Protein-protein interaction (PPI) and their interaction sites [PPI site (PPIS)] hold immense potential for elucidating cellular mechanisms and advancing targeted drug development. While deep learning has driven progress in PPI research by capturing protein features, it remains limited by its overreliance on sequence information and inability to effectively integrate protein internal structural features. To address these challenges, we propose MEGAE, a novel model capable of achieving high-precision prediction of PPI and PPIS. MEGAE reconstructs amino acid microenvironments through a vector quantization autoencoder, integrating physicochemical properties, structural details, and sequence data to provide a comprehensive representation of proteins. We innovatively introduce a multiview random masking training strategy, introducing controlled randomness during the reconstruction process to enhance the robustness of microenvironment embeddings. The model combines these fused embeddings with protein graphs and protein interaction networks, leveraging graph neural networks (GNNs) to capture multilevel relationships from local amino acid interactions to global signal network connections-thereby achieving precise predictions. Experimental results demonstrate that MEGAE outperforms state-of-the-art sequence- and structure-based methods across multiple datasets, exhibiting higher accuracy in predicting interaction types and interaction sites. This advancement underscores the potential of microenvironment-aware modeling in uncovering complex protein interactions.

As a novel distributed learning paradigm, federated learning (FL) allows clients to train global models collaboratively without exchanging private data. However, recent research not only demonstrates the vulnerability of FL against privacy attacks where adversaries try to recover private data by intercepting local gradients/models but also its inadequacy in defending against poisoning attacks launched by malicious adversaries, who modify local datasets to disrupt the global training process. Even though many solutions have been proposed to defend against these attacks, there is still a gap in mitigating the risks in more complex nonindependent and identically distributed (Non-IID) scenarios that are prevalent in Internet of Things (IoT) systems. To fill this gap, this article proposes a data poisoning resistible and privacy protection FL mechanism (DPR-PPFL) for ubiquitous IoT. Based on representational similarity analysis, DPR-PPFL allows clients to construct asymmetric local models in defending against data inversion attacks, and also the server to detect and aggregate benign local models uploaded by the clients to correctly train the global model in the face of data poisoning attacks. By comparing the performance of DPR-PPFL with state-of-the-art baselines, its merits in securing the learning process under IID and Non-IID scenes of IoT are demonstrated.

Federated Learning (FL) offers a privacy-preserving and cost-efficient paradigm to collaboratively train a global model without exposing local data of clients in IoT. However, since client data remain decentralized, it makes the learning vulnerable to malicious behaviors, such as data poisoning attacks, through which, updates can be manipulated to corrupt the global model and damage the overall IoT system. To address such a security threat, gradient similarity-based methods have been proposed to remedy the impact of data poisoning in securing FL, mainly under independent and identically distributed (IID) scenarios. Since heterogeneous Non-IID data are widely distributed in IoT systems, and direct aggregation on local models is more native for FL to update the global model, it becomes challenging for current solutions to distinguish whether models are learned from clients with poisoned or imbalanced data samples. Therefore, this paper proposes FedCon, a model consistency-based mechanism to secure the FL process. It leverages the consistency of local models to identify benign models for global model aggregation. Experimental results demonstrate that FedCon can outperform state-of-the-art methods in defending against data poisoning attacks under both IID and Non-IID scenarios to not only boost model accuracy but also reduce attack success rate.

Electric vehicles (EVs) are driving green and low-carbon transport in modern cities. It makes charging station occupancy prediction (CSOP) critual for intelligent transportation systems (ITS) to achieve a balance between the supply and demand in resolving the dynamics between EVs and changing stations. Even though several Big Data-based solutions have been discussed, they are still struggling to collaboratively utilize heterogeneous data and distributed computing resources located at both physically and logicially isolated charging stations to better support context-driven CSOP. To addres this challenge, we propose an Asynchronous Federated Meta-learning Mechanism (AFML) for CSOP, which can train a meta-model with strong adaptation ability in an asynchronous and collaborative manner. In general, it incorporates an adaptive reptile algorithm (AR) and an weighted aggregation strategy (WA) to jointly ensure the training efficiency and model adaptivity. Evaluations on real-world CSOP datasets demonstrate that compared to the second best method, AFML can significantly improve forecasting accuracy by 14%, accelerate model convergence by 9% and enhance model generalizability by 10%, illustrating its merits in support CSOP to embrace a smart and sustainable city.

