Efficient Context-Aware Edge Computing Algorithm in Mobile Cloud

Mobile edge computing enables the execution of compute-intensive applications, e.g. deep learning applications, on the end devices with limited computation resources. However, the deep learning applications bring the performance bottleneck in mobile edge computing, due to the movements of a large amount of data incurred by the large number of layers and millions of weights. In this paper, the computing model for parallel deep learning applications in mobile edge computing is proposed, by considering the occupancy allocation of processors, cost of context switch, and multi-processors in edge server and remote cloud. The problem of minimizing the completion time for deep learning applications is formulated, and the NP-hardness of the problem is proved. To solve the problem, an integrated algorithm by merging and scheduling is proposed. Moreover, a real-world distributed platform is developed for evaluating the proposed algorithm. Experimental results show that, the completion time of deep learning application for the proposed algorithm is decreased by 63% and 75%, respectively, without extra control costs, compared with the existing algorithms.

Optical Grid that provides a way to integrate the geographical distributed resources for large- scale grid applications. This paper mainly focuses on the task scheduling issue in Optical Grid and proposes two task scheduling algorithms to mini-mize the total time or scheduling length required for a given task. A simulated optical grid has been addressed to demon-strate the effectiveness of the schedulin g approach. The performance tests and anal ysis of the two algorithms are investi-gated to show the effect of the routing policy on the schedulin g length. A more flexible policy is able to further improve scheduling length. Keywords: Optical Grid, Task Scheduling Algorithm, Communication Contention I INTRODUCTION Distributed computing, also known as computational Grid, is a technology that makes it possible to utilize the geographi-cal distributed computational resources to solve the intensive computation of large-scale data. Most Grid systems were built over the IP packet switched networks in the past. In the situation when some data-intensive Grid applications re-quire moving Gigabytes or even larger of data, the low speed of the network becomes the bottleneck of Grid system, which could not allow the remote resources to be used efficiently. Nowadays the optical network with Synchronous Digital Hierarchy (SDH), Wavelength-D ivision Multiplexing (WDM), and Automa tic Switched Optical Network (ASON) infrastructure can provide a much larger amount of bandwidth than the electronic network, such as IP packet switched network. Therefore, it is significant to use the optical network as the network infrastructure of the computational Grid. We refer to this infrastructure as Optical Grid, which employs optical network to interconnect grid computational re-sources (e.g. supercomputers, computer clusters, storage and display devices) with dynamically provisioned lightpaths [1]. It has been realized that task scheduling is a fundamental issue in achieving high performance in grid environments [6]. Task scheduling aims to optimize the overall performance of a system, e.g., minimizing the average job response time and maximizing the number of jobs exec uted in certain period of time. Optical grid task scheduling is quite different from classic grid task scheduling model. In Optical Grid system, we can treat the optical network as a kind of resource, the scheduling algorithm in Optical Grid system should schedule the tasks to appropriate resources as we ll as scheduling the communications between tasks to appropriate optical links. The objec-tive of task scheduling is to minimize the completion time (we called it as scheduling length or make span ) of an appli-cation. Usually, this problem is modeled and solved under several assumptions. Unless the assumptions are simplified enough, the problem has been proven to be NP-complete [8]. Therefore, many heuristic algorithms have been proposed. But these heuristics either are based on the assumption that the processors are fully connected, or just don’t take into ac-count the optical network’s characters, es pecially the characters of WDM optical network. While actually, in the Optical Grid system, the computational resources are more likely not fully connected, and the communication contention is an important factor that affects the completion time of a Grid application. Thus, a new heuris tic algorithm that can schedule tasks and also the communications are needed. In this paper, we mainly focus on the static scheduling problem, which means the character of the Grid applica tion, including the task execution times, task dependencies, task communications and synchronization are known a priori.

Few-shot learning aims to obtain a better deep learning model through training with a smaller amount of data. In recent years, with the development and application of deep learning, deep learning has faced the problem of few-shot in many scenarios. Therefore, the study of few-shot learning will promote the application and deployment of deep learning in the industrial field. First of all, this survey specifically introduces two few-shot learning implementation methods: based on data augmentation and based on transfer learning. Then, this survey lists actual cases to illustrate the application of few-shot learning in industry. One case is about Few-shot parts surface defect detection based on metric learning. Another case is about poultry egg detection in few-shot based on meta learning. Finally, this survey summarizes the research achievements and research value of few-shot learning. Survey summarizes the problems and challenges faced by few-shot learning and the future development direction of few-shot learning.KeywordsFew-shot learningData augmentationTransfer learningMetric learningMeta learning

With the rapid development of high-throughput sequencing technology, massive microbial data has been accumulated. The understanding of the microbial data could help us to find the relationships between microbes and diseases. However, due to the high dimensionality, sparseness, and complexity of the data, traditional machine learning methods have insufficient learning and representational ability. Meanwhile, the rise of deep learning enables us to deal with these complex problems effectively. In this survey, we introduce the application of machine learning in microbial data analysis and focus on microbial classification and feature selection tasks. In particular, we discuss the current application and challenges of deep learning in microbial studies. Based on these discussions, we recommend that before using deep learning to conduct microbiome-wide association studies, it is essential to consider prior knowledge such as phylogeny, which would improve the accuracy and interpretability of the model.

