This paper presents the first study on scheduling for cooperative data dissemination in a hybrid infrastructure-to-vehicle (I2V) and vehicle-to-vehicle (V2V) communication environment. We formulate the novel problem of cooperative data scheduling (CDS). Each vehicle informs the road-side unit (RSU) the list of its current neighboring vehicles and the identifiers of the retrieved and newly requested data. The RSU then selects sender and receiver vehicles and corresponding data for V2V communication, while it simultaneously broadcasts a data item to vehicles that are instructed to tune into the I2V channel. The goal is to maximize the number of vehicles that retrieve their requested data. We prove that CDS is NP-hard by constructing a polynomial-time reduction from the Maximum Weighted Independent Set (MWIS) problem. Scheduling decisions are made by transforming CDS to MWIS and using a greedy method to approximately solve MWIS. We build a simulation model based on realistic traffic and communication characteristics and demonstrate the superiority and scalability of the proposed solution. The proposed model and solution, which are based on the centralized scheduler at the RSU, represent the first known vehicular ad hoc network (VANET) implementation of software defined network (SDN) concept.Index Terms-Cooperative data dissemination, scheduling, software defined network, vehicular ad hoc networks.

No abstract

No abstract

In this paper, by applying motion detection and machine learning technologies, we have designed and developed an activity tracking and monitoring system, called SmartMind, to help Alzheimer's Disease (AD) patients to live independently within their living rooms while providing emergency assistances and supports when necessary. Allowing AD patients to handle their daily activities not only can release the burdens on their families and caregivers, it is also highly important to help them regain confidence towards a healthy life. The daily activities of a patient captured from SmartMind can also serve as an important indicator to describe his/her normal living habit (NLH). By checking NLH, the patient's current health status can be estimated on a daily basis. In the testing experiments of SmartMind, we have demonstrated the accuracy of SmartMind in activity detection and investigated its A preliminary version of the paper is appearred in Multimed Tools Appl performance when different machine learning algorithms were adopted for posture detection. The performance results indicate that both support vector machine (SVM) and naive bayes (NB) can achieve an accuracy of higher than 97 % while the random forrests (RF) only gives an accuracy of around 73 %.