A data-secure and cost-efficient Personalized Travel Recommendation (PTR) is necessary to develop urban intelligence in transportation. Although prevalent machine learning-based methods have gained tremendous progress on PTR, Mixed Logit Model (MXL), as a mathematical method, is attracting much attention from industry and academia to analyze refined individual behavior for PTR. Since MXL is still in its infancy in PTR, it encounters three challenges that need to be resolved jointly, namely 1) how to use personal data to describe user preferences without violating user privacy, 2) how to utilize the idle computing resources at the edge to improve the estimation efficiency, and 3) how to coordinate devices whose capability and availability may change over time and space. To fill the gap, we propose an asynchronous and privacy-preserving mixed logit model (APMXL), which aims to integrate MXL with asynchronous federated learning (AFL), which can 1) non-intrusively exchange model parameters between the clients and the server without exposing the raw data, 2) separately perform local and global estimation at the client and server to optimize the load, and 3) collaboratively approximate the posterior of the standard MXL through a continuous asynchronous interaction mechanism. Moreover, based on a standard dataset, APMXL is evaluated, showing that the model accuracy is about 13% higher compared to a flat logit model. Meanwhile, the estimation time has been reduced by about 60% compared to a centralized MXL model, and the robustness of the model has been improved compared with the synchronous and privacy-preserving mixed logit model (SPMXL).

The effective reasoning of integrated multimodal perception information is crucial for achieving enhanced end-to-end autonomous driving performance. In this paper, we introduce a novel multitask imitation learning framework for end-to-end autonomous driving that leverages a dual attention transformer (DualAT) to enhance the multimodal fusion and waypoint prediction processes. A self-attention mechanism captures global context information and models the long-term temporal dependencies of waypoints for multiple time steps. On the other hand, a cross-attention mechanism implicitly associates the latent feature representations derived from different modalities through a learnable geometrically linked positional embedding. Specifically, the DualAT excels at processing and fusing information from multiple camera views and LiDAR sensors, enabling comprehensive scene understanding for multitask learning. Furthermore, the DualAT introduces a novel waypoint prediction architecture that combines the temporal relationships between waypoints with the spatial features extracted from sensor inputs. We evaluate our approach on both the Town05 and Longest6 benchmarks using the closed-loop CARLA urban driving simulator and provide extensive ablation studies. The experimental results demonstrate that our approach significantly outperforms the state-of-the-art methods.

Recent booming successes of electric vehicles (EVs) motivate emerging exploration of spatio-temporal EV charging demand forecasting to inform policy making. Recent studies have contributed to remarkable accuracy improvement by developing deep learning methods. However, when they access massive amounts of data and frequently exchange data through the Internet of Things (IoT), data silos and inefficient training emerge as main challenges. To tackle these challenges, this study proposes an integrated approach for regional EV charging demand forecasting, named FMGCN, which consists of two modules, namely 1) Spatio-temporal Learning module, which introduces spatial and temporal attentions to capture the underlying charging patterns between different regions and cities effectively; and 2) Distributed Pretraining module, which incorporates Federated Learning and Meta-Learning to enhance the adaptivity and generalisability of the forecasting model. A comprehensive evaluation based on a real-world dataset of 25,246 public EV charging piles shows that the proposed model outperforms other representative models with 1) an average improvement of 29.9% in forecasting errors; 2) an acceleration of 65% in convergence speed; and 3) a sound adaptability to support varying charging demand.

Along with the vast application of Internet of Things (IoT) and the ever-growing concerns about data protection, a novel type of learning, named incremental federated learning (IFL), is rising to further elevate the intelligence and quality of various IoT systems and services by consistently learning and updating their models, e.g., deep neural networks, in dynamic contexts, where clients and data can increase and accumulate gradually. Since IFL is still in its infancy, to overcome its emerging challenges as represented in 1) periodic learning about how to initialize the model update rationally to avoid catastrophic performance dropping, and 2) iterative learning about how to update the model cost-efficiently to remedy overlearning on duplicated information, this paper proposes a stage-based and layer-wise mechanism for IFL, called SLMFed, in which, the periodic learning is managed by a stage transition and client selection strategy to trigger model update according to the quantitative and qualitative changes on clients, data, and user experience, and the iterative learning is enhanced by an adaptive layer uploading and aggregation strategy to update the global model by measuring representational consistencies and information richness of local model layers. As shown by the evaluation results, SLMFed can not only stabilize the learning across various learning stages but also boost the performance in terms of learning accuracy, communication cost, and stage contribution by about 32.09%, 105.94%, and 22.02%, respectively.

