Universiti Teknologi Petronas

About: Universiti Teknologi Petronas is a education organization based out in Ipoh, Malaysia. It is known for research contribution in the topics: Adsorption & Ionic liquid. The organization has 6127 authors who have published 11284 publications receiving 119400 citations.

GIS- based Land Suitability Analysis Using AHP for Public Parks Planning in Larkana City

Abstract: Optimal locations for public facilities such as public parks are significant issues in the urban planning of Larkana city. Therefore, specifically, Larkana city of Pakistan is selected as the study area where the land suitability model was applied to determine suitable land for public parks. This study was carried out within the framework of an Analytic Hierarchy Process (AHP) as a multi-criteria evaluation approach by integrating it with the Geographic Information System (GIS). Decision support system software called Expert choice 11.5 was used to calculate the weights based on three alternative scenarios. Computed composite weights were inserted into the spatial analysis function of GIS and produced three scenarios of suitability maps, i.e.: (a) land availability, (b) land value and (c) population density. Hence, based on the analysis and findings made in this research, finding suitable locations using the land suitability model for future park development is highly helpful. Results can be useful in the planning of public facilities and future land use planning in Larkana city.

A novel deep learning instance segmentation model for automated marine oil spill detection

Abstract: The visual similarity of oil slick and other elements, known as look-alike, affects the reliability of synthetic aperture radar (SAR) images for marine oil spill detection. So far, detection and discrimination of oil spill and look-alike are still limited to the use of traditional machine learning algorithms and semantic segmentation deep learning models with limited accuracy. Thus, this study developed a novel deep learning oil spill detection model using computer vision instance segmentation Mask-Region-based Convolutional Neural Network (Mask R-CNN) model. The model training was conducted using transfer learning on the ResNet 101 on COCO as backbone in combination with Feature Pyramid Network (FPN) architecture for feature extraction at 30 epochs with 0.001 learning rate. Testing of the model was conducted using the least training and validation loss value on the withheld testing images. The model’s performance was evaluated using precision, recall, specificity, IoU, F1-measure and overall accuracy values. Ship detection and segmentation had the highest performance with overall accuracy of 98.3%. The model equally showed a higher accuracy for oil spill and look-alike detection and segmentation although oil spill detection outperformed look-alike with overall accuracy values of 96.6% and 91.0% respectively. The study concluded that the deep learning instance segmentation model performs better than conventional machine learning models and deep learning semantic segmentation models in detection and segmentation.

Smart parking reservation system using short message services (SMS)

Abstract: This paper proposes a smart parking system to solve the problem of unnecessary time consumption in finding parking spot in commercial car park areas. A parking reservation system is developed in such a way that users book their parking spots through short message services (SMS). The SMS sent will be processed by a wireless communication instrumentation device called micro-RTU (Remote Terminal Unit). This micro-RTU will reply the confirmation of booking by giving the details of reservation like password and lot number. The password will be used to enter the parking area and valid for a certain period of time. The system is fully automated with the use of the Peripheral Interface Controller (PIC). This microcontroller is capable in storing information of empty parking spaces, provide passwords as well as allowing or denying access to the parking area. A prototype of a car park system has been designed to demonstrate the capability of the proposed work. The demonstration has proven the capability of the system to reserve the parking, gain entry to the parking area and hence eliminates the hassle of searching empty parking lots.