University of Engineering and Technology, Taxila
Recent publications
NPTs have vast applications because of no tyre puncture, no need for air pressure, low rolling resistance, and also have higher flexibility for design and recyclability. In this research work, different structures of polyurethane (PU) spokes have been designed and analyzed under radial loading conditions which include structures like honeycomb with varying cell angles, simple spoke, and trapezoid type by keeping in view that the cell wall thickness and somehow the mass of the structures remain the same. Based on the Mooney-Rivlin hyper-elastic material model and performing 2D non-linear static structural analysis on different types of NPTs using ANSYS, it has been observed that the simple spoke structure has the lowest spoke stress and deformation values of 2.01 MPa and 11.7 mm, while HC–A1 has the least value of strain energy of 2.58 mJ, at a load of 2500 N. The above results show that the straight spoke structures like simple spoke and trapezoid type have a high load-carrying ability than the honeycomb type NPTs under same boundary conditions. While honeycomb NPTs have higher fatigue life as compared to straight-spoke NPTs.
Multispectral transmission imaging provides a possibility for early breast cancer screening. Due to the strong scattering effect of the light source and the absorption characteristics of the material itself, the image signal is weak. The frame accumulation and demodulation technique can improve the accuracy of the image, but it brings a lot of redundant data. This paper proposes the “Two-dimensional Terraced Compression Method” and applies it to detecting heterogeneity contour in transmission images. The experiment is designed to prove its effectiveness. Four kinds of LEDs with different central wavelengths are respectively modulated as the light source to obtain the image sequences, and the Fast Fourier Transform (FFT) and frame accumulation are used to obtain single-wavelength images respectively. The image is first low-pass filtered, then find the gray minimum value in the image, and then find the connected area in the influence domain of the gradient threshold. If the connected area meets the area threshold, it is used as an effective growth point, and the gray value in the connected area is reassigned. Otherwise, mark it as an isolated point, return to find the minimum, and finally implement terraced compression on the image. This method not only reduces the redundancy of gray numbers but also greatly improves the gradient information of the image, and be used as a preprocessing image algorithm—nonlinear filtering also can be used to detect the contour of heterogeneity.
Taking into consideration of substantial role of energy system and sustainable development goals (SDGs) in modern society, it is critical to analyse current situation and forthcoming renewable energy development strategies under the impact of COVID-19. For this purpose, this paper provides significant new insights to assess effective approaches, opportunities, challenges and future potential capabilities for the development of energy systems and SDGs under on-going pandemic and in case of a future global crisis. The digital energy systems with Industry 4.0 (I4.0), which provide noteworthy solutions such as enhancing energy efficiency policy, providing clean, secure and efficient energy and achieving SDG targets, has been discussed and evaluated. Integration of the smart grid (SG) architecture with blockchain-Internet of Things (IoT)-based technologies is also offered. Alongside the various discussions, short-term, mid-term and long-term plans have been suggested in determining the well-defined renewable energy development and SDGs targets, struggling with climate change, transition to a more sustainable energy future and reaching global net-zero emissions. To achieve SDGs and provide more strong and sustainable energy systems under the continuing pandemic and in case of potential risk of forthcoming global crisis, this paper reveals significant perceptions that inform politicians and legislators in performing successful policy decisions.
Surveillance Systems Application based on deep learning algorithms is speedily growing in a broad range of fields such as Facial Recognition, Real Time Attendance Systems etc. Identifying several appearances in a real time environment is very crucial due to its difficult and heterogenous environmental conditions and blocking effects. We used state-of-the-art YOLOv5 model for investigating the efficiency of surveillance system with very limited experimental analysis. We used Face Detection Dataset & Benchmark (FDDB) and Celebrity Face Recognition (CFR) Dataset for training from scratch and for testing over YOLOv5 and private dataset taken from run-time video stream. Experimentations showing that we got 93% accuracy on FDDB on the other hand 99% accuracy on the tailored dataset. Comparison has been made for the analysis showing that our algorithm has produced better outcomes with the predecessor editions of YOLOv5 like YOLOv4 and YOLOv3 respectively. The aforementioned models are also validated over the run-time streaming, and it has the ability to recognize many faces with maximal precision.
