Refine Search

New Search

Results: 60

(searched for: publisher_group_id:13636)
Save to Scifeed
Page of 2
Articles per Page
by
Show export options
  Select all
Mukil Alagirisamy
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 7, pp 1-10; https://doi.org/10.29284/ijasis.7.1.2021.1-10

Abstract:
A fully automatic Computer Aided diagnosis (CAD) of glaucoma is developed that aims to reduce the false positive detection rate and increasing the sensitivity of classification. It consists of three main steps: Region of Interest (ROI) extraction (Optic Disc (OD) region), feature extraction (micro textures) and classification using Linear Vector Quantizer-Artificial Neural Network (LVQ-ANN). The search area for glaucoma is the OD region wherein the cupping occurs, so in the first step ROI is extracted from the whole image. Feature extraction and classification are the most challenging tasks as the performance of the system depend both of them. Laws defined five spatial filters to extract micro-statistical estimators such as Level, Edge, Spot, Wave, and Ripple. Fundus images in three databases; DRISHTI-GS1, ORIGA, and RIM-ONE are classified using LVQ-ANN classifier. Results indicate the strength of the LVQ-ANN classifier for glaucoma diagnosis with sensitivity of 95.71% (DRISHTI-GS1), 83.33% (ORIGA) and 94.87% (RIM-ONE).
Ahmed A. Mustafa, Ahmed Ak. Tahir
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 7, pp 38-56; https://doi.org/10.29284/ijasis.7.1.2021.38-56

Abstract:
A new system for finger-vein recognition is proposed based on the Complete Local Binary pattern (CLBP) as afeature extractor and the Phase Only Correlation (POC) for post-processing alignment and for speeding up the system. The CLBP produces three components of image descriptors and thus holds more details compared to the previous methods such as the Local Binary Pattern (LBP), the Local Directional Pattern (LDP), the Local Line Binary Pattern (LLBP), the Repeated Line Tracking (RLT), the Maximum Curvature (MC) and the Wide Line Detector (WLD). In the proposed system, POC is used for two purposes. First, to increase the performance of the system the alignment between the CLBP components of the test image and the enrolled CLBP components are performed. Second, to speed up the matching stage, a portion of the enrolled images is excluded that are highly misaligned with the test image from the Hamming Distance (HD) measure competition in the matching stage. To make the system more secure against attacks targeting personal information, only CLBP components are enrolled in the system and the alignment process POC is implemented on these components without the need to original images. For image pre-processing a novel scheme of pre-processing methods is adopted including finger-vein localization, alignment, and the Region-Of-Interest (ROI) extraction and enhancement. Two databases, UTFVP and SDUMLA-HMT, are used to evaluate the performance of the system. The results have shown that the values for the Identification Recognition Rate (IRR) and the Equal Error Rate (EER) are respectively (99.66%) and (0.139) for the UTFVP database and (98.95%, and 0.53%) for SDUMLA-HMT database. These results are competitive compared to those achieved by the state-of-art systems.
Arnold Sachith A Hans, Smitha Rao
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 7, pp 11-20; https://doi.org/10.29284/ijasis.7.1.2021.11-20

Abstract:
Human beings while communicating use emotions as a medium to understand the other person. Face being the primary source of contact while communicating and being the most communicative component of the body for exhibiting emotions, facial emotion detection in videos has been a challenging and an interesting problem to be addressed. The Facial expressions fall under the category of non-verbal type of communication and understanding Emotional state of a person through Facial Expressions has many use cases such as in the field of marketing research – understanding the customers responses for various products, Virtual classroom – understanding the comprehension level of the students, Job Interview – in understanding the changes in emotional state of the Interviewee, etc. This research paper proposes a CNN- LSTM based Neural Network which has been trained on CREMA-D dataset and tested on RAVDEES dataset for six basic emotions i.e. Angry, Happy, Sad, Fear, Disgust, and Neutral. The Faces in the videos were masked using Open Face software which gets the attention on the Face ignoring the background, which were further fed to the Convolutional Neural Network. The research focuses on using LSTM networks which have the capability of using the series of data which will aid in the final prediction of emotions in a video. We achieved an accuracy of 78.52% on CREMA-D dataset and further also tested the model on RAVDEES dataset and achieved an accuracy of 63.35%. This research work will help in making machines understand emotions, can help systems make better decisions and respond accordingly to the user.
Ramitha M A, MohanaSundaram N
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 7, pp 30-37; https://doi.org/10.29284/ijasis.7.1.2021.30-37

Abstract:
In Deep Learning, a Convolutional Neural Network (CNN) extracts the features from the visual imagery. These features can be used for various complex tasks such as image classification and segmentation and detection of different objects. The convolutional layers are stacked over each other to form the state-of-the-art models. A modified SENet architecture is introduced in this study to classify pneumonia from chest x-ray images. Six ResNet blocks are connected back to back. The output from the sixth ResNet and the side outputs from the last three ResNets are fused together. This output is fed as input to the SENet block. The validation accuracy of this fusion architecture is 91.84% on chest x-ray images.
Stalin Jacob, Jenifer Darling Rosita
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 7, pp 21-29; https://doi.org/10.29284/ijasis.7.1.2021.21-29

