arXiv subjects

Mingming Liu

Publications and source records attributed to Mingming Liu.

At least 37 records · Page 2Linked to original sources

arXiv2024

Optimal Design and Implementation of an Open-source Emulation Platform for User-Centric Shared E-mobility Services

With the rising concern over transportation emissions and pollution on a global scale, shared electric mobility services like E-cars, E-bikes, and E-scooters have emerged as promising solutions to mitigate these pressing challenges. However, existing shared E-mobility services exhibit critical design deficiencies, including insufficient service integration, imprecise energy consumption forecasting, limited scalability and geographical coverage, and a notable absence of a user-centric perspective, particularly in the context of multi-modal transportation. More importantly, there is no consolidated open-source platform which could benefit the E-mobility research community. This paper aims to bridge this gap by providing an open-source platform for shared E-mobility. The proposed platform, with an agent-in-the-loop approach and modular architecture, is tailored to diverse user preferences and offers enhanced customization. We demonstrate the viability of this platform by providing a comprehensive analysis for integrated multi-modal route-optimization in diverse scenarios of energy availability, user preferences and E-mobility tools placement for which we use modified Ant Colony Optimization algorithm so called Multi-Model Energy Constrained ACO (MMEC-ACO) and Q-Learning algorithms. Our findings demonstrate that Q-learning achieves significantly better performance in terms of travel time cost for more than 90\% of the instances as compared to MMEC-ACO for different scenarios including energy availability, user preference and E-mobility tools distribution. For a fixed (O, D) pair, the average execution time to achieve optimal time cost solution for MMEC-ACO is less than 2 seconds, while Q-learning reaches an optimal time cost in 20 seconds on average. For a run-time of 2 seconds, Q-learning still achieves a better optimal time cost with a 20\% reduction over MMEC-ACO's time cost.

cs.AI↗

arXiv2023

Privacy-Aware Energy Consumption Modeling of Connected Battery Electric Vehicles using Federated Learning

Battery Electric Vehicles (BEVs) are increasingly significant in modern cities due to their potential to reduce air pollution. Precise and real-time estimation of energy consumption for them is imperative for effective itinerary planning and optimizing vehicle systems, which can reduce driving range anxiety and decrease energy costs. As public awareness of data privacy increases, adopting approaches that safeguard data privacy in the context of BEV energy consumption modeling is crucial. Federated Learning (FL) is a promising solution mitigating the risk of exposing sensitive information to third parties by allowing local data to remain on devices and only sharing model updates with a central server. Our work investigates the potential of using FL methods, such as FedAvg, and FedPer, to improve BEV energy consumption prediction while maintaining user privacy. We conducted experiments using data from 10 BEVs under simulated real-world driving conditions. Our results demonstrate that the FedAvg-LSTM model achieved a reduction of up to 67.84\% in the MAE value of the prediction results. Furthermore, we explored various real-world scenarios and discussed how FL methods can be employed in those cases. Our findings show that FL methods can effectively improve the performance of BEV energy consumption prediction while maintaining user privacy.

cs.LG↗

arXiv2023

A Review on AI Algorithms for Energy Management in E-Mobility Services

E-mobility, or electric mobility, has emerged as a pivotal solution to address pressing environmental and sustainability concerns in the transportation sector. The depletion of fossil fuels, escalating greenhouse gas emissions, and the imperative to combat climate change underscore the significance of transitioning to electric vehicles (EVs). This paper seeks to explore the potential of artificial intelligence (AI) in addressing various challenges related to effective energy management in e-mobility systems (EMS). These challenges encompass critical factors such as range anxiety, charge rate optimization, and the longevity of energy storage in EVs. By analyzing existing literature, we delve into the role that AI can play in tackling these challenges and enabling efficient energy management in EMS. Our objectives are twofold: to provide an overview of the current state-of-the-art in this research domain and propose effective avenues for future investigations. Through this analysis, we aim to contribute to the advancement of sustainable and efficient e-mobility solutions, shaping a greener and more sustainable future for transportation.

