Preferred Language
Articles
/
Oxbt4osBVTCNdQwCpOO1
Automatic voice activity detection using fuzzy-neuro classifier
...Show More Authors

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.

Scopus
View Publication Preview PDF
Quick Preview PDF
Publication Date
Mon Mar 01 2021
Journal Name
Al-khwarizmi Engineering Journal
Hurst Exponent and Tsallis Entropy Markers for Epileptic Detection from Children
...Show More Authors

The aim of the present study was to distinguish between healthy children and those with epilepsy by electroencephalography (EEG). Two biomarkers including Hurst exponents (H) and Tsallis entropy (TE) were used to investigate the background activity of EEG of 10 healthy children and 10 with epilepsy. EEG artifacts were removed using Savitzky-Golay (SG) filter. As it hypothesize, there was a significant changes in irregularity and complexity in epileptic EEG in comparison with healthy control subjects using t-test (p< 0.05). The increasing in complexity changes were observed in H and TE results of epileptic subjects make them suggested EEG biomarker associated with epilepsy and a reliable tool for detection and identification of this di

... Show More
View Publication Preview PDF
Scopus (4)
Crossref (1)
Scopus Crossref
Publication Date
Sat Jun 03 2023
Journal Name
Journal Of Electronic Materials
Thiophosgene Detection by Ag-Decorated AlN Nanotube: A Mechanical Quantum Survey
...Show More Authors

The density functional B3LYP is used to investigate the effect of decorating the silver (Ag) atom on the sensing capability of an AlN nanotube (AlN-NT) in detecting thiophosgene (TP). There is a weak interaction between the pristine AlN-NT and TP with the sensing response (SR) of approximately 9.4. Decoration of the Ag atom into the structure of AlN-NT causes the adsorption energy of TP to decrease from − 6.2 to − 22.5 kcal/mol. Also, the corresponding SR increases significantly to 100.5. Moreover, the recovery time when TP is desorbed from the surface of the Ag-decorated AlN-NT (Ag@AlN-NT) is short, i.e., 24.9 s. The results show that Ag@AlN-NT can selectively detect TP among other gases, such as N2, O2, CO2, CO, and H2O.

View Publication
Scopus Clarivate Crossref
Publication Date
Wed Jan 01 2020
Journal Name
Medical Journal Of Babylon
Diagnostic value of neutrophil lymphocyte ratio in detection of acute appendicitis
...Show More Authors

The diagnosis of acute appendicitis (AA) sometimes is illusive and the accompanying clinical and laboratory manifestations cannot be used for definitive diagnosis. Objective: This study aimed to evaluate the diagnostic value of neutrophil/lymphocyte ratio (NLR) in detection of AA. Materials and Methods: This is a cross-sectional study that included a total of 80 adult patients with AA and 62 age- and gender-matched patients with abdominal pain due to causes other than AA. Three milliliter of peripheral blood were collected from each participant. The NLR was calculated by dividing the absolute neutrophil count by the absolute lymphocyte count. Receiver operating characteristic curve was used to assess the diagnostic value of NLR in detection

... Show More
View Publication
Scopus Crossref
Publication Date
Tue Mar 01 2022
Journal Name
Malaysian Journal Of Medicine & Health Sciences
Detection of Iron and Ferritin in Diabetes Mellitus Type 2 Patients
...Show More Authors

Scopus (4)
Scopus
Publication Date
Mon Jun 01 2020
Journal Name
Journal Of Engineering
GIS as A Tool for Expansive Soil Detection at Sulaymaniyah City
...Show More Authors

Geotechnical engineering like any other engineering field has to develop and cope with new technologies. This article intends to investigate the spatial relationships between soil’s liquid limit (LL), plasticity index (PI) and Liquidity index (LI) for particular zones of Sulaymaniyah City. The main objective is to study the ability to produce digital soil maps for the study area and determine regions of high expansive soil. Inverse Distance Weighting (IDW) interpolation tool within the GIS (Geographic Information System) program was used to produce the maps. Data from 592 boreholes for LL and PI and 245 boreholes for LI were used for this study. Layers were allocated into three depth ranges (1 to 2, 2 to 4 and 4 to 6)

