Ghous Bakhsh Narejo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ghous Bakhsh Narejo has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Ayesha Amir Siddiqi
Department of Telecommunication Engineering, Dawood University of Engineering & Technology, Karachi, Pakistan
2 shared publications - Saleha Bano
Department of Electronic Engineering, NED University of Engineering and Technology, Karachi 75270, Pakistan
2 shared publications - Abdul Fatah
Atlantic Technological University
1 shared publication Adnan Hashmi
KIRAN Hospital Karachi, Karachi, Pakistan
1 shared publication- Lala Rukh
University of Galway
1 shared publication - Mahjabeen Memon
Mehran University of Engineering and Technology
1 shared publication
Latest Publications
- 23 November 2025
- Published by Springer Nature
- p. 782-791
AI and IoT-Enabled Home Energy Management Systems (HEMS) for Hybrid Renewable Energy Sources
- 23 November 2025
- Published by Springer Nature
- p. 782-791
AI and IoT-Enabled Home Energy Management Systems (HEMS) for Hybrid Renewable Energy Sources
- 30 December 2021
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 34 (03)
A NOVEL IMAGE PROCESSING ALGORITHM TO AUTOMATICALLY EXTRACT AND CLASSIFY LIVER BEARING TUMORS USING PATTERN RECOGNITION AND FUZZY TRANSFORM
This study presents a novel liver disease classification method by applying pattern recognition technique to automatically segmented liver from the images of computed tomographic (CT) scans. The methodology comprises of disease classification by the extraction of textural features from focal liver region bearing tumors. Two types of liver textures are investigated in this study for classification accuracy judgement. First, original liver texture is considered for feature extraction. Second, liver is used for feature extraction. The CT image dataset comprises 308 liver samples with 193 samples of malignant tumor and 115 samples of benign tumor. The entire liver tissue bearing tumor is segmented from the CT image automatically in the pre-processing stage using fuzzy transformation function and morphological processing. Four sets of textural feature matrices are applied to the liver for feature extraction. Gray level co-occurrence matrix (GLCM), standard deviation gray level co-occurrence matrix (SDGLCM), seven-moment matrix (7MM) and seven-moment gray level co-occurrence matrix (7MGLCM) are the combinational feature matrices applied to classify the liver as malignant or benign using support vector machines (SVMs). The best classification accuracy is achieved for original liver texture by 7MGLCM, which is 97% with AUC = 0.99 for training dataset and 97.8% with AUC = 1 for test dataset.
- 30 December 2021
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 34 (03)
A NOVEL IMAGE PROCESSING ALGORITHM TO AUTOMATICALLY EXTRACT AND CLASSIFY LIVER BEARING TUMORS USING PATTERN RECOGNITION AND FUZZY TRANSFORM
This study presents a novel liver disease classification method by applying pattern recognition technique to automatically segmented liver from the images of computed tomographic (CT) scans. The methodology comprises of disease classification by the extraction of textural features from focal liver region bearing tumors. Two types of liver textures are investigated in this study for classification accuracy judgement. First, original liver texture is considered for feature extraction. Second, liver is used for feature extraction. The CT image dataset comprises 308 liver samples with 193 samples of malignant tumor and 115 samples of benign tumor. The entire liver tissue bearing tumor is segmented from the CT image automatically in the pre-processing stage using fuzzy transformation function and morphological processing. Four sets of textural feature matrices are applied to the liver for feature extraction. Gray level co-occurrence matrix (GLCM), standard deviation gray level co-occurrence matrix (SDGLCM), seven-moment matrix (7MM) and seven-moment gray level co-occurrence matrix (7MGLCM) are the combinational feature matrices applied to classify the liver as malignant or benign using support vector machines (SVMs). The best classification accuracy is achieved for original liver texture by 7MGLCM, which is 97% with AUC = 0.99 for training dataset and 97.8% with AUC = 1 for test dataset.