cs.LG↗

arXiv2023

Recent Advances in Graph-based Machine Learning for Applications in Smart Urban Transportation Systems

The Intelligent Transportation System (ITS) is an important part of modern transportation infrastructure, employing a combination of communication technology, information processing and control systems to manage transportation networks. This integration of various components such as roads, vehicles, and communication systems, is expected to improve efficiency and safety by providing better information, services, and coordination of transportation modes. In recent years, graph-based machine learning has become an increasingly important research focus in the field of ITS aiming at the development of complex, data-driven solutions to address various ITS-related challenges. This chapter presents background information on the key technical challenges for ITS design, along with a review of research methods ranging from classic statistical approaches to modern machine learning and deep learning-based approaches. Specifically, we provide an in-depth review of graph-based machine learning methods, including basic concepts of graphs, graph data representation, graph neural network architectures and their relation to ITS applications. Additionally, two case studies of graph-based ITS applications proposed in our recent work are presented in detail to demonstrate the potential of graph-based machine learning in the ITS domain.

cs.LG↗

arXiv2022

Classical Sequence Match is a Competitive Few-Shot One-Class Learner

Nowadays, transformer-based models gradually become the default choice for artificial intelligence pioneers. The models also show superiority even in the few-shot scenarios. In this paper, we revisit the classical methods and propose a new few-shot alternative. Specifically, we investigate the few-shot one-class problem, which actually takes a known sample as a reference to detect whether an unknown instance belongs to the same class. This problem can be studied from the perspective of sequence match. It is shown that with meta-learning, the classical sequence match method, i.e. Compare-Aggregate, significantly outperforms transformer ones. The classical approach requires much less training cost. Furthermore, we perform an empirical comparison between two kinds of sequence match approaches under simple fine-tuning and meta-learning. Meta-learning causes the transformer models' features to have high-correlation dimensions. The reason is closely related to the number of layers and heads of transformer models. Experimental codes and data are available at https://github.com/hmt2014/FewOne

cs.LG↗

arXiv2022

Graph-PHPA: Graph-based Proactive Horizontal Pod Autoscaling for Microservices using LSTM-GNN

Microservice-based architecture has become prevalent for cloud-native applications. With an increasing number of applications being deployed on cloud platforms every day leveraging this architecture, more research efforts are required to understand how different strategies can be applied to effectively manage various cloud resources at scale. A large body of research has deployed automatic resource allocation algorithms using reactive and proactive autoscaling policies. However, there is still a gap in the efficiency of current algorithms in capturing the important features of microservices from their architecture and deployment environment, for example, lack of consideration of graphical dependency. To address this challenge, we propose Graph-PHPA, a graph-based proactive horizontal pod autoscaling strategy for allocating cloud resources to microservices leveraging long short-term memory (LSTM) and graph neural network (GNN) based prediction methods. We evaluate the performance of Graph-PHPA using the Bookinfo microservices deployed in a dedicated testing environment with real-time workloads generated based on realistic datasets. We demonstrate the efficacy of Graph-PHPA by comparing it with the rule-based resource allocation scheme in Kubernetes as our baseline. Extensive experiments have been implemented and our results illustrate the superiority of our proposed approach in resource savings over the reactive rule-based baseline algorithm in different testing scenarios.

cs.DC↗

arXiv2022

Playback-centric visualisations of video usage using weighted interactions to guide where to watch in an educational context

The increase in use of online educational tools has led to a large amount of educational video materials made available for students. Finding the right video content is usually supported by the overarching learning management system and its interface that organises video items by course, categories and weeks, and makes them searchable. However, once a video is found, students are left without further guidance as to what parts in that video they should focus on. In this article, an additional timeline visualisation to augment the conventional playback timeline is introduced which employs a novel playback weighting strategy in which the history of different video interactions generate scores based on the context of each playback. The resultant scores are presented on the additional timeline, making it in effect a playback-centric usage graph nuanced by how each playback was executed. Students can selectively watch those portions which the contour of the usage visualisation suggests. The visualisation was implemented and deployed in an undergraduate course at a university for two full semesters. 270 students used the system throughout both semesters watching 52 videos, guided by visualisations on what to watch. Analysis of playback logs revealed students selectively watched corresponding to the most important portions of the videos as assessed by the instructor who created the videos. The characteristics of this as a way of guiding students as to where to watch as well as a complementary tool for playback analysis, are discussed. Further insights into the potential values of this visualisation and its underlying playback weighting strategy are also discussed.