Abstract:
The early detection of skin cancer can lead to high prognosis rate. Thus it is very important to identify abnormalities in skin as early as possible. However, the detection of abnormalities at their early stages is a challenging task since the shape and colour of the abnormalities vary with different persons. In this study, fractal model for skin cancer diagnosis is developed. Differential Box Counting (DBC) method is implemented to get the fractal dimension from the dermoscopic images from two databases; International Skin Imaging Collaboration (ISIC) and PH2 database. The fractal features are classified using a parametric and non-parametric classification approach. The system provides promising results for skin cancer diagnosis with 96.5% accuracy on PH2 images and 91.5% accuracy on ISIC database images using the non-parametric classifier whereas parametric classifier gives 95% (PH2) and 90% (ISIC) images.
Mustafa Mashali, Miftah Addeif, Mohamed Embarak
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 8-19; https://doi.org/10.29284/ijasis.6.2.2020.8-19

Abstract:
This paper aims for optimizing links length that consumed the minimum energy, for a customized Selective Compliant Assembly Robot Arm (SCARA) robot. Nine link length combinations are tested and simulated. This research is a part of a project of designing a robotic arm for a packing task. Kinematic and dynamic studies are performed for a 2R robotic arm. The results of kinematic study which are angular displacement, angular velocity and angular acceleration for each joint are determined and exported to the dynamic study to obtain the torque and power consumed. The dynamic study is performed with the aid of MATLAB code, MATLAB/SimMechanics and Solidworks are used to simulate and analyze the dynamic of the robotic arm. The energy consumed for each link length combination using the three methods is calculated.
Ibrahim A. Farhat, Abdullah O. Hawal
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 1-7; https://doi.org/10.29284/ijasis.6.2.2020.1-7

Abstract:
The problem of Maximum Loadability of power systems is addressed in this paper using a proposed dynamic JAYA algorithm. The maximum loadability problem is a typical optimization problem in which the maximum loadability point is to be determined optimally. Voltage stability of power systems is maintained by determining the estimated margin between the system operating point and the maximum loadability limit. The basic JAYA algorithm has been introduced to solve foremost optimization problems with small-scaled nature. However, when applied to large-scale, nonlinear and non-convex constrained problems, it showed a poor convergence characteristic. In order to deal with these weaknesses, the original algorithm has been improved by adding some dynamic features to its convergence behavior. The modified algorithm has been presented and validated when applied to well-known typical power systems. The obtained results were compared to the results achieved by other equivalent optimization techniques.
Salem A. S. Ahbil, Hamid H. Sherwali
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 29-39; https://doi.org/10.29284/ijasis.6.2.2020.29-39

Abstract:
In this paper, a methodology for estimating end-use load shapes using the hourly whole-house metered load data, the household demographic survey data and the weather data (temperature) is presented. End use load shapes presents a method of generating realistic electricity load profile data for some of city of Tripoli domestic buildings. This method could help in predicting the daily load profile from individual flats to community. The results obtained show that the overall methodology provides an effective means for end-use load shape modeling and estimation.
Mohamed Elsharif, Tareq Elgargani
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 20-28; https://doi.org/10.29284/ijasis.6.2.2020.20-28

Abstract:
High performance motor drives require high accuracy, fast response, wide range of control, robustness and immunity from the effect of parameter variations. Three phase motors have a complex and highly nonlinear mathematical model associated with interactive parameters. This makes designing a conventional controller for such a system is a hard task. Researchers are paying more attention to fuzzy logic controllers (FLCs) since they can be employed to control complex or nonlinear systems even without knowing their mathematical model. The main task of this paper is to design and implement an FLC for indirect field orientated control of a three phase induction motor drive. The proposed controller is a proportional-derivative (PD) FLC. It uses the speed and its derivative as input and the electromagnetic torque as output. The input and output are coupled with simple linguistic if-then rules. The spread of each input and output is adjusted using a gain block to achieve the best performance in a trial-and-error process. Also, an incremental counter is attached to the output of the controller to yield the desired electromagnetic torque. The design was implemented and tested using MATLAB/SIMULINK. Finally, the simulation results and figures were presented.
Abdusalam Yahya, Ashraf Gasim Elsid Abdalla
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 40-49; https://doi.org/10.29284/ijasis.6.2.2020.40-49

Abstract:
Voiceover Internet Protocol (VoIP) application is a vital technology that is quickly growing in the Mobile Ad hoc NETwork (MANET). Packet loss is a factor that can significantly affect the Quality of Service (QoS) for VoIP performance. Due to the dynamic nature of MANET, it is a challenging task to maintain the desired packet loss rate. This paper aims to enhance the performance of VoIP in the MANET using a fuzzy logic model. The input for the model is VoIP packet loss and the outputs are the optimal parameters of MANET (node number, pause time, maximum speed, and maximum connection).Network Simulator (NS2) was used to perform all simulations. MATLAB was used to implement the proposed fuzzy model. Moreover, the performance of the model was evaluated using NS2, and the results show that our proposed fuzzy model offers a significant enhancement in terms of the VoIP packet loss rate (P.LR).
Sundaramoorthi P, Rajeenamol P.T, Anoopkumar M.V
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 38-44; https://doi.org/10.29284/ijasis.6.1.2020.38-44

