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.
With the high usage of computers and networks in the current time, the amount of security threats is increased. The study of intrusion detection systems (IDS) has received much attention throughout the computer science field. The main objective of this study is to examine the existing literature on various approaches for Intrusion Detection. This paper presents an overview of different intrusion detection systems and a detailed analysis of multiple techniques for these systems, including their advantages and disadvantages. These techniques include artificial neural networks, bio-inspired computing, evolutionary techniques, machine learning, and pattern recognition.
Background: Parvovirus B19 is a human pathogenic virus associated with a wide range of clinical conditions. During pregnancy congenital infection with parvovirus B19 can be associated with poor outcome, including miscarriage, fetal anemia and non-immune hydrops.
Objective: The study aimed to determine the prevalenceof Parvovirus B19 DNA in pregnant women attending the Military hospital in Khartoum, demonstrating the association between the virus and poor pregnancy outcomes.
Subjects and methods: This study was a cross sectional study, testing pregnant Sudanese women whole blood samples (n= 97) for the presence of Parvovirus B1
... Show MoreThe catalytic activity of faujasite type NaY catalysts prepared from local clay (kaolin) with different Si/Al ratio was studied using cumene cracking as a model for catalytic cracking process in the temperature range of 450-525° C, weight hourly space velocity (WHSV) of 5-20 h1, particle size ≤75μm and atmospheric pressure. The catalytic activity was investigated using experimental laboratory plant scale of fluidized bed reactor.
It was found that the cumene conversion increases with increasing temperature and decreasing WHSV. At 525° C and WHSV 5 h-1, the conversion was 42.36 and 35.43 mol% for catalyst with 3.54 Si/Al ratio and Catalyst with 5.75 Si/Al ratio, respectively, while at 450° C and at the same WHSV, the conversion w
In this work the design and application of a fuzzy logic controller to DC-servomotor is investigated. The proposed strategy is intended to improve the performance of the original control system by use of a fuzzy logic controller (FLC) as the motor load changes. Computer simulation demonstrates that FLC is effective in position control of a DC-servomotor comparing with conventional one.
The concept of a small f- subm was presented in a previous study. This work introduced a concept of a hollow f- module, where a module is said to be hollow fuzzy when every subm of it is a small f- subm. Some new types of hollow modules are provided namely, Loc- hollow f- modules as a strength of the hollow module, where every Loc- hollow f- module is a hollow module, but the converse is not true. Many properties and characterizations of these concepts are proved, also the relationship between all these types is researched. Many important results that explain this relationship are demonstrated also several characterizations and properties related to these concepts are given.
In the present paper, discuss the concept of fuzzy topological spectrum of a bounded commutative KU-algebra and study some of the characteristics of this topology. Also, we show that the fuzzy topological spectrum of this structure is compact and T1 -space.
In this research for each positive integer integer and is accompanied by connecting that number with the number of Bashz Attabq result any two functions midwives to derive a positive integer so that there is a point
The aim of this paper is to introduce and study the notion type of fibrewise topological spaces, namely fibrewise fuzzy j-topological spaces, Also, we introduce the concepts of fibrewise j-closed fuzzy topological spaces, fibrewise j-open fuzzy topological spaces, fibrewise locally sliceable fuzzy j-topological spaces and fibrewise locally sectionable fuzzy j-topological spaces. Furthermore, we state and prove several Theorems concerning these concepts, where j = {δ, θ, α, p, s, b, β}.