Heterogeneous Devices Research Articles

Implementation of Distributed Machine Learning in Cloud Calculation: Evidence from Consumer Behavior Prediction

Abstract. In the field of machine learning, distributed machine learning (DML) has gained massive popularity in research and appeared in a wide range of applications including transportation, medicine, and business. Distributed machine learning showed huge potential in processing large amounts of data while keeping the data private. In this paper, a distributed implementation of a deep neural network (DNN) with a large dataset from a telecom company, aiming to predict consumer behavior based on usage data is carried out. Various datasets with distinct heterogeneity settings were applied to the network, simulating a real-world cloud application scenario. Comparisons between both the centralized model and the distributed models were made to analyze the impact on model performance with device heterogeneity and data heterogeneity. These result indicate that under certain circumstances, DML models showed better accuracy and lower loss compared to the centralized model. The paper provided some insights and made some assumptions on how the data and the parameters affect the model performance.

A hybrid approach using support vector machine rule-based system: detecting cyber threats in internet of things

While the proliferation of the Internet of Things (IoT) has revolutionized several industries, it has also created severe data security concerns. The security of these network devices and the dependability of IoT networks depend on efficient threat detection. Device heterogeneity, computing resource constraints, and the ever-changing nature of cyber threats are a few of the obstacles that make detecting cyber threats in IoT systems difficult. Complex threats often go undetected by conventional security measures, requiring more sophisticated, adaptive detection methods. Therefore, this study presents the Hybrid approach based on the Support Vector Machines Rule-Based Detection (HSVMR-D) method for an all-encompassing approach to identifying cyber threats to the IoT. The HSVMR-D employs SVM to categorize known and unknown threats using attributes acquired from IoT data. Identifying known attack signatures and patterns using rule-based approaches improves detection efficiency without retraining by adapting pre-trained models to new IoT contexts. Moreover, protecting vital infrastructure and sensitive data, HSVMR-D provides a thorough and adaptable solution to improve the security posture of IoT deployments. Comprehensive experiment analysis and simulation results compared to the baseline study have confirmed the efficiency of the proposed HSVMR-D. Furthermore, increased resilience to completely novel changing threats, fewer false positives, and improved accuracy in threat detection are all outcomes that show the proposed work outperforms others. The HSVMR-D approach is helpful where the primary objective is a secure environment in the Internet of Things (IoT) when resources are limited.

An efficient deep reinforcement learning based task scheduler in cloud-fog environment

Efficient task scheduling in cloud and fog computing environments remains a significant challenge due to the diverse nature and critical processing requirements of tasks originating from heterogeneous devices. Traditional scheduling methods often struggle with high latency and inadequate processing times, especially in applications demanding strict computational efficiency. To address these challenges, this paper proposes an advanced fog-cloud integration approach utilizing a deep reinforcement learning-based task scheduler, DRLMOTS (Deep Reinforcement Learning based Multi Objective Task Scheduler in Cloud Fog Environment). This novel scheduler intelligently evaluates task characteristics, such as length and processing capacity, to dynamically allocate computation to either fog nodes or cloud resources. The methodology leverages a Deep Q-Learning Network model and includes extensive simulations using both randomized workloads and real-world Google Jobs Workloads. Comparative analysis demonstrates that DRLMOTS significantly outperforms existing baseline algorithms such as CNN, LSTM, and GGCN, achieving a substantial reduction in makespan by up to 26.80%, 18.84, and 13.83% and decreasing energy consumption by up to 39.60%, 30.29%, and 27.11%. Additionally, the proposed scheduler enhances fault tolerance, showcasing improvements of up to 221.89%, 17.05%, and 11.05% over conventional methods. These results validate the efficiency and robustness of DRLMOTS in optimizing task scheduling in fog-cloud environments.

Solving blockage problem of the 5G mmWaves Wireless Communications using Jellyfish Search Optimizer

The 5G technologies are aimed to support a variety of vertically connected applications with heterogeneous devices and machines with significant improvements in terms of higher quality of service, increased network capacity and improved system throughput. However, 5G systems still face a number of challenges mentioned by researchers and organizations, and among these challenges, we highlight that millimeter wave links are very susceptible to blockage. If the line-of-sight communication path is blocked, reflexive path communication can help maintain communication. The shortest route was to take an alternate route when the first route was blocked. Among the proposed solutions to the blocking problem is an algorithm to distribute the power between different mmWave communication paths in order to overcome the masses of links under randomly distributed obstacles. The problem has been resolved with an exact method. In this article, we have optimized all the results of this exact method by applying a powerful metaheuristic technique called jellyfish search optimizer to maximize the overall capacity of the path between two nodes. The results showed that our approach procures an improvements exceed 100% over the results of the exact method.