Abstract:
A device to know the health status of all the animals in a farm along with its missing and theft prevention is proposed in this article. The necessary sensors to sense the health information of animals and the short range wireless communication technology and internet to communicate with the owner of the farm, are planned to use in the devices. This system will be very helpful to diagnose the health condition of all the animals simultaneously and to improve it. The system can prevent the animals from missing or theft. A mobile application which acts as a user interface provides the owner with useful information such as animal’s body temperature, heart rate, rumination and their presence inside the farm. The prototype of this idea is developed and is included for testing. Since the animal health status can be monitored from anywhere in world using a mobile application, the device will ease the work of farm owner and the laborers.
Wogderes Semunigus
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 1-11; https://doi.org/10.29284/ijasis.6.1.2020.1-11

Abstract:
The emergence of High Resolution Computed Tomography (HRCT) images of the lungs clearly shows the parenchymal lung architecture and thus the quantification of obstructive lung disease becomes most accurate. In this study, an automated system to diagnose obstructive lung disease called emphysema is presented using HRCT images of the lungs. The kind of texture information that ideally can be extracted from HRCT images depends on the multi-resolution representation system. The proposed Pulmonary Emphysema Analysis (PEA) system employs Shearlets as it can extracts more texture information than wavelets in different directions and levels. Radial Basis Function Network (RBFN) is employed for the classification of HRCT images into three categories; Normal Tissue (NT), Paraseptal Emphysema (PSE) and Centrilobular Emphysema (CLE). Results prove that a confident diagnosis of pulmonary emphysema is established to help clinicians which will also increase the precision of diagnosis.
Santosh Kumar Srivastava
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 29-37; https://doi.org/10.29284/ijasis.6.1.2020.29-37

Abstract:
In this study, Acoustic Scene Classification (ASC) system is designed with the help of S-transform and Gaussian Mixture Model (GMM). The S-transform is an extension of continuous wavelet transform that combines the progressive resolution with phase information. Thus, it exhibits the amplitude response of the frequency samples in contrast to wavelet transform. The S-transform coefficients are modeled by GMM using posterior probabilities of testing features. Also, preprocessing of acoustic signals is done by a series of operations; explosion, pre-emphasis filtration and windowing approach. The number of Gaussian components which is used to model the scene is varied (GMM-4, GMM-8, GMM-16, and GMM-32) and the performance of ASC system is analyzed using TAU Urban Acoustic Scenes 2019. The results show the effectiveness of the system with average recognition rate of 77.59%, 81.58%, 87.66% and 84.50% for GMM-4, GMM-8, GMM-16, and GMM-32 respectively.
Pandiaraj R, Rani Hemamalini R
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 21-28; https://doi.org/10.29284/ijasis.6.1.2020.21-28

Abstract:
End users of electricity want to receive a quality and reliable electric power without interruption all the time throughout year. Even though, power generation station maintains quality, some natural and man-made sources affect the quality of electric power supply being distributed. Various conventional devices are available to improve electric power quality, but their performance is inadequate. The main aim of the work is to design and simulate a system which provides quality and reliable electric power. The system uses Distribution STATic COMpensator (DSTATCOM) to maintain the power at near sinusoidal voltage and at designed frequency. DSTATCOM is a shunt connected Voltage Source Inverter (VSI) based custom power device, used to mitigate power quality issues. The system also uses the fuzzy logic control algorithm, to control the Pulse Width Modulation (PWM) controllers used in VSI of DSTATCOM.
Shekaina Justin, Manjula Pattnaik
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 6, pp 12-20; https://doi.org/10.29284/ijasis.6.1.2020.12-20

Abstract:
Skin lesion segmentation is an imperative step for image analysis and visualization task. Manual segmentation by an expert operator is too time-consuming and its accuracy may be degraded by different human operators. An automatic segmentation method is therefore required and one of the important parts in any classification system. In this work, more accurate skin lesion segmentation by Pixel-by-Pixel (PbP) approach using deep learning is presented. Before employing PbP approach, dermoscopic images are prepared for more accurate segmentation by Top-Hat Transform (THT) which removes the hair in the skin regions. The PbP approach has four stages; study the training images consists of skin lesions, construction of deep learning network followed by training it and finally evaluate the network with testing images. The evaluation of PbP approach is carried out using PH2 database images. Results of PbP approach in terms of Jaccard Index (JI), Accuracy (Acc) and DIce Coefficients (DIC) show the effectiveness of the system for skin lesion segmentation.
Ajay Kumar Gupta, Rama Krishna K
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 5; https://doi.org/10.29284/ijasis.5.2.2019.32-38

