In this paper, we present a novel color independent components based SIFT descriptor (termed CIC-SIFT) for object/scene classification. We first learn an efficient color transformation matrix based on independent component analysis (ICA), which is adaptive to each category in a database. The ICA-based color transformation can enhance contrast between the objects and the background in an image. Then we compute CIC-SIFT descriptors over all three transformed color independent components. Since the ICA-based color transformation can boost the objects and suppress the background, the proposed CIC-SIFT can extract more effective and discriminative local features for object/scene classification. The comparison is performed among seven SIFT descriptors, and the experimental classification results show that our proposed CIC-SIFT is superior to other conventional SIFT descriptors.

A scheme for designing a hierarchical fuzzy classification system with a different number of fuzzy partitions based on statistical characteristics of the data is proposed. To minimize the number of misclassified patterns in intermediate layers, a method of fuzzy partitioning from the defuzzified outputs of previous layers is also presented. The effectiveness of the proposed scheme is demonstrated by comparing the results from five datasets in the UCI Machine Learning Repository.

In differentiated services, packet classification is used to categorize incoming packets into multiple forwarding classes based on pre-defined filters and make information accessible for quality of service. Although numerous algorithms have presented novel data structures to improve the search performance of packet classification, the performance of these algorithms are usually limited by the characteristics of filter databases. In this paper, we use a different approach of filter preprocessing to enhance the search performance of packet classification. Before generating the searchable data structures, we cluster filters in a bottom-up manner. The procedure of the filter clustering merges filters with high degrees of similarity. The experimental results show that the technique of filter clustering could significantly improve the search performance of Pruned Tuple Space Search, a notable hash-based algorithm. As compared to the prominent existing algorithms, our enhanced Pruned Tuple Space Search also has superior performance in terms of speed and space.

Bag-of-Visual-Words representation has recently become popular for scene classification. However, learning the visual words in an unsupervised manner suffers from the problem when faced these patches with similar appearances corresponding to distinct semantic concepts. This paper proposes a novel supervised learning framework, which aims at taking full advantage of label information to address the problem. Specifically, the Gaussian Mixture Modeling (GMM) is firstly applied to obtain "semantic interpretation" of patches using scene labels. Each scene induces a probability density on the low-level visual features space, and patches are represented as vectors of posterior scene semantic concepts probabilities. And then the Information Bottleneck (IB) algorithm is introduce to cluster the patches into "visual words" via a supervised manner, from the perspective of semantic interpretations. Such operation can maximize the semantic information of the visual words. Once obtained the visual words, the appearing frequency of the corresponding visual words in a given image forms a histogram, which can be subsequently used in the scene categorization task via the Support Vector Machine (SVM) classifier. Experiments on a challenging dataset show that the proposed visual words better perform scene classification task than most existing methods.

Packet classification has become one of the most important application techniques in network security since the last decade. The technique involves a traffic descriptor or user-defined criteria to categorize packets to a specific forwarding class which will be accessible for future security handling. To achieve fast packet classification, we propose a new scheme, Hierarchical Cross-Producting. This approach simplifies the classification procedure and decreases the distinct combinations of fields by hierarchically decomposing the multi-dimensional space based on the concept of telescopic search. Analogous to the use of telescopes with different powers**, a multiple-step process is used to search for targets. In our scheme, the multi-dimensional space is endowed with a hierarchical property which self-divides into several smaller subspaces, whereas the procedure of packet classification is translated into recursive searching for matching subspaces. The required storage of our scheme could be significantly reduced since the distinct field specifications of subspaces is manageable. The performance are evaluated based on both real and synthetic filter databases. The experimental results demonstrate the effectiveness and scalability of the proposed scheme.

In the last decade, the technique of packet classification has been widely deployed in various network devices, including routers, firewalls and network intrusion detection systems. In this work, we improve the performance of packet classification by using multiple hash tables. The existing hash-based algorithms have superior scalability with respect to the required space; however, their search performance may not be comparable to other algorithms. To improve the search performance, we propose a tuple reordering algorithm to minimize the number of accessed hash tables with the aid of bitmaps. We also use pre-computation to ensure the accuracy of our search procedure. Performance evaluation based on both real and synthetic filter databases shows that our scheme is effective and scalable and the pre-computation cost is moderate.

