Face classification by a random forest

This paper presents a random forest-based face image classification method. The random forest is an ensemble learning method that grows many classification trees. Each tree gives a classification. The forest selects the classification that has the most votes. Three experiments are performed. The random forest-based method together with several existing approaches are trained and evaluated. The experimental results are presented and discussed.

Email categorization using multi-stage classification technique

This paper presents an innovative email categorization using a serialized multi-stage classification ensembles technique. Many approaches are used in practice for email categorization to control the menace of spam emails in different ways. Content-based email categorization employs filtering techniques using classification algorithms to learn to predict spam e-mails given a corpus of training e-mails. This process achieves a substantial performance with some amount of FP tradeoffs. It has been studied and investigated with different classification algorithms and found that the outputs of the classifiers vary from one classifier to another with same email corpora. In this paper we have proposed a multi-stage classification technique using different popular learning algorithms with an analyser which reduces the FP (false positive) problems substantially and increases classification accuracy compared to similar existing techniques.

An innovative analyser for email classification based on grey list analysis

In this paper we propose a new technique of email classification based on grey list (GL) analysis of user emails. This technique is based on the analysis of output emails of an integrated model which uses multiple classifiers of statistical learning algorithms. The GL is a list of classifier/(s) output which is/are not considered as true positive (TP) and true negative (TN) but in the middle of them. Many works have been done to filter spam from legitimate emails using classification algorithm and substantial performance has been achieved with some amount of false positive (FP) tradeoffs. In the case of spam detection the FP problem is unacceptable, sometimes. The proposed technique will provide a list of output emails, called "grey list (GL)", to the analyser for making decisions about the status of these emails. It has been shown that the performance of our proposed technique for email classification is much better compare to existing systems, in order to reducing FP problems and accuracy.

Image semantic classification by using SVM

There exists an enormous gap between low-level visual feature and high-level semantic information, and the accuracy of content-based image classification and retrieval depends greatly on the description of low-level visual features. Taking this into consideration, a novel texture and edge descriptor is proposed in this paper, which can be represented with a histogram. Furthermore, with the incorporation of the color, texture and edge histograms searnlessly, the images are grouped into semantic classes using a support vector machine (SVM). Experiment results show that the combination descriptor is more discriminative than other feature descriptors such as Gabor texture.

A novel application of a microaccelerometer for target classification

This paper presents a novel method of target classification by means of a microaccelerometer. Its principle is that the seismic signals from moving vehicle targets are detected by a microaccelerometer, and targets are automatically recognized by the advanced signal processing method. The detection system based on the microaccelerometer is small in size, light in weight, has low power consumption and low cost, and can work under severe circumstances for many different applications, such as battlefield surveillance, traffic monitoring, etc. In order to extract features of seismic signals stimulated by different vehicle targets and to recognize targets, seismic properties of typical vehicle targets are researched in this paper. A technique of artificial neural networks (ANNs) is applied to the recognition of seismic signals for vehicle targets. An improved back propagation (BP) algorithm and ANN architecture have been presented to improve learning speed and avoid local minimum points in error curve. The improved BP algorithm has been used for classification and recognition of seismic signals of vehicle targets in the outdoor environment. Through experiments, it can be proven that target seismic properties acquired are correct, ANN is effective to solve the problem of classification and recognition of moving vehicle targets, and the microaccelerometer can be used in vehicle target recognition.

Trophic classification of non-perennial reservoirs utilized for the development of culture-based fisheries, Sri Lanka

The aim of this study was to check the suitability of some trophic models developed for temperate regions to classify the non-perennial reservoirs of Sri Lanka in order to manage culture-based fisheries of those reservoirs. A limnological study was carried out in 45 non-perennial reservoirs, which have been randomly selected for stocking of fish fingerlings for the development of culture-based fisheries. High total phosphorous (TP) content in relation to algal biomass indicates high non-algal turbidity in all reservoirs. Carlson's trophic state indices (TSI) measured on the basis of Secchi disc depth [TSI (SDD)], TP [TSI (TP)] and chlorophyll a [TSI (Chl-a)] show that the 45 reservoirs studied are characterized by TSI (TP) = TSI (SDD) > TSI (Chl-a), indicating that non-algal particulate matter or colour dominates underwater light attenuation. As TSI (Chl-a) is positively correlated to culture-based fisheries yield, it is useful for planning culture-based fisheries development strategies in non-perennial reservoirs of Sri Lanka, and has the potential to be used elsewhere in the tropics for comparable developments.