Using Deep Reinforcement Learning (DRL) for minimizing power consumption in Video-on-Demand (VoD) storage systems

As video streaming services such as Netflix become popular, resolving the problem of high power consumption arising from both large data size and high bandwidth in video storage systems has become important. However, because various factors, such as the power characteristics of heterogeneous storage devices, variable workloads, and disk array models, influence storage power consumption, reducing power consumption with deterministic policies is ineffective. To address this, we present a new deep reinforcement learning (DRL)-based file placement algorithm for replication-based video storage systems, which aims to minimize overall storage power consumption. We first model the video storage system with time-varying streaming workloads as the DRL environment, in which the agent aims to find power-efficient file placement. We then propose a proximal policy optimization (PPO) algorithm, consisting of (1) an action space that determines the placement of each file; (2) an observation space that allows the agent to learn a power-efficient placement based on the current I/O bandwidth utilization; (3) a reward model that assigns a greater penalty for increased power consumption for each action; and (4) an action masking model that supports effective learning by preventing agents from selecting unnecessary actions. Extensive simulations were performed to evaluate the proposed scheme under various solid-state disk (SSD) models and replication configurations. Results show that our scheme reduces storage power consumption by 5% to 25.8% (average 12%) compared to existing benchmark methods known to be effective for file placement.

HuNT: Exploiting Heterogeneous PIM Devices to Design a 3-D Manycore Architecture for DNN Training

HuNT: Exploiting Heterogeneous PIM Devices to Design a 3-D Manycore Architecture for DNN Training

Arch2End: Two-Stage Unified System-Level Modeling for Heterogeneous Intelligent Devices

Arch2End: Two-Stage Unified System-Level Modeling for Heterogeneous Intelligent Devices

DeepZoning: Re-accelerate CNN Inference with Zoning Graph for Heterogeneous Edge Cluster

Parallelizing CNN inference on heterogeneous edge clusters with data parallelism has gained popularity as a way to meet real-time requirements without sacrificing model accuracy. However, existing algorithms struggle to find optimal parallel granularity for complex CNNS, the structure of which is a directed acyclic graph (DAG) rather than a chain, and the parallel dimension is inflexible. To distribute the workload of modern CNNs on heterogeneous devices is also proven as NP-hard problem. In this paper, we introduce DeepZoning , a versatile and cooperative inference framework that combines both model and data parallelism to accelerate CNN inference. DeepZoning employs two algorithms at different levels: (1) a low-level Adaptive Workload Partition algorithm that uses linear programming and takes spatial and channel dimensions into optimization during the search for feature map distribution on heterogeneous devices, and (2) a high-level Model Partition algorithm that finds the optimal model granularity and organizes complex CNNs into sequential zones to balance communication and computation during execution. Our experimental evaluations show that DeepZoning is effective, achieving up to a 3.02 × speed improvement on our experimental prototype compared to state-of-the-art algorithms.

