A residual network-based framework for COVID-19 detection from CXR images

Neural Computing and Applications - In late 2019, a new Coronavirus disease (COVID-19) appeared in Wuhan, Hubei Province, China. The virus began to spread throughout many countries, affecting a...     

Graph convolutional network-based reinforcement learning for tasks offloading in multi-access edge computing

Multimedia Tools and Applications - To achieve high quality of service for computation-intensive applications, multi-access edge computing (MEC) is proposed for offloading tasks to MEC servers. The...     

Determinantal point process-based new radio unlicensed link scheduling for multi-access edge computing

World Wide Web - The combination of Multi-access Edge Computing (MEC) and New Radio Unlicensed (NR-U) can provide more powerful computing power and wireless access for the Internet of Things (IoT)....     

基于NFV MANO的边缘计算多种智能化部署方案研究

为了解决边缘计算业务部署时所需的管理编排组件与电信云中NFV MANO组件之间的高效协同等问题,首先,分析对比了两种主要部署方案中边缘计算与NFV的管理编排组件之间的职责分工与交互流程。其次,基于深度学习方法和模型分别给出了提高两种方案中电信云虚拟网元和基础设施和边缘计算应用之间的管理编排效率的解决方案。最后,对未来该领域需要关注的主要问题和方向进行了展望。     

Rule-based soft computing for edge detection

In this paper, we present a robust rule-based edge detection method. Although generalized edge detection approaches are effective for most images they often fail in others. Thus the goal of our method is to provide more reliable edge detection results that are effective in most images. We implement the proposed method as follows: (1) transform RGB images to YCbCr format, (2) apply Sobel mask in four edge directions (horizontal, vertical, diagonal, anti-diagonal), (3) apply a bi-directional mask in four edge directions (horizontal–diagonal, vertical–diagonal, horizontal–anti-diagonal, vertical–anti-diagonal), and (4) detect rule-based edges by calculating membership degrees. Simulation results demonstrate that the proposed method is effective in most given images. We used three benchmarks approaches (Canny edge mask, high-pass filter, and Sobel mask) to compare the subjective performance quality.     

A re-organizing biosurveillance framework based on fog and mobile edge computing

Multimedia Tools and Applications - Biological threats are becoming a serious security issue for many countries across the world. Effective biosurveillance systems can primarily support appropriate...     

A novel framework for rapid diagnosis of COVID-19 on computed tomography scans

Pattern Analysis and Applications - Since the emergence of COVID-19, thousands of people undergo chest X-ray and computed tomography scan for its screening on everyday basis. This has increased the...     

Scalable architecture for an automated surveillance system using edge computing

Over the past few years, the Internet of Things has gone from theoretical concept to our everyday living experience. The explosive growth of sensor streams also leads to a new paradigm of edge computing. In the surveillance system, edge-based automation is crucial to get fast response for fast data analytics among connected devices. In this paper, we propose an automated surveillance system to improve robustness and intelligence. Our scalable architecture is an alternative way of reducing the server resource and wireless network limitation.     

Deep reinforcement learning-based resource allocation and seamless handover in multi-access edge computing based on SDN

Knowledge and Information Systems - With the access devices that are densely deployed in multi-access edge computing environments, users frequently switch access devices when moving, which causes...     

A novel scheduling with multi-criteria for high-performance computing systems: an improved genetic algorithm-based approach

Engineering with Computers - Scheduling in high-performance computing systems is experiencing potential challenges in modern computing applications due to different application sizes, computational...     

A genetic algorithm-based solution methodology for modular design

Combinatorial optimization problems usually have a finite number of feasible solutions. However, the process of solving these types of problems can be a very long and tedious task. Moreover, the cost and time for getting accurate and acceptable results is usually quite large. As the complexity and size of these problems grow, the current methods for solving problems such as the scheduling problem or the classification problem have become obsolete, and the need for an efficient method that will ensure good solutions for these complicated problems has increased. This paper presents a genetic algorithm (GA)-based method used in the solution of a set of combinatorial optimization problems. A definition of a combinatorial optimization problem is first given. The definition is followed by an introduction to genetic algorithms and an explanation of their role in solving combinatorial optimization problems such as the traveling salesman problem. A heuristic GA is then developed and used as a tool for solving various combinatorial optimization problems such as the modular design problem. A modularity case study is used to test and measure the performance of the developed algorithm.     

基于EasyDL的新冠肺炎检测系统研究

通过EasyDL平台搭建基于CT影像的新冠肺炎检测系统,利用人工智能在图像识别上能够自动学习图像特征及区分图像特征之间差异的特点,来检测病人是否患有新冠肺炎.实验结果显示,新冠肺炎识别精确度为100.00％,感染性肺疾病识别精确度为98.06％,非感染性肺疾病识别精确度为93.64％,正常肺部识别精确度为98.03％....     