cs.MM↗

arXiv2022

Lane-GNN: Integrating GNN for Predicting Drivers' Lane Change Intention

Nowadays, intelligent highway traffic network is playing an important role in modern transportation infrastructures. A variable speed limit (VSL) system can be facilitated in the highway traffic network to provide useful and dynamic speed limit information for drivers to travel with enhanced safety. Such system is usually designed with a steady advisory speed in mind so that traffic can move smoothly when drivers follow the speed, rather than speeding up whenever there is a gap and slowing down at congestion. However, little attention has been given to the research of vehicles' behaviours when drivers left the road network governed by a VSL system, which may largely involve unexpected acceleration, deceleration and frequent lane changes, resulting in chaos for the subsequent highway road users. In this paper, we focus on the detection of traffic flow anomaly due to drivers' lane change intention on the highway traffic networks after a VSL system. More specifically, we apply graph modelling on the traffic flow data generated by a popular mobility simulator, SUMO, at road segment levels. We then evaluate the performance of lane changing detection using the proposed Lane-GNN scheme, an attention temporal graph convolutional neural network, and compare its performance with a temporal convolutional neural network (TCNN) as our baseline. Our experimental results show that the proposed Lane-GNN can detect drivers' lane change intention within 90 seconds with an accuracy of 99.42% under certain assumptions. Finally, some interpretation methods are applied to the trained models with a view to further illustrate our findings.

cs.LG↗

arXiv2022

Analysis of Individual Conversational Volatility in Tandem Telecollaboration for Second Language Learning

Second language learning can be enabled by tandem collaboration where students are grouped into video conference calls while learning the native language of other student(s) on the calls. This places students in an online environment where the more outgoing can actively contribute and engage in dialogue while those more shy and unsure of their second language skills can sit back and coast through the calls. We have built and deployed the L2L system which records timings of conversational utterances from all participants in a call. We generate visualisations including participation rates and timelines for each student in each call and present these on a dashboard. We have recently developed a measure called personal conversational volatility for how dynamic has been each student's contribution to the dialogue in each call. We present an analysis of conversational volatility measures for a sample of 19 individual English-speaking students from our University who are learning Frenchm, in each of 86 tandem telecollaboration calls over one teaching semester. Our analysis shows there is a need to look into the nature of the interactions and see if the choices of discussion topics assigned to them were too difficult for some students and that may have influenced their engagement in some way.

cs.CL↗

arXiv2022

A Comparative Study on Energy Consumption Models for Drones

Creating an appropriate energy consumption prediction model is becoming an important topic for drone-related research in the literature. However, a general consensus on the energy consumption model is yet to be reached at present. As a result, there are many variations that attempt to create models that range in complexity with a focus on different aspects. In this paper, we benchmark the five most popular energy consumption models for drones derived from their physical behaviours and point to the difficulties in matching with a realistic energy dataset collected from a delivery drone in flight under different testing conditions. Moreover, we propose a novel data-driven energy model using the Long Short-Term Memory (LSTM) based deep learning architecture and the accuracy is compared based on the dataset. Our experimental results have shown that the LSTM based approach can easily outperform other mathematical models for the dataset under study. Finally, sensitivity analysis has been carried out in order to interpret the model.

cs.RO↗

arXiv2022

An Analysis of Conversational Volatility During Telecollaboration Sessions for Second Language Learning

