The technological landscape of intelligent transport systems (ITS) has been radically transformed by the emergence of the big data streams generated by the Internet of Things (IoT), smart sensors, surveillance feeds, social media, as well as growing infrastructure needs. It is timely and pertinent that ITS harness the potential of an artificial intelligence (AI) to develop the big data-driven smart traffic management solutions for effective decision-making. The existing AI techniques that function in isolation exhibit clear limitations in developing a comprehensive platform due to the dynamicity of big data streams, highfrequency unlabeled data generation from the heterogeneous data sources, and volatility of traffic conditions. In this paper, we propose an expansive smart traffic management platform (STMP) based on the unsupervised online incremental machine learning, deep learning, and deep reinforcement learning to address these limitations. The STMP integrates the heterogeneous big data streams, such as the IoT, smart sensors, and social media, to detect concept drifts, distinguish between the recurrent and non-recurrent traffic events, and impact propagation, traffic flow forecasting, commuter sentiment analysis, and optimized traffic control decisions. The platform is successfully demonstrated on 190 million records of smart sensor network traffic data generated by 545,851 commuters and corresponding social media data on the arterial road network of Victoria, Australia.
The global ambitions of a carbon-neutral society necessitate a stable and robust smart grid that capitalises on frequency reserves of renewable energy. Frequency reserves are resources that adjust power production or consumption in real time to react to a power grid frequency deviation. Revenue generation motivates the availability of these resources for managing such deviations. However, limited research has been conducted on data-driven decisions and optimal bidding strategies for trading such capacities in multiple frequency reserves markets. We address this limitation by making the following research contributions. Firstly, a generalised model is designed based on an extensive study of critical characteristics of global frequency reserves markets. Secondly, three bidding strategies are proposed, based on this market model, to capitalise on price peaks in multi-stage markets. Two strategies are proposed for non-reschedulable loads, in which case the bidding strategy aims to select the market with the highest anticipated price, and the third bidding strategy focuses on rescheduling loads to hours on which highest reserve market prices are anticipated. The third research contribution is an Artificial Intelligence (AI) based bidding optimization framework that implements these three strategies, with novel uncertainty metrics that supplement data-driven price prediction. Finally, the framework is evaluated empirically using a case study of multiple frequency reserves markets in Finland. The results from this evaluation confirm the effectiveness of the proposed bidding strategies and the AI-based bidding optimization framework in terms of cumulative revenue generation, leading to an increased availability of frequency reserves.
Road traffic environments are highly dynamic and volatile with a multitude of roadside and external environmental factors contributing to its dynamicity. Apart from infrastructure-related means such as traffic lights, planned and unplanned road events and different road networks, a core component which contributes towards the traffic environment is the human factor which is heavily overlooked in the current studies. Due to diverse travel patterns of day-to-day activities, the commuter behaviour is directly depicted in traffic patterns providing an opportunity to further explore human behaviours using road traffic. Conducting such analysis would reveal different commuter behavioural patterns that can be used for optimization and timely management of operations. However, to conduct such real-time behaviour analysis, large volumes of high-frequency data are required with high granularity, as well as, a suitable technology to manage such data. Addressing these needs, we propose an environment-driven commuter behavioural model that can be used to elucidate diverse behaviours in road traffic environments. We conceptualized, designed and developed an artificial intelligence based commuter behaviour profiling framework to detect diverse commuter behavioural profiles, fluctuating and routine patterns among commuters using traffic flow profiling and travel trajectory analysis. We evaluated the framework using 190 million data points captured from the Bluetooth sensor network of the Melbourne arterial road network, in the state of Victoria in Australia. The results demonstrate that traffic flow profiling of the proposed framework can provide insights on recurrent commuter behaviours that are distinct to a selected area with a high granularity. Moreover, traffic trajectory analysis provides insights on non-recurrent behaviours such as accidents with regard to how such incidents impact the dynamics of the network and how the impact is propagated through the network. Besides road traffic management, the proposed framework will enable real-time decision-making when planning road infrastructure and support decision-making of government and business entities to optimize operations. KeywordsTraffic analysis Á Flow profiling Á Trajectory analysis Á Bluetooth data Á Human behaviour Á IoT & Naveen Chilamkurti
Motivated by recent innovations in biologicallyinspired neuromorphic hardware, this paper presents a novel unsupervised machine learning approach named Hyperseed that leverages Vector Symbolic Architectures (VSA) for fast learning a topology preserving feature map of unlabelled data. It relies on two major capabilities of VSAs: the binding operation and computing in superposition. In this paper, we introduce the algorithmic part of Hyperseed expressed within Fourier Holographic Reduced Representations VSA model, which is specifically suited for implementation on spiking neuromorphic hardware. The two distinctive novelties of the Hyperseed algorithm are: 1) Learning from only few input data samples and 2) A learning rule based on a single vector operation. These properties are demonstrated on synthetic datasets as well as on illustrative benchmark usecases, IRIS classification and a language identification task using n-gram statistics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.