Search
628 articles for “neural”
-
Perceptual Features Based Continuous Speech Recognition in Additive Noise Environment Using Various Modelling Techniques
Abstract: The main objective of this paper is to discuss the effectiveness of Mel frequency perceptual features and the noise reduction technique in evaluating the performance of multi speaker independent continuous speech recognition system in additive noise environment by using various modelling techniques. The proposed perceptual features are captured and trained using clustering technique, GMM, continuous density HMM and back propagation neural networks. Speech recognition system is evaluated on clean and …
Published in Current Trends in Signal Processing · Vol. 2, Issue 1-3, 2012 · pp. 67–81 Read article
-
Principal Component Analysis Based Dominant Features Selection Method for Speaker Identification
Abstract: Cepstrum based features are mostly used in speaker identification. Mel-frequency cepstrum coefficients (MFCCs) and their statistical properties (skewness, kurtosis and standard deviation) are used in this paper for text-dependent speaker identification. Principal component analysis (PCA) is employed to select the dominant feature vector representing the speaker characteristics. Multi-layer neural network is used as the classification engine. There occurs the inter-speaker variation of speech length uttering the same word. The feature …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 33–45 Read article
-
Controller Performance Assessment (CPA) of Intelligent Control for Non-linear System
Abstract: The objective of this paper is to design and undertake comparative analysis of classical and intelligentcontrollers for nonlinear system. These controllers are compared based on controller performanceassessment in which the different parameters as overshoot, steady-state error, rise time, settling time,response of reference change and output variance are analyzed. To achieve these objectives, the water tankcontrol problem as nonlinear system has been built in Simulink and implementations traditionally classicalcontroller and advance …
Published in Journal of Control & Instrumentation · Vol. 1, Issue 1-2-3, 2011 · pp. 25–33 Read article
-
Smart Electronic Real Time Text Recognition Application
Abstract: AbstractThe area of application of optical character recognition has been expanded in the last few years. There are many techniques which exist and provide high recognition rate, but it consumes time in training the network. Various mobile applications have been designed for optical character recognition (OCR) in Android platform and iOS platform. The limitation of such application is computation ability of mobile processor. This paper proposes a framework of optical …
Published in Journal of Electronic Design Technology · Vol. 8, Issue 3, 2017 · pp. 1–7 Read article
-
Automatic Chest X-ray Report Generation Using Machine Learning
Abstract: In this study, a deep neural network is suggested for the automatic creation of precise radiologist reports from chest X-ray pictures. The proposed network responds to the need for medical image captioning by learning to extract key features from the image and creating tag embeddings for each patient's X-ray images. Medical image captioning demands coherence and high accuracy in identifying abnormalities and extracting information. For a finer representation, the network …
Published in Journal of Instrumentation Technology & Innovations · Vol. 13, Issue 1, 2023 · pp. 29–39 Read article
-
Comparative Between (LiNbO3) and (LiTaO3) in Detecting Acoustics Microwaves Using Classification
Abstract: AbstractOur work is mainly about detecting acoustics microwaves in the type of BAW (Bulk acoustic waves), where we compared between Lithium Niobate (LiNbO3) and Lithium Tantalate (LiTaO3), during the propagation of acoustic microwaves in a piezoelectric substrate. In this paper, we have used the classification by Probabilistic Neural Network (PNN) as a means of numerical analysis in which we classify all the values of the real part and the imaginary …
Published in Journal of Microwave Engineering and Technologies · Vol. 5, Issue 3, 2018 Read article
-
A Novel Improved Model of Three-phase Shunt Active Power Filter using Adaptive Tabu Search and Genetic Algorithm in Aircraft Power Utility of 400 Hz
Abstract: A new improved model of aircraft shunt filter has been proposed in this paper. The shunt active power filter model has been improved using Adaptive Tabu Search Algorithm and Genetic Algorithm. ATS algorithm has been used to obtain the optimum value of parameters of the PI controller; whereas Genetic Algorithm has been used to find the optimum value of filter inductor used in active filter. The new improved model of …
