Skip to main content

Mukhtiar Unar

Followers

0

Following

1

Public Views

University of Melbourne

University of Cologne

Roshan Chitrakar

Nepal College of Information Technology

Graduate Center of the City University of New York

Rice University

Sajadin Sembiring

Universitas Sumatera Utara

Journal of Computer Science IJCSIS

Ashok Paranjothi

Sri Sairam Institute Of Technology

Politecnico di Bari

Nikos Mantzakouras

National & Kapodistrian University of Athens

Interests

Uploads

Papers by Mukhtiar Unar

MDEV Model: A Novel Ensemble-Based Transfer Learning Approach for Pneumonia Classification Using CXR Images

Computer systems science and engineering, 2023

Pneumonia is a dangerous respiratory disease due to which breathing becomes incredibly difficult ... more Pneumonia is a dangerous respiratory disease due to which breathing becomes incredibly difficult and painful; thus, catching it early is crucial. Medical physicians' time is limited in outdoor situations due to many patients; therefore, automated systems can be a rescue. The input images from the X-ray equipment are also highly unpredictable due to variances in radiologists' experience. Therefore, radiologists require an automated system that can swiftly and accurately detect pneumonic lungs from chest x-rays. In medical classifications, deep convolution neural networks are commonly used. This research aims to use deep pretrained transfer learning models to accurately categorize CXR images into binary classes, i.e., Normal and Pneumonia. The MDEV is a proposed novel ensemble approach that concatenates four heterogeneous transfer learning models: Mobile-Net, DenseNet-201, EfficientNet-B0, and VGG-16, which have been finetuned and trained on 5,856 CXR images. The evaluation matrices used in this research to contrast different deep transfer learning architectures include precision, accuracy, recall, AUC-roc, and f1-score. The model effectively decreases training loss while increasing accuracy. The findings conclude that the proposed MDEV model outperformed cutting-edge deep transfer learning models and obtains an overall precision of 92.26%, an accuracy of 92.15%, a recall of 90.90%, an auc-roc score of 90.9%, and f-score of 91.49% with minimal data pre-processing, data augmentation, finetuning and hyperparameter adjustment in classifying Normal and Pneumonia chests.

Design and Tuning of fixed structure PID Controllers - A Survey

HAL (Le Centre pour la Communication Scientifique Directe), Dec 1, 1995

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific r... more HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Parametric Study of Nonlinear Adaptive Cruise Control for a Road Vehicle Model by MPC

arXiv (Cornell University), Apr 2, 2016

Control) techniques, with constraints, are applied to a nonlinear vehicle model for the developme... more Control) techniques, with constraints, are applied to a nonlinear vehicle model for the development of an ACC (Adaptive Cruise Control) system for transitional manoeuvres. The dynamic model of the vehicle is developed in the continuous-time domain and captures the real dynamics of the sub-vehicle models for steady-state and transient operations. A parametric study for the MPC method is conducted to analyse the response of the ACC vehicle for critical manoeuvres. The simulation results show the significant sensitivity of the response of the vehicle model with ACC to controller parameter and comparisons are made with a previous study. Furthermore, the approach adopted in this work is believed to reflect the control actions taken by a real vehicle.

Modeling Mechanical Properties of Aluminum Composite Produced Using Stir Casting Method

arXiv (Cornell University), 2011

ANN (Artificial Neural Networks) modeling methodology was adopted for predicting mechanical prope... more ANN (Artificial Neural Networks) modeling methodology was adopted for predicting mechanical properties of aluminum cast composite materials. For this purpose aluminum alloy were developed using conventional foundry method. complex nature which posses the nonlinear relationship among heat treatment, processing parameters, and composition and affects their mechanical properties. These nonlinear relation ships with properties can more efficiently be modeled by ANNs. Neural networks modeling needs sufficient data base consisting of mechanical properties, chemical composition and processing parameters. Such data base is not available for modeling. Therefore, a large range of experimental work was carried out for the development of aluminum composite materials. Alloys containing Cu, Mg and Zn as matrix were reinforced with 1-15% Al 2 O 3 particles using stir casting method. Alloys composites were cast in a metal mold. More than eighty standard samples were prepared for tensile tests. Sixty samples were given solution treatments at 580 o C for half an hour and tempered at 120 o C for 24 hours. The samples were characterized to investigate mechanical properties using Scanning Electron Microscope, X-Ray Spectrometer, Optical Metallurgical Microscope, Vickers Hardness, Universal Testing Machine and Abrasive Wear Testing Machine. A MLP (Multilayer Perceptron) feedforward was developed and used for modeling purpose. Training, testing and validation of the model were carried out using back propagation learning algorithm. The modeling results show that an architecture of 14 inputs with 9 hidden neurons and 4 outputs which includes the tensile strength, elongation, hardness and abrasive wear resistance gives reasonably accurate results with an error within the range of 2-7 % in training, testing and validation.

