Advances In Hardware Research Articles

A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions

Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.

Factorization of large tetra and penta prime numbers on IBM quantum processor

The factorization of large digit integers in polynomial time is a challenging computational task to decipher. The development of Shor’s algorithm sparked a new resolution for solving the factorization problem. However, putting Shor’s algorithm into use in real-world situations presents major difficulties. The algorithm largely depends on the availability of large-scale, fault-tolerant quantum computers, which are not available at present. The need for qubit coherence and error correction makes the algorithm susceptible to noise and decoherence, hindering its practical realization. Therefore, exploring alternative quantum factorization algorithms and investing in quantum computing hardware advancements are vital steps toward overcoming these drawbacks and harnessing the full potential of quantum computing for factorization tasks. This article explores an alternative method of converting the factorization problem into an optimization problem using appropriate analytic algebra. The generalized Grover’s protocol is used to increase the amplitude of the necessary states and, in turn, help in the execution of the quantum factorization of tetra and penta primes as a proof of concept for different integers, including 875, 1 269 636 549 803, and 4375, using three and four qubits of IBMQ Perth (a seven-qubit processor). The fidelity of the quantum factorization protocol with the IBMQ Perth qubits was near unity. A generalization of the method is provided at the end for implementing factorization problems in various cases.

Task Scheduling by Hybrid Metaheuristic Approach in Cloud Environment

Abstract: Recent advancements in hardware, virtualization technology, distributed computing, and service delivery over the Internet have led to the formation of cloud computing. In a distributed computing platform, the scheduling of task workflow is a well-known NP-hard problem. This becomes more complex and challenging if the virtualized clusters execute a large number of tasks in a cloud computing platform. From low-level execution tasks in multiple processors to high-level execution tasks, many heuristics have been proposed. This chapter deals with the proposed min-min algorithm, max-min algorithm, PSO, and TS. The max-min and min-min algorithms estimate the execution time and overall completion time of all the tasks Then assign the tasks on better suitable resource. PSO is simple and effective in a wide range of applications with low computational cost and fast speed. TS approach is one of the popular local search techniques based on neighborhood search algorithm. TS can be directly applied to any kind of virtual optimization problem.

Integration effect of artificial intelligence and traditional animation creation technology

Abstract Despite the advancements in modern computer hardware and software, the creation of digital animation still demands a substantial investment of both manpower and time. This article aimed to explore how artificial intelligence (AI) technology can be combined with traditional animation creation techniques to achieve better integration effects. By combining intelligent character animation generation with hand drawing, a generative adversarial network was used to achieve high-quality animation generation. The generator generated realistic animations, and the discriminator measured the authenticity of the animations by comparing the differences between the generator-generated animations and the real animations, which was used for automated character animation generation. This can greatly reduce the cost and time of digital animation creation, improve the quality of digital animation, and provide more innovation for the application of traditional animation technology. The average number of audience attracted by characters through blended creation was 122.2% more than that of characters through traditional animation creation and 32.6% more than that of characters through AI creation. This not only helps animation producers complete animation production more quickly, but also enhances the creativity and artistic value of animation.

PyHySCO: GPU-enabled susceptibility artifact distortion correction in seconds.

Over the past decade, reversed gradient polarity (RGP) methods have become a popular approach for correcting susceptibility artifacts in echo-planar imaging (EPI). Although several post-processing tools for RGP are available, their implementations do not fully leverage recent hardware, algorithmic, and computational advances, leading to correction times of several minutes per image volume. To enable 3D RGP correction in seconds, we introduce PyTorch Hyperelastic Susceptibility Correction (PyHySCO), a user-friendly EPI distortion correction tool implemented in PyTorch that enables multi-threading and efficient use of graphics processing units (GPUs). PyHySCO uses a time-tested physical distortion model and mathematical formulation and is, therefore, reliable without training. An algorithmic improvement in PyHySCO is its use of the one-dimensional distortion correction method by Chang and Fitzpatrick to initialize the non-linear optimization. PyHySCO is published under the GNU public license and can be used from the command line or its Python interface. Our extensive numerical validation using 3T and 7T data from the Human Connectome Project suggests that PyHySCO can achieve accuracy comparable to that of leading RGP tools at a fraction of the cost. We also validate the new initialization scheme, compare different optimization algorithms, and test the algorithm on different hardware and arithmetic precisions.

