As a novel concept, "Informed Design" is proposed in a multidisciplinary project "Livable Places" in Singapore to innovate place design from empirical to evidential by harnessing geo-referenced "Big Data" for a responsive design. As a final delivery, an Informed Design Platform (IDP) is being implemented as a design support tool interpreting multi-source big data to adaptive urban designs for a more livable place. Due to the complexity in "Objects", which include physical devices and virtual services to generate space related data, "Data", which are massive and heterogenous to be interlinked and analyzed for valuable insights, and "Services", which integrate back-end and front-end service modules for innovative services, IDP collaborates them through dedicated mechanisms proposed by a Smart Service Orchestration Architecture (SSOA) to achieve a high scalability in data collection, integration, analysis, and visualization. In this paper, the overall design and currently available services of IDP are presented.
Future flow prediction in spatiotemporal traffic data is a critical requirement for real-world applications, particularly for multi-feature and large-scale data with intricate forecasting mechanisms and varied predictability. Prior sequence-to-sequence studies have demonstrated the superiority of attention learning in prediction tasks by effectively capturing reliable dependencies/correlations. However, despite the promising results, the single-feature input pattern of traffic prediction causes an information utilization bottleneck. In this paper, we focus on discovering the cause-effect relationship of traffic dynamics by fusing the origin-destination (OD) flow. To achieve both high accuracy and universality, we design a scalable composition architecture—a Multi-Feature Hybrid Network (MFHN)—based on the existing framework of spatiotemporal feature modeling. In particular, we break with the preprocessing convention of feature composition and propose a Hybrid-Correlation mechanism by integrating similar subseries of the OD flow. Furthermore, inspired by graph learning, we introduce the mobility pattern based on the OD flow, which reveals the node-to-node dependencies. In the experiment, we consider various prediction tasks with state-of-the-art baseline models and find that the MFHN yields competitive accuracy in short- and long-term prediction.
Abstract Advancements in information and communication technologies (ICT) and the advent of novel mobility solutions have brought about drastic changes in the urban mobility environment. Pervasive ICT devices acquire new sources of data that can inform detailed transportation simulation models, and are useful in analyzing new policies and technologies. In this context, we developed software laboratories that leverage the latest technological developments and enhance freight research. Future mobility sensing (FMS) is a data-collection platform that integrates tracking devices and mobile apps, a backend with machine-learning technologies and user interfaces to deliver highly accurate and detailed mobility data. The second platform, SimMobility, is an open-source, agent-based urban simulation platform which replicates urban passenger and goods movements in a fully disaggregated manner. The two platforms have been used jointly to advance the state of the art in behavioral modeling for passenger and goods movements. In this chapter, we review recent developments in freight-transportation data-collection techniques, including contributions to transportation modeling, and state-of-the-art transportation models. We then introduce FMS and SimMobility and demonstrate a coordinated application using three examples. Lastly, we highlight potential innovations and future challenges in these research domains.
Neuroticism, a personality trait linked to emotional instability and negative emotions, is associated with increased anxiety, depression, and poor mental health outcomes, particularly in individuals with psychiatric disorders. However, existing neuroticism scales often have too many items, are not tailored for psychiatric populations, and lack cultural adaptation for Chinese contexts. We aimed to develop a brief neuroticism scale with adequate reliability and validity for the Chinese population, including individuals with psychiatric disorders. The 14-item scale was developed based on the five-factor model and Eysenck’s personality theory. The scale, in the form of a questionnaire, was distributed to college students from Southeast University and patients from the Affiliated Zhongda Hospital of Southeast University. A total of 554 participants were recruited, and demographic information, the neurotic subscale of the Neuroticism Extraversion Openness Five-Factor Inventory (NEO-FFI), Patient Health Questionnaire (PHQ-9), and generalized anxiety disorder (GAD-7) were collected along with the neuroticism scale. Correlation analysis, Cronbach’s alpha, exploratory factor analysis (EFA), and confirmatory factor analysis (CFA) were conducted to test and revise the scale. EFA indicated that the neuroticism scale consisted of four factors: Low self-esteem, excessive emotional sensitivity, unstable mood, and excessive worry. The Cronbach’s alpha was 0.926. CFA suggested a good fit of the scale structure (χ2/df =2.506, root mean square error of approximation =0.039, Tucker–Lewis index =0.947, comparative fit index =0.959, and standardized root mean square residual =0.032). The total scores of the neuroticism scale were positively related to those of PHQ-9, GAD-7, and NEO-FFI. The results indicate that the neuroticism scale exhibited a stable four-dimensional structure with good reliability and validity in the Chinese population. It is useful and time-saving for assessing neuroticism in individuals with psychiatric disorders.
