基于MobileNetV3Small-ECA的水稻病害轻量级识别研究

为实现水稻病害的轻量化识别与检测,使用ECA注意力机制改进MobileNetV3Small模型,并使用共享参数迁移学习对水稻病害进行智能化轻量级识别和检测。在PlantVillage数据集上进行预训练,将预训练得到的共享参数迁移到对水稻病害识别模型上微调优化。在开源水稻病害数据集上进行试验测试,试验结果表明,在非迁移学习下,识别准确率达到97.47%,在迁移学习下识别准确率达到99.92%,同时参数量减少26.69%。其次,通过Grad-CAM进行可视化,本文方法与其他注意力机制CBAM和SENET相比,ECA模块生成的结果与图像中病斑的位置和颜色更加一致,表明网络可以更好地聚焦水稻病害的特征,并且通过可视化和各水稻病害分析了误分类原因。本文方法实现了水稻病害识别模型的轻量化,使其能够在移动设备等资源受限的场景中部署,达到快速、高效、便携的目的。同时开发了基于Android的水稻病害识别系统,方便于在边缘端进行水稻病害识别分析。

IRS Assisted UAV Communications against Proactive Eavesdropping in Mobile Edge Computing Networks

In this paper,we consider mobile edge computing(MEC)networks against proactive eavesdropping.To maximize the transmission rate,IRS assisted UAV communications are applied.We take the joint design of the trajectory of UAV,the transmitting beamforming of users,and the phase shift matrix of IRS.The original problem is strong non-convex and difficult to solve.We first propose two basic modes of the proactive eavesdropper,and obtain the closed-form solution for the boundary conditions of the two modes.Then we transform the original problem into an equivalent one and propose an alternating optimization(AO)based method to obtain a local optimal solution.The convergence of the algorithm is illustrated by numerical results.Further,we propose a zero forcing(ZF)based method as sub-optimal solution,and the simulation section shows that the proposed two schemes could obtain better performance compared with traditional schemes.

Time Parameter Based Low-Energy Data Encryption Method for Mobile Applications

Various mobile devices and applications are now used in daily life.These devices require high-speed data processing,low energy consumption,low communication latency,and secure data transmission,especially in 5G and 6G mobile networks.High-security cryptography guarantees that essential data can be transmitted securely;however,it increases energy consumption and reduces data processing speed.Therefore,this study proposes a low-energy data encryption(LEDE)algorithm based on the Advanced Encryption Standard(AES)for improving data transmission security and reducing the energy consumption of encryption in Internet-of-Things(IoT)devices.In the proposed LEDE algorithm,the system time parameter is employed to create a dynamic S-Box to replace the static S-Box of AES.Tests indicated that six-round LEDE encryption achieves the same security level as 10-round conventional AES encryption.This reduction in encryption time results in the LEDE algorithm having a 67.4%lower energy consumption and 43.9%shorter encryption time than conventional AES;thus,the proposed LEDE algorithm can improve the performance and the energy consumption of IoT edge devices.

Observer-based dynamic event-triggered control for distributed parameter systems over mobile sensor-plus-actuator networks

We develop a policy of observer-based dynamic event-triggered state feedback control for distributed parameter systems over a mobile sensor-plus-actuator network.It is assumed that the mobile sensing devices that provide spatially averaged state measurements can be used to improve state estimation in the network.For the purpose of decreasing the update frequency of controller and unnecessary sampled data transmission, an efficient dynamic event-triggered control policy is constructed.In an event-triggered system, when an error signal exceeds a specified time-varying threshold, it indicates the occurrence of a typical event.The global asymptotic stability of the event-triggered closed-loop system and the boundedness of the minimum inter-event time can be guaranteed.Based on the linear quadratic optimal regulator, the actuator selects the optimal displacement only when an event occurs.A simulation example is finally used to verify that the effectiveness of such a control strategy can enhance the system performance.