Domain knowledge is gradually renovating its attributes to exhibit distinct features in autonomy, propelled by the shift of modern transportation systems (TS) toward autonomous TS (ATS) comprising three progressive generations. The knowledge graph (KG) and its corresponding versions can help depict the evolving TS. Given that KG versions exhibit asymmetry primarily due to variations in evolved knowledge, it is imperative to harmonize the evolved knowledge embodied by the entity across disparate KG versions. Hence, this article proposes a siamese-based graph convolutional network (GCN) model, namely SiG , to address unresolved issues of low accuracy, efficiency, and effectiveness in aligning asymmetric KGs. SiG can optimize entity alignment in ATS and support the analysis of future-stage ATS development. Such a goal is attained through (a) generating unified KGs to enhance data quality, (b) defining graph split to facilitate entire-graph computation, (c) enhancing a GCN to extract intrinsic features, and (d) designing a siamese network to train asymmetric KGs. The evaluation results suggest that SiG surpasses other commonly employed models, resulting in average improvements of 23.90% and 37.89% in accuracy and efficiency, respectively. These findings have significant implications for TS evolution analysis and offer a novel perspective for research on complex systems limited by continuously updated knowledge.

Driver Distraction Detection (3D) is of great significance in helping intelligent vehicles decide whether to remind drivers or take over the driving task and avoid traffic accidents. However, the current centralized learning paradigm of 3D has become unpractical because of rising limitations on data sharing and increasing concerns about user privacy. In this context, 3D is further facing three emerging challenges, namely data islands, data heterogeneity, and the straggler issue. To jointly address these three issues and make the 3D model training and deployment more practical and efficient, this paper proposes an Asynchronous Federated Meta-learning framework called AFM3D. Specifically, AFM3D bridges data islands through Federated Learning (FL), a novel distributed learning paradigm that enables multiple clients (i.e., private vehicles with individual data of drivers) to learn a global model collaboratively without data exchange. Moreover, AFM3D further utilizes meta-learning to tackle data heterogeneity by training a meta-model that can adapt to new driver data quickly with satisfactory performance. Finally, AFM3D is designed to operate in an asynchronous mode to reduce delays caused by stragglers and achieve efficient learning. A temporally weighted aggregation strategy is also designed to handle stale models commonly encountered in the asynchronous mode and in turn, optimize the aggregation direction. Extensive experiment results show that AFM3D can boost performance in terms of model accuracy, recall, F1 score, test loss, and learning speed by 7.61%, 7.44%, 7.95%, 9.95%, and 50.91%, respectively, against five state-of-the-art methods.

Along with the proliferation of electric vehicles (EVs), optimizing the use of EV charging space can significantly alleviate the growing load on intelligent transportation systems. As the foundation to achieve such an optimization, a spatiotemporal method for EV charging demand prediction in urban areas is required. Although several solutions have been proposed by using data-driven deep learning methods, it can be that these performance-oriented approaches may struggle to correctly understand the underlying factors influencing charging demand, particularly charging prices. A representative case that highlights the challenge faced by existing methods is their potential misinterpretation of high prices during peak times, leading to an incorrect assumption that higher prices correspond to increased demand. To address the challenges associated with training an accurate and reliable prediction model for EV charging demand, this paper proposes a novel approach called PAG, which leverages the integration of graph and temporal attention mechanisms for effective feature extraction and introduces physics-informed meta-learning in the pre-training step to facilitate prior knowledge learning. Evaluation results on a dataset of 18,061 EV charging piles in Shenzhen, China, show that the proposed approach can achieve state-of-the-art forecasting performance and the ability to understand the adaptive changes in charging demands caused by price fluctuations.

With the growing concerns on data security and user privacy, a decentralized mechanism is implemented for federated data mining (FDM), which can bridge data silos and collaborate diverse devices in ubiquitous IoT (Internet of Things) systems and services to extract global and shareable knowledge, i.e., encoded in deep neural networks (DDNs). Moreover, compared with FDM in synchronous mode, asynchronous FDM (AFDM) is more suitable to accommodate devices with diversified computing resources and distinguishable working statuses. However, as AFDM is still in its infancy, how to harness heterogeneous resources and biased knowledge of learning participants within the asynchronous context remains to be addressed. Such that, this paper proposes an adaptive and integrated mechanism, named AiFed, in which, a layer-wise optimization of AFDM is implemented based on the integration of two dedicated strategies, i.e., an adaptive local model uploading strategy (ALMU), and an adaptive global model aggregation strategy (AGMA). As shown by the evaluation results, AiFed can outperform five state-of-the-art methods to reduce communication costs by about 61.76% and 56.88%, improve learning accuracy by about 1.66% and 3.05%, and accelerate learning speed by about 22.16% and 37.81% under IID (independent and identically distributed) and Non-IID settings of four standard datasets, respectively.

