Terminal Devices Research Articles

Cost-effectiveness Analysis and Application Prospects of Anti-Magnetic Interference Technology in Mobile Terminal Devices

Cost-effectiveness Analysis and Application Prospects of Anti-Magnetic Interference Technology in Mobile Terminal Devices

Engineering Design and Application Research of Key Technologies for Jitter Motors in Information Terminal Devices

Engineering Design and Application Research of Key Technologies for Jitter Motors in Information Terminal Devices

Research on Destination Network Selection Based on Trajectory Trend

The terminal will switch between different networks to maintain the network service required by the terminal device during the mobile process, and the unreasonable or inaccurate choice of the destination network will lead to the mobile device to switch between multiple networks for many times, resulting in the deterioration of the overall network service quality and the decline of user experience. Based on the trajectory trend, this paper comprehensively considers the terminal moving trajectory and the base station location, reasonably refers to network parameter factors, and combines the analytic hierarchy process to select the destination network, so as to improve the accuracy of network selection, reduce the number of switching times, reduce the efficiency of switching and improve the network utilization.

A comprehensive numerical study of the effects of the air distribution terminals on the performance of a novel VRF-SV hybrid system

This study aims to numerically investigate the impact of air supply terminal devices (ASTDs) on the performance of novel variable refrigerant flow (VRF) integrated stratum ventilation (SV) system. The novel VRF-SV hybrid system was designed and analyzed in the authors’ previous work, where different design configurations were tested and their performances were compared. However, the effect of ASTDs on the performance of novel system has not yet been thoroughly explored. Therefore, this study was designed to investigate the effect of four types of ASTDs, including bar grille, double deflection grille, drum louver and jet slot diffusers installed in the laboratory and meeting room environments. The temperature and velocity field distribution, thermal comfort and indoor air quality (IAQ) were examined as performance indicators. The Re-Normalization Group (RNG), Realizable and Standard k-ϵ turbulence models were also employed in this study to verify and validate the numerical predictions with the experimental measurements. The experimental results found relatively close to the predictions obtained through RNG k-ϵ model with maximum deviations at any location were found to be 0.28 m/s in terms of velocity and 1.6°C in terms of temperature magnitude. Further research demonstrated that among the studied ASTDs, the bar grille diffuser provided an adequate thermal environment for the occupants with an acceptable jet throw and IAQ. This benefit also suggests that if the bar grille is installed with the VRF-SV system, the system would require less fan power, and thus, it reduces the energy use by the fan.

Privacy-preserving federated learning based on partial low-quality data

AbstractTraditional machine learning requires collecting data from participants for training, which may lead to malicious acquisition of privacy in participants’ data. Federated learning provides a method to protect participants’ data privacy by transferring the training process from a centralized server to terminal devices. However, the server may still obtain participants’ privacy through inference attacks and other methods. In addition, the data provided by participants varies in quality, and the excessive involvement of low-quality data in the training process can render the model unusable, which is an important issue in current mainstream federated learning. To address the aforementioned issues, this paper proposes a Privacy Preserving Federated Learning Scheme with Partial Low-Quality Data (PPFL-LQDP). It can achieve good training results while allowing participants to utilize partial low-quality data, thereby enhancing the privacy and security of the federated learning scheme. Specifically, we use a distributed Paillier cryptographic mechanism to protect the privacy and security of participants’ data during the Federated training process. Additionally, we construct composite evaluation values for the data held by participants to reduce the involvement of low-quality data, thereby minimizing the negative impact of such data on the model. Through experiments on the MNIST dataset, we demonstrate that this scheme can complete the model training of federated learning with the participation of partial low-quality data, while effectively protecting the security and privacy of participants’ data. Comparisons with related schemes also show that our scheme has good overall performance.

SRA-E-ABCO: terminal task offloading for cloud-edge-end environments

AbstractThe rapid development of the Internet technology along with the emergence of intelligent applications has put forward higher requirements for task offloading. In Cloud-Edge-End (CEE) environments, offloading computing tasks of terminal devices to edge and cloud servers can effectively reduce system delay and alleviate network congestion. Designing a reliable task offloading strategy in CEE environments to meet users’ requirements is a challenging issue. To design an effective offloading strategy, a Service Reliability Analysis and Elite-Artificial Bee Colony Offloading model (SRA-E-ABCO) is presented for cloud-edge-end environments. Specifically, a Service Reliability Analysis (SRA) method is proposed to assist in predicting the offloading necessity of terminal tasks and analyzing the attributes of terminal devices and edge nodes. An Elite Artificial Bee Colony Offloading (E-ABCO) method is also proposed, which optimizes the offloading strategy by combining elite populations with improved fitness formulas, position update formulas, and population initialization methods. Simulation results on real datasets validate the efficient performance of the proposed scheme that not only reduces task offloading delay but also optimize system overhead in comparison to baseline schemes.

