generation machine vision systems.

FastUNet: Fast hierarchical multi-patch underwater enhancement network for industrial recirculating aquaculture

The industrialized aquaculture with recirculating water systems has gained increasing attention and rapid development in recent years. However, the existing underwater enhancement methods are time-consuming and severely hinder their online application in industrialized aquaculture due to the requirement for real-time processing. We found that their main limitations are the insufficient utilization of the hierarchical network approach and valuable prior information in underwater scenarios. To address this problem, we propose a novel architecture called FastUNet and introduce a visual enhancement benchmark dataset specifically designed for industrialized aquaculture with recirculating water systems. Surprisingly, by learning the fast multi-patch hierarchical module and employing prior constraints including color loss and homology loss, FastUNet achieves comparable or even better results than many deep learning methods. In terms of runtime, it is up to 30 times faster than current underwater enhancement methods. The processing time for images with a resolution of 5474 × 3653 is only 0.137s. The real application scenario of factory recirculating aquaculture is considered by FastUNet, and the embedding of prior information under the fast network framework is explored. In this paper, 14 state-of-the-art underwater enhancement methods are compared, and excellent results are obtained on 2 Full-reference datasets and 2 No-referenced datasets. The application test results of SIFT significant point detection, geometric rotation, edge detection, target segmentation and target detection were also presented, which strongly verified the feasibility of FastUNet in the field of factory recirculating aquaculture.

An inline point-tracking approach for the real-time monitoring of the free-form bending process

In order to make free-form bending a process of choice for the manufacturing of structural components, a robust strategy for process monitoring is required. Although the technology is particularly suitable for the production of bending components with variable and complex geometry, fluctuations in the process conditions, as well as in the quality of the semi-finished products can results in geometrical deviations from the target geometry. Currently, the quality assessment of the bent components can be done only offline by random sampling, with a considerable time and cost effort. In this contribution, a real-time process monitoring is realised and applied to free-form bending for the first time. First of all, an inline strategy based on single-point tracking for the assessment of the geometry is investigated through an extensive numerical sensitivity analysis. Successively, the method is implemented experimentally and validated with real tests. Finally, a small-batch series of deviating components is produced, and the developed strategy is adopted to perform a real-time process monitoring. The study highlights the potential of an inline measurement strategy for the process monitoring in free-form bending, and its advantages compared to the current offline methods.

Edge–cloud collaborative estimation lithium-ion battery SOH based on MEWOA-VMD and Transformer

The State of Health (SOH) of lithium-ion batteries significantly impacts the performance, safety, and reliability of the battery, making it a crucial component of the battery management system. Addressing the issues of inadequate accuracy and lack of robustness in current SOH estimation methods, this study introduces a novel methodology for estimating SOH in lithium-ion batteries. It leverages the multi-population evolution whale optimization algorithm optimized variational mode decomposition (MEWOA-VMD) in conjunction with Transformer architecture. This framework enhances the efficiency and accuracy of SOH estimation by leveraging the computational capabilities of edge devices for real-time data processing, as well as the robust data processing power and model training advantages offered by cloud computing. Specifically, MEWOA is utilized to optimize VMD parameters, enabling MEWOA-VMD to fully decompose the capacity signal of lithium-ion batteries. This results in a component showing a global attenuation trend and a set of fluctuating components that represent capacity regeneration, thereby minimizing the impact of capacity regeneration on SOH estimation. Subsequently, all components are collectively input into the Transformer, marking the first application of this method for input. To enhance convergence speed and training efficiency, the layer normalization (LN) layer within the neural network architecture is proactively advanced. Finally, various artificial neural networks are compared and validated on three publicly available datasets. Furthermore, Gaussian noise is introduced into the original data to validate robustness. To confirm the practical applicability of the proposed method, real-world vehicle data is used for SOH estimation. The results indicate that the proposed method achieves a maximum MSE of no more than 0.009% across three publicly available datasets, showcasing improved accuracy and stability in SOH estimation. The practical applicability is further validated using real-world vehicle data, proving the proposed method’s potential for application in edge cloud-based battery management systems.

