Forthcoming Articles
Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the SSURJET standard. Moreover, titles, authors' number, abstracts and keywords may change before publication.
Volume 14 Issue 1 Year 2024
- Title: Cutting through the noise: A Three-Way Comparison of Median, Adaptive Median, and Non-Local Means Filter for MRI Images.
Authors: Raniya Ashraf, Roz Nisha, Fahad Shamim and Sarmad Shams
Accepted on: February 19, 2024Abstract: Medical Imaging is an essential practice in radiology to create high-standard images of the human brain. In medical imaging, denoising techniques are essential during image processing for a meaningful view of the anatomical structure of the images. In order to overcome the denoising issues, various filtering techniques and smoothening algorithms have come forth to get an accurate image for better diagnosis while preserving the original image quality. This work utilizes three computational methods for filtering noise that could distort the factual information in MRI images. The input used as the data throughout this study are MR images in grayscale contaminated with Salt and paper noise, the most common noise in MRI images. To de-noise, a comparative analysis of three specific filters, namely the Non-Local Means filter, Median filter, and Adaptive Median filter, is conducted to do a study that gives the best results among them at different noise densities. Peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) are utilized as the main components to examine the behavior of the suggested filters in this study. The results show that at every value of noise density, i.e., 0.1, 0.3, 0.6, the adaptive median filter gives the highest average PSNR of 42.04, 34.36, and 28.10 and average SSIM of 0.97, 0.95, and 0.91, respectively. Hence, it indicates that the adaptive median filter outperforms the other two filters regarding PSNR and SSIM.
- Title: Energy, Society and Sociodemographic Constraints Nexus: Development and Future Prospects
Authors:Leezna Saleem and I Ulfat
Accepted on: March 03, 2024Abstract: To overcome the challenges faced by energy sector, policymakers need to prioritize the development of strategic policies that promote the adoption of waste-to-energy technologies, Tidal energy, solar power systems, and wind farms. These policies should emphasize the integration of renewable energy sources into the existing energy infrastructure, ensuring a more sustainable and resilient energy supply for urban areas. The study underscores the importance of collaboration between various stakeholders, including government bodies, private sector entities, and local communities. By fostering partnerships and creating incentives, it becomes possible to mobilize resources and expertise towards the implementation of renewable energy projects. This collaboration would not only address the energy crisis but also contribute to job creation and overall socioeconomic development.Proper utilization of renewable energy resources can resolve the dilemma of energy crises in the country According to our results solar stood first in the overall ranking followed by Tidal, waste to energy and wind energies. Solar performed better in indigenous manufacturing and development, resource potential and technological development. Pakistan has abundant green energy resource which could be utilized by the formation of a proper policy road map and mitigation of policy pathways to overcome the hazardous dependence on fossil fuel for energy requirements.The implementation of policies adapted should be assured to achieve energy sustainability.
- Title: Comparative Analysis of Supervised Machine Learning Algorithms for COVID-19 Prediction
Authors:Beenish Akram, Rubina Shaheen, Amna Zafar and Talha Waheed
Accepted on: March 12, 2024Abstract: With the emergence of COVID-19 as a disaster unheard of and beyond the so-called scientific development, each health structure of both the developed and underdeveloped world not only seemed helpless but rotten. The human interface was faced with the dilemma of infection causing the health workers to fall prey while identifying the patients. Given the nature of the disease, it is needed to mitigate the effects of spread by resorting to technological advancements for the diagnosis of disorder using machine learning algorithms. In this paper, three supervised machine learning algorithms; Decision tree, Naïve Bayes and logistic regression have been utilized for the prediction of disease encompassing 10 attributes considering various combinations of symptoms. A comparative analysis of the algorithms used revealed that Decision Trees 99% accuracy with 98% precision rendering it the most viable and accurate technique for the detection of COVID-19 illness.
- Title: Mixed Integer Nonlinear Programming-Based Unit Commitment of Conventional Thermal Generators using Hybrid Evolutionary Algorithms
Authors:Syed Arslan Ali Shah, Noor Hussain Mugheri, Riaz Hussain Memon, Aamir Ali Bhatti and Muhammad Usman Keerio
Accepted on: March 28, 2024Abstract: Unit commitment (UC) discusses the optimized generation resources (to turn on economical generators and turn off expensive generators), which are subjected to satisfy all the operational constraints. The operational constraints such as load balancing, security maximization, minimum up and down time, spinning reserve, and ramp up and down constraints are difficult to satisfy. Although, UC is a cost minimization problem that is realized by committing less expensive units while satisfying the corresponding constraints, and dispatching the committed units economically. The UC problem is np-hard mixed integer nonlinear problem (MINLP). Therefore, in this paper, hybrid EA based on a genetic algorithm (GA) has been applied to find the optimal solution to the UC problem. Moreover, during the search process, it is very difficult to discard infeasible solutions in EAs. Hence, the genetic algorithm (GA) is integrated with the feasibility rule constraint handling technique to emphasize feasible solutions. IEEE RTS eleven thermal generator standard test system is used to validate the performance of proposed methods. For the validation and the superiority of the proposed algorithm, simulation results are compared with the classical Lagrangian relaxation methods. Results show that the proposed method can find the global optimal solution to the UC problem which is subjected to satisfy all the operational constraints.
