Optimized design of hardware accelerator based on machine learning

In this modern technology era, in System on Chip (SoC) design, performance of processing units in computer is always on demand. By having hardware accelerators in computer system, core processor can offload task to it and this creates parallel execution to improve the processing speed. One of the functional blocks that are crucial in Hardware Accelerator's design is Storage Unit, which is used to keep data that is needed for processing or either the processed data. Under conventional hardware accelerator's design, the storage architecture is shaped to suit a certain processing algorithm and this introduced less flexibility in SoC design. In this paper, a novel design of storage architecture that is able to handle multiple accelerator engines and also modular to typical specification of hardware accelerators has been implemented.

With the expansion of Convolutional Neural Networks (CNNs) applications in various domains such as autonomous driving and real-time data processing, the demand for efficient computational resources has increased dramatically. Traditional computing platforms such as CPUs struggle to manage the complex and data-intensive tasks required by modern CNNs. This paper delves into the development and system optimization of dedicated hardware accelerators - GPUs, FPGAs, and ASICs to meet these demands. Through innovative architectural design and optimization techniques, these gas pedals improve computational speed and energy efficiency. Our study demonstrates that through these optimizations, the processing efficiency of hardware accelerators is significantly improved while energy consumption is effectively controlled, setting a new standard for the design of future hardware accelerators for convolutional neural networks. In addition, I discuss practical applications and future challenges, providing a comprehensive overview of current technologies and their potential development. This research highlights the critical role of advanced hardware accelerators in enabling the next generation of AI applications, ensuring technological advancement and sustainability in high-demand computing environments.

Design of exact reduct rough set hardware accelerator for early-stage diabetes risk prediction

Deep learning has transformed the use of machine learning technologies for the analysis of large experimental datasets. In science, such datasets are typically generated by large-scale experimental facilities, and machine learning focuses on the identification of patterns, trends and anomalies to extract meaningful scientific insights from the data. In upcoming experimental facilities, such as the Extreme Photonics Application Centre (EPAC) in the UK or the international Square Kilometre Array (SKA), the rate of data generation and the scale of data volumes will increasingly require the use of more automated data analysis. However, at present, identifying the most appropriate machine learning algorithm for the analysis of any given scientific dataset is a challenge due to the potential applicability of many different machine learning frameworks, computer architectures and machine learning models. Historically, for modelling and simulation on high-performance computing systems, these issues have been addressed through benchmarking computer applications, algorithms and architectures. Extending such a benchmarking approach and identifying metrics for the application of machine learning methods to open, curated scientific datasets is a new challenge for both scientists and computer scientists. Here, we introduce the concept of machine learning benchmarks for science and review existing approaches. As an example, we describe the SciMLBench suite of scientific machine learning benchmarks. Finding the most appropriate machine learning algorithm for the analysis of any given scientific dataset is currently challenging, but new machine learning benchmarks for science are being developed to help.

The modern developments in the Internet of Things (IoT) have been producing an increasing number of interconnected devices, allowing a variety of elegant applications. These IoT devices generate huge information that require smart data study and processing methods, for instance, deep learning (DL). Remarkably, the DL algorithms, when amalgamated with the industrial IoT (IIoT), can facilitate a mixture of applications, for example, elegant assembling, effective manufacturing, efficient networking, accident identifying, and prevention of errors. Also, IIoT can change the way in which industries use to produce autonomous self-healing machines and improve stocks using machine learning (ML). Alternatively, ML carries hidden imminence in IoT data for quick, automated answers, and enhanced assessment making. ML for IoT can be used to venture future trends, become aware of anomalies, and augment intelligence by consuming images, videos, and audios. Various industries currently use ML in IoT to keep up acceptable standards as well as maintain predictable things in terms of benefits and profits at different times. Banks and other businesses in the financial industry make use of ML technology for two main reasons: to recognise significant imminence in data and to avoid scams. Data mining can also be used to make out clients with high-risk outlines or use cyber-surveillance to locate notifying indications of fraud. IIoT has been a means to digital transformation in manufacturing. It takes up a network of sensors to implement a serious building of data and brings cloud software into action to use this data in expensive approaches about the effectiveness of manufacturing procedures. Machines can gain knowledge of the data and algorithms that are accountable for origin faults in the system to identify the errors before those can do damage. Manufacturers can make use of ML to get better safeguarding processes and facilitate them to construct real-time, smart judgments derived from data. So the main aim of this chapter is to focus on data acquisition, integration, and predictive control in the industry using ML for IIoTs for real-time collection and analysis of thousands of measurement points, an early detection of equipment failures and process disturbances, detection of new types of anomalies as they occur for the first time, and Web-based UI for handling alerts.