Channel Equalization Using Multilayer Perceptron Networks

arXiv (Cornell University), Apr 2, 2016

In most digital communication systems, bandwidth limited channel along with multipath propagation... more In most digital communication systems, bandwidth limited channel along with multipath propagation causes ISI (Inter Symbol Interference) to occur. This phenomenon causes distortion of the given transmitted symbol due to other transmitted symbols. With the help of equalization ISI can be reduced. This paper presents a solution to the ISI problem by performing blind equalization using ANN (Artificial Neural Networks). The simulated network is a multilayer feedforward Perceptron ANN, which has been trained by utilizing the error back-propagation algorithm. The weights of the network are updated in accordance with training of the network. This paper presents a very effective method for blind channel equalization, being more efficient than the pre-existing algorithms. The obtained results show a visible reduction in the noise content.

Manufacturing of Aluminum Composite Material Using Stir Casting Process

arXiv (Cornell University), Apr 2, 2016

Manufacturing of aluminum alloy based casting composite materials via stir casting is one of the ... more Manufacturing of aluminum alloy based casting composite materials via stir casting is one of the prominent and economical route for development and processing of metal matrix composites materials. Properties of these materials depend upon many processing parameters and selection of matrix and reinforcements. Literature reveals that most of the researchers are using 2, 6 and 7xxx aluminum matrix reinforced with SiC particles for high strength properties whereas, insufficient information is available on reinforcement of "Al 2 O 3 " particles in 7xxx aluminum matrix. The 7xxx series aluminum matrix usually contains Cu-Zn-Mg. Therefore, the present research was conducted to investigate the effect of elemental metal such as Cu-Zn-Mg in aluminum matrix on mechanical properties of stir casting of aluminum composite materials reinforced with alpha "Al 2 O 3 " particles using simple foundry melting alloying and casting route. The age hardening treatments were also applied to study the aging response of the aluminum matrix on strength, ductility and hardness. The experimental results indicate that aluminum matrix cast composite can be manufactured via conventional foundry method giving very good responses to the strength and ductility up to 10% "Al 2 O 3 " particles reinforced in aluminum matrix.

CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks

Wireless Communications and Mobile Computing

The technological advancement in sensor technology and pervasive computing has brought smart devi... more The technological advancement in sensor technology and pervasive computing has brought smart devices into our daily life. Due to the continuous connectivity of the internet with our everyday devices, researchers can deploy IoT sensors to health care and other applications, such as human activity recognition. Most of the state-of-the-art sensor-based human activity recognition systems can detect basic activities (such as standing, sitting, and walking), but they cannot accurately distinguish similar activities (ascending stairs or descending stairs). Such systems are not efficient for critical healthcare applications having complex activity sets. This paper proposes two sensor fusion approaches, i.e., position-based early and late sensor fusion using convolutional neural network (CNN) and convolutional long-short-term memory (CNN-LSTM). The performance of our proposed models is evaluated on two publicly available datasets. We also evaluated the effect of different normalization techn...

A neural network based heading and position control system of a ship

Mehran University Research Journal of Engineering and Technology

Heading and position control system of ships has remained a challenging control problem. It is a ... more Heading and position control system of ships has remained a challenging control problem. It is a nonlinear multiple input multiple output system. Moreover, the dynamics of the system vary with operating as well as environmental conditions. Conventionally, simple Proportional Integral Derivative controller is used which has well known limitations. Other conventional control techniques have also been investigated but they require an accurate mathematical model of a ship. Unfortunately, accuracy of mathematical models is very difficult to achieve. During the past few decades computational intelligence techniques such as artificial neural networks have been very successful when an accurate mathematical model is not available. Therefore, in this paper, an artificial neural network controller is proposed for heading and position control system. For simulation purposes, a mathematical model with four effective thrusters have been chosen to test the performance of the proposed controller. T...

