Data Mining - Concepts and Techniques.

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Social Network Analysis

Emotion and Adaptation

Emotion recognition aims to make computer understand ambiguous information of human emotion. Recently, research of emotion recognition is actively progressing in various fields such as natural language processing, speech signal processing, image data processing or brain wave analysis. We propose a method to recognize emotion in dialogue text by using originally created Emotion Word Dictionary. The words in the dictionary are weighted according to the occurrence rates in the existing emotion expression dictionary. We also propose a method to judge the object of emotion and emotion expressivity in dialogue sentences. The experiment using 1,190 sentences proved about 80% accuracy.

Emotion estimation algorithm based on interpersonal emotion included in emotional dialogue sentences

This paper presents an integrated method on question classification of Chinese Sichuan cuisine QA system. Classified features are extracted by means of domain attributes and the rule based classifier is constructed. SVM classifier is used for secondary classification to the questions which cannot be matched with rules. Experimental results show that the proposed method can achieve an accuracy of 96.22%.

An Integrated Approach for Question Classification in Chinese Cuisine Question Answering System

In order to solve the problems of highly redundant spatial information and motion noise in the heart rate (HR) estimation from facial videos based on remote Photoplethysmography(rPPG), this paper proposes a novel HR estimation method based on spatial-temporal attention model. Firstly, to reduce the redundant information and strengthen the association relationships of long-range videos, the spatial-temporal facial features are extracted by the 2D convolutional neural network (2DCNN) and 3D convolutional neural network (3DCNN), respectively. The aggregation function is adopted to incorporate feature maps into short segment spatial-temporal feature maps. Secondly, the spatial-temporal strip pooling is designed in the spatial-temporal attention module to reduce head movement noises. Then, via the two-part loss function, the model can focus more on the rPPG signal rather than the interference. We conduct extensive experiments on two public datasets to verify the effectiveness of our model. The experimental results show that the proposed method achieves significantly better performances than the state-of-the-art baselines: The mean absolute error could be reduced by 11% on the PURE dataset, and by 25% on the COHFACE dataset.

Robust Heart Rate Estimation with Spatial-Temporal Attention Network from Facial Videos

In order to improve shortage of Local Binary Pattern (LBP) algorithm in the field of facial feature extraction, this paper uses Local Directional Pattern (LDP) algorithm to extract the facial features about age estimation and gender classification. Because gradient information is more stable than gray information, LDP algorithm is not affected easily by noise. After preprocessing images, we use block strategy to represent facial features more fully. And then, we extract features of each block with LDP algorithm, storing the LDP histogram. Finally, we obtain age and gender identification results by Support Vector Machine (SVM). Experimental results on FG-NET face database show that this method has a good effect on age estimation and gender classification.

Age estimation and gender classification of facial images based on Local Directional Pattern

We have presented a new method called super-function based machine translation (SFBMT). SFBMT uses super-function (SF) to translate without syntactic and semantic analysis as most conventional MT systems do. SF represents correspondence with a source language sentence structure and a target language sentence structure directory. According to this feature, the system realizes very fast translation. Moreover we do not feel the sense of incompatibility in the translation result because the SFs are automatically generated from a large corpus. We describe (1) SF based machine translation, (2) extracting SF, (3) the evaluation experiment. As the experimental results, we obtain 84% of effective rates of translation.

Fuji Ren

Papers

Emotion estimation algorithm based on interpersonal emotion included in emotional dialogue sentences

An Integrated Approach for Question Classification in Chinese Cuisine Question Answering System

Robust Heart Rate Estimation with Spatial-Temporal Attention Network from Facial Videos

Age estimation and gender classification of facial images based on Local Directional Pattern

Super-function based Japanese-English machine translation