The growing integration of machine learning (ML) algorithms into social media platforms has not only transformed digital marketing but also raised critical issues related to data security, user privacy, and ethical governance. This study examines how ML algorithms influence user behavior and awareness, with a focus on the security and trust implications of algorithmic personalization. The research aims to assess the extent to which users understand how their data are collected and used for targeted content delivery and marketing purposes, testing hypotheses related to security awareness, data handling transparency, and behavioral risks. A survey conducted in 2023 among 100 students of the Faculty of Organization and Management at the Silesian University of Technology, selected through purposive sampling based on their active use of social networks, was analyzed using descriptive statistics and correlation methods in SPSS and Excel. The results indicate that 85% of respondents acknowledged that ML algorithms are actively used for content targeting and marketing, while 78% reported increased online engagement due to algorithmic recommendations. However, only 37% demonstrated awareness of data security implications, and 52% expressed concerns about the potential misuse of personal information. These findings reveal a significant gap between user engagement and understanding of security risks. The study underscores the urgent need for transparent data governance, algorithmic accountability, and improved user education to ensure safer and more ethical use of ML technologies in digital environments. It concludes by highlighting the importance of developing privacy-preserving ML models and promoting responsible innovation that balances personalization with user safety and trust.

This dissertation describes research activities broadly concerning the area of High-level synthesis (HLS), but more specifically, regarding the HLS-based design of energy-efficient hardware (HW) accelerators. HW accelerators, mostly implemented on FPGAs, are integral to the heterogeneous architectures employed in modern high performance computing (HPC) systems due to their ability to speed up the execution while dramatically reducing the energy consumption of computationally challenging portions of complex applications. Hence, the first activity was regarding an HLS-based approach to directly execute an OpenCL code on an FPGA instead of its traditional GPU-based counterpart. Modern FPGAs offer considerable computational capabilities while consuming significantly smaller as compared to high-end GPUs. Several different implementations of the K-Nearest Neighbor algorithm were considered on both FPGA- and GPU-based platforms and their performance was compared. FPGAs were generally more energy-efficient than the GPUs in all the test cases. Eventually, we were also able to get a faster (in terms of execution time) FPGA implementation by using an FPGA-specific OpenCL coding style and utilizing suitable HLS directives. The second activity was targeted towards the development of a methodology complementing HLS to automatically derive optimization directives (also known as power intent) from a system-level design description and use it to drive the design steps after HLS, by producing a directive file written using the common format (CPF) to achieve shut-off (PSO) in case of an ASIC design. The proposed LP-HLS methodology reduces the design effort by enabling designers to infer low information from the system-level description of a design rather than at the RTL. This methodology required a SystemC description of a generic management module to describe the design context of a HW module also modeled in SystemC, along with the development of a tool to automatically produce the CPF file to accomplish PSO. Several test cases were considered to validate the proposed methodology and the results demonstrated its ability to correctly extract the low information and apply it to achieve optimization in the backend flow.

