Aims and scope

Mobile Networks and Applications' technical scope covers mobility solutions that provide communication technologies and mobile services, which enables users to access resources and share information freely, anytime anywhere. The emerging symbiosis of wireless communication, the ever more powerful mobile devices, with the back-end resources of the cloud, making the user fully location independent.

The journal addresses the convergence of mobility, computing and information organization, services and management. In approving Special Issues, the Journal places an equal emphasis on the various areas of nomadic computing, data management, related software and hardware technologies, and mobile user services, alongside more `classical' topics in wireless and mobile networking. The journal documents practical and theoretical results which make a fundamental contribution.

Special Issue on Machine Learning for Hybrid Social Information
Submission Date: 2024-07-31

Social computing, such as hybrid social information (HSI) processing, has acted as an important research domain in science and technology today. It has used in all aspects of society today, such as mobile education, mobile medical, smart community, etc. Today, there are more remaining issues are waiting for solving in this domain. For example, how to detect or recognize people behavior with conflict modals, how to detect community in social network with uncertain graph structure.. All such entire problems need our more attention to solve. Therefore, more effective thoughts and machine learning (ML) methods are needed to enhance theory and application of HSI processing. Moreover, the use of sophisticated and robust psychological and cognitive scientific methods are important in HSI processing, and emerging methods which can improve the efficiency of this domain are also encouraged in this issue .

Special Issue on Machine Learning in Intrusions Detection and Attacks for Smart IoT Ecosystem
Submission Date: 2024-08-30

A smart IoT device could be a healthcare device, a wearable, an industrial robot, a television monitor, or a smart city infrastructure. IoT has a wide range of applications. It is estimated that almost 87 percent of individuals still do not comprehend what the IoT actually means, despite the fact that it seems to be a more industrial term. Detecting these assaults while still meeting IoT requirements requires machine learning-based intrusion detection. Our daily lives are becoming increasingly connected by the Internet of Things, as physical objects are being connected to e-services. Machine Learning (ML) has shown great promise in enhancing the security of the Internet of Things (IoT) ecosystem by aiding in the detection of intrusions and attacks. IoT networks, with their multitude of connected devices, generate massive volumes of data, and manually analyzing these to identify potential security incidents is a formidable task. ML algorithms, by automatically learning patterns and anomalies in the data, can greatly aid in this endeavor. Smartphones are expected to be replaced by IoT devices with access to the most current complex information, including confidential information. Increasing attack numbers will result in increasing attack predictor variables. Providing network security for possible attacks in health care systems will be another major challenge of IoT in the industry. Integrated Defense Systems (IDS) are technologies that are used to protect networks. IoT anomaly and attack detection is a growing concern in the IoT ecosystem. With the increased use of IoT infrastructure across all domains, threats and attacks against IoT infrastructure are on the rise. Due to the addition of multiple protocols, primarily from IoT, thousands of assaults are known to occur regularly. Most of these attacks repeat previously identified cyberattacks in minor variations. Even advanced techniques like cryptography have a hard time detecting even tiny mutations in threats over time. As a result of theuccess of ML in numerous big data sectors, cybersecurity has gained attention. While there are significant challenges to employing machine learning for intrusion detection in the IoT ecosystem, the benefits, including improved detection capabilities and automation, make it a worthwhile investment. The key to successful implementation lies in the careful selection of suitable algorithms, attention to privacy and resource constraints, and the integration of emerging technologies.