Understanding the COVID-19 crisis that arose in 2019 is a significant important case study to prepare scenarios and meet electrical energy consumption and high renewable energy production (REP), especially in the context of the power systems. Although many researchers have investigated the medical field and electric power sectors associated with the COVID-19 pandemic, critical factors affecting the development of the REP like electric demand, power system, electric markets, economy, and environment have are still not studied in great detail. In this perspective, this paper analyses the impact of the COVID-19 outbreak on the development of the REP, electrical energy consumption, power system maintenance, electric markets, energy demand, ongoing investment projects/investment plans, economy and renewable energy sectors. Estimation of energy demand based on cooling degree days (CDDs) and heating degree days (HDDs) methods has been examined and contrasted with the same period in prior years to observe electricity consumption Besides, climate change and energy efficiency or energy intensity related to the energy demand have been investigated and analysed before and following the pandemic. Some important energy statistical data is addressed and examined in detail. In addition to these, various critical factors such as driver and barrier forces affecting the REP has been discussed during lockdown restrictions of the COVID-19. These findings will help researchers and academicians to analyse the far-reaching implications of the COVID-19 outbreak on the energy demand and contribute to figuring out and plan higher renewables share scenarios and power system management issues.
Cardiac disorders are one of the prime reasons for an increasing global death rate. Reliable and efficient diagnosis procedures are imperative to minimize the risk posed by heart disorders. Computer‐aided diagnosis, based on machine learning and biomedical signal analysis, has recently been adopted by researchers to accurately predict cardiac ailments. Multi‐channel Electrocardiogram signals are mostly used in scientific literature as an indicator to diagnose cardiac disorders. Recently pulse plethysmograph (PuPG) signal got attention as an evolving biosignal and promising diagnostic tool to detect heart disorders since it has a simple sensor with low cost, non‐invasive, reliable, and easy to handle technology. This article proposes a computer‐aided diagnosis system to detect Myocardial Infarction, Dilated Cardiomyopathy, and Hypertension from PuPG signals. Raw PuPG signal is first preprocessed through empirical mode decomposition (EMD) by removing the redundant and useless information content. Then, highly discriminative features are extracted from preprocessed PuPG signal through novel local spectral ternary patterns (LSTP). Extracted LSTPs are input to a variety of classification methods such as support vector machines (SVM), K‐nearest neighbours, decision tree, and so on. SVM with cubic kernel yielded the best classification performance of 98.4% accuracy, 96.7% sensitivity, and 99.6% specificity with 10‐fold cross‐validation. The proposed framework was trained and tested on a self‐collected PuPG signals database of heart disorders. A comparison with previous studies and other feature descriptors shows the superiority of the proposed system. This research provides better insights into the contributions of PuPG signals towards reliable detection of heart disorder through low‐cost and non‐invasive means.
Conventional damp heat (DH) tests conducted at 85°C and 85% relative humidity (RH) for module degradation cannot reproduce outdoor failures in a short time and it may take up to 4000 h to reproduce multi–environmental stress values. Therefore, an accelerated DH test for photovoltaic (PV) modules has been proposed, in which temperatures up to 120°C were applied to accelerate the degradation mechanism while keeping the humidity fixed at 85%RH and their module performance and electroluminescence images were investigated. The environmental stress detected after 600 h at 120°C/85%RH was comparable to the results of the DH test recorded at 85°C/85%RH for approximately 5000 h. Moreover, we tried to mitigate the power drop by replacing the back sheet/EVA and back sheet/EVA/solar cell for one cell area in the PV module after a 1000 h DH test at 85°C and 85%RH. After replacing the EVA and back sheet of one cell from the mini–module, we achieved a power recovery of 1.6%. By replacing the back sheet, EVA, and one solar cell from the mini module, we achieved a power recovery of 1.9%. This analysis indicated that instead of replacing the complete module, it is possible to replace the damaged part of the module. This article is protected by copyright. All rights reserved.
Classification of human emotions based on electroencephalography (EEG) is a very popular topic nowadays in the provision of human health care and well-being. Fast and effective emotion recognition can play an important role in understanding a patient's emotions and in monitoring stress levels in real-time. Due to the noisy and non-linear nature of the EEG signal, it is still difficult to understand emotions and can generate large feature vectors. In this article, we have proposed an efficient spatial feature extraction and feature selection method with a short processing time. The raw EEG signal is first divided into a smaller set of eigenmode functions called (IMF) using the empirical model-based decomposition proposed in our work, known as intensive multivariate empirical mode decomposition (iMEMD). 2 Muhammad Adeel Asghar et al. Spatio-temporal analysis is performed with CCWT (Complex Continuous Wavelet Transform) to collect all the information in the time and frequency domains. The multiple model extraction method uses three deep neural networks (DNNs) to extract features and dissect them together to have a combined feature vector. To overcome the computational curse, we propose a method of differential entropy and mutual information , which further reduces feature size by selecting high-quality features and pooling the k-means results to produce less dimensional qualitative feature vectors. The system seems complex, but once the network is trained with this model, real-time application testing and validation with good classification performance is fast. The proposed method for selecting attributes for benchmarking is validated with two publicly available data sets, SEED, and DEAP. This method is less expensive to calculate than more modern sentiment recognition methods, provides real-time sentiment analysis, and offers good classification accuracy.