Social Media, Mobile Payment, and Mobile Gaming for Intentional and Behavioral Recommendations

During the corona virus disease 2019 (COVID-19) pandemic, the Internet-based zero-contact economy model has increased people’s online social, entertainment, and business activities. Social media are social network platforms that support users’ social interaction to foster an information society. Mobile gaming refers to the use of mobile terminal devices for online entertainment. The combination of mobile payment and social media provides online users with an integrated information system platform for socializing, mobile gaming entertainment, and payment. A recommendation system filters information to predict a user’s rating or preference for a product/service. With recent advances in computer science, recommendation systems are gradually moving to develop intentional and behavioral recommendations. Thus, this study implements data mining analytics, including clustering analysis and association rules, to investigate mobile gaming, mobile payment, and social media preferences in Taiwanese gaming players. This study first finds several meaningful clusters/patterns/rules to present research findings and practical implications for intentional and behavioral recommendations (N = 2326).

Contrastive learning-based knowledge distillation for RGB-thermal urban scene semantic segmentation

RGB thermal semantic segmentation facilitates unmanned platforms to perceive and characterize their surrounding environment, which is critical for autonomous driving tasks. Deep-learning-based algorithms have achieved dominance in terms of accuracy and robustness. However, their large parameter sizes and significant computational demands impede their application in terminal devices. To address this challenge, we propose a novel strategy for achieving a balance between effectiveness and compactness. It includes a robust teacher network, CLNet-T, and a streamlined student network, CLNet-S. Using knowledge distillation (KD), we obtained an optimized model called CLNet-S*. Specifically, CLNet-T and CLNet-S were identical in all aspects except for the feature extraction component. They included a multi-attribute hierarchical feature interaction module (MHFI) and a detail-guided semantic decoder (DGSD). The MHFI initially filters features by considering the characteristics of the low- and high-level features. It gradually combines complementary and common features from various modalities in distinct receptive fields. DGSD uses edge and distribution information to guide semantic decoding, thereby improving the segmentation accuracy at class boundaries. To enhance the performance of the compact student model, our KD strategy includes detail, semantic response distillation (DSRD), and contrastive learning-based feature distillation (CLFD). Practically, DSRD enables the student model to gain knowledge from the teacher model at both the detailed and semantic levels. At the same time, CLFD increases the similarity of features within the same categories and emphasizes the distinctiveness of features between different categories in both the student and teacher models. Extensive experiments conducted on two standard datasets have consistently demonstrated that both CLNet-T and CLNet-S* outperform other state-of-the-art methods. The code and results are available at https://github.com/xiaodonguo/CLNet.

High-performance broadband SnS photodetector based on photoconductive-bolometric coupling effect

Due to its large absorption coefficient and high carrier mobility, SnS exhibits strong promise in the area of optoelectronic devices. Nevertheless, the fabrication of large-area, high-quality films for SnS photodetectors (PDs) with superior photoresponse remains a formidable task, seriously limiting its further practical application. In the present study, we report a superior-performance broadband PD founded on the epitaxial SnS film. Large-area uniform SnS films were grown epitaxially on (100)-oriented KBr using magnetron sputtering technique, further exfoliated, and transferred in a wafer size to fabricated two-ends PD devices. Benefitting from high crystallization and unique photoconductive-bolometric coupling effect, the two modes of operation exhibit a wide range of spectral responses from the visible to near-infrared wavelength (405–1920 nm). Particularly noteworthy is the SnS device fabricated, which demonstrates an impressive responsivity of 95.5 A W−1 and a detectivity of 7.8 × 1011 Jones, outperforming other devices by 1–2 orders of magnitude. In addition, SnS PD shows excellent environmental durability. This work provides a robust approach to develop high-performance broadband SnS PDs, while simultaneously offering deep insight into the light–matter interactions.