A Problem Not to Be Ignored: The Influencing Factors of Mobile Phone Addiction and Its Influence on Sleep Quality

Background and Objective: With the popularity and widespread use of mobile phones, the effects of mobile phone dependence and addiction on individuals’ physical and mental health have attracted more and more attention. The present study aims to analyze the current state of mobile phone addiction and its impact on sleep quality within the population, while also exploring the influence of related factors on sleep quality. Ultimately, this research will provide a scientific foundation for targeted intervention measures and strategies. Methods: A total of 253 permanent residents in Nanjing were randomly selected as study subjects. The Mobile Phone Addiction Index (MPAI) and Pittsburgh Sleep Quality Index (PSQI) were used to evaluate the degree of smartphone addiction and sleep quality of the study subjects. Body mass index (BMI) was measured according to standardized procedures. Independent sample t-test, Chi-square test, rank sum test and multiple linear regression were used to analyze the correlation between mobile phone addiction and sleep quality, and P Results: 117 people (46.2%) were addicted to mobile phones. Chi-square test showed that the rate of mobile phone addiction in drinking group was significantly higher than that in non-drinking group (P P P P P P P P P P Conclusion: Mobile phone addiction may lead to shorter sleep duration and reduce sleep efficiency. The withdrawal of mobile phone addiction may have a negative impact on sleep quality. According to the characteristics of the population, appropriate comprehensive intervention measures should be taken to build an effective evaluation system, so as to reduce the impact of mobile phone addiction and withdrawal problems on sleep and improve sleep quality.

Air-Ground Collaborative Mobile Edge Computing:Architecture,Challenges,and Opportunities

By pushing computation,cache,and network control to the edge,mobile edge computing(MEC)is expected to play a leading role in fifth generation(5G)and future sixth generation(6G).Nevertheless,facing ubiquitous fast-growing computational demands,it is impossible for a single MEC paradigm to effectively support high-quality intelligent services at end user equipments(UEs).To address this issue,we propose an air-ground collaborative MEC(AGCMEC)architecture in this article.The proposed AGCMEC integrates all potentially available MEC servers within air and ground in the envisioned 6G,by a variety of collaborative ways to provide computation services at their best for UEs.Firstly,we introduce the AGC-MEC architecture and elaborate three typical use cases.Then,we discuss four main challenges in the AGC-MEC as well as their potential solutions.Next,we conduct a case study of collaborative service placement for AGC-MEC to validate the effectiveness of the proposed collaborative service placement strategy.Finally,we highlight several potential research directions of the AGC-MEC.

SAC-Based Computation Offloading for Reconfigurable Intelligent Surface-Aided Mobile Edge Networks

In this paper,we concentrate on a reconfigurable intelligent surface(RIS)-aided mobile edge computing(MEC)system to improve the offload efficiency with moving user equipments(UEs).We aim to minimize the energy consumption of all UEs by jointly optimizing the discrete phase shift of RIS,UEs’transmitting power,computing resources allocation,and the UEs’task offloading strategies for local computing and offloading.The formulated problem is a sequential decision making across multiple coherent time slots.Furthermore,the mobility of UEs brings uncertainties into the decision-making process.To cope with this challenging problem,the deep reinforcement learning-based Soft Actor-Critic(SAC)algorithm is first proposed to effectively optimize the discrete phase of RIS and the UEs’task offloading strategies.Then,the transmitting power and computing resource allocation can be determined based on the action.Numerical results demonstrate that the proposed algorithm can be trained more stably and perform approximately 14%lower than the deep deterministic policy gradient benchmark in terms of energy consumption.

Computing Resource Allocation for Blockchain-Based Mobile Edge Computing

Users and edge servers are not fullymutually trusted inmobile edge computing(MEC),and hence blockchain can be introduced to provide trustableMEC.In blockchain-basedMEC,each edge server functions as a node in bothMEC and blockchain,processing users’tasks and then uploading the task related information to the blockchain.That is,each edge server runs both users’offloaded tasks and blockchain tasks simultaneously.Note that there is a trade-off between the resource allocation for MEC and blockchain tasks.Therefore,the allocation of the resources of edge servers to the blockchain and theMEC is crucial for the processing delay of blockchain-based MEC.Most of the existing research tackles the problem of resource allocation in either blockchain or MEC,which leads to unfavorable performance of the blockchain-based MEC system.In this paper,we study how to allocate the computing resources of edge servers to the MEC and blockchain tasks with the aimtominimize the total systemprocessing delay.For the problem,we propose a computing resource Allocation algorithmfor Blockchain-based MEC(ABM)which utilizes the Slater’s condition,Karush-Kuhn-Tucker(KKT)conditions,partial derivatives of the Lagrangian function and subgradient projection method to obtain the solution.Simulation results show that ABM converges and effectively reduces the processing delay of blockchain-based MEC.