A framework for computing extrasentential references

We are concerned with developing a computational method for selecting possible antecedents of referring expressions over sentence boundaries. Our stratified model which uses a Λ-categorial language for meaning representation incorporates valuable features of Fregean-type semantics (a la Lewis, Montague, Partee, and others) along with features of situation semantics developed by Barwise and Perry. We consider a series of selected two-sentence stories which we use to illustrate referential interdependencies between sentences. We explain the conditions under which such dependencies arise, explain the conditions under which various translations can be performed, and formalize a set of rules which specify how to compute the reference. We restrict our discussion to two-sentence stories to avoid most of the problems inherent in where to look for the reference, that is, how to determine the proper antecedent. We restrict our considerations in this paper to situations where a reference, if it can be computed at all, has a unique antecedent. Thus we consider examples such as John wants to catch a fish. He (John) wants to eat it. and John interviewed a man. The man killed him (John). We then summarize the transformation which encompasses these rules and relate it to the stratified model. We discuss three aspects of this transformation that merit special attention from the computational viewpoint and summarize the contributions we have made. We also discuss the computational characteristics of the stratified model in general and present our ideas for a computer realization; there is no implementation of the _t"ratified model at this time.     

A framework for computing asset-sighting distance

Safety critical railway assets need to be visible from prescribed distances, ensuring safety. Traditional methods for measuring these sighting distances involve manual labour and disruption of rail services. Drawing parallels with other areas, efficiency and cost of such a task can be improved with automation. Hence, in this work, we describe a framework providing such automation, using image frames captured from video equipment as input. Any such framework needs to meet a set of associated challenges, including: determining the image position of decreasing sized assets as they appear farther from the observer, extracting three-dimensional positioning information (relative to motion) from two-dimensional video information and determining when an asset can no longer be seen (i.e. the sighting distance). Results show that the methods included in this framework perform better than a traditional method and information regarding asset-sighting distance is accurately computed.     

A survey of genetic algorithm-based face recognition

Traditionally, special objects can be detected and recognized by the template matching method, but the recognition speed has always been a problem. In addition, for recognition by a neural network, training the data is always time-consuming. In this article, the current method of genetic algorithm-based face recognition is summarized, and experiments for real-time use are described. The chromosomes generated by the genetic algorithm (GA) contain information (parameters) about the face, and genetic operators are used to detect and obtain the position of the face of interest in an image. Here, the parameters of the coordinates (x, y) of the center of the face, the rate of scale, and the angle of rotation θ, are encoded into the GA.     

A granular computing framework for self-organizing maps

When using granular computing for problem solving, one can focus on a specific level of understanding without looking at unwanted details of subsequent (more precise) levels. We present a granular computing framework for growing hierarchical self-organizing maps. This approach is ideal since the maps are arranged in a hierarchical manner and each is a complete abstraction of a pattern within data. The framework allows us to precisely define the connections between map levels. Formulating a neuron as a granule, the actions of granule construction and decomposition correspond to the growth and absorption of neurons in the previous model. In addition, we investigate the effects of updating granules with new information on both coarser and finer granules that have a derived relationship. Called bidirectional update propagation, the method ensures pattern consistency among data abstractions. An algorithm for the construction, decomposition, and updating of the granule-based self-organizing map is introduced. With examples, we demonstrate the effectiveness of this framework for abstracting patterns on many levels.     

A membrane computing framework for self-reconfigurable robots

Self-reconfigurable robots are built by modules which can move in relationship to each other, which allows the robot to change its physical form. Finding a sequence of module moves that reconfigures the robot from the initial configuration to the goal configuration is a hard task and many control algorithms have been proposed. In this paper, we present a novel method which combines a cluster-flow locomotion based on cellular automata together with a decentralized local representation of the spatial geometry based on membrane computing ideas. This new approach has been tested with computer simulations and real-world experiments performed with modular self-reconfigurable robots and represents a new point of view with respect other control methods found in the literature.

     

A general framework for computing block accesses

A physcial database system design should take account of skewed block access distributions, nonuniformly distributed attribute domains, and dependent attributes. In this paper we drive general formulas for the number of blocks accessed under these assumptions by considering a class of related occupancy problems. We then proceed to develop robust and accurate approximations for these formulas. We investigate three classes of approximation methods, respectively based on generating functions, Taylor series expansions, and majorization. These approximations are simple to use and more accurate than the cost estimate formulas generated by making uniformity and independence assumptions. Thus they are more representative of the actual database environment, and can be utilized by a query optimizer for better performance.     

A parallel computing framework for big data

Big data has received great attention in research and application. However, most of the current efforts focus on system and application to handle the challenges of “volume” and “velocity”, and not much has been done on the theoretical foundation and to handle the challenge of “variety”. Based on metric-space indexing and computationalcomplexity theory, we propose a parallel computing framework for big data. This framework consists of three components, i.e., universal representation of big data by abstracting various data types into metric space, partitioning of big data based on pair-wise distances in metric space, and parallel computing of big data with the NC-class computing theory.     

A low-latency computing framework for time-evolving graphs

The Journal of Supercomputing - The demand to deliver fast responses in processing time-evolving graphs is higher than ever before in a large number of big data applications. This problem promotes...