Online Incremental Machine Learning Platform for Big Data-Driven Smart Traffic Management

Abstract

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.

Self-Building Artificial Intelligence and Machine Learning to Empower Big Data Analytics in Smart Cities

“…Adding further complications, the environment changes constantly, and any labeling thus needs to be done frequently and regularly to be useful, making it a daunting task for humans. As such unsupervised machine learning techniques without the need of pre-labelled data that could self-learn and incrementally adapt to new situations become more relevant (Nallaperuma et al 2019). In this light, AI systems of the future is expected to incorporate higher degrees of unsupervised learning in order to generate value from unlabeled data (Nawaratne et al 2019a(Nawaratne et al , 2019b(Nawaratne et al , 2019c.…”

“…As such, the third significant problem in many smart city situations where even labelled or classified past data for training machine learning algorithms are available, the relevance of labels become obsolete due to the fastchanging dynamics (Nawaratne et al 2018). As such unsupervised machine learning techniques without the need of prelabelled data that could self-learn and incrementally adapt to new situations become more relevant (Nallaperuma et al 2019). The research discussed in this paper proposes an innovative solution to address these problems based on a new paradigm of self-building AI.…”

Toward Intelligent Industrial Informatics: A Review of Current Developments and Future Directions of Artificial Intelligence in Industrial Applications

“…This is important in industrial settings where training data becomes available gradually over time and it is necessary to adapt to new representations and dimensionality while maintaining a recallable memory of past learning outcomes. Early efforts towards incremental learning are reported in [117], [116], [118], [119].…”

A Review of the Contribution of Mechanomutable Asphalt Materials Towards Addressing the Upcoming Challenges of Asphalt Pavements

“…In addition, it is important to note that, with the emerging concept of smart cities, the mentioned benefits of MAMs would greatly benefit and be used in harmony with already existing smart systems. These other systems include smart sensors (both in the road and on vehicles and traffic signals), artificial intelligence (based on machine learning), image processing, big data and computer vision, to develop better traffic management systems and manage the road network in real time [61][62][63][64][65][66] (Figure 7).…”