Clear and trustworthy information is essential for people who are ill. People with cancer, in particular, are targeted with vast quantities of patient education material, but of variable quality. Machine learning technologies are popular across industries for automated tasks, like analyzing language and spotting readability issues. With the experience of patients with cancer in mind, we reviewed whether anyone has proposed, modeled, or applied machine learning technologies for the assessment of patient education materials and explored the utility of this application. We systematically searched the literature to identify English-language articles published in peer-reviewed journals or as conference abstracts that proposed, used, or modeled the use of machine learning technology to assess patient education materials. Specifically, we searched MEDLINE, Web of Science, CINAHL, and Compendex. Two reviewers assessed study eligibility and performed study screening. We identified 1,570 publications in our search after duplicate removal. After screening, we included five projects (detailed in nine articles) that proposed, modeled, or used machine learning technology to assess the quality of patient education materials. We evaluated the utility of each application across four domains: multidimensionality (2 of 5 applications), patient centeredness (1 of 5 applications), customizability (0 of 5 applications), and development stage (theoretical, 1 of 5 applications; in development, 3 of 5 applications; complete and available, 1 of 5 applications). Combining points across each domain, the mean utlity score across included projects was 1.8 of 5 possible points. Given its potential, machine learning has not yet been leveraged substantially in the assessment of patient education materials. We propose machine learning systems that can dynamically identify problematic language and content by assessing the quality of patient education materials across a range of flexible, customizable criteria. Assessment may help patients and families decide which materials to use and encourage developers to improve materials overall.

Low power & mobile hardware accelerators for deep convolutional neural networks

Simulation of street landscape design based on machine learning and entertainment design robots: An interactive entertainment design experience

Discontinuous processes face common tasks when implementing modeling and optimization techniques for process optimization. While domain data may be unequal, knowledge about approaches for each step toward the solution, e.g., data gathering, model reduction, and model optimization, may be useful across different processes. A joint development of methodologies for machine learning methods, among other things, ultimately supports fast advances in cross-domain production technologies. In this work, an overview of common maturation stages of data-intensive modeling approaches for production efficiency enhancement is given. The stages are analyzed and communal challenges are elaborated. The used approaches include both physically motivated surrogate modeling as well as the advanced use of machine learning technologies. Apt research is depicted for each stage based on demonstrator work for diverse production technologies, among them high-pressure die casting, surface engineering, plastics injection molding, open-die forging, and automated tape placement. Finally, a holistic and general framework is illustrated covering the main concepts regarding the transfer of mature models into production environments on the example of laser technologies.Increasing customer requirements regarding process stability, transparency and product quality as well as desired high production efficiency in diverse manufacturing processes pose high demands on production technologies. The further development of digital support systems for manufacturing technologies can contribute to meet these demands in various production settings. Especially for discontinuous production, such as injection molding and laser cutting, the joint research for different technologies helps to identify common challenges, ranging from problem identification to knowledge perpetuation after successfully installing digital tools. Workstream CRD-B2.II “Discontinuous Production” confronts this research task by use case-based joint development of transferable methods. Based on the joint definition of a standard pipeline to solve problems with digital support, various stages of this pipeline, such as data generation and collection, model training, optimization, and the development and deployment of assistance systems are actively being researched. Regarding data generation, e.g., for the high-pressure die-casting process, data acquisition and extraction approaches for machines and production lines using OPC UA are investigated to get detailed process insights. For diverse discontinuous processes and use cases, relevant production data is not directly available in sufficient quality and needs to be preprocessed. For vision systems, ptychographic methods may improve recorded data by enhancing the picture sharpness to enable the usage of inline or low-cost equipment to detect small defects. Further down the pipeline, several research activities concern the domain-specific model training and optimization tasks. Within the realm of surface technologies, machine learning is applied to predict process behavior, e.g., by predicting the particle properties in plasma spraying process or plasma intensities in the physical vapor deposition process. The injection molding process can also be modeled by data-based approaches. The modeling efficiency based on the used amount of data can furthermore be effectively reduced by using transfer learning to transfer knowledge stored in artificial neural networks from one process to the next. Successful modeling approaches can then be transferred prototypically into production. On the examples of vision-based defect classification in the tape-laying process and a process optimization assistance system in open-die forging, the realization of prototypical support systems is demonstrated. Once mature, research results and consequent digital services must be made available for integrated usage in specific production settings using relevant architecture. By the example of a microservice-based infrastructure for laser technology, a suitable and flexible implementation of a service framework is realized. The connectivity to production assets is guaranteed by state-of-the-art communication protocols. This chapter illustrates the state of research for use-case-driven development of joint approaches.