Vijayalakshmi N
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 5, pp 8-14; https://doi.org/10.29284/ijasis.5.1.2019.8-14

Abstract:
In this study, an efficient technique to improve and maintain the voltage levels of Cascaded H-Bridge Multi-Level Inverter (CHB-MLI) which utilizing PhotoVoltaic (PV) panel sources is presented. It is designed to make fifteen level output voltage and tested under the various levels of resistive loads. It produces staircase output with reduced component size, increases the output voltage level, reduces the voltage stress across the load/switches, reduces the Total Harmonic Distortion (THD) and increases the voltage gain. The switching pulses are generated using Phase Opposition Disposition (POD)-Pulse Width Modulation (PWM) technique. It is modeled and simulated using SIMULINK graphical programming environment in MATLAB. Results prove that the system provides lower THD than conventional systems.
, John Aravindar D
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 5, pp 15-21; https://doi.org/10.29284/ijasis.5.1.2019.15-21

Abstract:
The weld defects are formed due to the incorrect welding patterns or wrong welding process. The defects in the weld may vary from size, shape and their projected quality. The most common weld defects occur during welding process is slag inclusions, porosity, lack of fusion and incomplete penetration. In this study, an effective method for weld defect classification using machine learning algorithm is presented. The system uses Speeded-up Robust Features (SURF) for feature extraction and one of the machine learning algorithms called Auto-Encoder Classifier (AEC) for classification. Initially, the features that distinguish weld defects and no defects in the weld image are extracted by SURF. Then, AEC is analyzed for weld image classification using different number of neurons in different hidden layers (2 and 3 hidden layers). The performance of the system is evaluated by GD X-ray weld image database. The results show that the weld images are correctly classified with 98% accuracy using SURF and AEC.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 5, pp 22-28; https://doi.org/10.29284/ijasis.5.1.2019.22-28

Abstract:
In this study, an efficient system is designed to maintain the Direct Current (DC) link voltage and improving voltage gain at remote side inverter using Hysteresis Controller (HC). The energy from wind is fed to the Remote Area Power Systems (RAPS). There is a need to control the changing frequency due to environmental changes in order to sustain the voltage at inverter side. It is achieved by the HC controller that provides control signals to inverter switches. The two-levels of Energy Storage System (ESS) are used as battery at source side and transformer at load side. The battery stores energy from the power converter stage through bi-directional converter where the energy flows in both forward and reverse direction. The frequency regulation based RAPS system is implemented using MATLAB/Simulink tool.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 5, pp 1-7; https://doi.org/10.29284/ijasis.5.1.2019.1-7

Abstract:
An unidentified image sample is assigned to a recognized texture class is known as Texture Classification (TC). The main challenging task in TC is the non uniformity changes in orientation, visual appearance and scale. Texture is an important feature in computer analysis for the purpose of classification. In this paper, an efficient TC system based on Discrete Wavelet Transform (DWT) is presented. The performance of the system is evaluated by Brodatz database. At first, the DWT is used to decompose the input texture image for feature extraction at a particular decomposition level. From each sub-band coefficients statistical features are extracted. Finally, k-Nearest Neighbour (kNN) classifier is used for classification. Results show that a better classification accuracy of 94.72% is achieved by the features of 3rd level DWT and kNN classifier.
Mohana Priya R, Venkatesan P
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 5, pp 29-35; https://doi.org/10.29284/ijasis.5.1.2019.29-35

Abstract:
The uncontrollable cells in the lungs are the main cause of lung cancer that reduces the ability to breathe. In this study, fusion of Computed Tomography (CT) lung image and Positron Emission Tomography (PET) lung image using their structural similarity is presented. The fused image has more information compared to individual CT and PET lung images which helps radiologists to make decision quickly. Initially, the CT and PET images are divided into blocks of predefined size in an overlapping manner. The structural similarity between each block of CT and PET are computed for fusion. Image fusion is performed using a combination of structural similarity and MAX rule. If the structural similarity between CT and PET block is greater than a particular threshold, the MAX rule is applied; otherwise the pixel intensities in CT image are used. A simple thresholding approach is employed to detect the lung nodule from the fused image. The qualitative analyses show that the fusion approach provides more information with accurate detection of lung nodules.
Suseela B
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 23-30; https://doi.org/10.29284/ijasis.4.2.2018.23-30

Abstract:
Modern progress in Wireless Sensor Networks (WSNs) for instance observation, traffic observation as well as storeroom of probable applicable are planned to cherish the authentic planet. For these network severe necessities of quick, dependable protocol to convene the restraint that is latency, highest packet received ratio, good put as well as energy efficiency. In this article we have reviewed the several multi path routing protocols such as Energy Efficient Multi Path (EEMP) routing protocol, Secure and Energy efficient Multi Path (SEMP) routing protocol, Bandwidth Aware Multi Path (BAMP) routing protocol, Cooperative Multi Path (CMP) routing protocol as well as QoS Multi Path (QoSMP) routing protocol. The simulation of multi path routing is offered depend on packet received ratio, average delay as well as energy efficiency in WSN.
Karthick R
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 16-22; https://doi.org/10.29284/ijasis.4.2.2018.16-22