Making stateless and stateful network performance measurements unbiased

The Benchmarking Working Group (BMWG) of the Internet Engineering Task Force (IETF) has defined a series of Requests for Comments (RFC) to standardize the benchmarking of network interconnect devices (e.g., bridges, routers, different IPv6 transition solutions). The paper points out that there are cases where the performance results are significantly different when a single IP address pair or multiple IP addresses are used. The cause of this phenomenon is rooted in the recent hardware and software advancements: Receive Side Scaling (RSS) makes it possible to distribute packet processing workload over multiple CPU cores. However, this may be implemented in two ways: the first way only includes the IP addresses into the hash function used to distribute the workload among the CPU cores, whereas the second one also includes the port numbers. RFC 4814 proposed an excellent solution for the second case by recommending the usage of pseudorandom port numbers during benchmarking; however, the first case was not handled properly, because no explicit recommendation was given regarding the usage of multiple IP addresses. This paper attempts to bridge this methodological gap; a practical solution is proposed for using pseudorandom IP addresses in various scenarios including the benchmarking of IPv4 and IPv6 routers and Network Address Translation from IPv6 Clients to IPv4 Servers (stateful NAT64) gateways. Its feasibility is shown by disclosing the details of its implementation in siitperf. Then the proposed solution is validated by both stateless and stateful tests. It is shown that the measurement results of the tests following the proposed solution can better characterize the true performance of the network interconnect devices that follow the first type of RSS implementation than the results of the tests using a single IP address pair.

Deep Photonic Reservoir Computer for Speech Recognition.

Speech recognition is a critical task in the field of artificial intelligence (AI) and has witnessed remarkable advancements thanks to large and complex neural networks, whose training process typically requires massive amounts of labeled data and computationally intensive operations. An alternative paradigm, reservoir computing (RC), is energy efficient and is well adapted to implementation in physical substrates, but exhibits limitations in performance when compared with more resource-intensive machine learning algorithms. In this work, we address this challenge by investigating different architectures of interconnected reservoirs, all falling under the umbrella of deep RC (DRC). We propose a photonic-based deep reservoir computer and evaluate its effectiveness on different speech recognition tasks. We show specific design choices that aim to simplify the practical implementation of a reservoir computer while simultaneously achieving high-speed processing of high-dimensional audio signals. Overall, with the present work, we hope to help the advancement of low-power and high-performance neuromorphic hardware.

Precision Gait Stability Analysis Combining Hardware and Software

Maintaining stable gait and avoiding falls require effective control of the body’s center of mass (CoM) relative to the base of support (BoS), defined by the feet's contact points with the floor. Quadrupeds have an advantage over bipeds but share common spinal neural control mechanisms. Human walking poses stability challenges since the CoM often extends beyond the BoS. This project aims to monitor gait stability by integrating advanced hardware and software solutions. Machine learning algorithms, such as Random Forest, will be employed to predict gait instability by capturing foot positions and sensor data. Inertial measurement sensors will track stability changes, and hardware outputs will be validated against software predictions for accuracy. A mobile app developed using React Native will display predicted parameters and indicate gait instability (yes/no). In case of detected instability, a wearable buzzer will alert the user. This system promises a more accurate solution for monitoring gait stability compared to existing models, by combining real-time data collection and sophisticated algorithms

Speeding up the Training of Neural Networks with the One-Step Procedure

In the last decade, research and corporate have shown a dramatically growing interest in the field of machine learning, mostly due to the performances of deep neural networks. These increasingly complex architectures solved a wide range of problems. However, training these sophisticated architectures require many computation on advanced hardware. With this paper, we introduce a new approach based on the One-Step procedure that may fasten their training. In this procedure, an initial guess estimator is computed on a subsample that is then improved with only one step of the Newton gradient descent on the whole dataset. To show the efficiency of this framework, we consider regression and classification tasks using simulated and real datasets. We consider classic architectures, namely multi-layer perceptrons and show, on our examples, that the One-Step procedure is often halving the computation time to train the neural networks while preserving the performances.