We propose an e�cient formulation using the framework of Generalized Finite Element Method (GFEM) for the solutions of transient heat di�usion problems having multiple heat sources in the solution domain. The purpose here is to use minimal computational resources and rely on coarse mesh grids to capture the sharp variations of temperature �eld. We use Gaussian functions of global nature to enrich the GFEM approximation space which ensure e�cient solution in the whole solution domain. In order to capture steep thermal gradients at multiple locations, a multiplicity of enrichment functions is used and the peaks of enrichment functions are centred at the cores of heat sources. The advantage of this approach is that no further degrees of freedom (DOFs) are added to capture the solution at multiple locations. Besides, the enrichment functions are time-independent; the temporal variation of temperature is embedded in the de�nition of the enrichment functions. This formulation requires the assembly of system matrix once and only the right hand side of system of equations is updated at subsequent time steps which results in signi�cant reduction in the overall computational time. We consider problems in two-dimensional (2D) and three-dimensional (3D) domains to show the e�ectiveness of the proposed approach. A reduction of more than 95% in DOFs and more than 80% in computational time is achieved as compared to the h{version of �nite element method.
Spectral data pre-processing is a very effective method to improve the accuracy of constructing hyper spectral models, and differential spectroscopy is a valuable analysis method for the pre-processing of hyper spectral signals. It is usually used to increase the intensity of spectral signals and makes the researcher able to figure out hidden inflection points along with the minimum and maximum bands. In this particular study, fractional derivatives have been employed for the analysis of UV-VIS spectra of PE (ultra-high, MW) samples. The fractional order derivatives of UV-VIS (reflectance) spectra of un-irradiated and irradiated samples are simulated, and radiation modifications in UHMWPE are assessing. The classic definition of Riemann-Liouville (RL) integral is used for the calculation fractional order derivatives. For this the rule given by Lagrange operator (differential) is used i.e., taking the nth derivative over the (n−α) th order integral gives the derivative of αth order. It is of particular importance to mention here that n is the neighboring integer satisfying the condition n>α. Staring from following definition of RL integral (fractional) with 0<α<1 and initial value a=0. Ja+αf(x)=1Γ(α)∫ax(x−τ)α−1f(τ)dτ It is observed that the fractional order differential transformation gives better estimates regarding spectral pre-processing and accessing the radiation modification of UHMWPE while minimizing the loss of original data.
Good health is the most important and very necessary characteristic for stress-free, skillful, and hardworking people with a cooperative environment to create a sustainable society. Validating two algorithms, namely, sequential minimal optimization for regression (SMOreg) using vector machine and linear regression (LR) and using their predicted cancer patients’ cases, this study presents a patient’s stress estimation model (PSEM) to forecast their families’ stress for patients’ sustainable health and better care with early management by under-study cancer hospitals. The year-wise predictions (1998-2010) by LR and SMOreg are verified by comparing with observed values. The statistical difference between the predictions (2021-2030) by these models is analyzed using a statistical t -test. From the data of 217067 patients, patients’ stress-impacting factors are extracted to be used in the proposed PSEM. By considering the total population of under-study areas and getting the predicted population (2021-2030) of each area, the proposed PSEM forecasts overall stress for expected cancer patients (2021-2030). Root mean square error (RMSE) (1076.15.46) for LR is less than RSME for SMOreg (1223.75); hence, LR remains better than SMOreg in forecasting (2011-2020). There is no significant statistical difference between values (2021-2030) predicted by LR and SMOreg ( p value = 0.767 > 0.05 ). The average stress for a family member of a cancer patient is 72.71%. It is concluded that under-study areas face a minimum of 2.18% stress, on average 30.98% stress, and a maximum of 94.81% overall stress because of 179561 expected cancer patients of all major types from 2021 to 2030.
