Wei Liu

Wuhan Institute of Technology · Computer school

Efficiently detecting objects in the complex background at night with low illumination remains a challenge for image processing. To address this issue, this paper proposes LiteCortexNet, a lightweight deep learning object detection model inspired by the visual cortex. The model performs intrinsic image decomposition end-to-end to obtain the illumin...

The current power distribution Internet of Things (PDIoT) lacks security protection terminals and techniques. Network security has a large exposure surface that can be attacked from multiple paths. In addition, there are many network security vulnerabilities and weak security protection capabilities of power distribution Internet of Things terminal...

Nearest Neighbor method (KNN) is a typical method to solve the problem of automatic image annotation (AIA). However, traditional AIA methods based on KNN only consider the relationships among images and labels. In this paper, we propose an improved KNN image annotation method based on a tag semantic extension model (TSEM). Our approach uses the con...

The daily railway operation and maintenance suffers from a severe problem of the loss of railway tools. Aiming at the problem, an automatic counting method of railway tools based on deep learning is proposed. Our method is based on toolkit images obtained before a toolkit is delivered to a worker and after it is returned. By recognizing and compari...

This article addresses the challenge of collective decision making among the smart components in medical waste transportation. We search for an optimized alternative capability of an agent to generate a commitment according to two capabilities belonging to heterogeneous agents under ever-changing context conditions. we propose a Goal-Capability-Com...

The adaptive system requires each agent to provide effective adaptive scheme in runtime according to dynamic changes in the environment. This paper offers an Adaptive Graph Planning Protocol (AGPP) that uses the Goal-Capability-Commitment (GCC) meta-model to dynamically reconstruct. The method uses the concept of capability to represent the executa...

Collective adaptive systems (CAS) have been attracting increasing attention in the field of artificial intelligence (AI), in which collaboration of agents plays a key role. These systems aim to accomplish a certain goal though collaborating between a variety of agents with different tasks, which adapt to changes of environment to be of adaptability...

Forming an effective collaboration community is the key to any successful collaborative process. However, community formation approaches for the closed multi-agent systems may be not fit the need of collective adaptive system comprising multi-agent in open environment. We propose a context aware community formation approach (CFAgentColla) for agent...

The BDI model has solved the problem of reasoning and decision-making of agents in a particular environment by procedure reasoning. But in uncertain environment which the context is unknown the BDI model is not applicable, because in BDI model the context must be matched in plan library. To address this issue, in this paper we propose a method exte...

Automatic protocol mining is a promising approach for inferring accurate and complete API protocols. However, just as with any data-mining technique, this approach requires sufficient training data (object usage scenarios). Existing approaches resolve the problem by analyzing more programs, which may cause significant runtime overhead. In this pape...

Autonomous agents collaboration at run-time is a fundamental part of multi-agent oriented adaptive collaboration systems (ACSs) when an agent cannot accomplish a task by itself under changing environment. Such collaborations are usually regulated by commitment protocols, which are typically defined at design-time. However, agent commitments among t...

Agent commitments as a protocol among the participants to melding collaborative patterns typically defined at design-time may not fit the need of collective adaptive systems (CASs). In this paper we propose a Goal-Capability-Commitment (GCC) based context aware collaborative adaptive diagnosis and compensation approach. First, we give a formal and...

Service-oriented self-adaptation software (SoSAS) utilizes services as fundamental elements for developing applications that have the capability to autonomously modify their behavior at run-time in response to changes in their environment. While a few techniques have been developed to support the modeling and analysis of requirements for self-adapt...

Service oriented computing utilizes services as fundamental elements for developing applications that have the capability to autonomously modify their behavior at run-time in response to the changes in their environment, which is especially suitable for designing and developing self-adaptive software. While uncertainty induced by randomness environ...

Service-oriented software utilizes services as fundamental elements for developing applications that have the capability to autonomously modify their behavior at run-time in response to changes in their environment. While a few techniques have been developed to support the modeling and analysis of requirements for self-adaptive systems, limited att...

While a few techniques have been developed to support the modeling and analysis of requirements for self-adaptive systems, limited attention has been paid to the description of service requirements and uncertainty in requirements of SoSAS. In this paper, we discussed the characteristics of service-oriented self-adaptation software. A context snapsh...

Service-oriented computing (SOC) is the computing paradigm that utilizes services as fundamental elements for developing applications. The modeling and analysis of services-oriented software requirements is one of important study contents in SOC. Owing to frequent changes of individual or collective requirements, continuous evolution of system func...

Service-oriented computing (SOC) is a kind of computing paradigm that utilizes services as fundamental elements for developing applications. In study domain of SOC, modeling and analysis of services-oriented software requirements is an important research direction. Because of frequent changes of individual or collective requirements and continuous...

In this paper, we consider a birth–death process with generator $\mathcal{L}$ and reversible invariant probability π. Given an increasing function ρ and the associated Lipschitz norm ‖⋅‖Lip(ρ), we find an explicit formula for $\|(-\mathcal{L})^{-1}\|_{\operatorname {Lip}(\rho)}$ . As a typical application, with spectral theory, we revisit one varia...

Networked software (NS) is a kind of online software produced by linking information resources on the Web with the help of intercommunication and cooperation between networks and users. Due to the complexity of NS, requirements engineering is now emerging as a critical issue in it. In the user-driven and networked-resources oriented environment, ho...

Networked software (NS) is a service-oriented software application that is accessed via human-network interaction equipments. Owing to the characteristics(such as uncertainty, incompleteness, and evolution) of NS requirements, the requirements engineering face challenges in requirements elicitation. This paper proposes a requirements elicitation ap...

Requirement process for networked software is a human-web interaction. Requirement elicitation and analysis are emerging as a critical issue for supporting requirement modeling, as these are designed to satisfy diverse stakeholder service needs and evolution network environment. This paper proposed a heavyweight semantic inducement (HSI) approach f...

Networked software is a complex software system deployed on network environment. Web services are the essential components of Networked software, and reuse in this granularity is especially significant. In this paper, we propose a domain modeling framework for Networked software named O-RGPS, which is a layered network including five layers. O-RGPS...

Reusable software component repository (SCR) and retrieval management of components have long been in active research for many years. However, building interoperable SCRs is still a challenge for software engineering. Now, domain ontologies have been employed to manage software components, and the method has been deemed as an effective way to achie...

Complex information resources interoperability is becoming an important issue for information resources reuse and aggregation in semantic Web services. Current registration standards are relatively weak in the description of complex logic relationship between information resources. This paper proposes complex information resources registry method b...

In Web service, one of the essential requirements in e-business is to classify and register the complex information. How to describe the registry classification information and construct the registry classification model is a keystone of realizing complex information classification and registry in ebXML/R&R system. Semantic Web is an important init...