Smart structural health monitoring using computer vision and edge computing

Structural health monitoring (SHM) provides real-time data on the condition and performance of infrastructure, enabling timely and cost-effective maintenance interventions, and hence enhanced safety and extended service life. The computer vision-based non-contact sensor has emerged as a promising alternative to conventional contact-type sensors for structural displacement measurement and SHM. Many of the currently reported vision-based structural displacement measurement systems typically temporarily set up a video camera from a distance to the structure. The collected images or videos are usually stored locally and post-processed offline to obtain structural displacement responses, which is cumbersome and limited to short-term SHM applications. The recent development of technologies empowered by the Internet of Things (IoT) and edge computing has enabled real-time video processing and analysis at the source, minimizing latency, reducing bandwidth requirements, and enabling prompt decision-making, thereby enhancing efficiency and responsiveness compared to traditional offline video recording and processing systems. In this paper, an edge computing vision-based displacement measurement system (EdgeCVDMS) is developed. Video recording, processing, and displacement response identification are entirely performed on an edge device integrated with the vision-based displacement tracking algorithm, thereby greatly reducing the amount of data transmitted to the cloud server. The feasibility and applicability of the developed sensing system are experimentally validated on a laboratory-scaled transmission tower structure. The proposed EdgeCVDMS is cost-effective, easily deployable, and of great potential to be applied for the condition assessment of a larger population of aging civil infrastructure.

Data processing in internet of things networks

One of the distinctive features of cloud applications in the Internet of Things (IoT) network is the real-time collection and processing of data about the objects of the physical environment. To solve this problem, with the help of sensors, data about the state of physical objects is collected to form the processing of data streams. The performance of such systems is critically dependent on the ability to securely and efficiently collect, transmit, and analyze data streams between environmental (real-world) objects and information systems. In such a case, it is relevant to study the data stream in Internet of Things networks and the operations that may occur on them. The issue of which platforms to process the operations to be carried out at the same time is the main subject of discussion.

Machine Learning, Deep Learning, and Data Preprocessing Techniques for Detecting, Predicting, and Monitoring Stress and Stress-Related Mental Disorders: Scoping Review.

Mental stress and its consequent mental health disorders (MDs) constitute a significant public health issue. With the advent of machine learning (ML), there is potential to harness computational techniques for better understanding and addressing mental stress and MDs. This comprehensive review seeks to elucidate the current ML methodologies used in this domain to pave the way for enhanced detection, prediction, and analysis of mental stress and its subsequent MDs. This review aims to investigate the scope of ML methodologies used in the detection, prediction, and analysis of mental stress and its consequent MDs. Using a rigorous scoping review process with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, this investigation delves into the latest ML algorithms, preprocessing techniques, and data types used in the context of stress and stress-related MDs. A total of 98 peer-reviewed publications were examined for this review. The findings highlight that support vector machine, neural network, and random forest models consistently exhibited superior accuracy and robustness among all ML algorithms examined. Physiological parameters such as heart rate measurements and skin response are prevalently used as stress predictors due to their rich explanatory information concerning stress and stress-related MDs, as well as the relative ease of data acquisition. The application of dimensionality reduction techniques, including mappings, feature selection, filtering, and noise reduction, is frequently observed as a crucial step preceding the training of ML algorithms. The synthesis of this review identified significant research gaps and outlines future directions for the field. These encompass areas such as model interpretability, model personalization, the incorporation of naturalistic settings, and real-time processing capabilities for the detection and prediction of stress and stress-related MDs.

Enhanced Detection and Recognition of Road Objects in Infrared Imaging Using Multi-Scale Self-Attention.

In infrared detection scenarios, detecting and recognizing low-contrast and small-sized targets has always been a challenge in the field of computer vision, particularly in complex road traffic environments. Traditional target detection methods usually perform poorly when processing infrared small targets, mainly due to their inability to effectively extract key features and the significant feature loss that occurs during feature transmission. To address these issues, this paper proposes a fast detection and recognition model based on a multi-scale self-attention mechanism, specifically for small road targets in infrared detection scenarios. We first introduce and improve the DyHead structure based on the YOLOv8 algorithm, which employs a multi-head self-attention mechanism to capture target features at various scales and enhance the model's perception of small targets. Additionally, to prevent information loss during the feature transmission process via the FPN structure in traditional YOLO algorithms, this paper introduces and enhances the Gather-and-Distribute Mechanism. By computing dependencies between features using self-attention, it reallocates attention weights in the feature maps to highlight important features and suppress irrelevant information. These improvements significantly enhance the model's capability to detect small targets. Moreover, to further increase detection speed, we pruned the network architecture to reduce computational complexity and parameter count, making the model suitable for real-time processing scenarios. Experiments on our self built infrared road traffic dataset (mainly including two types of targets: vehicles and people) show that compared with the baseline, our method achieves a 3.1% improvement in AP and a 2.5% increase in mAP on the VisDrone2019 dataset, showing significant enhancements in both detection accuracy and processing speed for small targets, with improved robustness and adaptability.