Data ecosystem using smart home technology to support healthy aging

Abstract Background Smart home technology has been widely used to mitigate the challenges that population aging brings. However, the lack of a centralized data ecosystem has prevented these technologies from realizing their full potential. This project aimed to construct a data ecosystem compatible with smart home sensors to monitor healthcare for seniors, improving their quality of life. Methods The infrastructure was constructed using a user-centered design approach, allowing smart devices such as motion, temperature sensors to operate independently and communicate through a Wi-Fi mesh network. API technology provides a reliable channel for real-time data collection. To ensure data privacy and security, extracted data is hosted in a cloud environment that provides comprehensive data protection, and cloud computing is utilized for high-performance computation tasks. Analytical models such as Machine Learning can be implemented to recognize indoor activities, achieving the goal of remote monitoring. Results This data ecosystem advances in privacy and security, interoperability, accessibility, and data-sharing. Unified authentication mechanism ensures data is transmitted among heterogeneous devices with minimal vulnerability. Additionally, the common communication protocol provides the foundation of interoperability between devices. With unobtrusive devices, inhabitants are not burdened with operation, ensuring their accessibility and improving their user experience. Lastly, the data is exchanged in a standardized JSON data format, enabling efficient data-sharing board data integration. Conclusions This project developed a data ecosystem based on existing smart home environments. The ecosystem is compatible with smart devices that families already have, effectively reducing additional healthcare costs. Implications of this study include helping health policy and decision makers to adopt more smart home ecosystems to keep older people healthy at home. Key messages • Study constructed a data ecosystem compatible with smart home sensors, achieving remote monitoring of indoor activities and improving the quality of life for seniors. • The developed ecosystem offers promotion in privacy and security, interoperability, accessibility, and efficient data-sharing, reducing healthcare costs.

A Platform of Federated Learning Management for Enhanced Mobile Collaboration

Federated learning (FL) has emerged as a crucial technology in today’s data-centric environment, enabling decentralized machine learning while safeguarding user privacy. This study introduces “Federated Learning ML Operations (FedOps) Mobile”, a novel FL framework optimized for the dynamic and heterogeneous ecosystem of mobile devices. FedOps Mobile addresses the inherent challenges of FL—such as system scalability, device heterogeneity, and operational efficiency—through advanced on-device training using TensorFlow Lite and CoreML. The framework’s innovative approach includes sophisticated client selection mechanisms that assess device readiness and capabilities, ensuring equitable and efficient participation across the network. Additionally, FedOps Mobile leverages remote device control for seamless task management and continuous learning, all without compromising the user experience. The main contribution of this study is the demonstration that federated learning across heterogeneous devices, especially those using different operating systems, can be both practical and efficient using the FedOps Mobile framework. This was validated through experiments that evaluated three key areas: operational efficiency, model personalization, and resource optimization in multi-device settings. The results showed that the proposed method excels in client selection, energy consumption, and model optimization, establishing a new benchmark for federated learning in diverse and complex environments.

Identify devices and events from non-IP heterogeneous IoT network traffic

In recent years, notable advancements have been achieved in the realm of identifying IP-based Internet of Things (IoT) devices and events. Nevertheless, the majority of methods rely on extracting fingerprints or features from plain text IP-based packets, which limits their ability to accommodate heterogeneous IoT devices such as ZigBee and Z-Wave, and fails to address the challenge of limited traffic samples. To tackle these issues, we propose a novel approach based on IoT communication characteristics and featuring module extensibility. This method is presented to effectively identify IoT devices and events from non-IP heterogeneous IoT network traffic. To shield the differences caused by the heterogeneous IoT protocol, a heterogeneous sample extraction platform with an extensible structure is created to extract raw sequence samples from ZigBee and Z-Wave traffic, with potential for expansion to other protocols. To address the challenges arising from the scarcity of samples, a sample identification framework based on IoT communication characteristics is devised to create synthetic samples from the raw sequence samples, enabling concurrent processing of the raw and synthetic samples using an identification model featuring two separate sequence networks. Comparative assessments of our method against baseline sequence models and the latest techniques demonstrate the advantages of our approach in identifying non-IP heterogeneous IoT traffic. The experimental results indicate that our method achieves an average accuracy improvement of 29.7% compared to baseline models using only raw samples. Furthermore, our method shows improvements of 22.1%, 21.5%, and 21.8% in macro precision, macro recall, and macro F1-score, respectively, over the latest method.

EM-Rhythm: An Authentication Method for Heterogeneous IoT Devices

The popularity of IoT devices has penetrated our daily life while posing new challenges in user authentication. Today’s solutions, e.g., passwords, fingerprints, and FaceIDs, primarily rely on specialized sensors or user interfaces to collect user’s identification information, which may not universally exist on heterogeneous IoT devices. In this paper, we propose a novel user authentication method that exploits the EM emanations radiated from IoT devices. Our design is motivated by the observation that human touches on the IoT device can lead to time-varying coupling between these two. Consequently, it impacts the device’s EM emanations that can be picked up by its inertial ADC (analog-to-digital converter) interfaces. We ask the user to tap on the device rhythmically following a self-determined melody, such that the human-coupled EM emanations vary accordingly. We thus extract the rhythm pattern as the user’s secure password named EM-Rhythm . To examine its effectiveness, EM-Rhythm is implemented on a wide range of IoT devices. We show that our scheme achieves authentication accuracy as high as 98.67% with less than three login attempts. Besides, it is robust against various types of attacks and maintains stable performances under various settings. EM-Rhythm also exhibits satisfactory usability in terms of memorability and time consumption.

