Jian Pan Li

An Adaptive Cluster-Based Routing Mechanism for Energy Conservation in Mobile Ad Hoc Networks

In recent years, many studies have proposed various ways to strengthen wireless networks’ performance. In this paper, we identify some drawbacks arising from protocol improved location-aided routing (ILAR). Nodes around the borders of a given broadcast coverage might quickly and easily move out, resulting in a broken routing path. Another problem in ILAR is that, although it may have a better forwarding node available for use a relay node could fail. Therefore we propose a novel routing protocol integrated power balance scheme to help resolve the problems mentioned above. Furthermore, the scheme employs position information and a power-saving scheme to balance the energy of each node and to lengthen the entire network’s life. To achieve these goals, there must be a reduction in the simultaneous loading of networks. Therefore, we also propose a cluster-based routing mechanism in mobile ad hoc networks. This mechanism can reduce the loading of networks, energy conservation, and increase the lifetime of nodes and networks.

Using Ontology and RFID Technology to Develop an Agent-Based System for Campus-Safety Management

This study proposes a distributed multi-agent system combining radio-frequency identification press technology with an ontology for special-education students in support of dynamic campus-safety management. Safety management on campus typically involves relevant supporting measures and manuals, but serious safety-related incidents continue to take place on campuses. The goal of campus security should be to identify an incident and resolve it effectively and in real time before the incident evolves into an actual crisis. Our purpose here is to improve the traceability of students involving in campus activities—that is, to identify students’ whereabouts throughout the entire school day. When an incident occurs, our system will notify the relevant parties immediately. In the present study, the agents real-time event processing increases their situational awareness and reduces the likelihood and the severity of unwanted outcomes. Basically, in this paper, we aim to demonstrate the feasibility and applicability of utilizing agent-based technologies to the special-education students.

Classifier Learning and Decision Making for a Connection Manager on a Heterogeneous Network

An attractive feature of the Connection Manager Intelligence Agent is its use of network traffic and multi-attribute behavior to locate the best network devices. This study has integrated this agent with a user interface; a network connection handoff; wired and wireless network device drivers; network management applications of the (plug-in) play interface; module-to-module communication authentication; and a DBus for added versatility. To reduce the time that developers of embedded systems spend on the software engineering of this module and to achieve rapid operational efficiency, an Open Source platform, such as MeeGo or Android, must be used. This study has implemented an interactive interface through the function (based on Fuzzy-AHP) of acquisition user behavior and machine designers, boosting iterations for User-Case. The algorithm maintains a set of weights as a distribution class table of cases, as in the parameter learning by user-case; it is quite possible that the expectation–maximization of maximum probability model can be classified by user behavior. In this study, user interaction showed that the agent satisfactorily matched user intent.

Intelligent ridesharing system for taxi to reduce cab fee

This paper presents an intelligent ridesharing system for taxi to share cost and journey among the passengers. The objective of the system is to provide taxi-sharing service for passengers who want to save the payment cost. It is done by recommending taxis drivers for picking up passengers at a higher revenue. The passengers are able to find taxis easily and quickly as well. By exploiting the time-dependent R-Tree, we formulate the problem of choosing the paths among the taxis in the same region by using non-cooperative game theory. The results show that our method can find taxis and passengers at an acceptable range. In addition, applying our method can reduce the payment of passengers and increase the taxi revenue by sharing.

Game Theory Based Recommendation Mechanism for Taxi-Sharing

This paper presents a recommendation mechanism for taxi-sharing. The first aim of our model is to respectively recommend taxis and passengers for picking up passengers quickly and finding taxis easily. The second purpose is providing taxi-sharing service for passengers who want to save the payment. In our method, we analyze the historical Global Positioning System (GPS) trajectories generated by 10,357 taxis during 110 days and present the service region with time-dependent R-Tree. We formulate the problem of choosing the paths among the taxis in the same region by using non-cooperative game theory, and find out the solution of this game which is known as Nash equilibrium. The results show that our method can find taxis and passengers efficiently. In addition, applying our method can reduce the payment of passengers and increase the taxi revenue by taxi-sharing.

Combined hand gesture--speech model for human action recognition.

This study proposes a dynamic hand gesture detection technology to effectively detect dynamic hand gesture areas, and a hand gesture recognition technology to improve the dynamic hand gesture recognition rate. Meanwhile, the corresponding relationship between state sequences in hand gesture and speech models is considered by integrating speech recognition technology with a multimodal model, thus improving the accuracy of human behavior recognition. The experimental results proved that the proposed method can effectively improve human behavior recognition accuracy and the feasibility of system applications. Experimental results verified that the multimodal gesture-speech model provided superior accuracy when compared to the single modal versions.

Connection manager using FAHP of MCDM techniques in heterogeneous network

Connection Manager Intelligence Agents (CMIA) an attractive feature is use the network traffic and behavior with multi-attributes to find the best network devices and connection devices meet user habits that it possible to access various network contents everywhere at any time. In this agent, information process is thoroughly integrated into embedded system for connection manager of MeeGo or Android. This paper proposes a new and generic algorithm for connection manager in the heterogeneous wired or wireless environments. The proposed algorithm uses a Fuzzy Analytic Hierarchy Process theory (FAHP) of Multi-Criteria Decision Making (MCDM) system to achieve scalable, adaptable, and flexible solution. This study implemented an interactive interface through of this function acquisition user behavior and to scholars of the machine used a boosting iterations for User-Case, the algorithm maintains a set of weights as a distribution classes table of case as in the parameter learning by user-case and its quite possible that the Expectation-Maximization (EM) of Maximum Probability Model (MPM) by classification from user behavior. User interaction showed that the agent satisfactorily matched user intent.