- 21 November 2019
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 15 (10) , 972-982
Analysis of Abdominal Computed Tomography Images for Automatic Liver Cancer Diagnosis Using Image Processing Algorithm
Background: The application of image processing algorithms for medical image analysis has been found effectual in the past years. Imaging techniques provide assistance to the radiologists and physicians for the diagnosis of abnormalities in different organs. Objective: The proposed algorithm is designed for automatic computer-aided diagnosis of liver cancer from low contrast CT images. The idea expressed in this article is to classify the malignancy of the liver tumor ahead of liver segmentation and to locate HCC burden on the liver. Methods: A novel Fuzzy Linguistic Constant (FLC) is designed for image enhancement. To classify the enhanced liver image as cancerous or non-cancerous, fuzzy membership function is applied. The extracted features are assessed for malignancy and benignancy using the structural similarity index. The malignant CT image is further processed for automatic tumor segmentation and grading by applying morphological image processing techniques. Results: The validity of the concept is verified on a dataset of 179 clinical cases which consist of 98 benign and 81 malignant liver tumors. Classification accuracy of 98.3% is achieved by Support Vector Machine (SVM). The proposed method has the ability to automatically segment the tumor with an improved detection rate of 78% and a precision value of 0.6. Conclusion: The algorithm design offers an efficient tool to the radiologist in classifying the malignant cases from benign cases. The CAD system allows automatic segmentation of tumor and locates tumor burden on the liver. The methodology adopted can aid medical practitioners in tumor diagnosis and surgery planning.
- 21 November 2019
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 15 (10) , 972-982
Analysis of Abdominal Computed Tomography Images for Automatic Liver Cancer Diagnosis Using Image Processing Algorithm
Background: The application of image processing algorithms for medical image analysis has been found effectual in the past years. Imaging techniques provide assistance to the radiologists and physicians for the diagnosis of abnormalities in different organs. Objective: The proposed algorithm is designed for automatic computer-aided diagnosis of liver cancer from low contrast CT images. The idea expressed in this article is to classify the malignancy of the liver tumor ahead of liver segmentation and to locate HCC burden on the liver. Methods: A novel Fuzzy Linguistic Constant (FLC) is designed for image enhancement. To classify the enhanced liver image as cancerous or non-cancerous, fuzzy membership function is applied. The extracted features are assessed for malignancy and benignancy using the structural similarity index. The malignant CT image is further processed for automatic tumor segmentation and grading by applying morphological image processing techniques. Results: The validity of the concept is verified on a dataset of 179 clinical cases which consist of 98 benign and 81 malignant liver tumors. Classification accuracy of 98.3% is achieved by Support Vector Machine (SVM). The proposed method has the ability to automatically segment the tumor with an improved detection rate of 78% and a precision value of 0.6. Conclusion: The algorithm design offers an efficient tool to the radiologist in classifying the malignant cases from benign cases. The CAD system allows automatic segmentation of tumor and locates tumor burden on the liver. The methodology adopted can aid medical practitioners in tumor diagnosis and surgery planning.
- Open Access
- 20 March 2018
- Published by MDPI AG in Electronics
- Vol. 7 (3) , 41
Power Efficient Fully Differential Bulk Driven OTA for Portable Biomedical Application
This paper presents a power efficient, bulk driven, source degenerated fully differential operational transconductance amplifier (OTA), operating in the subthreshold region. The input part of the OTA consists of a bulk driven source degenerated differential pair and cross coupled transistors to improve the linearity of OTA. It consists of a bulk driven pair to reduce the supply voltage and to improve the linearity. The proposed fully differential OTA has utilized self-cascode current mirror loads which increases the output impedance and hence the overall intrinsic gain. A subthreshold region is adopted to reduce the power consumption of the circuit. For a 200 mVpp sinusoidal input at 100 Hz, a total harmonic distortion (THD) of −58.56 dB is achieved. The gain, gain bandwidth (GBW), phase margin (PM) and gain margin (GM) values obtained were 48.4 dB, 3.1 KHz, 80° and 19.01 dB, respectively. The common mode rejection ratio (CMRR), power supply rejection ratio (PSRR) and slew rate +/− values were 146.3 dB, 83 dB and 99.56/100 V/ms, respectively. The circuit is capable of operating under a supply voltage of 0.8 V with a power consumption of 59.04 nW, which proves that the circuit is suitable for portable biomedical devices. The proposed circuit is simulated in CADENCE environment virtuoso using LFoundry 150 nm Complementary metal oxide semiconductor (CMOS) process technology.