Classification of MRI Images Using Neural Network

Quaid-E-Awam University Research Journal of Engineering, Science & Technology, Nawabshah., Jun 30, 2020

Diagnosing a brain tumor usually begins with Magnetic Resonance Imaging (MRI). However, the compl... more Diagnosing a brain tumor usually begins with Magnetic Resonance Imaging (MRI). However, the complexity associated with the MRI system makes this task non-trivial. Especially, distinguishing between different types of tumors, i.e., Meningioma, Glioma and Pituitary is not easy and is highly subjective. To address this issue, we train a Convolutional Neural Network (CNN) using transfer learning to classifying MRI images into the mentioned tumor types. We used pre-trained models of VGG16 and VGG19 and retrained them on the publicly available dataset of figshare. A comparison of the performance of these models reveals that VGG16 models achieves a maximum accuracy of 84.59%, whereas the maximum accuracy attained by VGG19 is 86.70%. Our experimental results demonstrate that the task of classifying tumorous MRI images can be efficiently done with CNN.

Design and Development of an Automated Library Management System for Mehran University Library, Jamshoro

Control Theory and Informatics, 2016

This study aims to seek the requirements of the integrated library management system proposed and... more This study aims to seek the requirements of the integrated library management system proposed and developed for the Mehran University Library as a step to automate its library services. Study used models to come up with the system. Met most of the goals of the system by enabling library staff follow their clients and resources that they manage. A report generation as easy as all the information has become easier to manipulate because of the nature of electronic storage. Find reading material has been made easy because different criteria can be used to accomplish the task. The user interfaces are friendly and there was a need for re- training other than orientation. The researcher recommends that this system will be built on an ongoing basis to take care of library services other management includes serials and periodicals , and reservations book , e-mail notification automatic reminder , and the use of bar codes , scanners and labels , and the use of RFID ( Radio Frequency Identific...

Impact of Network Traffic Load on Performance of Queue Controllers

This study is performed to analyze the impact of network traffic load on performance of various A... more This study is performed to analyze the impact of network traffic load on performance of various Active Queue Management (AQM) controllers including traditional DropTail controller. This study represents four scenarios having identical network parameters except network traffic load. The performance of each controller is measured on multiple performance metrics

Neural Network Based Altitude-Hold Autopilot Control of an Aircraft

Neural Network Based Altitude-Hold Autopilot Control of an Aircraft 1YUSRA BANO, 2MUKHTIAR ALI... more Neural Network Based Altitude-Hold Autopilot Control of an Aircraft 1YUSRA BANO, 2MUKHTIAR ALI UNAR, AND 3ZEESHAN ALI 1Department of Mechatronics Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan. 2Department of Commuter Systems Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan. 3Department of Industrial Engineering & Management, Dawood University of Engineering & Technology, Karachi, Pakistan. [email protected], [email protected], [email protected]

A Novel Algorithm to Reduce Peak-To-Average Power Ratio of Orthogonal Frequency Division Multiplexing Signals

It has been observed over last several decades that bandwidth greediness of applications never ge... more It has been observed over last several decades that bandwidth greediness of applications never gets fulfilled. Hence, scientists, researchers, and engineers keep working on new ways of providing higher bandwidth. Recently, a new modulation technique called Orthogonal Frequency Division Multiplexing (OFDM) has been introduced which provides very high data rates. In OFDM the high frequency input signal is modulated over a large number of low frequency sub-carrier signals which are orthogonal to each other. This feature makes it very robust against efficiency degradation at higher frequencies. That is the reason why OFDM is a choice for the modern high and ultra-high data rate communication systems. However, it suffers from high levels of the peak power to the average power also called Peak-to-Average Power Ratio or PAPR. Reducing PAPR in OFDM is a hot research area. There are many schemes available which attempt to reduce PAPR. Some are in fact able to reduce PAPR but not sufficient e...

M Shape Memory Alloy Actuated Inchworm

Shape memory alloy (SMA) is a type of material that are able to return to its original shape.When... more Shape memory alloy (SMA) is a type of material that are able to return to its original shape.When subjected to appropriate temperature. The properties of SMA makes it suitable for actuation in robotics. When dealing with small size and weight of it. Especially when small size and weight are desirable. Shape memory alloy has many applications in bio-robotics such as Manta ray robot, Snake robot and fish robot etc. In this paper a SMA actuated inchworm is reported. The components used in the inchworm robot are the compression spring, shape memory alloys, plastic sheet, Crimps, Arduino board and ULN2003A and DC power supply. The designed inchworm robot mechanism has 2 plastic plates attached to glue. These plastic plates have negligible weight and compression spring is used for bias force .To assure better mechanical design of robot SMA actuator and spring are employed. When a signal is given from computer the power is transmitted from DC power supply, and supply SMA wire. Then current...

