Instance Retrieval Using Region of Interest Based CNN Features

Recently, image representations derived by convolutional neural networks(CNN) have achieved promising performance for instance retrieval, and they outperformthe traditional hand-crafted image features. However, most of existing CNN-based featuresare proposed to describe the entire images, and thus they are less robust to backgroundclutter. This paper proposes a region of interest (RoI)-based deep convolutionalrepresentation for instance retrieval. It first detects the region of interests (RoIs) from animage, and then extracts a set of RoI-based CNN features from the fully-connected layerof CNN. The proposed RoI-based CNN feature describes the patterns of the detected RoIs,so that the visual matching can be implemented at image region-level to effectively identifytarget objects from cluttered backgrounds. Moreover, we test the performance of theproposed RoI-based CNN feature, when it is extracted from different convolutional layersor fully-connected layers. Also, we compare the performance of RoI-based CNN featurewith those of the state-of-the-art CNN features on two instance retrieval benchmarks.Experimental results show that the proposed RoI-based CNN feature provides superiorperformance than the state-of-the-art CNN features for in-stance retrieval.

Peer-to-peer Electricity Transaction Decisions of the User-side Smart Energy System Based on the SARSA Reinforcement Learning

With the deep integration of advanced information technologies,such as artificial intelligence and traditional energy technologies,smart energy systems have been proposed as a method to provide the best solution for the coordination,balance,and control of the entire energy system.As a new way of energy balance and interaction in the user side energy market,a peer-to-peer(P2P)electricity transaction can effectively promote energy sharing within the user group and improve the economic benefits of users participating in the energy market.Reinforcement learning(RL)is an artificial intelligence method in which agents continuously acquire relevant experience and knowledge during the interaction with the environment,automatically update their decision-making behavior;and achieve maximum return.It is a suitable approach for P2P transaction decision analysis of small-scale users in the context of smart energy.First,this paper establishes a P2P transaction model that includes a participant model,equipment model and price model.Secondly,the transaction problem is equivalent to a Markov decision process(MDP)and each learning element model is established.Then,the MDP problem is solved and analyzed using the SARSA RL algorithm with average discrete processing.Finally,a case study of a community with multiple users is conducted to verify the effectiveness,economy,and security of the RL method in solving energy storage action selection and transaction decision problems of energy storage users.