Computer Science and Technology is an international, peer-reviewed open access journal dedicated to advancing research the field of computer science and technology. The journal provides a rapid publication process to ensure wide dissemination of high-quality articles to scientists, professionals, and interested individuals worldwide. Our goal is to serve as an efficient, reliable, and trusted platform for scholars and readers, publishing cutting-edge research in the field.
Abstract: Mobile edge computing (MEC) is an emerging technology that extends cloud computing to the edge of the network. It offloads computing intensive tasks to the edge server to solve the problem of insufficient computing power and resource of the terminal device, meets the low energy consumption and low latency requirements of the mobile user for application task computing, and greatly releases the pressure of the cloud center. Cloud-edge integration architecture has become a trend. How to perform optimal offload scheduling for terminal tasks has always been one of the key issue in the field of MEC research. This paper reviews the research directions and achievements of task offloading technology in today’s cloud-edge environment. First, the development status of MEC environment and task offloading technology are introduced, and the concepts and applications of classic schemes such as heuristic algorithm, metaheuristic algorithm, and reinforcement learning are elaborated. Based on the mainstream solutions in the research literature, two types of task offloading solutions are summarized: traditional task offloading solutions based on algorithm optimization and interactive task offloading solutions based on reinforcement learning. Second, the research literature on the two mainstream directions mentioned above is summarized and organized from aspects such as problem constraints, optimization objectives, and contributions made. Meanwhile, schemes are compared through the classic algorithms and innovations they used. Finally, the current challenges and future research objectives in this field are summarized to provide reference and help for the follow-up research.Abstract: Mobile edge computing (MEC) is an emerging technology that extends cloud computing to the edge of the network. It offloads computing intensive tasks to the edge server to solve the problem of insufficient computing power and resource of the terminal device, meets the low energy consumption and low latency requirements of the mobile user for applica...Learn More
Abstract: Big data technology is widely used in various fields, making the problem of digital economy feature recognition become a research hotspot. Traditional data analysis cannot solve the problem of feature recognition in the digital economy, and the feature recognition ability is weak. Therefore, this paper proposes an algorithm of data mining technology combined with Big data to build a judgment model for feature recognition. First of all, traditional data analysis methods are used to classify Big data, and Partition of a set is carried out according to characteristics to reduce the processing complexity of data with different characteristics and weaken the impact of multi-dimensional digital economic information on feature recognition. Then, traditional data analysis methods classify the data to form sub feature recognition domains of different dimensions, and make comprehensive judgments on sub feature recognition of different dimensions. With the help of MATLAB simulation, the accuracy and calculation time of the algorithm built in this paper are better than traditional data analysis methods and Big data mining technology under the condition of a certain recognition level. Under the conditions of initial feature recognition standards and expected effects, the algorithm constructed in this article can comprehensively judge feature recognition, which meets the requirements of digital economy feature recognition.Abstract: Big data technology is widely used in various fields, making the problem of digital economy feature recognition become a research hotspot. Traditional data analysis cannot solve the problem of feature recognition in the digital economy, and the feature recognition ability is weak. Therefore, this paper proposes an algorithm of data mining technolog...Learn More
Abstract: Images captured in low-light not only suffer from low visibility but also result in poor quality, which may significantly degrade the performance of multimedia and computer vision tasks. A large number of techniques have been proposed to enhance the low-light images. The majority of the low-light techniques use sRGB datasets and do not perform well in extreme low-light image enhancement. A few techniques use the raw data for extreme low-light enhancement but the output images suffer color correction and details loss. In this paper, to address this color correction problem a new dual MultiResUnet based network is proposed. In the proposed approach, raw and sRGB data is used as input, whereas sRGB images are generated from raw data by using the traditional pipeline. One branch of the dual CNN learns the structural details from raw data and the other branch learns a spatially variant color transformation matrix from sRGB data for color correction. The final result is produced by applying the learned color transformation matrix to the structural information produced by the first branch. The experimental results demonstrate that the proposed approach performs better and achieved well-adjusted color information for extremely low-light images.Abstract: Images captured in low-light not only suffer from low visibility but also result in poor quality, which may significantly degrade the performance of multimedia and computer vision tasks. A large number of techniques have been proposed to enhance the low-light images. The majority of the low-light techniques use sRGB datasets and do not perform well...Learn More
Abstract: Intelligence GIS service is of vital importance in industry and everyday life. Semantic Web technologies, such as ontology, is the most important tool in accomplish an intelligence GIS services, capable of deal with the heterogeneity of data from different sources and interoperability between these sources. This paper proposes a prototype system that can leverage from existing ontology engineering technologies, build a prototype intelligent GIS service for the campus of Nanjing University of Science and Technology. A formal ontology is built, an open SPARQL endpoint is provided as a web service. Evaluation experiments are carried out using real-life data from campus geo locations, smell, sound, food, and blossom. It is evident from the evaluation results that the accuracy of the queries are 100%, average time overhead is less than 5 ms/query.Abstract: Intelligence GIS service is of vital importance in industry and everyday life. Semantic Web technologies, such as ontology, is the most important tool in accomplish an intelligence GIS services, capable of deal with the heterogeneity of data from different sources and interoperability between these sources. This paper proposes a prototype system th...Learn More
Abstract: Multidimensional knapsack problem is a classical combinatorial optimization problem, the goal is to find a set of optimal options to satisfy all the constraints. The traditional algorithms for solving multidimensional knapsack problems generally have some disadvantages, such as slow computation speed and exponential increase of computation with the increase of problem dimension. To solve these problems, a QUBO (quadratic unconstrained binary optimization) model is proposed, and the multidimensional knapsack problem is expressed as a quadratic unconstrained binary optimization problem. Binary variables are used to represent the objective function of the multidimensional knapsack problem. The constraints are added to the objective function in the form of quadratic terms by means of penalty terms. The objective function is further transformed into QUBO form. The model is created by PyQUBO, an open source Python library, and solved by quantum annealing algorithm on D-Wave platform. The results show that the QUBO model has a strong ability of mathematical expression, which makes the problem more structured, and is suitable for large-scale problems, dealing with multidimensional knapsack problems with a lot of variables and constraints.Abstract: Multidimensional knapsack problem is a classical combinatorial optimization problem, the goal is to find a set of optimal options to satisfy all the constraints. The traditional algorithms for solving multidimensional knapsack problems generally have some disadvantages, such as slow computation speed and exponential increase of computation with the...Learn More