Modelling Decision and Reaction Against Detected Intrusions in IoT System Basing on Security Policy Rules

In recent years, The Internet of Things (IoT) is considered as one of the main technological revolutions, it connects heterogeneous devices, peoples, and services in order to exchange information and to improve existing deployments in different sectors. So far, existing security solutions are not adapted to this development, considering that IoT resources are exposed to different intrusions, which impact security management efficiency and the need for human interventions to increase. Although, it is too hard to depend on manual approaches that require the deep involvement of security managers to deliver the aimed security level. Therefore, a new solution is needed, that will facilitate the decision against detected intrusions and according to their magnitudes and their intentions to put the necessary reaction in the right place. In this context, this paper proposes a model which specify how the decision and correlation scenario will be carried out when a critical alert comes from the intrusion detector basing on security policy rules. This model simplifies and facilitates the decision and reaction against detected intrusions by enriching it with the rules defined in security policy to ensure the protection of IoT resources and help security administrators to make the right decisions in other tasks.

Improving QoS Parameters in Fog Computing Environment using QCSO Framework

Cloud computing is a complex infrastructure because heterogeneous devices are involved to share the resources on it. In recent years, the Internet of Things (IoT) is being used by a huge number of different devices which create large amounts of data. Due to their remote location, IoT devices create delays in processing the data. To ensure the Quality of Service (QoS) of the network, the real time applications need low latency and high bandwidth which in turn improves the quality of life. To solve this problem, Fog Computing (FC) is introduced which plays a vital role in computing paradise. Fog computing processes the request locally and uses available resources to reduce the latency and enhance the technological innovation and capabilities. To allocate and manage the resources is the primary goal of fog computing. To achieve this, Queuing theory method is used in which tasks are assigned to the resources. Proposed study presents an algorithm named Queue-Cuckoo Search Optimization Framework (QCSOF) to improve the quality of service through resource optimization. The aim of the proposed framework is to enhance resource allocation, energy utilization.

Leveraging HLS to Design a Versatile & High-Performance Classic McEliece Accelerator

By harnessing fundamental quantum properties, a large-scale quantum computer could undermine currently deployed public-key algorithms. The post-quantum, code-based cryptosystem Classic McEliece (CM) addresses this security concern. However, its large public key size (up to 1.3MB) poses various hardware implementation challenges. In this paper, we focus on the high memory bandwidth requirements of the CM encoding function, in the context of heterogeneous CPU-FPGA devices. More concretely, we target the acceleration of public-key loading and processing from any globally-shared or accelerator-private memory system. We present a novel and constant-time accelerator eEnc that exploits the elevated parallelization potential of FPGA devices to yield high-performance results. Our accelerator implements the encoding and the random error vector generation functions, which comprise the main computational load of Encapsulation. Two accelerator design variants are introduced, providing different hardware tradeoffs. Regarding intra-accelerator data communication, and unlike other state-of-the-art (SOTA) works, we combine a streaming protocol with task-level parallelization to remove the need to store the public key in accelerator-private memories. Our proposed design shows new record execution times over its SOTA counterparts, ranging on average from 3.5 × up to 7.7 × across the five security level parameter sets. Our end-to-end implementation in a Zynq SoC shows an average speedup of 2.2 × compared to a 64-bit vectorized CM software-baseline. The elevated logic resource consumption, characteristic of HLS designs, can be readily adjusted with a performance tradeoff.