- 20 March 2018
- Published by MDPI AG in Electronics
- Vol. 7 (3) , 41
Open AccessPower Efficient Fully Differential Bulk Driven OTA for Portable Biomedical Application
This paper presents a power efficient, bulk driven, source degenerated fully differential operational transconductance amplifier (OTA), operating in the subthreshold region. The input part of the OTA consists of a bulk driven source degenerated differential pair and cross coupled transistors to improve the linearity of OTA. It consists of a bulk driven pair to reduce the supply voltage and to improve the linearity. The proposed fully differential OTA has utilized self-cascode current mirror loads which increases the output impedance and hence the overall intrinsic gain. A subthreshold region is adopted to reduce the power consumption of the circuit. For a 200 mVpp sinusoidal input at 100 Hz, a total harmonic distortion (THD) of −58.56 dB is achieved. The gain, gain bandwidth (GBW), phase margin (PM) and gain margin (GM) values obtained were 48.4 dB, 3.1 KHz, 80° and 19.01 dB, respectively. The common mode rejection ratio (CMRR), power supply rejection ratio (PSRR) and slew rate +/− values were 146.3 dB, 83 dB and 99.56/100 V/ms, respectively. The circuit is capable of operating under a supply voltage of 0.8 V with a power consumption of 59.04 nW, which proves that the circuit is suitable for portable biomedical devices. The proposed circuit is simulated in CADENCE environment virtuoso using LFoundry 150 nm Complementary metal oxide semiconductor (CMOS) process technology.
- 23 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 37-41
Single CDBA based bilinear current mode universal filter
In this paper, a bilinear (first order) current mode universal filter is presented using a single current differencing buffered amplifier (CDBA). The main feature of this proposed circuit configuration is that it can provide all the filter responses i.e. low-pass, high-pass and all-pass responses. Noting the fact that first order filter realizes low-pass, high-pass and all-pass responses only. It uses single CDBA and minimum passive components that is one resistor and one grounded capacitor only to realize all the filter responses. The active and passive sensitivities of the cut-off frequency (ω0) are very low. The proposed circuit topology is verified by simulating the circuit on PSPICE using TSMC 0.35um CMOS process parameters with supply voltages of +/- 2.5V and biasing currents of 30uA. The simulated and theoretical results were found to be in good agreement with each other.
- 23 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 37-41
Single CDBA based bilinear current mode universal filter
In this paper, a bilinear (first order) current mode universal filter is presented using a single current differencing buffered amplifier (CDBA). The main feature of this proposed circuit configuration is that it can provide all the filter responses i.e. low-pass, high-pass and all-pass responses. Noting the fact that first order filter realizes low-pass, high-pass and all-pass responses only. It uses single CDBA and minimum passive components that is one resistor and one grounded capacitor only to realize all the filter responses. The active and passive sensitivities of the cut-off frequency (ω0) are very low. The proposed circuit topology is verified by simulating the circuit on PSPICE using TSMC 0.35um CMOS process parameters with supply voltages of +/- 2.5V and biasing currents of 30uA. The simulated and theoretical results were found to be in good agreement with each other.
- 1 June 2010
- Published by Elsevier in Chemical Physics Letters
- Vol. 493 (4-6) , 263-268
First-principles computation of second-order elastic constants and equations of state for tetragonal BaTiO3
- 1 June 2010
- Published by Elsevier in Chemical Physics Letters
- Vol. 493 (4-6) , 263-268
First-principles computation of second-order elastic constants and equations of state for tetragonal BaTiO3