Mahbub E. Khoda

Climate change poses a significant threat to our planet, particularly affecting intricate marine ecosystems like coral reefs. These ecosystems are crucial for biodiversity and serve as indicators of the overall health of our oceans. To better understand and predict these changes, this paper discusses a multidisciplinary technical approach incorporating machine learning, artificial intelligence (AI), geographic information systems (GIS), and remote sensing techniques. We focus primarily on the changes that occur in coral reefs over time, taking into account biological components, geographical considerations, and challenges stemming from climate change. We investigate the application of GIS technology in coral reef studies, analyze publicly available datasets from various organisations such as the National Oceanic and Atmospheric Administration (NOAA), the Monterey Bay Aquarium Research Institute, and the Hawaii Undersea Research Laboratory, and present the use of machine and deep learning models in coral reef surveillance. This article examines the application of GIS in coral reef studies across various contexts, identifying key research gaps, particularly the lack of a comprehensive catalogue of publicly available datasets. Additionally, it reviews the existing literature on machine and deep learning techniques for coral reef surveillance, critically evaluating their contributions and limitations. The insights provided in this work aim to guide future research, fostering advancements in coral reef monitoring and conservation.

Emergency Management System (EMS) is an important component of Intelligent transportation systems, and its primary objective is to send Emergency Vehicles (EVs) to the location of a reported incident. However, the increasing traffic in urban areas, especially during peak hours, results in the delayed arrival of EVs in many cases, which ultimately leads to higher fatality rates, increased property damage, and higher road congestion. Existing literature addressed this issue by giving higher priority to EVs while traveling to an incident place by changing traffic signals (e.g., making the signals green) on their travel path. A few works have also attempted to find the best route for an EV using traffic information (e.g., number of vehicles, flow rate, and clearance time) at the beginning of the journey. However, these works did not consider congestion or disruption faced by other non-emergency vehicles adjacent to the EV travel path. The selected travel paths are also static and do not consider changing traffic parameters while EVs are en route. To address these issues, this article proposes an Unmanned Aerial Vehicle (UAV) guided priority-based incident management system to assist EVs in obtaining a better clearance time in intersections and thus achieve a lower response time. The proposed model also considers disruption faced by other surrounding non-emergency vehicles adjacent to the EVs’ travel path and selects an optimal solution by controlling the traffic signal phase time to ensure that EVs can reach the incident place on time while causing minimal disruption to other on-road vehicles. Simulation results indicate that the proposed model achieves an 8% lower response time for EVs while the clearance time surrounding the incident place is improved by 12%.

Machine learning models, including deep neural networks, have been shown to be vulnerable to adversarial attacks. Adversarial samples are crafted from legitimate inputs by carefully introducing small perturbation to the input so that the classifier is fooled. Adversarial retraining, which involves retraining the classifier using adversarial samples, has been shown to improve the robustness of the classifier against adversarial attacks. However, it has been also shown that retraining with too many samples can lead to performance degradation. Hence, a careful selection of the adversarial samples that are used to retrain the classifier is necessary, yet existing works select these samples in a randomized fashion. In our work, we propose two novel approaches for selecting adversarial samples: based on the distance from cluster center of malware and based on the probability derived from a kernel based learning (KBL). Our experiment results show that both of our selective mechanisms for adversarial retraining outperform the random selection technique and significantly improve the classifier performance against adversarial attacks. In particular, selection with KBL delivers above 6% improvement in detection accuracy compared to random selection. The method proposed here has greater impact in designing robust machine learning system for security applications.

Due to its widespread use, with numerous applications deployed everyday, smartphones have become an inevitable target of the malware developers. This huge number of applications renders manual inspection of codes infeasible; as such, researchers have proposed several malware detection techniques based on automatic machine learning tools. Deep learning has gained a lot of attention from the malware researchers due to its ability of capture complex relationships among inputs and outputs. However, deep learning models depend largely on several hyper-parameters (i.e., learning rate, batch size, dropout rate). Hence, it is of utmost importance to analyze the effect of these parameters on classifier performance. In this paper, we systematically studied the effect of these parameters along with the effect of network architecture. We showed that building arbitrary deep networks does not always improve classifier performance. We also determined the combination of hyper-parameters that yields best result. This study will be useful in building better deep neural network based model for malware classification.