Resource allocation strategy based on service function Chaining in Multi-Access edge computing network

The Multi-access Edge Computing (MEC) network enhances the processing capability of Internet of Things (IoT) terminals by deploying 3C resources (computing resources, cache resources, and communication resources) at the IoT edge side, effectively improving the quality of service (QoS) of IoT applications. The majority of current MEC network research focuses on task offloading and energy management, with few studies looking at resource allocation from a service provisioning perspective. In this paper, we focus on the resource allocation problem when processing multiple tasks requested by IoT terminal devices in the MEC network. Firstly, we transform various tasks requested by IoT end devices into an SFC-based resource allocation problem. Then, we model the problem as a graph theory-based virtualized network function (VNF) node deployment cost optimization problem. Furthermore, we propose two resource allocation and deployment strategies by jointly considering the computing cost and security cost in VNF node deployment. Finally, extensive simulation experiments show that the proposed method can significantly improve the success rate of SFC task processing by more than 30% and network resource utilization by more than 20% when compared to other deployment methods for processing multiple SFC tasks with dynamic requests.

FGDB‐MLPP: A fine‐grained data‐sharing scheme with blockchain based on multi‐level privacy protection

AbstractIn the era of 5G, billions of terminal devices achieve global interconnection and intercommunication, which leads to the generation of massive data. However, the existing cloud‐based data‐sharing mechanism faces challenges such as sensitive information leakage and data islands, which makes it difficult to achieve secure sharing across domains. In this paper, the authors propose a fine‐grained data‐sharing scheme based on blockchain and ciphertext policy attribute‐based encryption, and design a verifiable outsourced computation method to reduce the computational pressure of end users. Second, the authors comprehensively consider the user's identity privacy and transaction privacy, and propose a multi‐level privacy protection method based on ring signature and garbled bloom filter, which enhance the user's data privacy and availability, and prevent the traceability of requests. Finally, the authors design a set of interconnected smart contracts, and verify that their scheme can achieve secure and efficient data sharing through security analysis and performance testing.

CCSFLF: Cloud‐edge‐terminal collaborative self‐adaptive federated learning framework

SummaryThis article addresses the issue of ensuring model accuracy and training efficiency in a constrained federated learning environment. In an actual federated learning environment, each device's software, hardware, and network conditions are heterogeneous. Some terminal devices may not be able to undertake the work assigned by the server, resulting in poor model accuracy and slower convergence speed. However, existing research cannot ensure that each terminal device participating in training can handle the workload allocated by the system without collecting too much equipment information. This article proposes the cloud‐edge‐terminal collaborative self‐adaptive federated learning framework (CCSFLF) to solve this problem. This framework combines the advantages of federated learning and edge computing, reduces the probability that devices cannot handle the workload of system allocation, solves the system heterogeneity, and improves the efficiency of federated learning. CCSFLF can adaptively adjust the number of training tasks for terminal devices and select valuable training participants using a terminal device selection strategy. Multiple edge servers can simultaneously aggregate local models. Cloud servers are responsible for the aggregation and task distribution of global models. The above strategy enables the framework to have a faster convergence rate and higher model accuracy. The experimental results confirm that this framework can reduce the dropout rate of terminal devices by more than 5% in heterogeneous federated learning systems, improve the model accuracy by about 2%, and reduce the training time by 1/3 compared with similar methods, with better performance and applicability.

A Dynamic Task Scheduling Algorithm for Airborne Device Clouds

The rapid development of mobile Internet has promoted the rapid rise of cloud computing technology. Mobile terminal devices have greatly expanded the service capacity of mobile terminals by migrating complex computing tasks to run in the cloud. However, in the process of data exchange between mobile terminals and cloud computing centers, on the one hand, it consumes the limited power of mobile terminals, and on the other hand, it results in longer communication time, which negatively affects user QoE. Mobile cloud can effectively improve user QoE by shortening the data transmission distance, reducing the power consumption, and shortening the communication time at the same time. In this paper, we utilize the property that genetic algorithm can perform global search seeking the global optimal solution and construct a dynamic task scheduling model by combining the device-cloud link. The task scheduling model based on genetic algorithm and random scheduling algorithm is compared through comparison experiments, which show that the assignment time of the task scheduling model based on genetic algorithm is shortened by 11.82% to 48.51% and the energy consumption is reduced by 22.28% to 47.52% under different load conditions.