Face detection and recognition are the most substantial research areas in computer vision and transfer learning due to the inspiring nature of faces as an object. In this paper, we show that we can obtain promising results on the standard face databanks when the features are extracted merely from the eye. The contributions of this work are divided into three parts, specifically face detection, eyes detection and recognition for individual identification. The key features for face recognition, used in this study are the eyes, nostrils, and mouth. The key features for eyes recognition are center of left eye, center of right eye, midpoint of eyes and extraction of eyebrows. Extracted Local Binary Pattern Histogram (LBPH) method is used to extract the facial features of face images whose computational complexity is very low and these features contain simple pixel values. Furthermore, neighborhood pixels are calculated to extract effective facial feature to realize eyes recognition and person verification. This study is able to identify an individual on the basis of even a single eye. The algorithm finds the brighter eye from the face and then, on the basis of that eye, the person is identified and the name of person is provided. The experimental results of this study show that faces are recognized accurately and LBPH method has achieved 98.2% accuracy.
Autism Spectrum Disorder (ASD) is characterized by impairments in social and cognitive skills, emotional disorders, anxiety, and depression. The prolonged conventional ASD diagnosis raises the sheer need for early meaningful intervention. Recently different works have proposed potential for ASD diagnosis and intervention through emotions prediction using deep neural networks (DNN) and machine learning algorithms. However, these systems lack an extensive large-scale feature extraction (LSFE) analysis through multiple benchmark data sets. LSFE analysis is required to identify and utilize the most relevant features and channels for emotion recognition and ASD prediction. Considering these challenges, for the first time, we have analyzed and evaluated an extensive feature set to select the optimal features using LSFE and feature selection algorithms (FSA). A set of up to eight most suitable channels was identified using different best-case FSA. The subject-wise importance of channels and features is also identified. The proposed method provides the best-case accuracies, precision, and recall of 95, 92, and 90%, respectively, for emotions prediction using a linear support vector machine (LSVM) classifier. It also provides the best-case accuracy, precision, and recall of 100% for ASD classification. This work utilized the largest number of benchmark data sets (5) and subjects (99) for validation reported till now in the literature. The LSVM classification algorithm proposed and utilized in this work has significantly lower complexity than the DNN, convolutional neural network (CNN), Naïve Bayes, and dynamic graph CNN used in recent ASD and emotion prediction systems.
Micro-cracking (MC) is one of the major defects in concrete which significantly reduces the durability of reinforced concrete structures. Achievement of high compressive strength using high cement content is the major reason for the MC of concrete. In the present research, the efficiency of steel-fiber reinforced concrete (SFRC) and carbon-fiber-reinforced concrete (CFRC) were examined to minimize the MC in concrete. The properties of SFRC and CFRC were compared with that of plain cement concrete (PCC). Hooked steel fibers (SF) and chopped carbon fibers (CF) were used in this research. Two different combinations of fibers denoted a combination-1 (C1) and combination-2 (C2) were also prepared to check their behavior on the MC of concrete. Different tests were carried out in the laboratory such as compressive strength (CS), tensile strength (TS), modulus of rupture (MOR), and flexure strength (FS) on PCC, SFRC, CFRC, C1, and C2 specimens. The results showed that there is an increase of 28.2%, 5.6%, 7.1%, and 18.3% for SFRC, CFRC, C1, and C2, respectively in CS of concrete as compared to that of PCC. The results also depicted that TS of SFRC, CFRC, C1, and C2 is increased by 39%, 30.1%, 8%, and 27.1%, respectively in comparison to PCC. The maximum flexural load of SFRC beams was increased by 11.6% while the maximum flexural load of CFRC is reduced by 10.5% as compared to the PCC beam. Therefore, it can be concluded from the results that the use of hybrid fibers is suitable for controlling the MC in concrete and enhancing the mechanical properties of concrete.
Abstract: This investigation explores the structural performance of glass fiber reinforced polymer (GFRP) reinforced concrete columns incorporating hybrid fibers (GHFRC columns) under different loading conditions. The hybrid fiber reinforced concrete (HFRC) consisted of two kinds of fibers (steel, SF and polypropylene, PF). A total of nine GHFRC specimens with a diameter of 250 mm and a height of 1150 mm were fabricated and tested to failure. A 3D finite element model (FEM) was developed for the GHFRC specimens using ABAQUS 6.14. The definition of HFRC was performed using an improved concrete damaged plasticity model and the definition of GFRP material was performed by using a linear elastic model. The test results revealed that the ductility of GHFRC columns was improved with the reduction in the ligature spacing. The columns eccentricity showed higher ductility indices than concentric columns. The loading eccentricity resulted in a substantial decrease in the axial strength (AS) of GHFRC columns. The close correlation between tests and FEM results validate the applicability of FEM. A mathematical model was suggested for predicting the AS of GHFRC specimens by taking into account the axial influence of GFRP bars and the confining influence of GFRP ties.