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.
Measurement techniques often result in domain gaps among batches of cellular data from a specific modality. The effectiveness of cross-batch annotation methods is influenced by inductive bias, which refers to a set of assumptions that describe the behavior of model predictions. Different annotation methods possess distinct inductive biases, leading to varying degrees of generalizability and interpretability. Given that certain cell types exhibit unique functional patterns, we hypothesize that the inductive biases of cell annotation methods should align with these biological patterns to produce meaningful predictions. In this study, we propose KIDA, Knowledge-based Inductive bias and Domain Adaptation. The knowledge-based inductive bias constrains the prediction rules learned from the reference dataset, composed of multiple batches, to functional patterns relevant to biology, thereby enhancing the generalization of the model to unseen batches. Since the query dataset also contains gaps from multiple batches, KIDA's domain adaptation employs pseudo labels for self-knowledge distillation, effectively narrowing the distribution gap between model predictions and the query dataset. Benchmark experiments demonstrate that KIDA is capable of achieving accurate cross-batch cell type annotation. Knowledge-based inductive bias and domain adaptation can enhance the cell type annotation accuracy of deep learning models.
Driver distraction detection (3D) is essential in improving the efficiency and safety of transportation systems. Considering the requirements for user privacy and the phenomenon of data growth in real-world scenarios, existing methods are insufficient to address four emerging challenges, i.e., data accumulation, communication optimization, data heterogeneity, and device heterogeneity. This paper presents an incremental and cost-efficient mechanism based on federated meta-learning, called ICMFed, to support the tasks of 3D by addressing the four challenges. In particular, it designs a temporal factor associated with local training batches to stabilize the local model training, introduces gradient filters of each model layer to optimize the client–server interaction, implements a normalized weight vector to enhance the global model aggregation process, and supports rapid personalization for each user by adapting the learned global meta-model. According to the evaluation made based on the standard dataset, ICMFed can outperform three baselines in training two common models (i.e., DenseNet and EfficientNet) with average accuracy improved by about 141.42%, training time saved by about 54.80%, communication cost reduced by about 54.94%, and service quality improved by about 96.86%.
Future flow prediction in spatiotemporal traffic data is a critical requirement for real-world applications, particularly for multi-feature and large-scale data with intricate forecasting mechanisms and varied predictability. Prior sequence-to-sequence studies have demonstrated the superiority of attention learning in prediction tasks by effectively capturing reliable dependencies/correlations. However, despite the promising results, the single-feature input pattern of traffic prediction causes an information utilization bottleneck. In this paper, we focus on discovering the cause-effect relationship of traffic dynamics by fusing the origin-destination (OD) flow. To achieve both high accuracy and universality, we design a scalable composition architecture—a Multi-Feature Hybrid Network (MFHN)—based on the existing framework of spatiotemporal feature modeling. In particular, we break with the preprocessing convention of feature composition and propose a Hybrid-Correlation mechanism by integrating similar subseries of the OD flow. Furthermore, inspired by graph learning, we introduce the mobility pattern based on the OD flow, which reveals the node-to-node dependencies. In the experiment, we consider various prediction tasks with state-of-the-art baseline models and find that the MFHN yields competitive accuracy in short- and long-term prediction.
Multivariate time series anomaly detection (MTAD) plays a vital role in a wide variety of real-world application domains. Over the past few years, MTAD has attracted rapidly increasing attention from both academia and industry. Many deep learning and graph learning models have been developed for effective anomaly detection in multivariate time series data, which enable advanced applications such as smart surveillance and risk management with unprecedented capabilities. Nevertheless, MTAD is facing critical challenges deriving from the dependencies among sensors and variables, which often change over time. To address this issue, we propose a coupled attention-based neural network framework (CAN) for anomaly detection in multivariate time series data featuring dynamic variable relationships. We combine adaptive graph learning methods with graph attention to generate a global-local graph that can represent both global correlations and dynamic local correlations among sensors. To capture inter-sensor relationships and temporal dependencies, a convolutional neural network based on the global-local graph is integrated with a temporal self-attention module to construct a coupled attention module. In addition, we develop a multilevel encoder-decoder architecture that accommodates reconstruction and prediction tasks to better characterize multivariate time series data. Extensive experiments on real-world datasets have been conducted to evaluate the performance of the proposed CAN approach, and the results show that CAN significantly outperforms state-of-the-art baselines.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)