As a novel learning paradigm, Federated learning (FL) aims at protecting privacy by avoiding raw data shifting between distributed clients and central servers. However, recent researches demonstrate the vulnerability of FL against gradient-based privacy attacks, in which, gradients intercepted by malicious adversaries may result in data leakage. Current defense methods suffer from performance drops, low privacy guarantees, and high communication costs. Motivated by this, we propose FedRSM, a Representational-Similarity-Based Secured Model Uploading for Federated Learning. FedRSM splits Deep Neural Networks (DNNs) into layers, calculates Representational Dissimilarity Vector (RDV), measures the similarity between local RDV and global RDV of each model layer, and constructs secured local model to be uploaded based on Representational Consistency Alteration (RCA). According to the evaluation result, FedRSM can improve testing accuracy by up to 2%, significantly reduce communication costs, and avoid data leakage under different model complexities.

In a city, the usage optimization of parking spaces with a near real-time response to car drivers can significantly reduce the unnecessary cruising for parking and the additional congestion of regional traffic. As the foundation to achieve such an optimization, a parking occupancy prediction method is required to address the emerging challenges of training a simple but effective model. To fill the gap, this paper proposes a novel approach that enables the integration of Time Series Decomposition (TSD), Gated Recurrent Unit (GRU), and First-order Model-agnostic Meta-learning (FOMAML) for feature engineering, model building, and model pre-training, respectively. Moreover, as shown by a detailed evaluation, such an integration strengthens the proposed approach, named Meta TSD-GRU, which outperforms other state-of-the-art methods with 1) prediction errors reduced by about 45% on average, 2) the speed of model adaptation and convergence improved about 2 and 102 times against the methods with and without pre-training, respectively, and 3) the generalizability of the model enhanced to handle various time intervals of forecasting and types of parking lots under a consistent and stable performance.

Through the vast adoption and application of emerging technologies, the intelligence and autonomy of smart mobility can be substantially elevated to address more diversified demands and supplies. Along with this trend, a systematic collaboration among three essential elements of smart mobility services, namely devices, data and functions, is being studied to comprehensively break down the intrinsic barriers that existed in current solutions, to support the integration of connectable devices, the fusion of heterogeneous data, the composability of reusable functions, and the flexibility in their cooperations. To enable such a collaboration, this paper proposes a federated platform, called Future Mobility Sensing Advisor (FMSA), which can 1) manage the three elements through standardized interfaces separately and uniformly; 2) create a fully connected knowledge graph to orchestrate the three elements efficiently and effectively; 3) support the client-server interaction in centralized and federated modes to handle service requests and edge resources with various availability and accessibilities jointly and adaptively; and 4) accommodate various mobility services to foster harmonious and sustainable mobility tenderly and invisibly. Moreover, the efficiency and effectiveness of the platform are also tested through a performance evaluation, and a pilot supported at the Great Boston Area, respectively. As a result, it shows that FMSA can 1) achieve high performance by using the two interaction modes selectively, and 2) renovate smart mobility towards sustainability through personalized services that can measure user preferences and system objectives mutually.

Federated learning (FL) is a novel decentralized machine learning mechanism, which bridges data silos to train a global model by utilizing data and computation power of local clients in a privacy-preserving way. Moreover, to handle heterogeneous data across domains, tasks and partities, federated meta-learning (FML) has been proposed, which leverages the fast adaptation of meta-learning for transferable and customizable models. Nevertheless, most of the existing studies focus on providing personalized models for different users, leaving other important issues not well solved, especially, incentive mechanisms, which are used as a common foundation for FML to attrack and maintain high-quality and reputable clients. To fill the gap, this paper proposes a learning-based incentive mechanism for FML to motivate local clients to participate in the data federation. First, we propose to reward clients according to the amount of data they contribute to the model training. Then, to analyze the behaviors of model owner and local clients, we formulate the incentivized training task as a Stackelberg game, and design a method based on reinforcement learning (RL) to learn optimal pricing and participating strategies for the task publisher and the local clients, respectively. Lastly, extensive experiments are conducted to demonstrate the efficiency and effectiveness of the proposed RL-based incentive mechanism, which assists multiple parties to reach the equilibrium of the game designed for FML.