In this paper, we propose a robust room inverse filtering algorithm for speech dereverberation based on a kurtosis maximization. The proposed algorithm utilizes a new normalized kurtosis function that nonlinearly maps the input kurtosis onto a finite range from zero to one, which results in a kurtosis warping. Due to the kurtosis warping, the proposed algorithm provides more stable convergence and, in turn, better performance than the conventional algorithm. Experimental results are presented to confirm the robustness of the proposed algorithm.

In this letter, we propose an improved speech/ nonspeech classification method to effectively classify a multimedia source. To improve performance, we introduce a feature based on spectral duration analysis, and combine recently proposed features such as high zero crossing rate ratio (HZCRR), low short time energy ratio (LSTER), and pitch ratio (PR). According to the results of our experiments on speech, music, and environmental sounds, the proposed method obtained high classification results when compared with conventional approaches.

In this study, a discriminative weight training is applied to a support vector machine (SVM) based speech/music classification for a 3GPP2 selectable mode vocoder (SMV). In the proposed approach, the speech/music decision rule is derived by the SVM by incorporating optimally weighted features derived from the SMV based on a minimum classification error (MCE) method. This method differs from that of the previous work in that different weights are assigned to each feature of the SMV a novel process. According to the experimental results, the proposed approach is effective for speech/music classification using the SVM.

This paper presents an extended Relief-F algorithm for nominal attribute estimation, for application to small-document classification. Relief algorithms are general and successful instance-based feature-filtering algorithms for data classification and regression. Many improved Relief algorithms have been introduced as solutions to problems of redundancy and irrelevant noisy features and to the limitations of the algorithms for multiclass datasets. However, these algorithms have only rarely been applied to text classification, because the numerous features in multiclass datasets lead to great time complexity. Therefore, in considering their application to text feature filtering and classification, we presented an extended Relief-F algorithm for numerical attribute estimation (E-Relief-F) in 2007. However, we found limitations and some problems with it. Therefore, in this paper, we introduce additional problems with Relief algorithms for text feature filtering, including the negative influence of computation similarities and weights caused by a small number of features in an instance, the absence of nearest hits and misses for some instances, and great time complexity. We then suggest a new extended Relief-F algorithm for nominal attribute estimation (E-Relief-Fd) to solve these problems, and we apply it to small text-document classification. We used the algorithm in experiments to estimate feature quality for various datasets, its application to classification, and its performance in comparison with existing Relief algorithms. The experimental results show that the new E-Relief-Fd algorithm offers better performance than previous Relief algorithms, including E-Relief-F.

A new algorithm for simultaneously detecting and identifying invariant blurs is proposed. This is mainly based on the behavior of extrema values in an image. It is computationally simple and fast thereby making it suitable for preprocessing especially in practical imaging applications. Benefits of employing this method includes the elimination of unnecessary processes since unblurred images will be separated from the blurred ones which require deconvolution. Additionally, it can improve reconstruction performance by proper identification of blur type so that a more effective blur specific deconvolution algorithm can be applied. Experimental results on natural images and its synthetically blurred versions show the characteristics and validity of the proposed method. Furthermore, it can be observed that feature selection makes the method more efficient and effective.

In conjunction with a first-order Taylor series approximation of the spatial scanning vector, this letter presents an iterative multiple signal classification (MUSIC) direction-of-arrival (DOA) estimation for code-division multiple access signals. This approach leads to a simple one-dimensional optimization problem to find each iterative optimal search grid. It can not only accurately estimate DOA, but also speed up the estimating process. Computer results demonstrate the effectiveness of the proposed algorithm.

Network intrusion detection systems rely on a signature-based detection engine. When under attack or during heavy traffic, the detection engines need to make a fast decision whether a packet or a sequence of packets is normal or malicious. However, if packets have a heavy payload or the system has a great deal of attack patterns, the high cost of payload inspection severely diminishes detection performance. Therefore, it would be better to avoid unnecessary payload scans by checking the protocol fields in the packet header, before executing their heavy operations of payload inspection. When payload inspection is necessary, it is better to compare a minimum number of attack patterns. In this paper, we propose new methods to classify attack signatures and make pre-computed multi-pattern groups. Based on IDS rule analysis, we grouped the signatures of attack rules by a multi-dimensional classification method adapted to a simplified address flow. The proposed methods reduce unnecessary payload scans and make light pattern groups to be checked. While performance improvements are dependent on a given networking environment, the experimental results with the DARPA data set and university traffic show that the proposed methods outperform the most recent Snort by up to 33%.