This paper evaluates the effect of local site conditions on the seismic hazard of the relocated new Balakot town as a result of the complete destruction of old Balakot city due to the 2005 Muzaffarabad Earthquake. The new Balakot town has been placed in a high seismic zone according to the Building Code of Pakistan because of its vicinity to active seismogenic faults. Representative sites from the new Balakot town have been selected to evaluate the local site effects. The acceleration time series was used as suite input motion in the ground response analysis selected from the worldwide earthquake catalog and matched to the target spectrum of Balakot. The site-specific equivalent linear (EL) and nonlinear (NL) analyses were conducted for which the ground model was developed based on the field and laboratory geotechnical test results. The mean surface ground response spectrum and also the mean Amplification Factor showed that the suite input motions were de-amplified and amplified respectively below and above the fundamental period of the site. The mean maximum amplification factor at 0.4 sec shows that a four-story building may be subjected to resonant conditions. The transfer function that relates the amplitude of incident and transmitted motion at interface resulted in different mean peak ground acceleration. The higher surface peak ground acceleration value was obtained from that of suit base motions. The NL analysis was observed to yield more conservative maximum AF and PGA values in comparison to the EL analysis. This study is helpful to provide improved and site-specific values of ground acceleration based on local site effects of the new Balakot town, which is an important locality in the 2005 Muzaffarabad earthquake-affected region.
Electric discharge machining with a powder mix dielectric is a promising technique to harden a work piece’s surface using electricity with a high energy density. The quality of the electrical discharge-machined surface is related to its surface integrity in which the surface’s roughness, residual stresses, micro hardness and surface micro cracks are some of the major factors. In this research, graphite powder was mixed in a dielectric with a particle size of 20 µm, 30 µm, and 40 µm, with the concentration of the graphite powder ranging from 2 g/L to 4 g/L. Moreover, the peak current and pulse time on were also coupled with an additive of graphite powder to investigate the effect on the surface quality, i.e., the recast layer thickness, micro hardness and crater depth as well as the material removal rate (MRR) and tool wear rate (TWR). A Box–Behnken design was employed to design the experiments and the experimental results revealed that the graphite powder size and concentration coupled with the electrical parameters (peak current and pulse time on) significantly influenced the recast layer thickness, micro hardness, crater size, MRR and TWR. The crater depth and micro hardness were maximized at a higher concentration and particle size, while the recast layer thickness was reduced with a higher gain size.
Network application classification (NAC) is a vital technology for intrusion detection, QoS-aware traffic engineering, traffic analysis, and network anomalies. Researchers have focused on designing algorithms using deep learning models based on statistical information to address the challenges of traditional payload and port-based traffic classification techniques. Internet of Things (IoT) and Software Defined Network (SDN) are two popular technologies nowadays and aims to connect devices over the internet and intelligently control networks from a centralized space. IoT aims to connect billions of devices; therefore, classification is essential for efficient processing. Software-defined networks (SDN) is a new networking paradigm, which separates data plane measurement from the control plane. The emergence of deep learning algorithms with SDN provides a scalable traffic classification architecture. Due to the inadequate results of payload and port-based approaches, a statistical technique to classify network traffic into different classes using a convolution neural network (CNN) and a recurrent neural network (RNN) is presented in this paper. This paper provides a classification method for software-defined IoT networks. The results show that, contrary to other traffic classification methods, the proposed approach offered a better accuracy rate of over 99 %, which is promising.
Institution pages aggregate content on ResearchGate related to an institution. The members listed on this page have self-identified as being affiliated with this institution. Publications listed on this page were identified by our algorithms as relating to this institution. This page was not created or approved by the institution. If you represent an institution and have questions about these pages or wish to report inaccurate content, you can contact us here.
2,413 members
Fawad Hussain
  • Department of Computer Engineering
Muhammad Haroon Yousaf
  • Department of Computer Engineering
Abdul Razzaq Ghumman
  • Department of Civil Engineering
Imran Hafeez
  • Department of Civil Engineering
Mohammad Choudhry
  • Department of Electrical Engineering
Khanpur Road, UET Taxila, 47070, Islamabad, Punjab, Pakistan
Head of institution
Prof. Dr. Muhammad Inayatullah Khan
+92 51-9047-401