Byron L. D. Bezerra

A symbolic approach for content-based information filtering

Recommender systems seek to furnish personalized suggestions automatically based on user preferences. These systems use information filtering techniques to recommend new items by comparing them with a user profile. This paper presents an approach through which each user profile is modelled using a set of modal symbolic descriptions that summarize the information taken from a set of items the user has previously evaluated. The comparison between a new item and a user profile is accomplished by way of a new suitable dissimilarity function that takes content and position differences into account. This new approach is evaluated by comparing it with a common information filtering technique: the standard kNN method.

HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps

The hand is an important part of the body used to express information through gestures, and its movements can be used in dynamic gesture recognition systems based on computer vision with practical applications, such as medical, games and sign language. Although depth sensors have led to great progress in gesture recognition, hand gesture recognition still is an open problem because of its complexity, which is due to the large number of small articulations in a hand. This paper proposes a novel approach for hand gesture recognition with depth maps generated by the Microsoft Kinect Sensor (Microsoft, Redmond, WA, USA) using a variation of the CIPBR (convex invariant position based on RANSAC) algorithm and a hybrid classifier composed of dynamic time warping (DTW) and Hidden Markov models (HMM), called the hybrid approach for gesture recognition with depth maps (HAGR-D). The experiments show that the proposed model overcomes other algorithms presented in the literature in hand gesture recognition tasks, achieving a classification rate of 97.49% in the MSRGesture3D dataset and 98.43% in the RPPDI dynamic gesture dataset.

Convexity local contour sequences for gesture recognition

Algorithms for hand feature extraction used in gesture recognition systems have some problems such as unnecessary information gathering. This paper proposes a novel method for feature extraction in gesture recognition systems based on the Local Contour Sequence (LCS). It is called the Convexity Local Contour Sequence (CLCS) and represents the hand shape only with the most significant information. This generates a smaller output result, but capable to model an entire dynamic gesture. It is used to classify dynamic gestures with an Elman Recurrent Network and Hidden Markov Model and presents a better result compared to regular LCS.

An Effective Dynamic Gesture Recognition System Based on the Feature Vector Reduction for SURF and LCS

Speed Up Robust Feature (SURF) and Local Contour Sequence(LCS) are methods used for feature extraction techniques for dynamic gesture recognition. A problem presented by these techniques is the large amount of data in the output vector which difficult the classification task. This paper presents a novel method for dimensionality reduction of the features extracted by SURF and LCS, called Convexity Approach. The proposed method is evaluated in a gesture recognition task and improves the recognition rate of LCS while SURF while decreases the amount of data in the output vector.

Speeding up Recommender Systems with Meta-prototypes

Recommender Systems use Information Filtering techniques to manage user preferences and provide the user with options, which will present greater possibility to satisfy them. Among these techniques, Content Based Filtering recommend new items by comparing them with a user profile, usually expressed as a set of items given by the user. This comparison is often performed using the k-NN method, which presents efficiency problems as the user profile grows. This paper presents an approach where each user profile is modeled by a meta-prototype and the comparison between an item and a profile is based on a suitable matching function. We show experimentally that our approach clearly outperforms the k-NN method while they presenting equal or even better prediction accuracy. The meta-prototype approach performs slightly worse than kd-tree speed up method but it exhibits a significant gain in prediction accuracy.

A symbolic hybrid approach to face the new user problem in recommender systems

Recommender Systems seek to furnish personalized suggestions automatically based on user preferences These preferences are usually expressed as a set of items either directly or indirectly given by the user (e.g., the set of products the user bought in a virtual store) In order to suggest new items, Recommender Systems generally use one of the following approaches: Content Based Filtering, Collaborative Filtering or hybrid filtering methods In this paper we propose a strategy to improve the quality of recommendation in the first user contact with the system Our approach includes a suitable plan to acquiring a user profile and a hybrid filtering method based on Modal Symbolic Data Our proposed technique outperforms the Modal Symbolic Content Based Filter and the standard kNN Collaborative Filter based on Pearson Correlation.

A Dynamic Gesture Recognition System based on CIPBR Algorithm

Dynamic gesture recognition has been studied actually for it big application in several areas such as virtual reality, games and sign language. But some problems have to be solved in computer applications, such as response time and classification rate, which directly affect the real-time usage. This paper proposes a novel algorithm called Convex Invariant Position Based on Ransac which improved the good results in dynamic gesture recognition problem. The proposed method is combined with a adapted PSO variation to reduce features and a HMM and three DTW variations as classifiers. Index Terms—Gesture recognition, computer vision, CIPBR, dynamic time wrapping, hidden Markov model.

A MDRNN-SVM hybrid model for cursive offline handwriting recognition

This paper presents a recurrent neural networks applied to handwriting character recognition. The method Multi-dimensional Recurrent Neural Network is evaluated against classical techniques. To improve the model performance we propose the use of specialized Support Vector Machine combined whit the original Multi-dimensional Recurrent Neural Network in cases of confusion letters. The experiments were performed in the C-Cube database and compared with different classifiers. The hierarchical combination presented promising results.

C^2:: A Collaborative Recommendation System Based on Modal Symbolic User Profile

Recommendation systems have become an important tool to cope with the information overload problem by acquiring information about the user behavior. However, the process of getting user personal data may vary in many different ways, and can be done implicitly (through actions) or explicitly (through rates). After tracing actions or getting rates of the user, computational recommendation technologies use information filtering techniques to recommend items. In this paper we describe an approach to improve the recommendation quality in the first moments the user interacts with the system. The main idea is: (1) first of all, we describe the items with the general users opinion about them; and (2) after this, we use modal symbolic structures to save this content in the user profile. The proposed methodology outperforms, concerning the find good items task measured by half-life utility metric, other approaches based on the following techniques: cognitive filtering, social filtering and hybrid methods

Information Filtering Based on Modal Symbolic Objects

Recommender systems aim to furnish automatically personalized suggestions based on user preferences. These systems use information filtering (IF) techniques to recommend new items by comparing them with a user profile. This paper presents an approach where each user profile is modelled by a set of modal symbolic descriptions, which summarize the information given by the set of items already evaluated by the user. The comparison between a new item and a user profile is accomplished by a new suitable dissimilarity function which takes into account differences in content and position. This new approach is evaluated in comparison with the kNN method, which is an IF technique often used in this kind of system.