Remote operation of the DIII-D National Fusion Facility

Full remote scientific operation of the DIII-D National Fusion Facility is now possible through significant advances in the computer science hardware and software infrastructure made over the last decade. Capabilities around information visualization, data movement, and communication have all been enhanced. The level of capability deployed to remotely operate DIII-D required an infrastructure advancement over what had previously been achieved in the fusion community. The large quantity of real-time data that is automatically displayed on DIII-D’s control room screens can now be visualized by remote participants via web-based applications. New audio/video solutions using the VoIP and instant messaging application Discord have been implemented to mimic the dynamic and ad-hoc scientific conversations that are critical in successfully operating an experimental campaign. Discord’s ability for a user to rapidly move between audio channels, text with images, and share screens is a significant enhancement over traditional videoconferencing tools. In addition, multiple combinations of broadcast audio are made available via a web-based application to allow remote participants to simultaneously listen to general announcements/sounds while conducting their own specific conversations. Secure methodologies have been put into place to allow remote control of hardware including DIII-D’s plasma control system application. Secure methods also included the ability of the on-site team to closely coordinate their work with remote team members which has been enhanced through extensions to the wireless network and the use of tablet computers for audio/video/screen sharing. However, no amount of software can fully replace the need for ‘hands on hardware.’ This infrastructure was severely stress tested during the COVID-19 pandemic where occupancy of the DIII-D control room was restricted. Operational efficiency during the pandemic, measured in discharges per hour, remained high (3.8 ± 0.8) compared to values obtained pre-pandemic (3.7 ± 0.8).

Application of Computer Image Processing Technology in Intelligent Monitoring System

With the continuous progress of science and technology and the rapid development of society, intelligent surveillance systems are gradually emerging in the field of security and other related fields, and have become a key tool for ensuring public safety and improving efficiency. Intelligent monitoring system with computer vision and image processing technology as the core, with the help of advanced hardware equipment and intelligent algorithms, can be efficiently processed and deeply analysed image information in real-time monitoring. This paper provides a strong support to build a safer and more efficient society by studying in depth the application of image processing technology in intelligent surveillance system with the goal of comprehensively promoting the technological innovation of intelligent surveillance system.

Current Aspects of Medical Rehabilitation of Patients with Cancer Related Lymphedema of Extremities: a Narrative Review

INTRODUCTION. Over the past decades, in developed countries and in the Russian Federation, there has been an increase in the number of patients with secondary lymphedema who have undergone surgical treatment with dissection of regional lymph nodes and radiation therapy for various forms of gynecological cancer in women and prostate cancer in men, as well as breast cancer. AIM. Search and analysis of the results of previously published randomized controlled trials (RCTs) of the effectiveness of various non-drug rehabilitation methods in patients with lymphedema of the extremities who underwent radical treatment for cancer of various locations. MATERIALS AND METHODS. A search was conducted and studied publications in international scientific peer-reviewed publications (PEDro Database) on medical rehabilitation for cancer treatment-related lymphedema (LSPR) for the period from 1996 to December 2023 using the keywords “lymphedema”, “rehabilitation”. 145 RCTs focused on medical rehabilitation and conservative treatment of LSPR. DISCUSSION. Lifestyle correction and psychosocial interventions are recommended to improve the quality of life of patients. Studies have found that early activation, various physical exercises with a slow increase in loads under the supervision of a physical therapist are safe and help increase endurance, strength and range of motion in a limb with lymphatic edema. The clinical effectiveness of therapeutic exercises in the pool has been proven, manifested in the reduction of edema in patients with LSPR. The effectiveness of compression products with Velcro technology as an alternative to rigid low-stretch bandages in patients with LSPR has been confirmed. The anti-edematous and anti-inflammatory effects of low-intensity laser therapy and magnetic therapy in the rehabilitation of patients with LSLR have been proven. Alternating pneumatic compression (APC) is recommended as an adjuvant treatment in addition to comprehensive decongestant therapy. Preference should be given to the use of technologies of advanced hardware lymphatic drainage methods that imitate manual techniques. CONCLUSION. To improve the physical and socio-psychological functioning of patients with LSPR, an integrated approach is required, including lifestyle changes, psychological correction, compression therapy, modern exercise therapy techniques, and safe physiotherapeutic technologies. Conducted scientific research indicates the high effectiveness of the use of manual and hardware lymphatic drainage techniques, while the use of PPC is more economical and accessible, and does not require the involvement of specialists who know the expensive method of manual lymphatic drainage.

Speculative computing for AAFM solutions in large-scale product configurations.