The Contribution of AI-Powered Mobile Apps to Smart City Ecosystems

In the groundbreaking study “The Contribution of AI-powered Mobile Apps to Smart City Ecosystems,” authored by Zaki Ali Bayashot, the transformative role of artificial intelligence (AI) in urban development is meticulously examined. This comprehensive research delineates the multifaceted ways in which AI-powered mobile applications can significantly enhance the efficiency, sustainability, and livability of urban environments, marking a pivotal step towards the realization of smart cities globally. Bayashot meticulously outlines the critical areas where AI-powered apps offer unprecedented advantages, including urban mobility, public safety, energy management, and environmental monitoring. By leveraging AI’s capabilities, these applications not only streamline city operations but also foster a more sustainable interaction between city dwellers and their environment. The paper emphasizes the importance of data-driven decision-making in urban planning, showcasing how AI analytics can predict and mitigate traffic congestion, optimize energy consumption, and enhance emergency response strategies. The author also explores the social implications of AI in urban settings, highlighting the potential for these technologies to bridge the gap between government entities and citizens. Through engaging case studies, Bayashot demonstrates how participatory governance models, enabled by AI apps, can promote transparency, accountability, and citizen engagement in urban management. A significant contribution of this research is its focus on the challenges and opportunities presented by the integration of AI into smart city ecosystems. Bayashot discusses the technical, ethical, and privacy concerns associated with AI applications, advocating for a balanced approach that ensures technological advancements do not come at the expense of civil liberties. The study calls for robust regulatory frameworks to govern the use of AI in public spaces, emphasizing the need for ethical AI practices that respect privacy and promote inclusivity. Furthermore, Bayashot’s research underscores the necessity of cross-disciplinary collaboration in the development and implementation of AI technologies in urban contexts. By bringing together experts from information technology, urban planning, environmental science, and social sciences, the author argues for a holistic approach to smart city development. This interdisciplinary strategy ensures that AI applications are not only technologically sound but also socially and environmentally responsible. The paper concludes with a visionary outlook on the future of smart cities, posited on the seamless integration of AI technologies. Bayashot envisions a world where AI-powered mobile apps not only facilitate smoother urban operations but also empower citizens to actively participate in the shaping of their urban environments. This research serves as a critical call to action for policymakers, technologists, and urban planners to embrace AI as a tool for creating more sustainable, efficient, and inclusive cities. By presenting a detailed analysis of the current state of AI in urban development, coupled with practical insights and forward-looking recommendations, “The Contribution of AI-powered Mobile Apps to Smart City Ecosystems” stands as a seminal work that is poised to inspire and guide the evolution of urban landscapes worldwide. Its comprehensive exploration of the subject matter, combined with its impactful conclusions, make it a must-read for anyone involved in the field of smart city development, AI technology, or urban policy-making.

Mechanism analysis of regulating Turing instability and Hopf bifurcation of malware propagation in mobile wireless sensor networks

A dynamical model is constructed to depict the spatial-temporal evolution of malware in mobile wireless sensor networks(MWSNs). Based on such a model, we design a hybrid control scheme combining parameter perturbation and state feedback to effectively manipulate the spatiotemporal dynamics of malware propagation. The hybrid control can not only suppress the Turing instability caused by diffusion factor but can also adjust the occurrence of Hopf bifurcation induced by time delay. Numerical simulation results show that the hybrid control strategy can efficiently manipulate the transmission dynamics to achieve our expected desired properties, thus reducing the harm of malware propagation to MWSNs.

RPL-Based IoT Networks under Decreased Rank Attack:Performance Analysis in Static and Mobile Environments

The RPL(IPv6 Routing Protocol for Low-Power and Lossy Networks)protocol is essential for efficient communi-cation within the Internet of Things(IoT)ecosystem.Despite its significance,RPL’s susceptibility to attacks remains a concern.This paper presents a comprehensive simulation-based analysis of the RPL protocol’s vulnerability to the decreased rank attack in both static andmobilenetwork environments.We employ the Random Direction Mobility Model(RDM)for mobile scenarios within the Cooja simulator.Our systematic evaluation focuses on critical performance metrics,including Packet Delivery Ratio(PDR),Average End to End Delay(AE2ED),throughput,Expected Transmission Count(ETX),and Average Power Consumption(APC).Our findings illuminate the disruptive impact of this attack on the routing hierarchy,resulting in decreased PDR and throughput,increased AE2ED,ETX,and APC.These results underscore the urgent need for robust security measures to protect RPL-based IoT networks.Furthermore,our study emphasizes the exacerbated impact of the attack in mobile scenarios,highlighting the evolving security requirements of IoT networks.