Tandem telecollaboration is a pedagogy used in second language learning where mixed groups of students meet online in videoconferencing sessions to practice their conversational skills in their target language. We have built and deployed a system called L2 Learning to support post-session review and self-reflection on students participation in such meetings. We automatically compute a metric called Conversational Volatility which quantifies the amount of interaction among participants, indicating how dynamic or flat the conversations were. Our analysis on more than 100 hours of video recordings involving 28 of our students indicates that conversations do not get more dynamic as meetings progress, that there is a wide variety of levels of interaction across students and student groups, and the speaking in French appears to have more animated conversations than speaking in English, though the reasons for that are not clear.

cs.HC↗

arXiv2022

Parking Behaviour Analysis of Shared E-Bike Users Based on a Real-World Dataset -- A Case Study in Dublin, Ireland

In recent years, an increasing number of shared E-bikes have been rolling out rapidly in our cities. It therefore becomes important to understand new behaviour patterns of the cyclists in using these E-bikes as a foundation for the novel design of shared micromobility services as part of the realisation for next generation intelligent transportation systems. In this paper, we deeply investigate the users' behaviour of shared E-bikes in a case study by using the real-world dataset collected from the shared E-bike company, MOBY, which currently operates in Dublin, Ireland. More specifically, we look into the parking behaviours of users as we know that inappropriate parking of these bikes can not only increase the management costs of the company but also result in other users' inconveniences, especially in situations of battery shortage, which inevitably reduces the overall operational efficacy of these shared E-bikes. Our work has conducted analysis at both bike station and individual level in a fully anonymous and GDPR-Compliant manner, and our results have shown that up to 12.9% of shared E-bike users did not park their bikes properly at the designated stands. Different visualisation tools have been applied to better illustrate our obtained results.

physics.soc-ph↗

arXiv2021

A fusion learning method to subgroup analysis of Alzheimer's disease

Uncovering the heterogeneity in the disease progression of Alzheimer's is a key factor to disease understanding and treatment development, so that interventions can be tailored to target the subgroups that will benefit most from the treatment, which is an important goal of precision medicine. However, in practice, one top methodological challenge hindering the heterogeneity investigation is that the true subgroup membership of each individual is often unknown. In this article, we aim to identify latent subgroups of individuals who share a common disorder progress over time, to predict latent subgroup memberships, and to estimate and infer the heterogeneous trajectories among the subgroups. To achieve these goals, we apply a concave fusion learning method proposed in Ma and Huang (2017) and Ma et al. (2019) to conduct subgroup analysis for longitudinal trajectories of the Alzheimer's disease data. The heterogeneous trajectories are represented by subject-specific unknown functions which are approximated by B-splines. The concave fusion method can simultaneously estimate the spline coefficients and merge them together for the subjects belonging to the same subgroup to automatically identify subgroups and recover the heterogeneous trajectories. The resulting estimator of the disease trajectory of each subgroup is supported by an asymptotic distribution. It provides a sound theoretical basis for further conducting statistical inference in subgroup analysis..

stat.ME↗

arXiv2021

Development of a Cesium Fountain Clock at HUST: Preliminary Results

A cesium atomic fountain clock is under development at Huazhong University of Science and Technology (HUST) in China. In this paper, we describe the construction of the entire fountain clock system and report the preliminary results. A frequency stability of $2.5\times 10^{-13} τ^{-1/2}$ has been achieved by inter-comparison with a hydrogen maser, and the factors limiting the frequency stability are also discussed.

physics.atom-ph↗

arXiv2021

Fed-BEV: A Federated Learning Framework for Modelling Energy Consumption of Battery Electric Vehicles

Recently, there has been an increasing interest in the roll-out of electric vehicles (EVs) in the global automotive market. Compared to conventional internal combustion engine vehicles (ICEVs), EVs can not only help users reduce monetary costs in their daily commuting, but also can effectively help mitigate the increasing level of traffic emissions produced in cities. Among many others, battery electric vehicles (BEVs) exclusively use chemical energy stored in their battery packs for propulsion. Hence, it becomes important to understand how much energy can be consumed by such vehicles in various traffic scenarios towards effective energy management. To address this challenge, we propose a novel framework in this paper by leveraging the federated learning approaches for modelling energy consumption for BEVs (Fed-BEV). More specifically, a group of BEVs involved in the Fed-BEV framework can learn from each other to jointly enhance their energy consumption model. We present the design of the proposed system architecture and implementation details in a co-simulation environment. Finally, comparative studies and simulation results are discussed to illustrate the efficacy of our proposed framework for accurate energy modelling of BEVs.