Parallel computing is a current algorithmic approach to looking for efficient solutions; that is, to define a set of processes in charge of performing at the same time the same task. Advances in hardware permit the massification of accessibility to and applications of parallel computing. Nonetheless, some algorithms include steps that require or depend on the results of other steps that cannot be parallelized. Speculative computing allows parallelizing those tasks and reviewing different execution flows, which can involve executing invalid steps. Speculative computing solutions should reduce those invalid flows. Product configuration refers to selecting features from a set of available options respecting some configuration constraints; a not complex task for small configurations and models, but a complex one for large-scale scenarios. This article exemplifies a videogame product line feature model and a few configurations, valid and non-valid, respectively. Configuring products of large-scale feature models is a complex and time-demanding task requiring algorithmic solutions. Hence, parallel solutions are highly desired to assist the feature model product configuration tasks. Existing solutions follow a sequential computing approach and include steps that depend on others that cannot be parallelized at all, where the speculative computing approach is necessary. This article describes traditional sequential solutions for conflict detection and diagnosis, two relevant tasks in the automated analysis of feature models, and how to define their speculative parallel version, highlighting their computing improvements. Given the current parallel computing world, we remark on the advantages and current applicability of speculative computing for producing faster algorithmic solutions.

A Greenhouse Gas Footprint Analysis of Advanced Hardware Technologies in Connected Autonomous Vehicles

Greenhouse gas emissions are a critical concern for China’s automotive industry, especially for passenger cars due to their high sales’ volume. Recently, the trend towards connected and autonomous driving vehicles has been significant in the passenger car market. However, the impact of these systems on the life cycle emissions of vehicles remains unclear. This paper focuses on system function levels from driver assistance to full driving automation and studies their life cycle greenhouse gas emissions. This research establishes a component list for the hardware system and a material inventory. Then, this paper reveals significant differences in total system emissions at these technology levels, 540.1 kg for primary, 1318.7 kg for medium, and 2279.2 kg for advanced systems. Despite this difference, the total is less than 7.23% of the total vehicle emissions. To further reduce this portion of GHG emissions, it is recommended that vehicles favor millimeter-wave radar over solid-state LiDAR in their sensing system hardware, coupled with cameras as the primary sensing element. In addition, Intelligent Hardware Systems are not recommended for internal combustion engine passenger cars for optimal balance between functionality and environmental impact.

A Novel Frame-Selection Metric for Video Inpainting to Enhance Urban Feature Extraction.

In our digitally driven society, advances in software and hardware to capture video data allow extensive gathering and analysis of large datasets. This has stimulated interest in extracting information from video data, such as buildings and urban streets, to enhance understanding of the environment. Urban buildings and streets, as essential parts of cities, carry valuable information relevant to daily life. Extracting features from these elements and integrating them with technologies such as VR and AR can contribute to more intelligent and personalized urban public services. Despite its potential benefits, collecting videos of urban environments introduces challenges because of the presence of dynamic objects. The varying shape of the target building in each frame necessitates careful selection to ensure the extraction of quality features. To address this problem, we propose a novel evaluation metric that considers the video-inpainting-restoration quality and the relevance of the target object, considering minimizing areas with cars, maximizing areas with the target building, and minimizing overlapping areas. This metric extends existing video-inpainting-evaluation metrics by considering the relevance of the target object and interconnectivity between objects. We conducted experiment to validate the proposed metrics using real-world datasets from Japanese cities Sapporo and Yokohama. The experiment results demonstrate feasibility of selecting video frames conducive to building feature extraction.

Global marine phytoplankton dynamics analysis with machine learning and reanalyzed remote sensing.

Phytoplankton are the world's largest oxygen producers found in oceans, seas and large water bodies, which play crucial roles in the marine food chain. Unbalanced biogeochemical features like salinity, pH, minerals, etc., can retard their growth. With advancements in better hardware, the usage of Artificial Intelligence techniques is rapidly increasing for creating an intelligent decision-making system. Therefore, we attempt to overcome this gap by using supervised regressions on reanalysis data targeting global phytoplankton levels in global waters. The presented experiment proposes the applications of different supervised machine learning regression techniques such as random forest, extra trees, bagging and histogram-based gradient boosting regressor on reanalysis data obtained from the Copernicus Global Ocean Biogeochemistry Hindcast dataset. Results obtained from the experiment have predicted the phytoplankton levels with a coefficient of determination score (R2) of up to 0.96. After further validation with larger datasets, the model can be deployed in a production environment in an attempt to complement in-situ measurement efforts.