Abstract:
Age Group Classification (AGC) is a difficult task due to variations in human genders, expression, races, poses and so on. The age group analysis is used in multimedia forensic investigation for crime scenes. In this study, an efficient method for AGC is presented. AGC system uses mainly two stage; preprocessing and classification. The preprocessing stage consists of face region detection, gamma correction, Difference Of Gaussian (DOG) filter and normalization. Then the preprocessed images are given to Visual Geometric Group (VGG) 16. The convolution and max-pooling layers in VGG 16 architecture is used to resize the image. The REctified Linear Unit (RELU) is used as an activation function in each convolution and max-pooling layer. The sigmoid layer is used for the AGC into adolescence, adult and senior adult. The system uses MORPH database for the performance evaluation. AGC system produces the classification accuracy of over 90% for all age groups using VGG16 architecture.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 31-37; https://doi.org/10.29284/ijasis.4.2.2018.31-37

Abstract:
Facial expression analysis (FEA) or Human Emotion Analysis (HEA) is an essential tool for human computer interaction. The nonverbal messages of humans are expressed by facial expression. In this study, an HEA system to classify seven classes of human emotions like happy, sad, angry, disgust, fear, surprise and neutral is presented. It uses Gabor filter for feature extraction and Multiple Instance Learning (MIL) for classification. Gabor filter analyzes the facial images in a localized region to extract specific frequency content in specific directions. Then, MIL classifier is used for the classification of emotions into any one of the seven emotions. The evaluation of HEA system is carried on JApanese Female Facial Expression (JAFFE) database. The overall recognition rate of the HEA system using Gabor and MIL technique is 95%.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 8-15; https://doi.org/10.29284/ijasis.4.2.2018.8-15

Abstract:
An efficient Fast Fourier Transform (FFT) algorithm is used in the Orthogonal Frequency Division Multiplexing (OFDM) applications in order to compute the discrete Fourier transform. Also, a Single Path Delay Feedback (SDF) which is pipeline FFT architecture is used for faster performance to achieve high throughput. In conventional method, the FFT design has high delay and power due to time taken by the multiplication part. To decrease the delay, Kogge Stone Parallel Prefix Adder (KSPPA) is used with booth multiplier. As SDF is a simpler approach to realize FFT in different length, 64-point Radix-4 SDF-FFT algorithm using KSPPA in the booth multiplier is discussed in this study. The system is implemented in Xilinx 12.4 ISE and simulated using MODELSIM 6.3c. Results show that the system reduces the delay and power.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 1-7; https://doi.org/10.29284/ijasis.4.2.2018.1-7

Abstract:
An Automatic Modulation Classification (AMC) system for Software Defined Radio (SDR) is presented in this study. Initially, the generated signals are modulated using different modulation techniques. Then, noise is added to the generated signals by using Additive White Gaussian Noise (AWGN). The noise added signal is used for further process to extract features and classification. The system uses Discrete Wavelet Transform (DWT) to analyze the signal that produces lower and higher frequency sub-bands. The Independent Component Analysis (ICA) is employed on lower frequency sub-band for dimensionality reduction. Finally, the classification is made by Pulse Coupled Neural Network (PCNN). The system uses three different digital modulation schemes; Phase Shift Keying (PSK), Quadrature Amplitude Modulation (QAM), and Differential PSK (DPSK). The results show the DWT, ICA and PCNN based AMC system provides promising results under various noise densities.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 8-15; https://doi.org/10.29284/ijasis.4.1.2018.8-15

Abstract:
Adiabatic logic circuit designs are used to reduce power dissipation in any circuits. For low power and low noise emission applications, adder plays a vital role. The Complementary Metal Oxide Semiconductor (CMOS) design of 16-bit Brent-kung adder provides less number of gates but it generates high power due to switching activities of the design. To overcome this problem, 16-bit Brent-kung adder is designed using complementary Pass Transistor Energy Recovery adiabatic Logic (CPERL) with less number of gates. Also, low power dissipation is achieved which can be used for long life battery operations. The CPERL based system offers 59.97% reduction in power when compared to the conventional design. Experimental results are obtained using TANNER EDA tool 13.1.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 16-22; https://doi.org/10.29284/ijasis.4.1.2018.16-22

Abstract:
The amount of plaque in coronary arteries in any particular point is identified by the IntraVascular UltraSound (IVUS) images. The classification of IVUS images is very important to diagnose various coronary artery diseases. In this study, the classification of IVUS images based on Non-negative Matrix Factorization (NMF) technique and Maximum Likelihood Classifier (MLC) is presented. Initially, the IVUS images are given to frost filter to remove speckle noise as the imaging technique uses ultrasound waves. Then, NMF technique is employed to extract the features and stored in database. Then MLC is used for classification of IVUS images for both normal and abnormal categories. The IVUS Image Classification (IIC) system obtains 98% classification accuracy by using NMF features and MLC classification.
Raja V L
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 1-7; https://doi.org/10.29284/ijasis.4.1.2018.1-7