Spectral kernels for classification

Spectral methods, as an unsupervised technique, have been used with success in data mining such as LSI in information retrieval, HITS and PageRank in Web search engines, and spectral clustering in machine learning. The essence of success in these applications is the spectral information that captures the semantics inherent in the large amount of data required during unsupervised learning. In this paper, we ask if spectral methods can also be used in supervised learning, e.g., classification. In an attempt to answer this question, our research reveals a novel kernel in which spectral clustering information can be easily exploited and extended to new incoming data during classification tasks. From our experimental results, the proposed Spectral Kernel has proved to speedup classification tasks without compromising accuracy.

A public sector scale for codes of ethics classification

This article examines the results of a study conducted of the top 100 public sector units in Sweden. These units comprise 40 entities of government, 40 municipalities, and 20 county councils. The aim of the study was to examine and describe the codes of ethics in these Swedish public sector units. This research reports on the responses of 27 public sector units that possessed a code of ethics. The principal contribution of this work is a customized PUB SEC-scale to measure and evaluate the content of codes of ethics artefacts in public sector units. The PUB SEC-scale differs to a large extent from the current private sector-scales (PRlSEC-scales) in literature, due to the specific characteristics of the public sector.

A statistical-driven approach for automatic classification of events in AFL video highlights

Due to the repetitive and lengthy nature, automatic content-based summarization is essential to extract a more compact and interesting representation of sport video. State-of-the art approaches have confirmed that high-level semantic in sport video can be detected based on the occurrences of specific audio and visual features (also known as cinematic). However, most of them still rely heavily on manual investigation to construct the algorithms for highlight detection. Thus, the primary aim of this paper is to demonstrate how the statistics of cinematic features within play-break sequences can be used to less-subjectively construct highlight classification rules. To verify the effectiveness of our algorithms, we will present some experimental results using six AFL (Australian Football League) matches from different broadcasters. At this stage, we have successfully classified each play-break sequence into: goal, behind, mark, tackle, and non-highlight. These events are chosen since they are commonly used for broadcasted AFL highlights. The proposed algorithms have also been tested successfully with soccer video.

Extraction and classification of self-consumable sport video highlights using generic HMM

This paper aims to automatically extract and classify self-consumable sport video highlights. For this purpose, we will emphasize the benefits of using play-break sequences as the effective inputs for HMMbased classifier. HMM is used to model the stochastic pattern of high-level states during specific sport highlights which correspond to the sequence of generic audio-visual measurements extracted from raw video data. This paper uses soccer as the domain study, focusing on the extraction and classification of goal, shot and foul highlights. The experiment work which uses183 play-break sequences from 6 soccer matches will be presented to demonstrate the performance of our proposed scheme.

Towards universal and statistical-driven heuristics for automatic classification of sports video events

Researchers worldwide have been actively seeking for the most robust and powerful solutions to detect and classify key events (or highlights) in various sports domains. Most approaches have employed manual heuristics that model the typical pattern of audio-visual features within particular sport events To avoid manual observation and knowledge, machine-learning can be used as an alternative approach. To bridge the gaps between these two alternatives, an attempt is made to integrate statistics into heuristic models during highlight detection in our investigation. The models can be designed with a modest amount of domain-knowledge, making them less subjective and more robust for different sports. We have also successfully used a universal scope of detection and a standard set of features that can be applied for different sports that include soccer, basketball and Australian football. An experiment on a large dataset of sport videos, with a total of around 15 hours, has demonstrated the effectiveness and robustness of our
aIlgorithms.

Using decision-tree to automatically construct learned-heuristics for events classification in sports video

Automatic events classification is an essential requirement for constructing an effective sports video summary. It has become a well-known theory that the high-level semantics in sport video can be “computationally interpreted” based on the occurrences of specific audio and visual features which can be extracted automatically. State-of-the-art solutions for features-based event classification have only relied on either manual-knowledge based heuristics or machine learning. To bridge the gaps, we have successfully combined the two approaches by using learning-based heuristics. The heuristics are constructed automatically using decision tree while manual supervision is only required to check the features and highlight contained in each training segment. Thus, fully automated construction of classification system for sports video events has been achieved. A comprehensive experiment on 10 hours video dataset, with five full-match soccer and five full-match basketball videos, has demonstrated the effectiveness/robustness of our algorithms.