Conference Publications by Muhammad Junaid Asif
4th International Conference on Communication, Computing and Digital Systems, 2025
With the recent advancement in the field of deep learning and computer vision, crowd scene analys... more With the recent advancement in the field of deep learning and computer vision, crowd scene analysis has become an essential research area for ensuring public safety. United Nations (UN) predicts world population growth of 0.82% by 2035, driving people to cities for better lifestyles and social events like concerts, shopping, political gatherings, and educational conferences. Manual monitoring, however, is often laborious and error-prone, underscoring the importance of automated solutions. In this paper, we propose a spatiotemporal framework based on the combination of Convolutional Neural Networks and Long Short-Term Memory (LSTM) for automatic classification of normal vs abnormal behavior of people present in a crowd. VGG-19 is proposed for extraction of spatial features of two consecutive frames at different time levels "t" and "t-1". These extracted spatial features are then concatenated by leveraging the Wide Dense Residual block (WDRB). The concatenated features are then fed to LSTM block to capture the temporal features. The proposed method is evaluated on two different data sets: hockey fight data set and Real-Life Violent Situation (RLVS). Evaluation shows that the proposed method provides an efficient and reliable framework for crowd anomaly detection, thereby enhancing public security and safety. The results show that the models achieve accuracy of 91.0%, and 93.5% on hockey fight datasets and RLVS respectively. The implementation code is available at https://github.com/junaid2066/CAD
2016 19th International Multi-Topic Conference (INMIC), 2016
This paper presents the Torque vs. Speed characteristics of induction motor by mathematical model... more This paper presents the Torque vs. Speed characteristics of induction motor by mathematical modeling using SIMULINK. It has been observed that during the past three decades the use of induction motor has been increased due to its high efficiency and speed control. It plays a very important role in our daily life as well as in industry because of its low maintenance cost, reliable operation, robustness and simple construction. Dynamic model is generally used to study the steady state and transient behavior of induction motor. This paper presents the mathematical model of an induction motor using the Clarkes transformation (αβγ transformation) of stator and rotor parameters on reference frame. First of all, the mechanical equations for speed and torque are stated. It also models the differential equation of voltages, currents and flux linkage between the stationary stator and moving rotor. According to that equations state space matrix is implemented. Then a mathematical model is developed using SIMULINK. This model is generally used to study the variation in parameters value on the dynamic performance of the induction motor.
2016 International Conference on Intelligent Systems Engineering (ICISE), 2016
Language of signs is usually used by the deaf-mute persons in order to convey their message. But,... more Language of signs is usually used by the deaf-mute persons in order to convey their message. But, it becomes very difficult for those who have no knowledge of the sign language. The aim of this research work is to resolve this problem using Digital Dactylology Converser (DOC) which is a device that converts a sign language into voice signal and text message. Primarily a hands gesture is recognised by computer vision program and based on that image a speech and text is played and displayed on the speaker and LCD respectively. Purpose of this device is to make conversation easy between dumb and the normal people around the world. In order to minimize their limitations and enable them to expand their boundaries, this is best suitable device. Experimental results verify the operational accuracy of the device for different users. The proposed device can work well and translates the letters, alphabets to text and sound.
2023 25th International Multitopic Conference (INMIC), 2023
Fully-supervised learning requires expensive and laborious annotations of labeled data for crowd-... more Fully-supervised learning requires expensive and laborious annotations of labeled data for crowd-counting tasks. To alleviate this burden, it is desirable to explore methods that reduce the need for extensive labeling. Fortunately, there are a vast number of unlabeled images available in the world, making them easily accessible compared to labeled datasets. This paper proposes a self-supervised learning-based M-CNN framework with an attention mechanism that aims to leverage unlabeled data for pre-training the model. The framework consists of four sub-modules: a data augmentation framework, a self-supervised training network, a multi-column CNN, and an attention mechanism. These networks receive the images that undergo random processing using two defined augmentation transformations. Transformed images are then subjected to selfsupervised learning and fed to a feature extraction network. FEN consists of M-CNN with five convolutional branches to extract features at a multi-scale level. These extracted features are then employed as an attention mechanism to focus on the head or shoulder location of people. To evaluate the effectiveness of our proposed model, experiments are conducted on two public datasets: ShanghaiTech Part A, Part B, and UCF-QNRF. The experimental results demonstrate that our approach outperforms state-of-the-art semi-supervised methods, showcasing the effectiveness of our proposed approach in leveraging both unlabeled and limited labeled data for crowd counting tasks.