Abstract:
He surface grading of ceramic tiles is essential for ceramic tile industries due to the huge development of infrastructure and essential usage of ceramic tiles. In some industries, surface grading is performed manually. It is a difficult task due to a large number of variations in the surface properties. In this study, a technique for surface grading of ceramic using deep learning is presented. The system uses the VxC Tiles of Surface Grading (TSG) database for performance evaluation. The deep learning based Convolution Neural Network (CNN) is used for the surface grading approach that classifies the tiles into Grade-1 (G1), Grade-2 (G2) and Grade-3 (G3). The system uses seven layers in CNN, which includes convolution, pooling and fully connected layers. Initially, the input tile image is converted Red, Green and Blue (RGB) color channels, and then CNN approach is applied for the classification of tile images. Experimental results show the better classification accuracy of 96.17% for surface grading of ceramic tiles using a deep learning approach.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 30-36; https://doi.org/10.29284/ijasis.4.1.2018.30-36

Abstract:
The information about the classification of plant leaf into appropriate taxonomies is very useful for botanists. In this study, an efficient Plant Leaf Recognition (PLR) system is designed using kernel ensemble approach by Support Vector Machine (SVM). At first, the plant leaf images are normalized and resized by color normalization and bicubic interpolation. Features such as 4th order color moments and nine energy maps of LAWS are combined to form a feature database. The classification is done by ensemble approach with different SVM kernels like Linear (SVM-L), Radial basis function (SVM-R), Polynomial (SVM-P) and Quadratic (SVM-Q). Finally, the outputs of each SVM classifier are fused to classify plant leaf images. The PLR system is carried on using Folio database that contains 640 leaf images captured from 32 species. The system achieves 90.63% recognition rate by the ensemble approach using colour moments and texture features by LAWS.
Reka R
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 4, pp 23-29; https://doi.org/10.29284/ijasis.4.1.2018.23-29

Abstract:
The main aim of the image segmentation is to change the representation of the image so that the boundaries and objects in an image can be easily observed. In this study, a novel algorithm is proposed for the image segmentation using gray scale images. The codebook algorithm is used in the proposed approach for optimal multidirectional thresholding approach. The background and foreground pixel values are stored in the codebook. It uses standard deviations along the four directions to search the background and foreground pixels iteratively. The misclassification error and Jaccard index are used to measure the system efficiency. The mean of misclassification error is 95.80% with standard deviation of 1.91 and the mean of Jaccard index is 92.36% with standard deviation of 5.6. These measures shows the efficacy of the proposed system.
, Rani Hemamalini R
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 14-20; https://doi.org/10.29284/ijasis.3.2.2017.14-20

Abstract:
Thinking about the ON/OFF state of electrical appliances, gas regulator and worrying about the safety of costly things in home are common to everyone. Carelessness or failing to off the appliances sometimes may cause minor or major accidents in home. The modern technologies available today will gives lot of solutions to overcome this problem. This paper gives details about a device built with sensors and Internet of Things (IoT), ZigBee wireless technology and a mobile phone application for monitoring and controlling. IoT means, things that are connected to internet and capable of accessing from anywhere. The device monitors the house with the help of sensors connected to it and updates information to the owner’s mobile phone through internet connection available in the house. The same way owner can control the home appliances and know its status from the mobile application. This device will reduce the burden of the owners, by keeping them aware of their home anywhere anytime. This device can also be useful for elderly and physically challenged people to control the appliances from mobile phone which is acting as a remote control in this device.
Jaison B
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 1-7; https://doi.org/10.29284/ijasis.3.2.2017.1-7

Abstract:
Gender identification or classification is a challenging task in computer vision as the biometrics of male and female such as fingerprints, face, vein have many variations. Among the various biometrics, fingerprints are commonly available in a crime scene. In this, study, gender identification system for crime scene analysis using fingerprints is presented. Initially, the fingerprints are de-noised by median filter and Otsu thresholding is employed to binarize the fingerprints in the preprocessing stage. Then, the features are extracted by Box-Cox transformation method. Finally, the classification is made by logistic regression classifier. A better classification accuracy of 96% is achieved by the gender identification system using Box-Cox transformation and logistic regression classifier.
Salai Thillai Thilagam J
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 21-26; https://doi.org/10.29284/ijasis.3.2.2017.21-26

Abstract:
The major concern for the governments and private network communication is the security of systems against eavesdropping and illegal access. To overcome such illegal access the security of modern computer systems uses public-ciphers key namely Rivest, Shamir and Adleman (RSA). The RSA provides both authentication and secrecy of communication. In conventional encryption method the cryptography using RSA provides good secrecy and reduces area but generates more delay due to time taken by the multiplication part. To overcome such a problem, a 32-bit RSA using modulo (2n+1) multiplication based VLSI architecture is presented in this study. This method offers less delay with high performance which can be used in any communication network field. The proposed method is implemented using Xilinx 12.4 ISE and simulated in MODELSIM 6.3c.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 27-33; https://doi.org/10.29284/ijasis.3.2.2017.27-33

