Text Categorization (TC), also known as Text Classification, is the task of automatically classifying a set of text documents into different categories from a predefined set. If a document belongs to exactly one of the categories, it is a single-label classification task; otherwise, it is a multi-label classification task. TC uses several tools from Information Retrieval (IR) and Machine Learning (ML) and has received much attention in the last years from both researchers in the academia and industry developers. In this paper, we first categorize the documents using KNN based machine learning approach and then return the most relevant documents.

Biometric recognition is becoming more and more important owing to the need for authentication in several fields like security or convenience applications. In this paper, a new imaging capturing technique based on near-infrared illumination [1] to acquire wrist vein pattern images for biometric purposes is analysed. Experiments and tests involving data acquisition in different illumination conditions are described using a population of 30 test subjects. Comparison and analysis of the data collected with other techniques show that this hardware method is suitable to obtain high quality wrist veins images that can be used in the feature extraction phase to extract the wrist vein patterns for biometric recognition.

In this paper, the authors will describe a new algorithm based on minutiae extraction which is inspired by currently fingerprint systems, but adapted to the own characteristics of vein patterns. All the steps of the system, from the image pre-processing to the comparison algorithm, are described, including also the biometric feature extraction process. After describing the system, some obtained results are detailed. The algorithm proposed has been tested with two different databases: one database acquired by the authors, using a self-designed sensor; and one semi-publicly accessible database. These results do not only show the low error rates obtained but also the universality of the proposed system, as well as the ease of adapting the algorithm to cope with the different characteristics of each database

Clustering in wireless sensor networks has been widely discussed in the literature as a strategy to reduce power consumption. However, aspects such as cluster formation and cluster head (CH) node assignment strategies have a significant impact on quality of service, as energy savings imply restrictions in application usage and data traffic within the network. Regarding the first aspect, this article proposes a hierarchical routing protocol based on the k-d tree algorithm, taking a partition data structure of the space to organize nodes into clusters. For the second aspect, we propose a reactive mechanism for the formation of CH nodes, with the purpose of improving delay, jitter, and throughput, in contrast with the low-energy adaptive clustering hierarchy/hierarchy-centralized protocol and validating the results through simulation.

Urban impedance is an important consideration in assessments of transportation and land-use systems. This work leverages checkin records obtained from mobile social networks to build a fine-grained but inexpensive urban impedance model. Check-in records and road networks are collected and used to calculate and adjust the various parameters of the model, including path length, number and angle of turns, number and direction of junctions, and population density. Check-in records can filter functional locations and supply the time factor, thereby providing excellent advantages over traditional models that do not employ this data type. The proposed model is more accurate than traditional impedance models, as verified by experiments using Sina Weibo data in Tianjin City.