Voice Activity Detection (VAD) is considered as an important pre-processing step in speech processing systems such as speech enhancement, speech recognition, gender and age identification. VAD helps in reducing the time required to process speech data and to improve final system accuracy by focusing the work on the voiced part of the speech. An automatic technique for VAD using Fuzzy-Neuro technique (FN-AVAD) is presented in this paper. The aim of this work is to alleviate the problem of choosing the best threshold value in traditional VAD methods and achieves automaticity by combining fuzzy clustering and machine learning techniques. Four features are extracted from each speech segment, which are short term energy, zero-crossing rate, autocorrelation, and log energy. A modified version of fuzzy C-Means is then used to cluster speech segments into three clusters; two clusters for voice and one for unvoiced. After that, three feed forward neural networks are trained to adjust their weights, in which each network represents one cluster. To make the final decision regarding the class type of a given speech segment, the membership degrees of this segment in all clusters along with neural networks' decisions are given to a defuzzification step which finally gives the class type of that segment. The proposed FN-AVAD is tested on the public multimodal emotion database, Surrey AudioVisual Expressed Emotion (SAVEE), and the error rate was 2.08%. The achieved results are comparable to the results achieved by the current published works in the literature.
Among the different passive techniques heat pipe heat exchanger (HPHE) seems to be the most effective one for energy saving in heating ventilation and air conditioning system (HVAC). The applications for nanofluids with high conductivity are favorable to increase the thermal performance in HPHE. Even though the nanofluid has the higher heat conduction coefficient that dispels more heat theoretically but the higher concentration will make clustering .Clustering is a problem that must be solved before nanofluids can be considered for long-term practical uses. Results showed that the maximum value of relative power is 0.13 mW at nanofluid compared with other concentrations due to the low density of nanofluid at this concentration. For highe
... Show MoreMagnetic Resonance Imaging (MRI) uses magnetization and radio waves, rather than x-rays to make very detailed, cross- sectional pictures of the brain. In this work we are going to explain some procedures belongs contrast and brightness improvement which is very important in the improvement the image quality such as the manipulation with the image histogram. Its has been explained in this worked the histogram shrink i.e. reducing the size of the gray level gives a dim low contrast picture is produced, where, the histogram stretching of the gray level was distributed on a wide scale but there is no increase in the number of pixels in the bright region. The histogram equalization has also been discuss together with its effects of the improveme
... Show MoreThe subject of the listen to the voice of the customer of topics relatively new in management thought, as it won the attention of many organizations of different types, because it is important to achieve success and to continue and superiority to them, so there is a need to study this term in the Iraqi organizations and try to diagnose the implementation of the study sample to listen voice of the Customer and its
... Show MoreDocument source identification in printer forensics involves determining the origin of a printed document based on characteristics such as the printer model, serial number, defects, or unique printing artifacts. This process is crucial in forensic investigations, particularly in cases involving counterfeit documents or unauthorized printing. However, consistent pattern identification across various printer types remains challenging, especially when efforts are made to alter printer-generated artifacts. Machine learning models are often used in these tasks, but selecting discriminative features while minimizing noise is essential. Traditional KNN classifiers require a careful selection of distance metrics to capture relevant printing
... Show MoreThis paper proposes a new approach, of Clustering Ultrasound images using the Hybrid Filter (CUHF) to determine the gender of the fetus in the early stages. The possible advantage of CUHF, a better result can be achieved when fuzzy c-mean FCM returns incorrect clusters. The proposed approach is conducted in two steps. Firstly, a preprocessing step to decrease the noise presented in ultrasound images by applying the filters: Local Binary Pattern (LBP), median, median and discrete wavelet (DWT), (median, DWT & LBP) and (median & Laplacian) ML. Secondly, implementing Fuzzy C-Mean (FCM) for clustering the resulted images from the first step. Amongst those filters, Median & Lap
Ad-Hoc Networks are a generation of networks that are truly wireless, and can be easily constructed without any operator. There are protocols for management of these networks, in which the effectiveness and the important elements in these networks are the Quality of Service (QoS). In this work the evaluation of QoS performance of MANETs is done by comparing the results of using AODV, DSR, OLSR and TORA routing protocols using the Op-Net Modeler, then conduct an extensive set of performance experiments for these protocols with a wide variety of settings. The results show that the best protocol depends on QoS using two types of applications (+ve and –ve QoS in the FIS evaluation). QoS of the protocol varies from one prot
... Show More