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

With the development of hardware devices and the upgrading of smartphones,a large number of users save privacy-related information in mobile devices,mainly smartphones,which puts forward higher demands on the protection of mobile users’privacy information.At present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of high precision and non-perception,but there are still shortcomings such as low data collection efficiency,untrustworthy participating nodes,and lack of practicability.To this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and federated learning to improve the data collection efficiency of mobile user authentication,reduce the probability of the model being bypassed by attackers,and reduce the overhead of data centralized processing and the risk of privacy leakage;(2)Use certificateless encryption to realize the authentication of the device to ensure the credibility of the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of mobile devices to improve the accuracy of model certification.The experimental results on the real environment dataset of 1513 people show that themethod proposed in this paper can effectively resist poisoning attacks while ensuring the accuracy and efficiency of mobile user authentication.

Mobile Crowdsourcing Task Allocation Based on Dynamic Self-Attention GANs

Crowdsourcing technology is widely recognized for its effectiveness in task scheduling and resource allocation.While traditional methods for task allocation can help reduce costs and improve efficiency,they may encounter challenges when dealing with abnormal data flow nodes,leading to decreased allocation accuracy and efficiency.To address these issues,this study proposes a novel two-part invalid detection task allocation framework.In the first step,an anomaly detection model is developed using a dynamic self-attentive GAN to identify anomalous data.Compared to the baseline method,the model achieves an approximately 4%increase in the F1 value on the public dataset.In the second step of the framework,task allocation modeling is performed using a twopart graph matching method.This phase introduces a P-queue KM algorithm that implements a more efficient optimization strategy.The allocation efficiency is improved by approximately 23.83%compared to the baseline method.Empirical results confirm the effectiveness of the proposed framework in detecting abnormal data nodes,enhancing allocation precision,and achieving efficient allocation.

Heuristic Expanding Disconnected Graph:A Rapid Path Planning Method for Mobile Robots

Existing mobile robots mostly use graph search algorithms for path planning,which suffer from relatively low planning efficiency owing to high redundancy and large computational complexity.Due to the limitations of the neighborhood search strategy,the robots could hardly obtain the most optimal global path.A global path planning algorithm,denoted as EDG*,is proposed by expanding nodes using a well-designed expanding disconnected graph operator(EDG)in this paper.Firstly,all obstacles are marked and their corners are located through the map pre-processing.Then,the EDG operator is designed to find points in non-obstruction areas to complete the rapid expansion of disconnected nodes.Finally,the EDG*heuristic iterative algorithm is proposed.It selects the candidate node through a specific valuation function and realizes the node expansion while avoiding collision with a minimum offset.Path planning experiments were conducted in a typical indoor environment and on the public dataset CSM.The result shows that the proposed EDG*reduced the planning time by more than 90%and total length of paths reduced by more than 4.6%.Compared to A*,Dijkstra and JPS,EDG*does not show an exponential explosion effect in map size.The EDG*showed better performance in terms of path smoothness,and collision avoidance.This shows that the EDG*algorithm proposed in this paper can improve the efficiency of path planning and enhance path quality.

Characteristics of long-distance mobile mRNAs from shoot to root in grafted plant species

Thousands of long-distance mobile mRNAs were identified from different grafting systems,based on high-throughput sequencing technology.Moreover,the long-distance delivery of RNAs was proved to involve multiple mechanisms.Here,we analyzed the homology,motif,and tRNA-like structure(TLS)of long-distance mobile mRNAs identified by RNA-seq as well as the RNA-binding protein(RBP)in nine grafting combinations including Arabidopsis thaliana,Vitis vinifera,Cucumis sativus,Citrullus lanatus,Nicotiana benthamiana,Malus domestica,Pyrus spp.,Glycine max and Phaseolus vulgaris.Although several mRNAs were found to be shared in herbaceous,woody,and related species,the vast majority of long-distance mobile mRNAs were species-specific.Four non-specific movement-related motifs were identified,while the TLS was not necessary for mRNA long distance mobility.In addition,we found that RBPs were conserved among herbaceous and woody plants as well as related species.This paper reports a further in-depth analysis of the endogenous mechanisms by which the species-specific transportable m RNAs were selected by bioinformatics,in order to provide insights for future research on long-distance mobile mRNAs.