A secure and efficient UAV network defense strategy: Convergence of blockchain and deep learning

Unmanned Aerial Vehicles (UAVs) are highly versatile and efficient tools utilized across diverse industries for data collection. However, they are vulnerable to wireless communication and data exchange risks, including unauthorized access, data theft, and network attacks. To address these problems, we introduce a secure and reliable UAV network service architecture that incorporates blockchain and deep learning to provide more secure and efficient network services for UAVs. We propose a UAV cluster identity management module by combining blockchain, encryption algorithms, and digital signatures to enhance the security of UAV communication data transmission. Then, based on machine learning, deep learning, and malicious process detection technology, we propose a real-time secure situational awareness system for UAV cluster terminal devices to enhance the security of the operating environment for UAVs. Finally, we propose a data-trustworthy interconnection platform based on blockchain, smart contracts, and consensus algorithms to realize secure and efficient sharing and transmission of terminal data. The results of the experiments demonstrate the feasibility and effectiveness of our UAV network service architecture.

A balanced and reliable data replica placement scheme based on reinforcement learning in edge–cloud environments

With the rapid development of edge–cloud computing, distributing resources to edge nodes and terminal devices to provide high-quality services for latency-sensitive applications and reduce network communication costs has become increasingly important. However, the complexity and heterogeneity of the edge–cloud environment pose significant challenges to the reliability of data storage and device load balancing. To address these issues, in this paper, we propose a Deep Reinforcement Learning (DRL)-based data replica placement scheme, BRPS. This scheme considers the different geographic locations of hardware devices, the heterogeneous storage capacity and reliability, and the different data requirements of varying user services in edge–cloud environments. Firstly, we constructed a model for data replica placement in the edge–cloud environment, addressing key factors such as latency, reliability, and load, focusing on the heterogeneity of device resources and reliability, and the diverse data needs of user services. Furthermore, we propose the BRPS scheme using the Double Deep Q-Network (DDQN) method of DRL, transforming the data replica placement issue into a multi-objective optimization problem. By placing the DRL-based decision process in a separate management edge node, the separation of decision and execution is achieved, which enhances the efficiency of data replica placement, ensures data reliability, reduces latency, and achieves system load balance. Experimental results demonstrate that BRPS significantly outperforms the existing comparison schemes while ensuring data reliability. The BRPS scheme reduces latency by 8.12% compared to the Random scheme and outperforms the best heuristic in system load balancing and memory utilization by 13.15% and 11.91%, respectively. Moreover, BRPS shows superior adaptability in extreme network congestion scenarios and effectively adapts to the dynamic changes of nodes in edge–cloud environments.

Device Identity Recognition Based on an Adaptive Environment for Intrinsic Security Fingerprints

A device’s intrinsic security fingerprint, representing its physical characteristics, serves as a unique identifier for user devices and is highly regarded in the realms of device security and identity recognition. However, fluctuations in the environmental noise can introduce variations in the physical features of the device. To address this issue, this paper proposes an innovative method to enable the device’s intrinsic security fingerprint to adapt to environmental changes, aiming to improve the accuracy of the device’s intrinsic security fingerprint recognition in real-world physical environments. This paper initiates continuous data collection of device features in authentic noisy environments, recording the temporal changes in the device’s physical characteristics. The problem of unstable physical features is framed as a restricted statistical learning problem with a localized information structure. This paper employs an aggregated hypergraph neural network architecture to process the temporally changing physical features. This allows the system to acquire aggregated local state information from the interactive influences of adjacent sequential signals, forming an adaptive environment-enhanced device intrinsic security fingerprint recognition model. The proposed method enhances the accuracy and reliability of device intrinsic security fingerprint recognition in outdoor environments, thereby strengthening the overall security of terminal devices. Experimental results indicate that the method achieves a recognition accuracy of 98% in continuously changing environmental conditions, representing a crucial step in reinforcing the security of Internet of Things (IoT) devices when confronted with real-world challenges.

Comparison and analysis of accuracy of various machine learning algorithms in abnormal state monitoring of internet of things devices

With the development of Internet of Things technology, more and more devices are connected to the Internet, including not only traditional computers, mobile phones and other smart terminal devices, but also various sensor devices. These sensor devices can collect a variety of environmental information and physical quantities, such as temperature, humidity, air pressure, light intensity, vibration, etc. These data have the characteristics of real-time, scale and diversity, and need to be processed and analyzed by appropriate algorithms. On the basis of previous studies, this project summarized the application of various machine learning algorithms in device state detection, compared the differences of various machine learning algorithms in sensor device detection and made comparative analysis, calculated the evaluation parameters of MSE, RMSE, MAE, MAPE, R² and other aspects of the machine learning regression model. Compare the effects of various regression models for better monitoring and prediction of equipment status. Through the analysis of a large number of historical data, different equipment state models can be established, and these models can be used to monitor and predict the current equipment state. This can effectively avoid production line downtime or other losses caused by equipment failures or abnormalities. At the same time, through the in-depth analysis of historical data, we can find some potential problems and take corresponding measures to prevent them. This project aims to summarize the application of various machine learning algorithms in device status detection, compare and contrast the differences of various machine learning algorithms in sensor device detection, realize efficient processing and analysis of sensor data, calculate MSE, RMSE, MAE, MAPE, R² and other evaluation parameters, and evaluate and compare each model. To provide more accurate, reliable and efficient equipment condition monitoring and forecasting services for enterprises and individuals.