Abstract: Geospatial intelligence (GEOINT) is transforming the way organizations analyze, visualize, and interpret spatial data to drive decision-making in critical domains such as urban planning, disaster management, defense, and environmental monitoring. This chapter explores the integration of ArcGIS and Python for advanced spatial analytics, providing a comprehensive framework for automating geospatial workflows, enhancing big data processing, and applying AI-driven modeling techniques. Key topics include spatial data management, network and topological analysis, machine learning for geospatial intelligence, and cloud-based GIS solutions. With advancements in real-time geospatial analytics, edge computing, and blockchain for geospatial security, this chapter provides cutting-edge methodologies for harnessing Python's geospatial libraries alongside ArcGIS to build scalable, automated, and AI-powered GIS solutions. The application of deep learning in satellite imagery classification, predictive spatial modeling, and geospatial intelligence automation positions this integration as a game-changer in modern geospatial decision-making. Keywords: Geospatial intelligence, ArcGIS, Python, spatial analytics, AI-driven GIS, machine learning, remote sensing, geospatial big data, network analysis, predictive modeling, geostatistical analysis, cloud GIS, edge computing, digital twins, GIS automation, real-time geospatial analytics, blockchain GIS, urban planning, disaster management, spatial optimization, geospatial cybersecurity, deep learning for GIS.

Building a new power system with new energy as the main body is one of the most important measures to achieve “carbon peak and carbon neutral” in China, which also puts forward higher requirements on the data analysis and processing capacity of the current power system. In recent years, artificial intelligence algorithms represented by deep learning have provided strong support for the realization and development of new energy power system. The paper summarizes the basic characteristics of deep learning algorithm and its five mainstream models. From the aspects of image recognition, power load prediction, fault diagnosis and system optimization scheduling, the application of deep learning in new energy power system is deeply analyzed. The application prospect of deep learning in new energy power system is prospected in order to provide reference for the research and construction of new power system.

A scheduling algorithm based on reinforcement learning for heterogeneous environments

We consider the problem of dependent task offloading in edge computing with unknown system-side information (e.g., edge transmission rate and computation resources). In this problem, tasks have complicated dependency relationships and have no prior knowledge of system-side information to assist offloading decision-making. Although existing learning-based approaches can help to address unknown system-side information, the impact of inherent task dependency on such approaches has not been formally explored. To bridge the gap, we first use a breadth-first-search (BFS) method to decouple task dependency, and then leverage the Lyapunov optimization technique to transfer the long-term offloading problem to an online optimization problem. Furthermore, we employ the multi-armed bandit (MAB) theory to develop the <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</u> nline <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</u> earning-based <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</u> ependent <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">t</u> ask <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</u> ffloading algorithm, called OL-DTO. The algorithm can address the unknown system-side information and is augmented with task dependency awareness. We present a rigorous theoretical analysis to evaluate the performance of this algorithm in terms of application delay and UD energy consumption. Our extensive experimental results demonstrate that the OL-DTO algorithm significantly reduces application delay while satisfying the long-term energy budget constraint of the UD.

Dependent task offloading mechanism for cloud–edge-device collaboration

In the context of Edge Computing (EC) and Internet of Things (IoT), numerous tasks are offloaded from mobile users and sensor devices to edge nodes for further processing to reduce delay and solve the problem of insufficient local computation resources. These tasks can be mainly divided into delay-sensitive and computation-oriented tasks. The former tasks depend on the service provided by the container, while the latter tasks are submitted as a batch with task dependencies. Considering the heterogeneity of edge nodes, joint task scheduling can effectively improve resource utilization. However, relatively few researches consider the different characteristics of tasks like container constraints and task dependencies in joint task scheduling in EC. In order to fill in this gap, we propose a deep deterministic policy gradient (DDPG) based online joint task scheduling (OJTS) algorithm. Specifically, 1) We first model the problem of joint scheduling of delay-sensitive and computation-oriented tasks in resource-constrained EC scenario with the goals of maximizing system utility and minimizing system cost (weighted sum of the number and duration of unfinished tasks). 2) Then, we propose a deep reinforcement learning (DRL) algorithm to solve the above problem and make appropriate adjustments to the original network structure according to the scheduling decision. 3) Through validation on real-world trace, OJTS can improve the system utility by 26.0% and overall reward by 51.2% compared with baselines and meet real-time decision-making requirements.