Published in Journal of Power Electronics and Power Systems · Vol. 3, Issue 3, 2013 · pp. 6–14 Read article
-
Application of AI Techniques in Three-phase Shunt Active Power Filter in Unbalanced and Distorted Supply Conditions
Abstract: This paper deals with a new improved model of the shunt active power filter having the control scheme using Artificial Neural Networks (ANN) technique in unbalanced and distorted supply system. In this paper, three soft computing techniques viz; Genetic algorithm, Fuzz logic, neural network are used. The simulation results using MATLAB model confirm that combination of these algorithms together create an optimum system, which clearly proves the effectiveness of the …
Published in Journal of Power Electronics and Power Systems · Vol. 3, Issue 3, 2013 · pp. 15–26 Read article
-
Utilization of Statistical Learning Algorithms for Prediction of Elastic Modulus of Jointed Rock Mass
Abstract: This study uses two statistical learning algorithms for the prediction of elastic modulus (Ej) of jointed rockmass. The first algorithm uses support vector machine (SVM) that is firmly based on the theory of statisticallearning and uses regression technique by introducing -insensitive loss functionhas been adopted. Thesecond algorithm uses relevance vector machine (RVM). It is based on a Bayesian formulation of a linearmodel with an appropriate prior that results in a …
Published in Recent Trends in Civil Engineering & Technology · Vol. 1, Issue 1-3, 2011 · pp. 81–94 Read article
-
Website Summarization Using Deep Learning
Abstract: They are a lot of websites, articles and blogs on the internet with a lot of textual information it is sometimes impossible to read all of them, without knowing the underlying summary of the whole text. The whole concept is to reduce or minimize the entire Textual information into a small summary of important information present in the documents so that we get an idea of what the blog or …
Published in Recent Trends in Electronics Communication Systems · Vol. 9, Issue 2, 2022 · pp. 7–12 Read article
-
Process Variable Optimization and Experimental Review of Aero-engine Blade using ECM
Abstract: AbstractProcess of blade in (EMC) can be effected by numerous factors, e.g., shape of blade, electrolytic liquid field and anodic dissolution, ECM parameters may result in affections on blade accuracy. Some aero-engine blade as research object, five main process parameters, voltage, machining gap, feed rate, temperature of working fluid and pressure variation of electrolyte inlet/outlet, are evaluated and optimized as per BP neural network Method. From 3125 possible operating parameter …
Published in Recent Trends in Sensor Research & Technology · Vol. 5, Issue 3, 2018 · pp. 27–32 Read article
-
Adaptive Selective Harmonic Elimination Method for Quasi Z-Source Cascaded Multilevel Inverters in Varying DC Voltage Condition
Abstract: AbstractIn this paper, a new control method for adaptive selective harmonic elimination in a quasi Z-source cascaded multilevel inverter (QZS-CMI) is proposed. According to real condition, the DC sources feeding the inverter are considered to be varying in time. In this condition, the switching angle and shoot-through duty ratio for each module are obtained off-line for different DC source values using particle swarm optimization (PSO) algorithm. The off-line data set …
Published in Trends in Electrical Engineering · Vol. 4, Issue 3, 2014 · pp. 1–9 Read article
-
Multi-layer Perceptron Ensemble for Estimation of Available Transfer Capability in Deregulated Environment
Abstract: The available transfer capability (ATC) estimation problem can be considered as a unique answered puzzle to be solved with highly nonlinear complexity of power systems and the uncertain state of the energy market. To implement the open access in deregulated markets, system operator should post ATC at a small and regular interval on openly accessible network. This forces the quick computation of ATC of transmission path. In these situations, the …
Published in Trends in Electrical Engineering · Vol. 6, Issue 1, 2016 · pp. 57–71 Read article
-
Use of Intelligent Control Systems to Manage Traffic Effectively and Productively
Abstract: Intelligent control system is the advanced technology in which the collected data is provided to A.I. and with the help ofvarious methods like machine learning, neural networks, Bayesian probability, fuzzy logic the solution to a particularproblem is found.In a country’s growth the traffic management plays a great role as the maximum industries depends on the highways orroads and when it is well planned it can reduce the commute time and …