Deep Reinforcement Learning-Based Task Offloading and Service Migrating Policies in Service Caching-Assisted Mobile Edge Computing

Emerging mobile edge computing(MEC)is considered a feasible solution for offloading the computation-intensive request tasks generated from mobile wireless equipment(MWE)with limited computational resources and energy.Due to the homogeneity of request tasks from one MWE during a longterm time period,it is vital to predeploy the particular service cachings required by the request tasks at the MEC server.In this paper,we model a service caching-assisted MEC framework that takes into account the constraint on the number of service cachings hosted by each edge server and the migration of request tasks from the current edge server to another edge server with service caching required by tasks.Furthermore,we propose a multiagent deep reinforcement learning-based computation offloading and task migrating decision-making scheme(MBOMS)to minimize the long-term average weighted cost.The proposed MBOMS can learn the near-optimal offloading and migrating decision-making policy by centralized training and decentralized execution.Systematic and comprehensive simulation results reveal that our proposed MBOMS can converge well after training and outperforms the other five baseline algorithms.

Mobile genetic elements facilitate the transmission of antibiotic resistance genes in multidrug-resistant Enterobacteriaceae from duck farms

Multidrug-resistant(MDR)Enterobacteriaceae critically threaten duck farming and public health.The phenotypes,genotypes,and associated mobile genetic elements(MGEs)of MDR Enterobacteriaceae isolated from 6 duck farms in Zhejiang Province,China,were investigated.A total of 215 isolates were identified as Escherichia coli(64.65%),Klebsiella pneumoniae(12.09%),Proteus mirabilis(10.23%),Salmonella(8.84%),and Enterobacter cloacae(4.19%).Meanwhile,all isolates were resistant to at least two antibiotics.Most isolates carried tet(A)(85.12%),blaTEM(78.60%)and sul1(67.44%)resistance genes.Gene co-occurrence analysis showed that the resistance genes were associated with IS26 and integrons.A conjugative IncFII plasmid pSDM004 containing all the above MGEs was detected in Proteus mirabilis isolate SDM004.This isolate was resistant to 18 antibiotics and carried the blaNDM-5 gene.MGEs,especially plasmids,are the primary antibiotic resistance gene transmission route in duck farms.These findings provide a theoretical basis for the rational use of antibiotics in farms which are substantial for evaluating public health and food safety.

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trainedCNN(PCNN)MobileNetV2 architecture combined with a SupportVectorMachine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy forMobileNetV2-SVM,InceptionV3,andMobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.

Online Learning-Based Offloading Decision and Resource Allocation in Mobile Edge Computing-Enabled Satellite-Terrestrial Networks

Mobile edge computing(MEC)-enabled satellite-terrestrial networks(STNs)can provide Internet of Things(IoT)devices with global computing services.Sometimes,the network state information is uncertain or unknown.To deal with this situation,we investigate online learning-based offloading decision and resource allocation in MEC-enabled STNs in this paper.The problem of minimizing the average sum task completion delay of all IoT devices over all time periods is formulated.We decompose this optimization problem into a task offloading decision problem and a computing resource allocation problem.A joint optimization scheme of offloading decision and resource allocation is then proposed,which consists of a task offloading decision algorithm based on the devices cooperation aided upper confidence bound(UCB)algorithm and a computing resource allocation algorithm based on the Lagrange multiplier method.Simulation results validate that the proposed scheme performs better than other baseline schemes.

Leveraging User-Generated Comments and Fused BiLSTM Models to Detect and Predict Issues with Mobile Apps

In the last decade, technical advancements and faster Internet speeds have also led to an increasing number ofmobile devices and users. Thus, all contributors to society, whether young or old members, can use these mobileapps. The use of these apps eases our daily lives, and all customers who need any type of service can accessit easily, comfortably, and efficiently through mobile apps. Particularly, Saudi Arabia greatly depends on digitalservices to assist people and visitors. Such mobile devices are used in organizing daily work schedules and services,particularly during two large occasions, Umrah and Hajj. However, pilgrims encounter mobile app issues such asslowness, conflict, unreliability, or user-unfriendliness. Pilgrims comment on these issues on mobile app platformsthrough reviews of their experiences with these digital services. Scholars have made several attempts to solve suchmobile issues by reporting bugs or non-functional requirements by utilizing user comments.However, solving suchissues is a great challenge, and the issues still exist. Therefore, this study aims to propose a hybrid deep learningmodel to classify and predict mobile app software issues encountered by millions of pilgrims during the Hajj andUmrah periods from the user perspective. Firstly, a dataset was constructed using user-generated comments fromrelevant mobile apps using natural language processing methods, including information extraction, the annotationprocess, and pre-processing steps, considering a multi-class classification problem. Then, several experimentswere conducted using common machine learning classifiers, Artificial Neural Networks (ANN), Long Short-TermMemory (LSTM), and Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) architectures, toexamine the performance of the proposed model. Results show 96% in F1-score and accuracy, and the proposedmodel outperformed the mentioned models.