In this paper, we propose a new deep network that learns multi-level deep representations for image emotion classification (MldrNet). Image emotion can be recognized through image semantics, image aesthetics and low-level visual features from both global and local views. Existing image emotion classification works using hand-crafted features or deep features mainly focus on either low-level vis...

This paper proposes a novel neural network structure for speech synthesis, in which spectrum, F0 and duration parameters are simultaneously modeled in a unified framework. In the conventional neural network approaches, spectrum and F0 parameters are predicted by neural networks while phone and/or state durations are given from other external duration predictors. In order to consistently model n...

certain advantages of service-oriented architecture have led to the spread of this type of architecture around the world. however, some special features of this type of architecture have led to more compromise between the security in the information system and other information systems. the purpose of this paper is to identify and examine the impact of factors and dimensions of the information ...

Most of the approaches of Content-Based Image Retrieval (CBIR) presume a linear relationship between different image features, and the efficiency of such systems was limited due to the difficulty in representing high-level concepts using low-level features. In this paper, a new architecture for a CBIR system is proposed; the Splines Neural Network-based Image Retrieval (SNNIR) system. SNNIR mak...

objective: interest in the subject of creativity and its impacts on human life is growing extensively. however, only a few surveys pay attention to the relation between creativity and physiological changes. this paper presents a novel approach to distinguish between creativity states from electrocardiogram signals. nineteen linear and nonlinear features of the cardiac signal were extracted to d...

The industrial Internet of Things (IoT) is aiming to interconnect humans, machines, materials, processes and services in a network. Wireless Sensor Network (WSN) comprises the less power consuming, light weight and effective Sensor Nodes (SNs) for higher network performance. Radio Frequency Identification (RFID) and sensor networks are both wireless technologies that provide limitless future po...

Sentiment lexicons and other linguistic knowledge proved to be beneficial in polarity classification. This paper introduces a linguistically informed Convolutional Neural Network (lingCNN), which incorporates this valuable kind of information into the model. We present two intuitive and simple methods: The first one integrates word-level features, the second sentence-level features. By combinin...

Recent studies have shown that aggregating convolutional features of a pre-trained Convolutional Neural Network (CNN) can obtain impressive performance for a variety of visual tasks. The symmetric Positive Definite (SPD) matrix becomes a powerful tool due to its remarkable ability to learn an appropriate statistic representation to characterize the underlying structure of visual features. In th...