Federated Learning in asynchronous mode (AFL) is attracting much attention from both industry and academia to build intelligent cores for various Internet of Things (IoT) systems and services by harnessing sensitive data and idle computing resources dispersed at massive IoT devices in a privacy-preserving and interaction-unblocking manner. Since AFL is still in its infancy, it encounters three challenges that need to be resolved jointly, namely: 1) how to rationally utilize AFL clients, whose local data grow gradually, to avoid overlearning issues; 2) how to properly manage the client-server interaction with both communication cost reduced and model performance improved; and finally, 3) how to effectively and efficiently aggregate heterogeneous parameters received at the server to build a global model. To fill the gap, this article proposes a triple-step asynchronous federated learning mechanism (TrisaFed), which can: 1) activate clients with rich information according to an informative client activating strategy (ICA); 2) optimize the client–server interaction by a multiphase layer updating strategy (MLU); and 3) enhance the model aggregation function by a temporal weight fading strategy (TWF), and an informative weight enhancing strategy (IWE). Moreover, based on four standard data sets, TrisaFed is evaluated. As shown by the result, compared with four state-of-the-art baselines, TrisaFed can not only dramatically reduce the communication cost by over 80% but also can significantly improve the learning performance in terms of model accuracy and training speed by over 8% and 70%, respectively.

Recent advancements in information and communication technologies have led to the ubiquitous use of mobile sensing devices, such as smartphones and vehicle trackers, to obtain high-resolution movement data of commercial vehicles during the conduct of freight studies. Using a digital data collection platform known as the Future Mobility Sensing (FMS) platform, an ongoing commercial vehicle survey was conducted to collect the stop activity and movement information of heavy goods vehicles operating within Singapore. However, despite the successful recruitment of 1,662 drivers who verified their stop activities as part of the survey, a majority of the stops recorded are left unverified with the verified stops showing a significant imbalance between the different activity types reported. Therefore, the objective of the paper is to develop an activity prediction model using the temporal, sequential, contextual, and environmental features collected through the FMS platform, as well as point-of-interest information from Open Street Map. The proposed model was developed based on a gradient boosting approach and supplemented with different data resampling techniques to address the issue of class imbalance. By integrating the proposed model into the FMS platform, the activity-related fields of the survey can be pre-populated to reduce respondent burden and improve the completion rates of future surveys. The activity prediction model can also be used to recover the activity information from the unverified stops collected through the FMS platform, leading to an increased understanding of the movement and parking behaviours of commercial vehicles operating within Singapore.

In studies of human mobility, there is a need for a holistic system for collection of sensing data, management of data flows, fusion of multiple data sources, and visualization of integrated data to better understand travel behavior. We have designed and implemented a generic Future Mobility Sensing (FMS) system to serve these purposes. FMS harnesses various sensing technologies, heterogeneous multi-source data and analytical functionalities with three dedicated platforms, namely 1) the FMS Data Collection Platform, which intertwines sensing objects, machine learning algorithms and user verifications to collect high resolution, multi-day travel data; 2) the FMS Data Management Platform, which provides standardized APIs to access data stored in an interconnected data model; and 3) the FMS Data Fusion and Visualization Platform, which consolidates multi-source data to be interpreted and presented. Together, the three platforms form a mobility sensing flow to facilitate data-driven analysis and decision-making. With FMS, heterogeneous multi-source data are suitably integrated for analysis, and multi-dimensional knowledge is extracted and presented in intuitive and interactive analytical dashboards. The system is intended to be generic to support different requirements of mobility studies, such as travel surveys, as its function modules are reusable and can be customized to support a unified data collection, management, fusion and visualization process. This paper introduces the overall architecture of the FMS system and summarizes various applications that it can support. Specifically, we present a study of commercial vehicle parking in Singapore to demonstrate the capability of the system.