The Role of Knowledge Management and Data Mining in Improving Educational Practices and the Learning Infrastructure

April 2020, 2020

Higher Educational Institutes hold a central and vital role in the knowledge economy. Knowledge g... more Higher Educational Institutes hold a central and vital role in the knowledge economy. Knowledge generated by these institutes needs to be collected and disseminated to bring about improvement in not only student learning and performance, but also in educational practices, processes and the society in general. Sadly, in many institutes, this knowledge is rarely recognized, captured, analysed or utilized. Apart from the need for improved learning outcomes, rapid growth in educational data and technology has motivated several educational institutes to implement Knowledge Management (KM). KM is the key to enable educational institutes reach their goals and achieve their objectives. This paper explores the basic concept of KM and addresses the need of KM in higher educational institutes by proposing a framework to improve knowledge processes and practices in academia. This paper also highlights the role of data mining in facilitating KM in higher education through a case study that focus...

Modeling of Flux linkage Characteristics of Switched Reluctance Motor

Indian Journal of Science and Technology, 2019

The increasing popularity of the switched reluctance machine has created more challenges to prese... more The increasing popularity of the switched reluctance machine has created more challenges to present it as a good performer machine under different operational conditions. For modeling and simulation of the machine, the necessity of static characteristics, in particular, flux linkage characteristics which look like the base stone for initialization of simulation is unavoidable. The importance of flux linkage characteristics, and how other data tables such as inverter flux linkage characteristics, co energy and static torque table are obtained are presented in this work. This paper describes a set of equations for modeling of the flux linkage characteristics of switched reluctance machine and also hardware for the 3-phase machine is presented.

Intelligent Aircraft Control System Using Neural Networks

Artificial neural networks increasingly are being used in a variety of automation and control app... more Artificial neural networks increasingly are being used in a variety of automation and control applications where the characteristics of the controlled system change significantly with the operating conditions or with time. This study investigates the potential of radial basis function (RBF) network architecture of feed-forward neural networks as an intelligent altitude hold autopilot of an aircraft. The approach involves the training of a single artificial neural network to represent a conventional controller. The resulting network thus captures, in a nonlinear fashion, the essential characteristics of the conventional controller. Preliminary investigations confirm that RBF architecture of feed forward neural networks is suitable for developing automatic control systems. This research will help in the development of a multi-objective robust adaptive intelligent automatic pilot that can control the aircraft under different operating and environmental conditions.

Ship steering control using feedforward neural networks

One significant problem in the design of ship steering control systems is that the dynamics of th... more One significant problem in the design of ship steering control systems is that the dynamics of the vessel change with operating conditions such as the forward speed of the vessel, the depth of water and loading conditions etc. Approaches considered in the past to overcome these difficulties include the use of self adaptive control systems which adjust the control characteristics on continuous basis to suit the current operating conditions. Artificial neural networks have been receiving considerable attention in recent years and have been considered. for a variety of applications where the characteristics of the controlled system change significantly with operating conditions or with time. Such networks have a configuration which remains fixed once the training phase is complete. The resulting controlled systems thus have more predictable characteristics than those which are found in many forms of traditional self-adaptive control systems. In particular, stability bounds can he investigated through simulation studies as with any other form of controller having. fixed characteristics heedforward neural networks have enjoyed many successful applications in the field of systems and control. These networks include two major categories: multilayer perceptrons and radial basis function networks. In this thesis, we explore the applicability of both of these artificial neural network architectures for automatic steering of ships in a course changing mode of operation.

SAM: Support Vector Machine Based Active Queue Management

Recent years have seen an increasing interest in the design of AQM (Active Queue Management) cont... more Recent years have seen an increasing interest in the design of AQM (Active Queue Management) controllers. The purpose of these controllers is to manage the network congestion under varying loads, link delays and bandwidth. In this paper, a new AQM controller is proposed which is trained by using the SVM (Support Vector Machine) with the RBF (Radial Basis Function) kernal. The proposed controller is called the support vector based AQM (SAM) controller.

Design of Heading Controller for Cargo Ship using Feed Forward Artificial Neural Network

International Journal of Advancements in Computing Technology, 2013

ABSTRACT For successful design and development in marine engineering systems, computer analysis a... more ABSTRACT For successful design and development in marine engineering systems, computer analysis and simulation is considered as an important tool. Ship motion is highly nonlinear and complex controlled process with several hydrodynamic parameters. Therefore to control the ship effectively in a desired course is always an important task for ship designers. In this paper, the application of artificial neural network (ANN) is investigated in order to design an autopilot for controlling the heading angle of a cargo ship. Feed forward multilayered architecture of ANN is used because of layered architecture. It is easy to design and can control nonlinear systems efficiently. Efficiency of proposed autopilot controller is studied and compared with sliding mode controller. Simulation carried out in MATLAB environment using cargo ship model in ideal condition (with no environmental disturbances). This study demonstrates that proposed autopilot system can efficiently be used to control the heading of a ship in all operating conditions. Keywords: Ship Autopilots, Ship Dynamics, Artificial Neural Network (ANN), NN based Ship Heading Controller