... Show More
View Publication Preview PDF
Crossref (8)
Crossref
Publication Date
Wed Jan 15 2020
Journal Name
Iraqi Journal Of Laser
Electronically Implementation and Detection of Pulse Laser from Continuous Laser Diode
...Show More Authors

This research aims to design a high-speed laser diode driver and photodetector, the result is the
design of the high-speed laser diode driver with a short pulse of 10 ns at 30 KHz frequency and the
delivered maximum pulse voltage is 5.5 mV. Also, its optical output power of the laser diode driver is
about 2.529 mW for the centroied wavelength 1546.7 nm with FWHM of 286 pm and (1270-1610) nm.
The design of the circuit based on bipolar transistor where the input pulse signal is simply generated by
an arduino kit with 15 kHz frequency and then compensated to trigger to small signal amplifier which
was is simply NPN C3355 transistor and the output is a current driver to the laser diode. OptiSystem
software and Electronic

... Show More
View Publication Preview PDF
Publication Date
Tue Sep 30 2014
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Analytical Model for Detection the Tilt in Originally Oil Water Contacts
...Show More Authors

Many carbonate reservoirs in the world show a tilted in originally oil-water contact (OOWC) which requires a special consideration in the selection of the capillary pressure curves and an understanding of reservoir fluids distribution while initializing the reservoir simulation models.
An analytical model for predicting the capillary pressure across the interface that separates two immiscible fluids was derived from reservoir pressure transient analysis. The model reflected the entire interaction between the reservoir-aquifer fluids and rock properties measured under downhole reservoir conditions.
This model retained the natural coupling of oil reservoirs with the aquifer zone and treated them as an explicit-region composite system

... Show More
View Publication Preview PDF
Publication Date
Sun May 01 2022
Journal Name
Journal Of Engineering
Performance Analysis of different Machine Learning Models for Intrusion Detection Systems
...Show More Authors

In recent years, the world witnessed a rapid growth in attacks on the internet which resulted in deficiencies in networks performances. The growth was in both quantity and versatility of the attacks. To cope with this, new detection techniques are required especially the ones that use Artificial Intelligence techniques such as machine learning based intrusion detection and prevention systems. Many machine learning models are used to deal with intrusion detection and each has its own pros and cons and this is where this paper falls in, performance analysis of different Machine Learning Models for Intrusion Detection Systems based on supervised machine learning algorithms. Using Python Scikit-Learn library KNN, Support Ve

... Show More
View Publication Preview PDF
Scopus (19)
Crossref (8)
Scopus Crossref
Publication Date
Wed Oct 01 2025
Journal Name
Iop Conference Series: Earth And Environmental Science
16S rRNA gene detection of Hafnia alvei isolated from infected rabbits
...Show More Authors
Abstract<p> This research investigates <italic>Hafnia alvei</italic> infection in rabbits exhibiting respiratory distress and sudden death in Baghdad, Iraq. Seventy-five lung samples were collected, with a 66.6% isolation rate for <italic>H. alvei</italic> . Identification was performed using the VITEK 2 compact system and 16S rRNA gene sequencing, which showed 100% homology with a reference strain (Z83203). Antimicrobial susceptibility testing revealed multidrug resistance to various ß-lactams. Histopathological examination demonstrated multiorgan damage, including enterit</p> ... Show More
View Publication
Scopus Crossref
Publication Date
Tue Jun 24 2025
Journal Name
Baghdad Science Journal
Accelerating Face Mask Detection Training Model Based on Multi-GPUs and Multi-core CPU
...Show More Authors

Modern machine-learning applications require GPUs, and modern platforms can leverage numerous GPUs on one or more machines to increase performance. Contemporary deep-learning models are too huge for CPU or GPU training. Training these models with many GPUs without performance degradation is necessary to train them rapidly and maximize GPU consumption. Thus, training deep convolutional neural networks (DCNN) with multiple GPUs has become necessary for improving training. Therefore, we presented a parallel design and development of an efficient model for enhancing face mask CNN performance and improving resource efficiency. This DCNN model is a parallel training system over multiple GPUs, a multi-core CPU, and a multi-process GPU platform wit

... Show More
View Publication Preview PDF
Scopus Crossref