- Title: Fault Detection & Fault Diagnosis In Power System Using AI: A Review
Authors:Syeda faiza Nasim, Sidra Aziz, Asma Qaiser, Umme Kulsoom, and Saad Ahmed
Accepted on: March 28, 2024Abstract:Electric power is the fuel that drives our world today. The stability and uninterrupted operation of a power system are extremely vital. Faults disrupt our power system and cause interruptions in the supply of power. The proper handling of these faults is extremely important for both safety and the continuous operation of a power system. The two terms most commonly used in this regard are fault detection and fault diagnosis. With time, multiple methods and approaches have been created for fault detection and diagnosis. With these recent advancements in AI, new methods are being researched to better use AI in fault detection and diagnosis. The paper provides a brief review of the already developed literature in this regard. It is concluded that although new research is being carried out each day, the field is still in its infancy and lacks a proper path and structure.
- Title: A Novel Active RFID and TinyML based system for livestock Localization in Pakistan
Authors:Syed Atir Raza Shirazi, Maham Fatima, Abdul Wahab and Sadaf Ali
Accepted on: March 31, 2024Abstract: Localization of livestock is a vital component of good livestock management in Pakistan. This abstract describes a unique method for livestock localization in Pakistan that makes use of Active RFID technology and Tiny Machine Learning (TinyML) approaches. The incorporation of ACTIVE RFID technology allows for precise and long-range livestock tracking, while TinyML provides on-device analysis and decision-making. This method has a number of advantages, including high precision, real-time localization, and less reliance on external infrastructure. Accurate triangulation-based localization is obtained by putting ACTIVE RFID tags on cattle and carefully positioning ACTIVE RFID anchors in specific regions. TinyML integration on resource-constrained microcontrollers within ACTIVE RFID tags allows for efficient on-device analysis of ACTIVE RFID signals. The suggested system has the potential to significantly improve livestock management practices in Pakistan, including animal tracking and monitoring, behavior analysis, and increased animal welfare. To realize the full potential of this unique ACTIVE RFID and TinyML-based livestock localization system in Pakistan, further research should focus on optimizing localization algorithms, enhancing TinyML models, and exploring interaction with upcoming technologies.
- Title: Analysis and Characterization of Composites for their potential use in Disc Brake Pad
Authors:Umer Ijaz, Fouzia Gillani, Muhammad Fraz Anwar, Muhammad Saad Sharif, Ali Iqbal and Raza Hassan Ali.
Accepted on: March 31, 2024Abstract: Brake pads are crucial for vehicle safety, converting kinetic energy to halt motion. They come in types like organic, semi-metallic, ceramic, and metallic. Beyond automotive, brake pads find application in industries such as aerospace, railways, manufacturing, and wind energy for controlled deceleration and safety. This study is primarily concerned with the quality and appropriateness of ceramic brake pads for automotive applications, which are an essential aspect of braking systems for vehicles. The performance characteristics of ceramic brake pads are well established, and this study explores the variables affecting their quality. Under high pressure, brake pad samples are prepared in the study using powder metallurgy (PM), which guarantees superior mechanical qualities by removing interface bonding problems. The samples are then sintered at 2850. Hardness, temperature resistance, wear resistance, and electron dispersive spectroscopy (EDS) analysis are all included in the evaluation to ascertain the make-up and distribution of the materials in the brake pad. EDS sheds light on the degree of sintering and the presence of reinforcements. Heat resistance is evaluated using controlled thermal testing, while wear resistance and hardness are determined through Rockwell Hardness testing and wear tests, respectively. These measurements are validated for use in automotive disc braking systems for vehicles and motorcycles. The findings are more reliable thanks to statistical analysis done with MINITAB. The study highlights research gaps in environmentally friendly materials, emerging technology impacts, and long-term brake pad durability.
- Title: Fuzzy-Logic Based Model for VANET Performance Metrics Analysis
Authors:Shahnila Badar Baloch, Muhammad Tayyab Yaqoob, Asif Gulraiz and Rabbia Muhammad Qasmi
Accepted on: April 02, 2024Abstract:Vehicular Ad-hoc Networks (VANETs) allows a spontaneous communication between vehicle to vehicles and road-side units(RSU) using wireless interfaces and road-side infrastructure to form Intelligent Transportation System (ITS). VANET, prime objective is to provide information about accidents or unwanted situations and traffic conditions to the drivers. As VANETs are dynamic in nature, the vehicle nodes to discover the best possible route to broadcast an emergency message is a challenge. To study different highway and urban road scenarios, there is a need to simulate and evaluate the network performance analysis of routing protocols beforehand since real-time implementation is rather challenging or expensive. This paper focuses on the VANET routing protocols evaluation, to find an appropriate protocol which provide suitable Quality of Service (QoS) to end users in both safety and non-safety conditions. To simplify the QoS evaluation problem, Hierarchical Fuzzy Inference System (HFIS) model has been designed and simulated in MATLAB R2018b that analysis the network performance metrics of VANET routing protocols. From the simulations, it is observed that that OLSR routing protocol for both safety and non-safety applications, outperforms other routing protocols as its global QoS reaches to approximately 84% efficiency.