Packet classification categorizes incoming packets into multiple forwarding classes based on pre-defined filters. This categorization makes information accessible for quality of service or security handling in the network. In this paper, we propose a scheme which combines the Aggregate Bit Vector algorithm and the Pruned Tuple Space Search algorithm to improve the performance of packet classification in terms of speed and storage. We also present the procedures of incremental update. Our scheme is evaluated with filter databases of varying sizes and characteristics. The experimental results demonstrate that our scheme is feasible and scalable.

This paper proposes an ultra-wideband double-directional spatio-temporal channel sounding technique using transformation between frequency- and time-domain (FD and TD) signals. Virtual antenna arrays, composed of omnidirectional antennas and scanners, are used for transmission and reception in the FD. After Fourier transforming the received FD signals to TD ones, time of arrival (TOA) is estimated using a peak search over the TD signals, and then angle of arrivals (AOA) and angle of departure (AOD) are estimated using a weighted angle histogram with a multiple signal classification (MUSIC) algorithm applied to the FD signals, inverse-Fourier transformed from the TD signals divided into subregions. Indoor channel sounding results validated that an appropriate weighting reduced a spurious level in the angle histogram by a factor of 0.1 to 0.2 in comparison with that of non-weighting. The proposed technique successfully resolved dominant multipath components, including a direct path, a single reflection, and a single diffraction, in line-of-sight (LOS) and non-LOS environments. Joint TOA and AOA/AOD spectra were also derived from the sounding signals. The spectra illustrated the dominant multipath components (agreed with the prediction by ray tracing) as clusters.

In this Letter, a robust system identification method is proposed for the generalized sidelobe canceller using dual microphones. The conventional transfer-function generalized sidelobe canceller employs the non-stationarity characteristics of the speech signal to estimate the relative transfer function and thus is difficult to apply when the noise is also non-stationary. Under the assumption of W-disjoint orthogonality between the speech and the non-stationary noise, the proposed algorithm finds the speech-dominant time-frequency bins of the input signal by inspecting the system output and the inter-microphone time delay. Only these bins are used to estimate the relative transfer function, so reliable estimates can be obtained under non-stationary noise conditions. The experimental results show that the proposed algorithm significantly improves the performance of the transfer-function generalized sidelobe canceller, while only sustaining a modest estimation error in adverse non-stationary noise environments.

We present a novel model named Integrated Latent Topic Model (ILTM), to learn and recognize natural scene category. Unlike previous work, which considered the discrepancy and common property separately among all categories, Our approach combines universal topics from all categories with specific topics from each category. As a result, the model is implemented to produce a few but specific topics and more generic topics among categories, and each category is represented in a different topics simplex, which correlates well with human scene understanding. We investigate the classification performance with variable scene category tasks. The experiments have shown our model outperforms latent-space methods with less training data.

In this paper, we propose a new feature selection algorithm for multi-class classification. The proposed algorithm is based on Gaussian mixture models (GMMs) of the features, and it uses the distance between the two least separable classes as a metric for feature selection. The proposed system was tested with a support vector machine (SVM) for multi-class classification of music. Results show that the proposed feature selection scheme is superior to conventional schemes.

With a Gaussian kernel function, we find that the distance between two classes (DBTC) can be used as a class separability criterion in feature space since the between-class separation and the within-class data distribution are taken into account impliedly. To test the validity of DBTC, we develop a method of tuning the kernel parameters in support vector machine (SVM) algorithm by maximizing the DBTC in feature space. Experimental results on the real-world data show that the proposed method consistently outperforms corresponding hyperparameters tuning methods.

In this letter, an acoustic environment classification algorithm based on the 3GPP2 selectable mode vocoder (SMV) is proposed for context-aware mobile phones. Classification of the acoustic environment is performed based on a Gaussian mixture model (GMM) using coding parameters of the SMV extracted directly from the encoding process of the acoustic input data in the mobile phone. Experimental results show that the proposed environment classification algorithm provides superior performance over a conventional method in various acoustic environments.