Abstract:
Video classification is one of the rising fields in the video analysis. A large number of videos are accessed by people’s daily from television and internet. It is easy for humans to index the video from the collection of videos which contains news, cartoon, sports, comedy and drama. Among the categories, sports video plays a vital role due to their commercial demand. There is a similarity between the different sports video which makes the classification task difficult. In this study, the sports video categorization for five categories of sports like football, cricket, volleyball, tennis and basketball is presented. The sports video categorization system uses Higher Order Spectra Features (HOSF) for the feature extraction from video frames and multiclass Support Vector Machine (SVM) classifier for the classification of videos. The system gives average classification accuracy of 93.44% using HOSF and multiclass SVM classifier.
Thivya K.S, Anandhi S, Sudhaman K
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 8-13; https://doi.org/10.29284/ijasis.3.2.2017.8-13

Abstract:
Quantum Cellular Automata (QCA) is a transistor-less computation model that addresses the problem of device interconnection and density which holds the promise of high speed and fewer sizes compare to the Complementary Metal Oxide Semiconductor (CMOS) design. In this study, the design of 4-bit down asynchronous counter which is the fundamental block of the digital technology using new D-Flip Flops (D-FF) layouts is discussed. This D-FF is designed using majority gates. The FF clock inputs are not driven by the same clock and each FF output depends on the previous output. This design finds its application in nanotechnology fields including medical field to monitor the patient’s activity by utilizing timer based tools. The design of 4-bit down asynchronous counter is simulated in the QCA design tool.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 19-24; https://doi.org/10.29284/ijasis.3.1.2017.19-24

Abstract:
Deoxyribo Nucleic Acid (DNA) microarrays are widely used to monitor the expression levels of genes in parallel. It is possible to predict human cancer using the expression levels from a collection of DNA samples. Due to the vast number of genes expression level, it is challenging to analyze them manually. In this paper, data mining approach is used to extract the prevailing information from DNA microarray with the help of multiresolution analysis tool. Dual Tree M-Band Wavelet Transform (DTMBWT) is employed for the extraction of features from the given dataset at the 2nd level of decomposition. K-Nearest Neighbor (KNN) classifier is used for cancer classification. Results show that KNN classifier classifies five different cancer datasets; Breast, Colon, Ovarian, CNS, and Leukemia with over 90% accuracy.
, Mohan Kumar N
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 7-12; https://doi.org/10.29284/ijasis.3.1.2017.7-12

Abstract:
A communication tool in the form of sign language is required for deaf and dump persons as there is no oral communication possible between them. They perform the conversion of sign languages into voice/text. Recently, many algorithms are developed for this purpose. An Indian Sign Language Recognition (ISLR) system is presented in this paper. It uses curvelet transform based entropy features for the recognition, and the transform is applied only to the segmented hand region. Then, the features of each sign of English alphabets are modelled by a classier network called Hidden Markov Models (HMM). The system gives an average accuracy of 82.95% using 3rd level features which can help to reduce the communication gap between deaf-dumb and normal people in the world.
Gokul Kannan K,
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 1-6; https://doi.org/10.29284/ijasis.3.1.2017.1-6

Abstract:
Glaucoma is an eye condition which is caused by the improved blood pressure in the optic nerve. It causes a functional failure of the visual field and irreversible. A Computer Aided Diagnosis (CAD) can help the doctors to find glaucoma at the earliest. In this paper, a CAD system for glaucoma diagnosis using Discrete Orthogonal Stockwell Transform (DOST) is presented. DOST distribute its coefficients based on sample spacing paradigm where low frequencies have a lower sampling rate, and high frequencies have higher sampling rate. All DOST coefficients are considered for the diagnosis of glaucoma using Random Forest (RF) classifier. Results show that the glaucoma diagnosis system has 96% sensitivity, 92% specificity, and 94% accuracy using 100 fundus images of normal and glaucoma cases.
Keerthi Anand V D
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 13-18; https://doi.org/10.29284/ijasis.3.1.2017.13-18

Abstract:
Speaker recognition plays an important role in a biometric based identification of the person using the information available in their speech signals. In any speaker recognition system, feature extraction using signal processing approaches is an important stage. In this paper, an efficient speaker recognition system is presented by extracting the energy features of the speech signals using Discrete Wavelet Transform (DWT). Then, the extracted DWT energy features are modeled using Gaussian mixture model (GMM) classifier for the recognition of the speaker. Results prove the efficiency of the speaker recognition system with an accuracy of 96.31% at 4th level DWT features with 16 Gaussian densities.
, Himanshu Shekhar
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 3, pp 25-30; https://doi.org/10.29284/ijasis.3.1.2017.25-30