Special Issue on Intelligent Regulation and Governance of Digital Services
Submission Date: 2024-09-10

Overview: The digital economy has become an important engine driving economic growth and a significant breakthrough in industrial upgrading. In the digital economy, digital services, supported by information technologies, such as the Internet, the Internet of Things, and big data, form an efficient connection between service suppliers and service consumers in various sectors of modern service industry. It has changed the traditional supply-demand model, cooperative division of labors, as well as the way of value creation and distribution, and has grown into a new economic model. While supporting economic growth, digital services should also undertake social responsibilities. Over the past few years, the rapid growth of digital services and various platforms has led to a series of problems caused by regulatory gaps, including internet financial fraud, counterfeit and shoddy products in e-commerce, data misuse and infringement of user privacy, dissemination of illegal content, unfairness and potential discrimination caused by AI algorithms and so on. Effective governance of digital services is urgently needed. Research on the regulation and governance of digital services should be conducted, to form a stable, orderly, and vibrant governance system for digital services and cultivate a healthy governance ecosystem. Therefore, this issue aims to investigate the research related to the intelligent regulation and governance of digital services.

Special Issue on Mobile Educational Intelligent System
Submission Date: 2024-09-15

Today, the rapid improvement of artificial intelligence brings rapid change in Education area, especially mobile and online education. Mobile educational intelligent systems (MEISs), such as Mobile/Online Deep Neural Network (DNN), in educational quality measurement, automatic evaluation of students and classroom, resourse recommendation are all showing vigorous vitality. Therefore, how to ensure the quality of AI assisted system in education, how to ensure the reliablity and robustness, how to construct an effective system for mobile and distanced education, need to gather high-level professionals of education technology and information technology to conduct in-depth cooperation and interdisciplinary cross research.Indeed, more effective theories and applications are needed to solve in this area, and this special issue aims to provide an opportunity for researchers to publish their gifted theoretical and technological studies of emerging theory with mobile educational intelligent system with high reliablity, and their novel engineering applications within this domain. Surveys with excellent quality are also welcome.

Special Issue on Resource Efficient Deep Learning for Computer Vision Applications
Submission Date: 2024-10-30

Despite the success of deep learning models in many areas, they have been emerging at the cost of increasingly large scale of models, which require powerful computing and data resources. However, as a common situation in practical computer vision applications, especially on the edge side such as mobile applications, resource limitations are something that must be considered, such as limited computing power, high real-time requirement, and insufficient data. Thus, resource-constrained deep learning theories, methods and applications should receive enough attention. There exist several different directions towards making deep learning efficient for computer vision, thereby leading to a reduction in the required data set size, computational memory or the associated training and inference time. Most research that exists focuses on making deep learning methods efficient, however, the resource associated with real-world mobile devices can vary drastically, and a method termed efficient for a certain choice of resource budgets might be completely inefficient for a different one. This special issue focuses on budget-aware model training and inference, thereby maximally utilizing the available resources of data and computing.

Special Issue on Cloud-Edge Intelligence Collaborative Computing: Software, Communication and Human
Submission Date: 2024-12-25

With the development of 5G communications and the Internet of Things, IoT devices are becoming the primary smart devices for billions of users worldwide. It will result in amount of data generated by billions of sensors and devices. It is of great significance to mine the characteristics and values of massive data efficiently and safely, for the practical industrial scenarios, such as finance, medicine, natural language processing, etc. Distributed machine learning technology has become a key method to efficiently process and explore the value of massive data, as it can make use of the computing capacity of multiple computing devices and has the self-learning, pre-training and fast reasoning abilities. Recent advancement in computational power at the cloud server and edge devices, have made it possible to execute machine learning models by the cooperation of cloud server and edge devices. However, the research of distributed machine learning on Cloud-Edge computing is still in its early stages and there are still many problems to be solved. For instance, how to manage and schedule cloud-edge heterogeneous resources? How to ensure data security and efficient transmission with limited network? How to conduct distributed high-performance training and inference? Therefore, distributed training and inference system or framework, data security, network transmission, resource management and scheduling, and algorithms for AI in cloud-edge computing should be researched in depth, and needs a special communication for the recent advances of the next generation distributed machine learning system. The focus for this special issue is on advances in Cloud-Edge Intelligence Collaborative Computing. Researchers from academic fields and industries worldwide are encouraged to submit high quality unpublished original research articles as well as review articles in broad areas relevant to theories, technologies, and emerging applications.