MDEV Model: A Novel Ensemble-Based Transfer Learning Approach for Pneumonia Classification Using CXR Images

Computer systems science and engineering, 2023

Pneumonia is a dangerous respiratory disease due to which breathing becomes incredibly difficult ... more Pneumonia is a dangerous respiratory disease due to which breathing becomes incredibly difficult and painful; thus, catching it early is crucial. Medical physicians' time is limited in outdoor situations due to many patients; therefore, automated systems can be a rescue. The input images from the X-ray equipment are also highly unpredictable due to variances in radiologists' experience. Therefore, radiologists require an automated system that can swiftly and accurately detect pneumonic lungs from chest x-rays. In medical classifications, deep convolution neural networks are commonly used. This research aims to use deep pretrained transfer learning models to accurately categorize CXR images into binary classes, i.e., Normal and Pneumonia. The MDEV is a proposed novel ensemble approach that concatenates four heterogeneous transfer learning models: Mobile-Net, DenseNet-201, EfficientNet-B0, and VGG-16, which have been finetuned and trained on 5,856 CXR images. The evaluation matrices used in this research to contrast different deep transfer learning architectures include precision, accuracy, recall, AUC-roc, and f1-score. The model effectively decreases training loss while increasing accuracy. The findings conclude that the proposed MDEV model outperformed cutting-edge deep transfer learning models and obtains an overall precision of 92.26%, an accuracy of 92.15%, a recall of 90.90%, an auc-roc score of 90.9%, and f-score of 91.49% with minimal data pre-processing, data augmentation, finetuning and hyperparameter adjustment in classifying Normal and Pneumonia chests.

Design and Tuning of fixed structure PID Controllers - A Survey

HAL (Le Centre pour la Communication Scientifique Directe), Dec 1, 1995

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific r... more HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Parametric Study of Nonlinear Adaptive Cruise Control for a Road Vehicle Model by MPC

arXiv (Cornell University), Apr 2, 2016

Control) techniques, with constraints, are applied to a nonlinear vehicle model for the developme... more Control) techniques, with constraints, are applied to a nonlinear vehicle model for the development of an ACC (Adaptive Cruise Control) system for transitional manoeuvres. The dynamic model of the vehicle is developed in the continuous-time domain and captures the real dynamics of the sub-vehicle models for steady-state and transient operations. A parametric study for the MPC method is conducted to analyse the response of the ACC vehicle for critical manoeuvres. The simulation results show the significant sensitivity of the response of the vehicle model with ACC to controller parameter and comparisons are made with a previous study. Furthermore, the approach adopted in this work is believed to reflect the control actions taken by a real vehicle.

Modeling Mechanical Properties of Aluminum Composite Produced Using Stir Casting Method

arXiv (Cornell University), 2011

ANN (Artificial Neural Networks) modeling methodology was adopted for predicting mechanical prope... more ANN (Artificial Neural Networks) modeling methodology was adopted for predicting mechanical properties of aluminum cast composite materials. For this purpose aluminum alloy were developed using conventional foundry method. complex nature which posses the nonlinear relationship among heat treatment, processing parameters, and composition and affects their mechanical properties. These nonlinear relation ships with properties can more efficiently be modeled by ANNs. Neural networks modeling needs sufficient data base consisting of mechanical properties, chemical composition and processing parameters. Such data base is not available for modeling. Therefore, a large range of experimental work was carried out for the development of aluminum composite materials. Alloys containing Cu, Mg and Zn as matrix were reinforced with 1-15% Al 2 O 3 particles using stir casting method. Alloys composites were cast in a metal mold. More than eighty standard samples were prepared for tensile tests. Sixty samples were given solution treatments at 580 o C for half an hour and tempered at 120 o C for 24 hours. The samples were characterized to investigate mechanical properties using Scanning Electron Microscope, X-Ray Spectrometer, Optical Metallurgical Microscope, Vickers Hardness, Universal Testing Machine and Abrasive Wear Testing Machine. A MLP (Multilayer Perceptron) feedforward was developed and used for modeling purpose. Training, testing and validation of the model were carried out using back propagation learning algorithm. The modeling results show that an architecture of 14 inputs with 9 hidden neurons and 4 outputs which includes the tensile strength, elongation, hardness and abrasive wear resistance gives reasonably accurate results with an error within the range of 2-7 % in training, testing and validation.