Deep Learning (DL) applications in the Internet of Things (IoT) have garnered significant attention, with numerous studies exploring various models and implementations. Concurrently, the emerging field of the Internet of Behaviors (IoB) has captured broad interest, extending the capabilities of IoT through the synergy of DL. This transformative approach presents novel possibilities across diverse domains (e.g. healthcare, business, education, and insurance). In this survey, we uniquely contribute by elucidating the synergistic potential of integrating IoB with DL. Our literature review provides a state-of-the-art analysis of DL implementations within the IoB ecosystem, highlighting architectures, features, and advantages over traditional machine learning methods. Through a meticulous examination of findings, we reveal specific insights gained from the survey, and we discuss issues, challenges, and future research directions in applying DL in IoB applications. Our survey stands as a testament to achievements in this dynamic intersection and serves as a call to action for exploring uncharted territories.

In today’s complex and ever-changing world, Supply Chain Management (SCM) is increasingly becoming a cornerstone to any company to reckon with in this global era for all industries. The rapidly growing interest in the application of Deep Learning (a class of machine learning algorithms) in SCM, has urged the need for an up-to-date systematic review on the research development. The main purpose of this study is to provide a comprehensive vision by reviewing a set of 43 papers about applications of Deep Learning (DL) methods to the SCM, as well as the trends, perspectives, and potential research gaps. This review uses content analysis to answer three research questions namely: 1- What SCM problems have been solved by the use of DL techniques? 2- What DL algorithms have been used to solve these problems? 3- What alternative algorithms have been used to tackle the same problems? And do DL outperform these methods and through which evaluation metrics? This review also responds to this call by developing a conceptual framework in a value-adding perspective that provides a full picture of areas on where and how DL can be applied within the SCM context. This makes it easier to identify potential applications to corporations, in addition to potential future research areas to science. It might also provide businesses a competitive advantage over their competitors by allowing them to add value to their data by analyzing it quickly and precisely.

This paper focuses on the theme of the application of deep learning in the field of basketball sports, using research methods such as literature research, video analysis, comparative research, and mathematical statistics to explore deep learning in real‐time analysis of basketball sports data. The basketball posture action recognition and analysis system proposed for basketball movement is composed of two parts serially. The first part is based on the bottom‐up posture estimation method to locate the joint points and is used to extract the posture sequence of the target in the video. The second part is the analysis and research of the action recognition algorithm based on the convolution of the space‐time graph. According to the extracted posture sequence, the basketball action of the set classification is recognized. In order to obtain more accurate and three‐dimensional information, a multitraining target method can be used in training; that is, multiple indicators can be detected and feedback is provided at the same time to correct player errors in time; the other is an auxiliary method, which is compared with ordinary training. The method can actively correct technical movements, train players to form muscle memory, and improve their abilities. Through the research of this article, it provides a theoretical basis for promoting the application of deep learning in the field of basketball and also provides a theoretical reference for the wider application of deep learning in the field of sports. At the same time, the designed real‐time analysis system of basketball data also provides more actual reference values for coaches and athletes.

Artificial Intelligence has accelerated research on autonomous vehicles in the past few years. However, it is not easy to achieve full autonomy on account of the essence of a complex and dynamic driving environment. Fortunately, the rapid development of deep learning has made great progress, which can be used to solve problems about image processing in the autonomous vehicles field. This paper offers a comprehensive review of the recent deep-learning-based image processing methods that leverage data detected. The paper gives a brief overview of deep learning, discussing basic concepts and principles. We also discuss the common models and architectures of deep learning and introduce typical deep learning techniques: convolutional neural networks (CNN). Furthermore, we divided the application of deep learning in the autonomous vehicles into three parts and discuss them respectively. Finally, we review the disadvantages of the application of deep learning in image processing for autonomous vehicles. On this basis, we put forward our insights and point out promising research directions.

The application of artificial intelligence technology, especially Deep Learning, in the world of education is increasingly developing and has the potential to improve students' cognitive abilities. This study aims to analyze the effect of the application of Deep Learning on improving students' cognitive abilities in the Independent Curriculum in Yogyakarta High Schools. This study analyzes the effect of the application of Deep Learning technology on improving students' cognitive abilities in the Independent Curriculum in Yogyakarta High Schools. Using an interpretive quantitative method with simple linear regression, the results show a positive relationship between the application of Deep Learning and students' cognitive development with a contribution of 34.2%. The regression equation Y = 33.136 + 1.241X shows that the higher the application of Deep Learning, the higher the students' cognitive abilities. Although effective, challenges in infrastructure, teacher readiness, and student readiness still need to be overcome. With the support of the government and schools, this technology can be optimized to support more interactive, adaptive, and data analysis-based learning, thereby increasing the effectiveness of education and achieving the goals of the Independent Curriculum.