Abstract:
For efficient digital FIR filter applications, the Multiplication and Accumulation (MAC) unit is implemented by using various methods. In a digital filter, the MAC unit is one of the main units for performing multiplications and additions. This paper presents an efficient filter design for digital signal processing (DSP) applications with the reduction of carry propagation. In general, the performance of transpose filter mainly depends on the design of MAC unit. The design of a traditional filter consists of a large number of logical elements and has a high computational delay due to the conventional MAC unit. To design an efficient MAC unit, a serial adder is employed by using 2:1 multiplexer and a shifter block. The proposed work is implemented by using Xilinx ISE synthesis tool.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 2, pp 27-33; https://doi.org/10.29284/ijasis.2.2.2016.27-33

Abstract:
The knowledge obtained from a classification system is increasingly important for making a final decision. In this paper, a skin cancer classification system using Non-Sub sampled Contourlet Transform (NSCT) is presented. It uses double iterated filter banks to detect point discontinuities by a Laplacian pyramid and directional features by a directional filter bank. It allows the approximation of given image into a smooth contour at various level of decomposition. The Bayesian classifier is utilized in this work to classify the dermoscopic images in the PH2 database into normal or abnormal. From the results of the system, the melanoma image classification system can be used as a tool to make a final decision for the physicians.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 2, pp 1-8; https://doi.org/10.29284/ijasis.2.2.2016.1-8

Abstract:
Online Social Networks (OSNs) is major prevalent interactive media in current days to divide, collective, and allocate an essential amount of human life messages. In OSNs, messages filtering can also be worn for a dissimilar, more reactive, meaning. It is happening because of the alternative of posting or remarking different posts on fastidious open/private locales, brought in General Messages. Messages separating can thusly be utilized to give clients the fitness to naturally control the messages composed on their messages, by sifting through disposed of messages. Facebook enables clients to state to post messages (i.e., companions, characterized gatherings of companions or companions of companions). To overcome the problems, the proposed mechanism implements an estimated automated framework, is defined Filtered Wall (FW), to filter discarded content from OSN user contents. The objective of paper is to utilize effective classification technique to avoid overpowered by unsuccessful messages. Content filtering can additionally misused for a disparate, more responsive for OSNs. The procedures outline of a framework gives adaptable substance based content filtering for OSNs, in light of ML strategy. It sets up the connections similarly with the condition of the expertise in content-based separating based personalization for OSNs down alongside web substances. The focal segments of the Filtered Wall scheme are the Content Based Messages Filtering (CBMF) and the Short Text Classifier essentials. Based on experimental evaluations, proposed method performs good precision, recall and F1 score on overall dataset.
Pandiaraj P
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 2, pp 9-13; https://doi.org/10.29284/ijasis.2.2.2016.9-13

Abstract:
An efficient design of combined radix-2 Single path Delay Feedback (SDF)-Single path Delay Commutator (SDC)-Decimation In Frequency (DIF) algorithm is proposed in this paper which can be used in Orthogonal Frequency Division Multiplexing (OFDM) with Multiple Input Multiple Output (MIMO) applications. The MIMO-OFDM communication system has tremendous and swift growth in various applications used over last decade, especially wireless and digital communication where adaptability, reconfigurability, less chip size, hardware improvements, and lower power consumption are mandatory requirements during communication. The main aim of this structure is to improve the performance of combined Fast Fourier Transform (FFT) for the MIMO-OFDM system and also to reduce the complexity of the hardware.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 2, pp 21-26; https://doi.org/10.29284/ijasis.2.2.2016.21-26

Abstract:
Speech enhancement techniques are very important in the field of signal processing for their numerous applications. They are employed in many contexts such as hands-free telephony, hearing aid systems, re-mastering of audio recordings, preprocessing for speech recognition interfaces, etc. In this paper, an efficient cascade combination approach for cancellation of noises in speech signals is discussed. It is possible to obtain higher performance by cascading two or more algorithms. A better noise removal approach is presented by cascading wavelet and adaptive filters. Results show that the cascade approach gives high Peak Signal to Noise Ratio (PSNR) and low Root Mean Square Error (RMSE) than individual performances of wavelet and an adaptive filter.
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, Volume 2, pp 14-20; https://doi.org/10.29284/ijasis.2.2.2016.14-20

Abstract:
In this paper, an experimental evaluation of Mel-Frequency Cepstral Coefficients (MFCCs) for use in Electroencephalogram (EEG) signal classification is presented. The MFCC features are tested using CHB-MIT Scalp EEG Database. The objective is to classify the given EEG signal into normal or abnormal that is based on the MFCC representation of EEG signal. Initially, the QRS complex waves are detected using Pan Tompkins algorithm, and then the MFCC features are extracted. The performance of MFCC feature representation is analyzed in the context of an Artificial Neural Network (ANN) classification system in terms of sensitivity and specificity. The performance of EEG classification approach depends on the number of MFCC components used for the classification. When compared with 15 and 35 MFCC components, 25 MFCC components gives better result in terms of sensitivity (98%) and specificity (96%).
Page of 2
Articles per Page
by
Show export options
  Select all
Back to Top Top