Channel Equalization Using Multilayer Perceptron Networks

arXiv (Cornell University), Apr 2, 2016

In most digital communication systems, bandwidth limited channel along with multipath propagation... more In most digital communication systems, bandwidth limited channel along with multipath propagation causes ISI (Inter Symbol Interference) to occur. This phenomenon causes distortion of the given transmitted symbol due to other transmitted symbols. With the help of equalization ISI can be reduced. This paper presents a solution to the ISI problem by performing blind equalization using ANN (Artificial Neural Networks). The simulated network is a multilayer feedforward Perceptron ANN, which has been trained by utilizing the error back-propagation algorithm. The weights of the network are updated in accordance with training of the network. This paper presents a very effective method for blind channel equalization, being more efficient than the pre-existing algorithms. The obtained results show a visible reduction in the noise content.

Manufacturing of Aluminum Composite Material Using Stir Casting Process

arXiv (Cornell University), Apr 2, 2016

Manufacturing of aluminum alloy based casting composite materials via stir casting is one of the ... more Manufacturing of aluminum alloy based casting composite materials via stir casting is one of the prominent and economical route for development and processing of metal matrix composites materials. Properties of these materials depend upon many processing parameters and selection of matrix and reinforcements. Literature reveals that most of the researchers are using 2, 6 and 7xxx aluminum matrix reinforced with SiC particles for high strength properties whereas, insufficient information is available on reinforcement of "Al 2 O 3 " particles in 7xxx aluminum matrix. The 7xxx series aluminum matrix usually contains Cu-Zn-Mg. Therefore, the present research was conducted to investigate the effect of elemental metal such as Cu-Zn-Mg in aluminum matrix on mechanical properties of stir casting of aluminum composite materials reinforced with alpha "Al 2 O 3 " particles using simple foundry melting alloying and casting route. The age hardening treatments were also applied to study the aging response of the aluminum matrix on strength, ductility and hardness. The experimental results indicate that aluminum matrix cast composite can be manufactured via conventional foundry method giving very good responses to the strength and ductility up to 10% "Al 2 O 3 " particles reinforced in aluminum matrix.

CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks

Wireless Communications and Mobile Computing

The technological advancement in sensor technology and pervasive computing has brought smart devi... more The technological advancement in sensor technology and pervasive computing has brought smart devices into our daily life. Due to the continuous connectivity of the internet with our everyday devices, researchers can deploy IoT sensors to health care and other applications, such as human activity recognition. Most of the state-of-the-art sensor-based human activity recognition systems can detect basic activities (such as standing, sitting, and walking), but they cannot accurately distinguish similar activities (ascending stairs or descending stairs). Such systems are not efficient for critical healthcare applications having complex activity sets. This paper proposes two sensor fusion approaches, i.e., position-based early and late sensor fusion using convolutional neural network (CNN) and convolutional long-short-term memory (CNN-LSTM). The performance of our proposed models is evaluated on two publicly available datasets. We also evaluated the effect of different normalization techn...

A neural network based heading and position control system of a ship

Mehran University Research Journal of Engineering and Technology

Heading and position control system of ships has remained a challenging control problem. It is a ... more Heading and position control system of ships has remained a challenging control problem. It is a nonlinear multiple input multiple output system. Moreover, the dynamics of the system vary with operating as well as environmental conditions. Conventionally, simple Proportional Integral Derivative controller is used which has well known limitations. Other conventional control techniques have also been investigated but they require an accurate mathematical model of a ship. Unfortunately, accuracy of mathematical models is very difficult to achieve. During the past few decades computational intelligence techniques such as artificial neural networks have been very successful when an accurate mathematical model is not available. Therefore, in this paper, an artificial neural network controller is proposed for heading and position control system. For simulation purposes, a mathematical model with four effective thrusters have been chosen to test the performance of the proposed controller. T...

Classification of MRI Images Using Neural Network

Quaid-E-Awam University Research Journal of Engineering, Science & Technology, Nawabshah., Jun 30, 2020

Diagnosing a brain tumor usually begins with Magnetic Resonance Imaging (MRI). However, the compl... more Diagnosing a brain tumor usually begins with Magnetic Resonance Imaging (MRI). However, the complexity associated with the MRI system makes this task non-trivial. Especially, distinguishing between different types of tumors, i.e., Meningioma, Glioma and Pituitary is not easy and is highly subjective. To address this issue, we train a Convolutional Neural Network (CNN) using transfer learning to classifying MRI images into the mentioned tumor types. We used pre-trained models of VGG16 and VGG19 and retrained them on the publicly available dataset of figshare. A comparison of the performance of these models reveals that VGG16 models achieves a maximum accuracy of 84.59%, whereas the maximum accuracy attained by VGG19 is 86.70%. Our experimental results demonstrate that the task of classifying tumorous MRI images can be efficiently done with CNN.

