Search

The analysis of acoustic data typically discusses the problem of segmenting the acoustic events into non-overlapping acoustically compact categories. In Acoustic Event Detection (AED), an acoustic event is categorized into speech and non-speech events. Detection of non-speech sounds such as scream, gun shots, explosions, and glass break events is very helpful in acoustic surveillance, multimedia information retrieval, and acoustic forensic applications. In this paper, we propose global statistical features-based representation for multi-variate varying length acoustic data. A discriminative model-based classifier is then used to classify different acoustic events. The proposed representation is of very less dimension. The proposed approach is evaluated on surveillance-oriented AED datasets such as CICESE (recorded from a smart room scenario), Environmental Sound Classification (ESC), and IEEE AASP/DCASE2013 (Office environment) datasets. The proposed approach gives a better performance when compared with the conventional Hidden Markov Model (HMM) and Gaussian Mixture Model (GMM) approaches. [ABSTRACT FROM AUTHOR]

Wireless sensor networks comprise nodes with limited power supply. The dense deployment of nodes on a terrain for monitoring the environment causes contention in wireless channels that leads to interference and high energy consumption. The topology of the network changes frequently because of failure of nodes, addition of new nodes, and channel fading. Topology control is an important technique for reducing energy consumption, interference, and maintaining connectivity in the network. This paper provides a survey on state scheduling-based topology control techniques for unattended wireless sensor networks. Topology control algorithms for both flat and hierarchical networks are discussed. The algorithms are further categorized according to the key parameters used for state scheduling. The advantages, disadvantages, and results of the algorithms are tabulated. In addition, we highlight future research directions in designing state scheduling-based topology control algorithms. [ABSTRACT FROM AUTHOR]

Recognition of speech uttered by severe dysarthric speakers needs a robust learning technique. One of the commonly used generative model-based classifiers for speech recognition is a hidden Markov model. Generative model-based classifiers do not do well for overlapping classes and due to insufficient training data. Dysarthric speech is normally partial or incomplete that leads to improper learning of temporal dynamics. To overcome these issues, we focus on learning features for dysarthric speech recognition that involves recognizing the sequential patterns of varying length utterances. We propose a Generative Model-Driven Feature Learning based discriminative framework that maps the sequence of feature vectors to fixed dimension vector spaces induced by the generative models. The discriminative classifier is built in that vector space. The proposed HMM-based fixed dimensional vector representation provides better discrimination for dysarthric speech than the conventional HMM. We examine the performance of the proposed method to recognize the isolated utterances from the UA-Speech database. The recognition accuracy of the proposed model is better than the conventional hidden Markov model-based approach. [ABSTRACT FROM AUTHOR]

Abstract: Chronic myeloid leukemia (CML) occurs due to t(9,22) (q34;q11) and molecularly BCR/ABL gene fusion. About 15–18% Philadelphia positive CML patients have gene deletions around the translocation breakpoints on 9q34.1. The microRNAs (miRNAs), namely miR-219-2 and miR-199b, centromeric to the ABL1 gene are frequently lost in CML patients. We have designed a study to determine miR-219-2 and miR-199b expression levels which would help to understand the prognosis of imatinib therapy. A total of 150 CML patients were analyzed to identify 9q deletion. Fluorescent in-situ hybridization (FISH) was performed using BCR/ABL dual color, dual fusion probe to study the signal pattern and BAC probes for miR-199b and miR-219-2 (RP11-339B21 and RP11-395P17) to study the miRNA deletions. The expression level of miRNA was analyzed by real-time polymerase chain reaction (RT-PCR). FISH analysis revealed 9q34.1 deletion in 34 (23%) CML patients. The deletions were not detected using BAC probes for miRNAs in 9q deleted patients. The expression analysis showed down-regulation of miR-199b and miR-219-2 in the 9q deleted patients (34 CML) as compared to a pool of patients without deletion. However, miR-199b (9q34.11) was significantly (p=0.001) down-regulated compared to miR-219-2. The follow-up study showed that the miR-199b was found to be strongly associated with imatinib resistance, as 44.11% patients showed resistance to imatinib therapy. Hence, the deletion in 9q34.1 region (ABL) plays an important role in disease pathogenesis. Eventually, miRNAs can provide new therapeutic strategies and can be used as a prognostic indicator. [Copyright &y& Elsevier]