Dynamic pricing‐based integration for non‐cooperative ubiquitous sensing and communication network

AbstractAs 5G and early‐stage network technologies mature, a wealth of data and experience is accumulated. The ubiquitous sensing and communication network (USCN) can leverage these existing communication infrastructures to maximize resource utilization and reduce the costs of redeployment through integration with modern 6G and beyond 6G networks. However, implementing future integrated sensing and communication (ISAC) functions in USCN may possess different hardware capabilities and communication protocols, presenting significant challenges. This is due to the lack of a unified framework for managing and optimizing these heterogeneous resources, as well as the absence of reasonable performance metrics. This letter proposes a dynamic pricing coordinated resource allocation (DPCRA) mechanism to realize the emerging ISAC in legacy USCNs. The DPCRA is designed to optimize the spectrum efficiency (SE) of USCN and manages resource interactions between heterogeneous devices through price variables, thereby resolving resource conflicts and deadlocks. The novelties include: (1) employing a price mechanism to foster resource cooperation in non‐cooperative networks; (2) introducing an SE metric incorporating an information similarity factor for optimization; (3) dynamically selecting resources to enhance SE. Simulations demonstrate that the DPCRA effectively resolves device deadlock while maintaining high SE levels, promoting device collaboration.

Solvent-free Acrylate/BCB drop-on-demand (DOD) inkjet dielectric ink for 3D printing

Currently, drop-on-demand (DOD) inkjet-printed dielectric inks used to produce next-generation high-frequency electronic devices fail to meet the requirements of circuit board substrates in terms of thermal, mechanical, and dielectric properties. To address this gap, we synthesized a low-viscosity acrylate monomer featuring an intrinsically low dielectric structure (hexafluorobisphenol A) and multiple cross-linking sites, and a benzocyclobutene monomer with low curing shrinkage and excellent thermomechanical properties. By mixing these monomers with other reactive diluents and verifying them through theoretical calculations and printing, we have developed a range of dielectric inks suitable for inkjet 3D printing. To enhance the overall performance of the cured inks, a sequential UV/thermal curing strategy was employed to form interpenetrating networks (IPNs). The optimal ink formulations met the requirements of circuit board substrates, demonstrating excellent heat resistance (Td5% = 334 °C, Tg = 181 °C), mechanical properties (tensile strength = 85 MPa, elongation at break = 13.5 %), and dielectric properties (Dk = 2.526 and Df = 0.113 at 15 GHz). These formulations meet the performance requirements for circuit board substrates and lead the industry in mechanical and dielectric properties. Furthermore, the feasibility of inkjet printing heterogeneous integrated electronic devices was verified, showing excellent print resolution and continuity of the conductive network. This work provides new insights into the future development of dielectric materials for inkjet 3D printing.

FedDA: Resource-adaptive federated learning with dual-alignment aggregation optimization for heterogeneous edge devices

Federated learning (FL) is an emerging distributed learning paradigm that allows multiple clients to collaborate on training a global model without sharing their local data. However, in practical heterogeneous edge device scenarios, FL faces the challenges of system heterogeneity and data heterogeneity, which leads to unfair participation and degraded global model performance. In this paper, we introduce FedDA, a resource-adaptive FL framework, which adapts to the client’s computing resources by assigning heterogeneous models of different sizes. To improve the performance of heterogeneous model aggregation and adjust to non-independent and identically distributed (non-i.i.d.) data, we propose a dual-alignment aggregation optimization method, i.e., parameter feature space alignment and output space alignment. Specifically, FedDA exploits the permutation symmetry property of weight space to permutate the model parameter positions via an adaptive layer-wise matching method, thereby aligning models with significant deviations in parameter feature space. FedDA mitigates the imbalance in parameter quantity between smaller and larger models through parameter expansion. Additionally, FedDA maps client labels into a uniform embedding space through output space alignment, thus reducing model parameter deviations due to non-i.i.d. data without additional client-side computing overhead. We evaluate the performance of FedDA on benchmark datasets, including FashionMNIST, CIFAR10, CIFAR100 and AGNews. Experimental results demonstrate that FedDA achieves up to 8.71% improvement in model accuracy compared to baseline methods, highlighting its effectiveness in addressing the challenges of heterogeneity.

Filling the Missing: Exploring Generative AI for Enhanced Federated Learning Over Heterogeneous Mobile Edge Devices

Filling the Missing: Exploring Generative AI for Enhanced Federated Learning Over Heterogeneous Mobile Edge Devices

Asynchronous Decentralized Federated Learning for Heterogeneous Devices

Asynchronous Decentralized Federated Learning for Heterogeneous Devices