Design and Development of an Automated Library Management System for Mehran University Library, Jamshoro

Control Theory and Informatics, 2016

This study aims to seek the requirements of the integrated library management system proposed and... more This study aims to seek the requirements of the integrated library management system proposed and developed for the Mehran University Library as a step to automate its library services. Study used models to come up with the system. Met most of the goals of the system by enabling library staff follow their clients and resources that they manage. A report generation as easy as all the information has become easier to manipulate because of the nature of electronic storage. Find reading material has been made easy because different criteria can be used to accomplish the task. The user interfaces are friendly and there was a need for re- training other than orientation. The researcher recommends that this system will be built on an ongoing basis to take care of library services other management includes serials and periodicals , and reservations book , e-mail notification automatic reminder , and the use of bar codes , scanners and labels , and the use of RFID ( Radio Frequency Identific...

Impact of Network Traffic Load on Performance of Queue Controllers

This study is performed to analyze the impact of network traffic load on performance of various A... more This study is performed to analyze the impact of network traffic load on performance of various Active Queue Management (AQM) controllers including traditional DropTail controller. This study represents four scenarios having identical network parameters except network traffic load. The performance of each controller is measured on multiple performance metrics

Neural Network Based Altitude-Hold Autopilot Control of an Aircraft

Neural Network Based Altitude-Hold Autopilot Control of an Aircraft 1YUSRA BANO, 2MUKHTIAR ALI... more Neural Network Based Altitude-Hold Autopilot Control of an Aircraft 1YUSRA BANO, 2MUKHTIAR ALI UNAR, AND 3ZEESHAN ALI 1Department of Mechatronics Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan. 2Department of Commuter Systems Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan. 3Department of Industrial Engineering & Management, Dawood University of Engineering & Technology, Karachi, Pakistan. [email protected], [email protected], [email protected]

A Novel Algorithm to Reduce Peak-To-Average Power Ratio of Orthogonal Frequency Division Multiplexing Signals

It has been observed over last several decades that bandwidth greediness of applications never ge... more It has been observed over last several decades that bandwidth greediness of applications never gets fulfilled. Hence, scientists, researchers, and engineers keep working on new ways of providing higher bandwidth. Recently, a new modulation technique called Orthogonal Frequency Division Multiplexing (OFDM) has been introduced which provides very high data rates. In OFDM the high frequency input signal is modulated over a large number of low frequency sub-carrier signals which are orthogonal to each other. This feature makes it very robust against efficiency degradation at higher frequencies. That is the reason why OFDM is a choice for the modern high and ultra-high data rate communication systems. However, it suffers from high levels of the peak power to the average power also called Peak-to-Average Power Ratio or PAPR. Reducing PAPR in OFDM is a hot research area. There are many schemes available which attempt to reduce PAPR. Some are in fact able to reduce PAPR but not sufficient e...

M Shape Memory Alloy Actuated Inchworm

Shape memory alloy (SMA) is a type of material that are able to return to its original shape.When... more Shape memory alloy (SMA) is a type of material that are able to return to its original shape.When subjected to appropriate temperature. The properties of SMA makes it suitable for actuation in robotics. When dealing with small size and weight of it. Especially when small size and weight are desirable. Shape memory alloy has many applications in bio-robotics such as Manta ray robot, Snake robot and fish robot etc. In this paper a SMA actuated inchworm is reported. The components used in the inchworm robot are the compression spring, shape memory alloys, plastic sheet, Crimps, Arduino board and ULN2003A and DC power supply. The designed inchworm robot mechanism has 2 plastic plates attached to glue. These plastic plates have negligible weight and compression spring is used for bias force .To assure better mechanical design of robot SMA actuator and spring are employed. When a signal is given from computer the power is transmitted from DC power supply, and supply SMA wire. Then current...

The Role of Knowledge Management and Data Mining in Improving Educational Practices and the Learning Infrastructure

April 2020, 2020

Higher Educational Institutes hold a central and vital role in the knowledge economy. Knowledge g... more Higher Educational Institutes hold a central and vital role in the knowledge economy. Knowledge generated by these institutes needs to be collected and disseminated to bring about improvement in not only student learning and performance, but also in educational practices, processes and the society in general. Sadly, in many institutes, this knowledge is rarely recognized, captured, analysed or utilized. Apart from the need for improved learning outcomes, rapid growth in educational data and technology has motivated several educational institutes to implement Knowledge Management (KM). KM is the key to enable educational institutes reach their goals and achieve their objectives. This paper explores the basic concept of KM and addresses the need of KM in higher educational institutes by proposing a framework to improve knowledge processes and practices in academia. This paper also highlights the role of data mining in facilitating KM in higher education through a case study that focus...