Homomorphic Encryption (HE) allows performing specific algebraic computations on encrypted data without the need for decryption. For this reason, HE is emerging as a strong privacy-preserving solution in cloud computing environments since it allows to keep data secure even in the case the cloud server is not trusted. HE libraries such as Microsoft SEAL have been recently released; however, such libraries are not specifically designed for resource-constrained platforms and they are often expensive in terms of computational resources and memory consumption, which limits their usage in edge devices. This limitation is contained by the SEAL-Embedded library, the first C-based HE library specifically designed for embedded platforms. In this article, we propose a hardware accelerator specifically designed for the SEAL-Embedded library and its implementation of the CKKS scheme: the proposed hardware presents a configurable Number Theoretic Transform (NTT) unit for all the polynomial degrees available on the SEAL-Embedded, a memory architecture able to reduce the I/O latency and a dedicated module for the generation of roots of unity. A complete system that includes a 32-bit RISC-V processor has been implemented on a Xilinx ZCU106 FPGA board to test the functionality of the hardware accelerator and to measure performance improvements. The results showed a speed-up of around x1000 with the hardware acceleration respect to the pure software implementation of the SEAL-Embedded library for the symmetric encryption function.

The concrete mix design is a crucial step in ensuring the quality of concrete used in construction projects. Traditional mix design methods rely on trial and error, which can be time-consuming and escalate construction costs. In recent years, machine learning technology has been developed to predict concrete properties and optimize mix designs for high-quality concrete. This study aims to explore the application of machine learning in high-quality concrete mix design, considering theoretical conditions, methods, and related research. The focus of this research is to test the use of machine learning techniques in predicting concrete properties and optimizing mix designs for high-quality concrete. The theory and concepts of machine learning will be applied to concrete mix design datasets and relevant properties. The methods employed will include data pre-processing, feature selection, and model training and evaluation. The performance of the machine learning model will be compared with traditional mix design methods to determine its effectiveness. Furthermore, the results and benefits of this study will demonstrate the potential advantages of using machine learning in determining high-performance concrete mix designs. By accurately predicting concrete properties and optimizing mix designs, construction projects can be completed more efficiently and with higher quality. This technology also has the potential to reduce costs associated with trial and error methods and minimize the environmental impact of concrete production. The success of this study will pave the way for further research and development in the field of machine learning for high-performance concrete mix designs.

In the present situation, a recent study investigated the use of machine learning technologies to foresee the future in all sectors. Itsability to anticipate the stock market has increased its importance in economic research. However, due to the loudness and volatility ofthe stock market, described forecast is sometimes seen as one of the most difficult jobs. To overcome these issues, we provide a stockmarket prediction model based on deep learning. To begin, we recommend introducing shareholder emotion into stock prediction,which can significantly improve the model's predictive ability. Second, because the share value series is a sophisticated period processwith a broad range of fluctuation sizes, creating a reliable forecasts is highly tough. Third, we employ LSTM because of its memorycapabilities, which allows us to examine correlations between stock data. Fourth, we integrate the numerous corporate facts to thisprice analysis and create a dashboard. And in comparison to CNN and RNN approaches. The data was divided using the random forestapproach. Using cross-validation, the data was divided into training and testing groups. Finally, we contrast machine learning and deeplearning methodologies.

Computational methods in fluid research have been progressing during the past few years, driven by the incorporation of massive amounts of data, either in textual or graphical form, generated from multi-scale simulations, laboratory experiments, and real data from the field. Artificial Intelligence (AI) and its adjacent field, Machine Learning (ML), are about to reach standardization in most fields of computational science and engineering, as they provide multiple ways for extracting information from data that turn into knowledge, with the aid of portable software implementations that are easy to adopt. There is ample information on the historical and mathematical background of all aspects of AI/ML in the literature. Thus, this review article focuses mainly on their impact on fluid research at present, highlighting advances and opportunities, recognizing techniques and methods having been proposed, tabulating, and testing some of the most popular algorithms that have shown significant accuracy and performance on fluid applications. We also investigate algorithmic accuracy on several fluid datasets that correspond to simulation results for the transport properties of fluids and suggest that non-linear, decision tree-based methods have shown remarkable performance on reproducing fluid properties.