MDSRC - 2015 Proceedings, 14-15 November, 2015 Wah/Pakistan, 2015
Based on ARDUINO and SONAR, multi syringe infusion pump for biomedical applications is presented ... more Based on ARDUINO and SONAR, multi syringe infusion pump for biomedical applications is presented in this paper. The ARDUINO uses ATMEGA 2560 which mainly takes charge of the system to infuse medication, drugs, fluids and nutrients into the patient's circulatory system at low doses and constant controllable rates. The main aspect of this system is to provide relief to the nursing and medical staff. This system is more secure; there is no need of human operator. The system is designed at volume rate instead of flow rate. The system is able to infuse fluid according to the required infusion rate. The minimum acceptable delivery precision is 3.5µL/hr. During injection Built-in microcontroller decides the speed of stepper motor according to the defined injection rate. Stepper motor is coupled to the syringe to control the activity of pump. A lead screw is used to convert the rotational movement of the motor into the linear movement that pushes the plunger in a syringe. The size of syringe is selected by using the SONAR. The step size of stepper motor is 2.4 0 and linear motion of syringe is 4 µm/step. A built-in safety mechanism is implemented to avoid malfunctioning of machine and gives alert to the medical staff.
Rice Grain Identification and Quality Analysis using Image Processing based on Principal Component Analysis
2018 International Symposium on Recent Advances in Electrical Engineering (RAEE), 2018
Different types of foods are available in grain form, but rice is one of the important and most u... more Different types of foods are available in grain form, but rice is one of the important and most used cereal grains of Pakistan and all over the world. Quality inspection of rice grain is also important for both local as well as export purpose. It is necessary to propose an automatic solution to perform the quality analysis as well as to distinguish between different classes of rice. Main purpose of this paper is to present an image processing-based solution to classify the different varieties of rice and its quality analysis. An approach based on the combination of principal component analysis and canny edge detection is used for the classification. Quality analysis of rice grain is determined by morphological features of rice grains. These morphological features include eccentricity, major axis length, minor axis length, perimeter, area and size of the grains. Six different varieties of rice are classified and analyzed in this paper. A database is trained by feeding the 100 images of each variety of rice grains. Classification and quality analysis is done by comparing the sample image with database image. Canny edge detector is applied to detect the edges of rice grains. Eigen values and Eigen vectors are calculated on the basis of morphological features. Then by applying the PCA, different varieties of rice are classified by comparing the sample image with a database. Results obtained in terms of classification and quality analysis are 92.3% and 89.5% respectively. Proposed system can work well within minimum time and low cost.
Visual impairment aid using haptic and sound feedback
2017 International Conference on Communication, Computing and Digital Systems (C-CODE), 2017
In this paper, implementation of a wearable glove is presented that can be used to assist the vis... more In this paper, implementation of a wearable glove is presented that can be used to assist the visually impaired people. It can help the blind person to avoid hurdles using haptic and voice feedback. It does not only navigate the path to the blind person but also informs about his/her location to others through a message on the mobile device. It can help his/her caretaker (in case he is not near to the blind person) to locate him using the received coordinates from the communication module of glove having Global Positioning System (GPS) and Global System for Mobile Communication (GSM) technology. This wearable glove is physically realized by interfacing different sensors and communication modules with Arduino UNO. Different modes of obstacles detection and alerts are provided using various sensors and actuators to assist visually impaired person.
Journal Publications by Muhammad Junaid Asif
Journal of Engineering and Higher Technologies, 2015
In this research paper, implementation of embedded system based robotic hand that can reproduce a... more In this research paper, implementation of embedded system based robotic hand that can reproduce all the movements of human hand and provides comparable sensitivity is discussed. Moreover, the control system of wireless controlled shadow dexterous hand is presented which can be used for hazardous environments. This hand allows a direct mapping from a human to the robot movement using sensors placed on hand. Sensors placed on hand detect the muscles response of a person and then the responses of corresponding sensors are delivered to the microcontroller. Then Xbee module is used to transfer the wireless signals to the microcontroller, which drives the mechanical hand according to the acquired signal and produces the shadow movement of human hand.