Smart cities (SCs), as a novel solution built on top of large-scale Internet of Things (IoT) systems, experiences a rapid growth worldwide, in which, a synergetic orchestration among objects, data, and services is emphasized for innovative solutions to elevate the intelligence of cities based on the fusion of multisource and multimodal data. To enable such orchestration, this article proposes a smart service orchestration architecture (SSOA) to coordinate ubiquitous objects, create interlinked data, and implement versatile smart services. As a proof of concept of SSOA, an informed design platform (IDP) is presented to demonstrate how a smart service system can be designed and how a synergetic orchestration can be implemented to support an informed place design. Moreover, two dedicated mechanisms, namely, place utilization analysis mechanism (PUAM) and ensemble-based activity detection mechanism (EADM), are implemented in a multisource data processing flow to illustrate how massive geo-referenced data can be analyzed effectively and efficiently by machine learning algorithms to extract key information for a comprehensive data fusion required in using multimodal IoT systems. As evaluated, PUAM running in a distributed environment can dramatically improve the performance of geospatial clustering about 11 times from the baseline 53.6 to 4.7 s, and EADM with an ensemble activity classifier achieves the highest accuracy about 87.7% and also the highest f-score per activity category. Finally, various insights about the project testbed Jurong East, Singapore, are discussed to reveal its place design context.

The intelligence of Smart Cities (SC) is represented by its ability in collecting, managing, integrating, analyzing, and mining multi-source data for valuable insights. In order to harness multi-source data for an informed place design, this paper presents “Public Sentiments and Activities in Places” multi-source data analysis flow (PSAP) in an Informed Design Platform (IDP). In terms of key contributions, PSAP implements 1) an Interconnected Data Model (IDM) to manage multi-source data independently and integrally, 2) an efficient and effective data mining mechanism based on multi-dimension and multi-measure queries (MMQs), and 3) concurrent data processing cascades with Sentiments in Places Analysis Mechanism (SPAM) and Activities in Places Analysis Mechanism (APAM), to fuse social network data with other data on public sentiment and activity comprehensively. As proved by a holistic evaluation, both SPAM and APAM outperform compared methods. Specifically, SPAM improves its classification accuracy gradually and significantly from 72.37 to about 85 percent within nine crowd-calibration cycles, and APAM with an ensemble classifier achieves the highest precision of 92.13 percent, which is approximately 13 percent higher than the second best method. Finally, by applying MMQs on “Sentiment&Activity Linked Data”, various place design insights of our testbed are mined to improve its livability.

With the explosion of social networks, people more often share their opinions on-line, which provides a great opportunity to detect the public sentiment of a place in an automatic and timely way comparing to the conventional approaches, e.g., surveys, workshops and interviews. Even through the application of social sentiment analysis is widely discussed in many domains, e.g., politics, e-commerce, economy, and health and environment, to the best of our knowledge, no research has ever studied the effects of public sentiments of social networks in the domain of place design. In order to fill this vacancy, a sentiment analysis service, called geo-sentiment analysis service, is required, whose cores are 1) a social sentiment analysis engine, and 2) an intuitive and interactive visualization service. Thus, this paper firstly proposes CGSA: a Crowd-calibrated Geo-Sentiment Analysis mechanism, which can 1) start the sentiment analysis process based on the design of CTS (Compound Training Samples), and SSF (Social Sentiment Features), 2) perform three analyses, namely sentiment, clustering and time series analysis on geotagged social network messages, and 3) collect crowd-labelled data based on a crowdsourced calibration service to gradually improve the classification accuracy. As proved by two detailed analyses, SSF has the best accuracy in training sentiment classifiers, and the performance of the calibrated classifier increases gradually and significantly from 74.71% to 80.05% in three calibration cycles. Moreover, as a part of a big project “Liveable Places”, “Sentiment in places” service with two visualization modes, namely 2D sentiment dashboard and 3D sentiment map, is implemented to support local authorities, urban designers and city planners better understand the effects of public sentiments regarding place (re)design in the testbed area: Jurong East, Singapore.