Published in Trends in Mechanical Engineering & Technology · Vol. 13, Issue 1, 2023 · pp. 22–27 Read article
-
Multi-variable Analysis and Optimization of Electrical Discharge Machining Process Using a PCA-ANN Based Approach
Abstract: AbstractThe optimum selection of process parameters has played a crucial role in electrical discharge machining (EDM) for improving the material removal rate, reducing the tool wear rate and radial overcut. In this paper, optimum parameters while machining 202 stainless steel using copper electrode as a tool has been investigated. For optimization of process parameters along with multiple quality characteristics, principal component analysis coupled with artificial neural network method has been …
Published in Trends in Opto-electro & Optical Communication · Vol. 6, Issue 3, 2016 · pp. 39–45 Read article
-
Revolutionizing Urban Traffic Management: An AI and Multi-Agent System Approach Leveraging IoT Technology
Abstract: Our study addresses the challenging issue of traffic congestion in modern urban areas and the limitations of traditional solutions like road expansion and network indicators. To effectively tackle traffic congestion, the study explores various strategies that analyze traffic elements, falling into the Macroscopic and Microscopic Models. However, conventional traffic modeling faces significant challenges in dealing with complex traffic systems.Artificial Intelligence (AI) techniques, including fuzzy logic, evolutionary algorithms, neural networks, and …
Published in Trends in Transport Engineering and Applications · Vol. 10, Issue 3, 2023 · pp. 1–8 Read article
-
A New Effective MUSIC Algorithm for Direction of Arrival Estimation and Combining It with Beam Forming in Smart Antenna Systems
Abstract: ABSTRACT Smart antenna is now commonly used in communication systems due to its high advantages. Two important functions in smart antenna are direction of arrival estimation and beam forming. The main aim of direction of arrival estimation in smart antenna is to estimate the direction of the signal and based on this angle the beam forming will identify the exact position and phase angle of the antenna. Here we proposed …
Published in Journal of Communication Engineering & Systems · Vol. 2, Issue 2, 2012 · pp. 1–6 Read article
-
Background Suppression for Visual Surveillance Using SOM
Abstract: AbstractBackground suppression is widely used approach for detection of moving objects in video streams which is the first relevant step of information extraction in many computer vision applications. Aside from the intrinsic usefulness of being able to segment video streams into moving and background components, detecting moving objects provides a focus of attention for recognition, classification, and activity analysis, making these later steps more efficient. An approach based on self-organization …
Published in Journal of Communication Engineering & Systems · Vol. 5, Issue 1, 2015 · pp. 15–20 Read article
-
Analysis of Various Tools of Natural Language Processing Based on Developers Perspective
Abstract: The subject of natural language method has visible mind-blowing development in current years, with neural network community substitution numerous of the traditional structures. A subset of artificial intelligence known as “natural language processing”, or NLP, analyses, comprehends, and generates natural human languages so that computers can reuse written and spoken human language without resorting to computer-generated language. Semantics and syntax are used in natural language processing, which is sometimes referred …
Published in Journal of Communication Engineering & Systems · Vol. 12, Issue 2, 2022 · pp. 1–5 Read article
-
Perturbed Quantum Computation of the Non-linear Dynamical System in Terms of Bose-Mesner Algebra Using N-Coupled Maps
Abstract: AbstractThe author has considered the non-linear dynamical system comprising of brain, heart, kidney, physiological processes, thinking mechanism and immune system. The components of the dynamical system are interconnected with each other. In the present work he has discussed the perturbation in the non-linear dynamical system due to intense BIS processes. The BIS processes occurring in the surroundings constantly affect our neural network bringing about sudden changes in nervous system. The …
Published in Journal of Computer Technology & Applications · Vol. 6, Issue 1, 2015 · pp. 27–42 Read article