LGU Research Journal of Computer Science & IT, 2024
This research paper explores the burgeoning field of machine learning and its application in stra... more This research paper explores the burgeoning field of machine learning and its application in strategic customer segmentation within the aviation industry. Leveraging the Airline Passenger dataset, this study assesses the potential of various machine learning classifiers to enhance customer retention by effectively segmenting satisfied customers. Our methodology involves a comparative analysis of five machine learning classifiers: Random Forest, K-Nearest Neighbors (KNN), Decision Tree, Naive Bayes, and Artificial Neural Network (ANN). Each classifier is rigorously tested and evaluated based on key performance metrics, including accuracy, precision, recall, and F1-score. The results indicate a diverse range of classifier effectiveness. Notably, the Random Forest classifier outperforms others with outstanding metrics: accuracy, precision, recall, and F1-score of 0.96. Decision Tree follows closely, achieving high performance with a score of 0.95 across all metrics. Naive Bayes and ANN demonstrate respectable performance, with accuracy scores of 0.86 and 0.90, respectively. In contrast, KNN presents lower but consistent performance, with all metrics at 0.75. These quantitative findings highlight the nuanced performance differences among classifiers, emphasizing the critical role of algorithm selection in achieving precise customer segmentation. This study provides significant insights into the application of machine learning for strategic customer retention in the aviation sector, presenting practical implications for airlines aiming to optimize their segmentation strategies and retain satisfied customers. By showcasing the varying performances of different classifiers, this research contributes to the broader discourse on integrating machine learning into customer-centric strategies, ultimately aiding airlines in engaging and retaining their customer base more effectively.
Papers by Muhammad Junaid Asif
This project paper presents on the Programmable Syringe Pump. An infusion pump infuses fluids, me... more This project paper presents on the Programmable Syringe Pump. An infusion pump infuses fluids, medication or nutrients into a patient's circulatory system Since there are many kind of syringe pump in the market which are used in hospitals and medical labs. However, in this project, a volume rate syringe pump was designed, instead of flow rate.
This project has dealt with a simple designed pump with simple mechanical movement using a ball screw actuator which overcomes friction problem and a suitable stepper motor. In this project, focused was on a discontinuous pump, where volume is dispensed with respect to time.
The control is done via a Micro-controller and Keypad. The project was done by defining different kinds of volume rate which is a low volume rate (5mL/min) and a high volume rate (20mL/10min). Using a small syringe size proved to be much improvement in a high volume dispensed.
Mathematical modelling of 3-phase induction motor to study the Torque vs. Speed characteristics using MATLAB Simulink
2016 19th International Multi-Topic Conference (INMIC), 2016
This paper presents the Torque vs. Speed characteristics of induction motor by mathematical model... more This paper presents the Torque vs. Speed characteristics of induction motor by mathematical modeling using SIMULINK. It has been observed that during the past three decades the use of induction motor has been increased due to its high efficiency and speed control. It plays a very important role in our daily life as well as in industry because of its low maintenance cost, reliable operation, robustness and simple construction. Dynamic model is generally used to study the steady state and transient behavior of induction motor. This paper presents the mathematical model of an induction motor using the Clarkes transformation (aPy transformation) of stator and rotor parameters on reference frame. First of all, the mechanical equations for speed and torque are stated. It also models the differential equation of voltages, currents and flux linkage between the stationary stator and moving rotor. According to that equations state space matrix is implemented. Then a mathematical model is developed using SIMULINK. This model is generally used to study the variation in parameters value on the dynamic performance of the induction motor.
Thesis Chapters by Muhammad Junaid Asif
This project proposal outlines the construction of 3-D computer numerical control (CNC) leather ... more This project proposal outlines the construction of 3-D computer numerical control (CNC) leather cutting machine. The CNC leather cutting machine cuts the leather in to different shapes and. The CNC software will take an input image from the CAD/CAM file. The main purpose of this project is eliminating the human factor.
This machine will be able to move on 2-axis and cut the leather in to different shapes by using CUTTER. After taking input in the form of CAD/CAM file. We will use the KCAM4 software to convert CAD/CAM file into GCode file. The main part of the machine is Machine Control Unit (MCU). MCU will convert the graphical input into electrical signals. These electrical signals are used to control the stepping sequence of stepper motors and driving circuitry. The whole process of cutting becomes more precise, accurate and less cost effective.
Uploads
Conference Publications by Muhammad Junaid Asif
Journal Publications by Muhammad Junaid Asif
Papers by Muhammad Junaid Asif
This project has dealt with a simple designed pump with simple mechanical movement using a ball screw actuator which overcomes friction problem and a suitable stepper motor. In this project, focused was on a discontinuous pump, where volume is dispensed with respect to time.
The control is done via a Micro-controller and Keypad. The project was done by defining different kinds of volume rate which is a low volume rate (5mL/min) and a high volume rate (20mL/10min). Using a small syringe size proved to be much improvement in a high volume dispensed.
Thesis Chapters by Muhammad Junaid Asif
This machine will be able to move on 2-axis and cut the leather in to different shapes by using CUTTER. After taking input in the form of CAD/CAM file. We will use the KCAM4 software to convert CAD/CAM file into GCode file. The main part of the machine is Machine Control Unit (MCU). MCU will convert the graphical input into electrical signals. These electrical signals are used to control the stepping sequence of stepper motors and driving circuitry. The whole process of cutting becomes more precise, accurate and less cost effective.