As a novel concept, "Informed Design" is being practiced in the Future Cities Laboratory at the Singapore-ETH Centre to innovate place design from empirical to evidential by harnessing geo-referenced "Big Data" for a responsive design. Initially, potentials of people sensing data derived from multi-sources, such as social networks, dedicated applications, sensors, etc., shall be explored to measure place utilization for a better understanding of design contexts and elicitation of design requirements. Therefore, an "Activities in Places" service is required to detect frequently used places, called hot places (HPs), and measure their utilizations in various dimensions. In order to fulfill emerging requirements and properly handle big and heterogeneous geo-located data in a near-real time manner for a responsive design, a unsupervised method, called Scalable "Activities in Places" Analysis Mechanism (SAPAM), is proposed with two main analysis mechanisms, namely 1) a scalable density-based spatial clustering of applications with noise (SDBSCAN), which dramatically improves the performance of DBSCAN through concurrent clusterings on data partitions, 2) a hot place detection procedure (HPDP) to extract HPs from clusters based on a continuous place usage pattern (CPUP), and analyze performed activities through a topic model trained by a corpus of daily documents of places. As proved by a comprehensive evaluation, 1) SDBSCAN, indeed, greatly improves the performance as shown by its best performance 4.71s, which is 11 times faster than DBSCAN, 2) HPDP can precisely detect HPs with a high recall of Singaporean regional centers, main transportation hubs and famous attractions, and 3) the utilization of HPs can be unveiled by three indicators, namely the number of visitors, the size of influence area, and the density of people, and also by performed activities in HPs. As a case study, three top 10 HP lists of three utilization indexes are created, and performed activities in a regional center Jurong East are analyzed.

People sensing data have been successfully utilized in various domains to support a more livable place with on-demand transport system, green environment, profitable economy and interactive governance, however, their potentials in supporting the design of places are not widely studied and explained. As an on-going multidisciplinary project in Singapore, “Livable Places” mins valuable insights from these data through a novel mechanism, called Scalable “Activities in Places” Analysis Mechanism (SAPAM), which conducts three kinds of analyses on their spatial, temporal and textual information respectively to reveal frequently used places, called Hot Places (HP), and to measure their utilization quantitively and qualitatively for a better understanding of design contexts. Accordingly, three analysis mechanisms are designed and implemented, namely 1) a Scalable sPace Clustering Mechanism (SPCM) based on spatial information to cluster geo-referenced data, 2) a Hot Place Detection Mechanism (HPDM) based on temporal information to detect frequently used places, and 3) a Discussing Topic Detection Mechanism (DTDM) based on textual information to explore people's activities in a place. As proved by a comprehensive evaluation, 1) SPCM, which implements a scalable version of DBSCAN, indeed, can dramatically improve the clustering performance from the baseline 53.57s to less than 5s; 2) HPDM can precisely detect HPs with a high recall of Singaporean regional centers, main transportation hubs and famous attractions; and 3) DTDM classifies discussing topics of a given HP with a high precision about 85%. As the project testbed, Jurong East is detailedly investigated, and comparing to other Singaporean regional centers, it is marked as a growing regional center with a prosperous and stable commercial ecosystem.

Crowdsourcing implies user collaboration and engagement, which fosters a renewal of city governance processes. In this article, we address a subset of crowdsourcing, named citizen-sourcing, where citizens interact with authorities collaboratively and actively. Many systems have experimented citizen-sourcing in city governance processes; however, their maturity levels are mixed. In order to focus on the service maturity, we introduce a city service maturity framework that contains five levels of service support and two levels of information integration. As an example, we introduce CITY FEED, which implements citizen-sourcing in city issue management process. In order to support such process, CITY FEED supports all levels of the maturity framework (publishing, transacting, interacting, collaborating, and evaluating) and integrates related information relationally and heterogeneously. In order to integrate heterogeneous information, it implements a threefold feed deduplication mechanism based on the geographic, text semantic, and image similarities of feeds. Currently, CITY FEED is in a pilot stage.

Crowdsourcing is a valuable social sensing for the smarter city. We present an approach for classifying crowd sourced feeds from a threefold point of view, namely image, text, and geography. The main idea is to extract feeds within a specific geographic range, and then analyze similarity of image color and text semantic. The approach enables to identify feeds that report the same issue, hence filtering redundant information. Based on proved methods and algorithms, such approach has been implemented in a software application, called CITY FEED, that is used by the Municipality of Pavia.

The key issue in cloud computing in enterprises is the management of the Quality of Service (QoS), by an appropriate SLM (Service Level Management). Cloud Service Provider are offering SLMs to their users. We think that a third party SLM can be a better way to assure a robust and equal SLM. This paper presents the elements of third party SLM, namely Cloud Service Registration Agent, Negotiation Agent, Compensation Agent, Comment Agent, Billing Agent and Service Monitoring Engine. Such framework has been tested in a real life case. Results show that third party SLM is not only equal, but also dependable and reasonably easy to implement.