cs.LG↗

arXiv2021

A Comparative Study of Using Spatial-Temporal Graph Convolutional Networks for Predicting Availability in Bike Sharing Schemes

Accurately forecasting transportation demand is crucial for efficient urban traffic guidance, control and management. One solution to enhance the level of prediction accuracy is to leverage graph convolutional networks (GCN), a neural network based modelling approach with the ability to process data contained in graph based structures. As a powerful extension of GCN, a spatial-temporal graph convolutional network (ST-GCN) aims to capture the relationship of data contained in the graphical nodes across both spatial and temporal dimensions, which presents a novel deep learning paradigm for the analysis of complex time-series data that also involves spatial information as present in transportation use cases. In this paper, we present an Attention-based ST-GCN (AST-GCN) for predicting the number of available bikes in bike-sharing systems in cities, where the attention-based mechanism is introduced to further improve the performance of an ST-GCN. Furthermore, we also discuss the impacts of different modelling methods of adjacency matrices on the proposed architecture. Our experimental results are presented using two real-world datasets, Dublinbikes and NYC-Citi Bike, to illustrate the efficacy of our proposed model which outperforms the majority of existing approaches.

cs.LG↗

arXiv2021

Usage-based Summaries of Learning Videos

Much of the delivery of University education is now by synchronous or asynchronous video. For students, one of the challenges is managing the sheer volume of such video material as video presentations of taught material are difficult to abbreviate and summarise because they do not have highlights which stand out. Apart from video bookmarks there are no tools available to determine which parts of video content should be replayed at revision time or just before examinations. We have developed and deployed a digital library for managing video learning material which has many dozens of hours of short-form video content from a range of taught courses for hundreds of students at undergraduate level. Through a web browser we allow students to access and play these videos and we log their anonymised playback usage. From these logs we score to each segment of each video based on the amount of playback it receives from across all students, whether the segment has been re-wound and re-played in the same student session, whether the on-screen window is the window in focus on the student's desktop/laptop, and speed of playback. We also incorporate negative scoring if a video segment is skipped or fast-forward, and overarching all this we include a decay function based on recency of playback, so the most recent days of playback contribute more to the video segment scores. For each video in the library we present a usage-based graph which allows students to see which parts of each video attract the most playback from their peers, which helps them select material at revision time. Usage of the system is fully anonymised and GDPR-compliant.

cs.MM↗

arXiv2021

Highly Efficient Ultrathin Light Emitting Diodes based on Perovskite Nanocrystals

Light-emitting diodes based on perovskite nanocrystals (PNCs-LEDs) have gained great interest for next-generation display and lighting technologies prized for their color purity, high brightness and luminous efficiency approaching the intrinsic limit imposed by extraction of electroluminescence from the device structure. Although the time is ripe for the development of effective light outcoupling strategies to further boost the device performance, this technologically relevant aspect of PNC-LEDs is still without a definitive solution. Here, following theoretical guidelines and without the integration of complex photonic structures, we realize stable PNC-LEDs with EQE as high as 29.2% (average EQE=24.7%), which substantially break the outcoupling limit of common PNC-LEDs and systematically surpass any previous perovskite-based device. Key to such unprecedented performance is channeling the recombination zone in PNC emissive layers as thin as 10 nm, which we achieve by finely balancing the electron and hole transport using CsPbBr3 PNCs resurfaced with a nickel oxide layer. The ultra-thin approach general and, in principle, applicable to other perovskite nanostructures for fabricating highly efficient, color tunable transparent LEDs ideal for unobtrusive screens and displays and is compatible with the integration of photonic components for further enhanced performance.

physics.optics↗