Adaptive temporal compression for reduction of computational complexity in human behavior recognition

The research on video analytics especially in the area of human behavior recognition has become increasingly popular recently. It is widely applied in virtual reality, video surveillance, and video retrieval. With the advancement of deep learning algorithms and computer hardware, the conventional two-dimensional convolution technique for training video models has been replaced by three-dimensional convolution, which enables the extraction of spatio-temporal features. Specifically, the use of 3D convolution in human behavior recognition has been the subject of growing interest. However, the increased dimensionality has led to challenges such as the dramatic increase in the number of parameters, increased time complexity, and a strong dependence on GPUs for effective spatio-temporal feature extraction. The training speed can be considerably slow without the support of powerful GPU hardware. To address these issues, this study proposes an Adaptive Time Compression (ATC) module. Functioning as an independent component, ATC can be seamlessly integrated into existing architectures and achieves data compression by eliminating redundant frames within video data. The ATC module effectively reduces GPU computing load and time complexity with negligible loss of accuracy, thereby facilitating real-time human behavior recognition.

Development of Micro/Nano Pattern Arrays with Grating-Based Periodic Structures using the Direct Laser Lithography System

Introduction: This research delves into utilizing the Direct Laser Lithography System to produce micro/nanopattern arrays with grating-based periodic structures. Initially, refining the variation in periodic structures within these arrays becomes a pivotal pursuit. This demands a deep comprehension of how structural variation aligns with specific applications, particularly in photonics and material science. Method: Advancements in hardware, software, or process optimization techniques hold potential for reaching this objective. Using an optical beam, this system enables the engraving of moderate periodic and quasi-periodic structures, enhancing pattern formation in a three-dimensional environment. Through cost-effective direct-beam interferometry systems utilizing 405 nm GaN and 290 to 780 nm AlInGaN semiconductor laser diodes, patterns ranging from in period were created, employing 300 nm gratings. Result: The system's cost-efficiency and ability to achieve high-resolution permit the creation of both regular and irregular grating designs. By employing an optical head assembly from a bluray disc recorder, housing a semiconductor laser diode and an objective lens with an NA of 0.85, this system displays promising potential in progressing the fabrication of micro/nanopattern arrays. Conclusion: Assessing their optical, mechanical, and electrical properties and exploring potential applications across varied fields like optoelectronics, photovoltaics, sensors, and biomedical devices represent critical strides for further exploration and advancement.

Quantum Fourier networks for solving parametric PDEs

Many real-world problems, like modelling environment dynamics, physical processes, time series etc involve solving partial differential equations (PDEs) parameterised by problem-specific conditions. Recently, a deep learning architecture called Fourier neural operator (FNO) proved to be capable of learning solutions of given PDE families for any initial conditions as input. However, it results in a time complexity linear in the number of evaluations of the PDEs while testing. Given the advancements in quantum hardware and the recent results in quantum machine learning methods, we exploit the running efficiency offered by these and propose quantum algorithms inspired by the classical FNO, which result in time complexity logarithmic in the number of evaluations and are expected to be substantially faster than their classical counterpart. At their core, we use the unary encoding paradigm and orthogonal quantum layers and introduce a new quantum Fourier transform in the unary basis. We propose three different quantum circuits to perform a quantum FNO. The proposals differ in their depth and their similarity to the classical FNO. We also benchmark our proposed algorithms on three PDE families, namely Burgers’ equation, Darcy’s flow equation and the Navier–Stokes equation. The results show that our quantum methods are comparable in performance to the classical FNO. We also perform an analysis on small-scale image classification tasks where our proposed algorithms are at par with the performance of classical convolutional neural networks, proving their applicability to other domains as well.

FLOATING DOCK ANALYSIS SUBJECT TO DYNAMIC WAVE LOADS USING COMPUTATIONAL FLUID DYNAMICS

Floating dock systems are widely used in marine and waterfront facilities. Environmental loading and movements applied on these systems can be challenging to predict due to the complex interaction between structures and fluids under dynamic wave loads. Design of floating dock systems requires analysis of wave induced forces, relative movements of the dock, effects of connections, and subsequent loads and deflections in piles or mooring line anchors. Supporting structures such as piles or mooring lines can have significant impacts on load distribution within a floating dock system and shall be analyzed carefully during design. Recent advances in computer hardware and multi-physics computational fluid dynamics (CFD) technology have permitted transient dynamic wave analysis of entire floating dock system, to explicitly consider fluid-structure interaction in the analysis and design of floating dock systems. In this study, a CFD technology is applied to investigate the dynamic system characteristics of a floating dock system supported by both piles and mooring lines. CFD analysis is based on software package FLOW-3D® Hydro. Floating dock, piles, and mooring lines are modeled, and analysis results are presented. It is shown to be useful for analyzing floating docks which are typically too complex to accurately evaluate using empirical methods.