Enhancing conversational ai with the Rasa framework: intent understanding and NLU pipeline optimization

Implementing the Rasa NLU pipeline allowed intent detection and entity recognition, particularly in complex scenarios with multi-intent queries. Communication within the Rasa NLU pipeline was effectively managed, ensuring seamless data flow between components, which preserved context and enhanced interpretability. The voice assistant developed with STT and TTS capabilities demonstrated robust real-time natural language processing, handling spoken queries efficiently. This confirmed the practical viability of using the Rasa framework for scalable and customizable conversational AI applications. Discussing: The findings underscore the robustness of the Rasa NLU pipeline in handling diverse conversational demands and the flexibility of its components to adapt to different linguistic contexts. The research discusses the potential of integrating sophisticated NLU techniques to create more intuitive and responsive conversational agents, highlighting the critical role of context-aware processing in improving user interaction with AI systems.

An efficient low-delay polyphase implementation method for active noise control systems

When implementing active noise control systems on signal processing hardware, the time delay introduced by electronic components (especially components requiring additional lowpass filters or introducing fixed-sample-size delays) may adversely affect the noise control performance. One common approach to reducing this delay is to use a high sampling rate, but this increases the computation significantly when implementing the ANC filters in real time. In the current work, a polyphase-structure-based filter design method is developed for active noise control systems that can reduce the computation load for real-time filter implementation but do not introduce an additional time delay. Although the computation reduction capability of a polyphase filter structure is well known for multi-rate systems, the traditional use of such multi-rate systems requires additional anti-aliasing and reconstruction filters which introduces an additional time delay. Thus, in delay-sensitive applications, such as active noise control, this method was previously applied only on the filter adaption phase, instead of directly on the real-time filtering process. In this article, a filter decomposition method using the minimum-phase technique is proposed to decompose an ANC filter into two multiplicative causal filters both of which have lowpass frequency response shapes at high frequencies such that the polyphase structure can be applied directly to the two multiplicative causal control filters without introducing additional anti-aliasing and reconstruction filters. Results show that, compared with various traditional low sampling rate implementations, the proposed method can significantly improve the noise control performance. Compared with the non-polyphase high-sampling rate method, the real-time computations that increase with the sampling rate are improved from quadratically to linearly.

Research on Lithology Identification based on Machine Learning

Machine learning has great potential in lithology identification. Through supervised learning, unsupervised learning, semi-supervised learning, deep learning and other methods, features can be automatically extracted from complex seismic data and logging data to achieve efficient and accurate lithology classification. These methods not only improve the accuracy and efficiency of lithology identification, but also reduce the workload of geologists, allowing them to focus on higher-level analysis and decision making. Despite significant progress, machine learning still faces many challenges in lithology identification. First, data quality and quantity limitations remain a major problem, especially in certain areas where obtaining high-quality seismic and logging data is difficult. Second, the training and interpretability of complex models also need to be addressed, especially because the "black box" nature of deep learning models makes it difficult for geologists to understand their internal mechanisms and predictions. In addition, the generalization ability and overfitting of models, as well as the need for real-time data processing in practical applications, are also urgent challenges to be solved. To address these challenges, this paper proposes several solutions and future directions. Data enhancement and synthesis techniques can extend existing data sets and improve the robustness and accuracy of models. The development of interpretative models and visualization tools helps geologists understand and trust the decision-making process of models. Multi-source data fusion technology can effectively use multi-source heterogeneous data such as seismic data, well logging data and geological map to improve model performance. Online learning and transfer learning technologies can update models in real time, improve the adaptability and generalization ability of models, and develop more accurate and interpretable models.

Digital technology-enabled capability development pathways

Production firms are increasingly rushing to develop digital-technology-enabled capabilities. However, little is known whether companies show consistent capability development pathways, how these pathways vary among firms, and how they affect firms’ revenue enhancement through digitalization. Using a survey data study of 506 production companies, we aim to reveal how companies develop Horizontal integration, Real-time data accumulation, Process automation, and Process virtualization digital technology-enabled capabilities, invoking a combination of PLS-SEM and process mining algorithms, which allows clustering capability development pathways and identifying their duration. The study revealed that 49.04 % of the firms that have introduced all four capabilities have followed the Integration->Real-time->Automation->Virtualization capability development pathway. The subsequent quantitative analysis shows that companies that follow this path develop their capabilities on average faster than companies that follow other capability development pathways. We also found that the number of introduced capabilities positively affected revenue enhancement through digitalization. Our results contribute to the capability dynamics and digital transformation literature, revealing that while some degree of equifinality manifests, companies tend to follow particular capability development pathways determined by the sequential complementarity of capabilities.