Enhancement of GUI Display Error Detection Using Improved Faster R-CNN and Multi-Scale Attention Mechanism

Graphical user interfaces (GUIs) hold an irreplaceable position in modern software and applications. Users can interact through them. Due to different terminal devices, there are sometimes display errors, such as component occlusion, image loss, text overlap, and empty values during software rendering. To address the aforementioned common four GUI display errors, a target detection algorithm based on the improved Faster R-CNN is proposed. Specifically, ResNet-50 is used instead of the traditional VGG-16 as the feature extraction network. The feature pyramid network (FPN) and the enhanced multi-scale attention (EMA) algorithm are introduced to improve accuracy. ROI-Align is used instead of ROI-Pooling to enhance the generalization capability of the network. Since training models require a large number of labeled screenshots of errors, there is currently no publicly available dataset with GUI display problems. Therefore, a training data generation algorithm has been developed, which can automatically generate screenshots with GUI display problems based on the Rico dataset. Experimental results show that the improved Faster R-CNN achieves a detection accuracy of 87.3% in the generated GUI problem dataset, which is a 7% improvement compared to the previous version.

DRL-based dependent task offloading with delay-energy tradeoff in medical image edge computing

AbstractTask offloading solves the problem that the computing resources of terminal devices in hospitals are limited by offloading massive radiomics-based medical image diagnosis model (RIDM) tasks to edge servers (ESs). However, sequential offloading decision-making is NP-hard. Representing the dependencies of tasks and developing collaborative computing between ESs have become challenges. In addition, model-free deep reinforcement learning (DRL) has poor sample efficiency and brittleness to hyperparameters. To address these challenges, we propose a distributed collaborative dependent task offloading strategy based on DRL (DCDO-DRL). The objective is to maximize the utility of RIDM tasks, which is a weighted sum of the delay and energy consumption generated by execution. The dependencies of the RIDM task are modeled as a directed acyclic graph (DAG). The sequence prediction of the S2S neural network is adopted to represent the offloading decision process within the DAG. Next, a distributed collaborative processing algorithm is designed on the edge layer to further improve run efficiency. Finally, the DCDO-DRL strategy follows the discrete soft actor-critic method to improve the robustness of the S2S neural network. The numerical results prove the convergence and statistical superiority of the DCDO-DRL strategy. Compared with other algorithms, the DCDO-DRL strategy improves the execution utility of the RIDM task by at least 23.07, 12.77, and 8.51% in the three scenarios.

Realization of Selector‐Memory Bi‐Functionality with Self‐Current Regulation Utilizing Poly‐Crystalline Based GST Electrolyte for Memristor Hardware Development

AbstractConductive bridge random‐access memory (CBRAM) are two terminal devices that offer excellent switching performance. In addition, CBRAM shows various switching modes, including volatile threshold switching (TS) and nonvolatile threshold switching (N‐TS). These properties expand its applications to memory, selector, biological synapses, and neurons. However, due to the uncontrollable behavior of stochastic switching between TS and N‐TS in CBRAM devices, a novel approach is needed to improve the switching performance of CBRAM. Moreover, conventional devices that have different stacking between TS and N‐TS increase fabrication cost and worsen the device yield. Here, the selector‐memory bi‐functionality with self‐current regulation effect of Ag‐inserted Ge2Sb2Te5 (GST) thin films is demonstrated. Selector‐memory bi‐functionality, having TS behavior with an adjustable on/off current, with confined conductive filaments (CFs) improves the uniformity and reduces the fabrication cost by implementing TS/N‐TS in a single stack. From the material analysis, it becomes evident that confined Ag‐based CFs within GST films are key factors for realizing selector‐memory bi‐functionality. The selector‐memory bi‐functionality is achieved through the reaction of Ag metal cations with non‐bonded Te atoms in GST film depending on field polarity. These results suggest that the Ag‐inserted GST film contributes to the development of large‐scale nonvolatile memory and neuromorphic application.