Biblio

Nowadays, video surveillance cameras are widely used in many smart city applications for ensuring road safety. We can use video data from them to solve such tasks as traffic management, driving control, environmental monitoring, etc. Most of these applications are based on object recognition and tracking algorithms. However, the video image quality is not always meet the requirements of such algorithms due to the influence of different external factors. A variety of adverse weather conditions produce noise on the images, which often makes it difficult to detect objects correctly. Lately, deep learning methods show good results in image processing, including denoising tasks. This work is devoted to the study of using these methods for image quality enhancement in difficult weather conditions such as snow, rain, fog. Different deep learning techniques were evaluated in terms of their impact on the quality of object detection/recognition. Finally, the system for automatic image denoising was developed.

Wireless communication in the field of radio frequency (RF) have modernized our society. People experience persistent connection and high-speed data through wireless technologies like Wi-Fi and LTE while browsing the internet. This causes congestion to network; users make it difficult for everyone to access the internet or to communicate reliably on time. The major issues of RF spectrum are intrusion, high latency and it requires an individual transmitter receiver setup in order to function. Dr. Herald Hass came up with an idea of `data through illumination'. Surmounting the drawbacks of RF spectrum, visible light communication (VLC) is more favored technique. In intelligent transportation system (ITS), this evolving technology of VLC has a strong hold in order to connect vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) links wirelessly. Indoor VLC applications have been studied deeply while the field of vehicular VLC (V-VLC) networking is relatively a less researched domain because it has greater level of intrusion and additive ambient light noise is higher in outdoor VLC. Other factors due to which the implementation of VLC faces a lot of hurdles are mostly related to environment such as dust, haze, snow, sunlight, rain, fog, smog and atmospheric disturbances. In this paper, we executed a thorough channel modelling in order to study the effects of clear weather, fog, snow and rain quantitatively with respect to different wavelengths in consideration for an ITS. This makes ITS more robust in nature. The parameters under consideration will be signal-to-noise ratio (SNR), bit error rate (BER) and optical power received (OPR) for different LED wavelengths.

Advanced Persistent Threats (APTs) are stealthy, sophisticated, long-term, multi-stage attacks that threaten the security of sensitive information. Dynamic Information Flow Tracking (DIFT) has been proposed as a promising mechanism to detect and prevent various cyber attacks in computer systems. DIFT tracks suspicious information flows in the system and generates security analysis when anomalous behavior is detected. The number of information flows in a system is typically large and the amount of resources (such as memory, processing power and storage) required for analyzing different flows at different system locations varies. Hence, efficient use of resources is essential to maintain an acceptable level of system performance when using DIFT. On the other hand, the quickest detection of APTs is crucial as APTs are persistent and the damage caused to the system is more when the attacker spends more time in the system. We address the problem of detecting APTs and model the trade-off between resource efficiency and quickest detection of APTs. We propose a game model that captures the interaction of APT and a DIFT-based defender as a two-player, multi-stage, zero-sum, Stackelberg semi-Markov game. Our game considers the performance parameters such as false-negatives generated by DIFT and the time required for executing various operations in the system. We propose a two-time scale Q-learning algorithm that converges to a Stackelberg equilibrium under infinite horizon, limiting average payoff criteria. We validate our model and algorithm on a real-word attack dataset obtained using Refinable Attack INvestigation (RAIN) framework.

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limitations of current Image Generative Models in their application to counterfactual creation.