Modeling of Flux linkage Characteristics of Switched Reluctance Motor

Indian Journal of Science and Technology, 2019

The increasing popularity of the switched reluctance machine has created more challenges to prese... more The increasing popularity of the switched reluctance machine has created more challenges to present it as a good performer machine under different operational conditions. For modeling and simulation of the machine, the necessity of static characteristics, in particular, flux linkage characteristics which look like the base stone for initialization of simulation is unavoidable. The importance of flux linkage characteristics, and how other data tables such as inverter flux linkage characteristics, co energy and static torque table are obtained are presented in this work. This paper describes a set of equations for modeling of the flux linkage characteristics of switched reluctance machine and also hardware for the 3-phase machine is presented.

Intelligent Aircraft Control System Using Neural Networks

Artificial neural networks increasingly are being used in a variety of automation and control app... more Artificial neural networks increasingly are being used in a variety of automation and control applications where the characteristics of the controlled system change significantly with the operating conditions or with time. This study investigates the potential of radial basis function (RBF) network architecture of feed-forward neural networks as an intelligent altitude hold autopilot of an aircraft. The approach involves the training of a single artificial neural network to represent a conventional controller. The resulting network thus captures, in a nonlinear fashion, the essential characteristics of the conventional controller. Preliminary investigations confirm that RBF architecture of feed forward neural networks is suitable for developing automatic control systems. This research will help in the development of a multi-objective robust adaptive intelligent automatic pilot that can control the aircraft under different operating and environmental conditions.

Ship steering control using feedforward neural networks

One significant problem in the design of ship steering control systems is that the dynamics of th... more One significant problem in the design of ship steering control systems is that the dynamics of the vessel change with operating conditions such as the forward speed of the vessel, the depth of water and loading conditions etc. Approaches considered in the past to overcome these difficulties include the use of self adaptive control systems which adjust the control characteristics on continuous basis to suit the current operating conditions. Artificial neural networks have been receiving considerable attention in recent years and have been considered. for a variety of applications where the characteristics of the controlled system change significantly with operating conditions or with time. Such networks have a configuration which remains fixed once the training phase is complete. The resulting controlled systems thus have more predictable characteristics than those which are found in many forms of traditional self-adaptive control systems. In particular, stability bounds can he investigated through simulation studies as with any other form of controller having. fixed characteristics heedforward neural networks have enjoyed many successful applications in the field of systems and control. These networks include two major categories: multilayer perceptrons and radial basis function networks. In this thesis, we explore the applicability of both of these artificial neural network architectures for automatic steering of ships in a course changing mode of operation.

SAM: Support Vector Machine Based Active Queue Management

Recent years have seen an increasing interest in the design of AQM (Active Queue Management) cont... more Recent years have seen an increasing interest in the design of AQM (Active Queue Management) controllers. The purpose of these controllers is to manage the network congestion under varying loads, link delays and bandwidth. In this paper, a new AQM controller is proposed which is trained by using the SVM (Support Vector Machine) with the RBF (Radial Basis Function) kernal. The proposed controller is called the support vector based AQM (SAM) controller.

Design of Heading Controller for Cargo Ship using Feed Forward Artificial Neural Network

International Journal of Advancements in Computing Technology, 2013

ABSTRACT For successful design and development in marine engineering systems, computer analysis a... more ABSTRACT For successful design and development in marine engineering systems, computer analysis and simulation is considered as an important tool. Ship motion is highly nonlinear and complex controlled process with several hydrodynamic parameters. Therefore to control the ship effectively in a desired course is always an important task for ship designers. In this paper, the application of artificial neural network (ANN) is investigated in order to design an autopilot for controlling the heading angle of a cargo ship. Feed forward multilayered architecture of ANN is used because of layered architecture. It is easy to design and can control nonlinear systems efficiently. Efficiency of proposed autopilot controller is studied and compared with sliding mode controller. Simulation carried out in MATLAB environment using cargo ship model in ideal condition (with no environmental disturbances). This study demonstrates that proposed autopilot system can efficiently be used to control the heading of a ship in all operating conditions. Keywords: Ship Autopilots, Ship Dynamics, Artificial Neural Network (ANN), NN based Ship Heading Controller