Search

In recent years, the rapid growth of vehicles has imposed a significant burden on urban road resources. To alleviate urban traffic congestion in intelligent transportation systems (ITS), real-time and accurate traffic flow prediction has emerged as an effective approach. However, selecting relevant parameters from traffic flow information and adjusting hyperparameters in intelligent algorithms to achieve high prediction accuracy is a time-consuming process, posing practical challenges in dynamically changing traffic conditions. To address these challenges, this paper introduces a novel prediction architecture called Multiple Variables Heuristic Selection Long Short-Term Memory (MVHS-LSTM). The key innovation lies in its ability to select informative parameters, eliminating unnecessary factors to reduce computational costs while achieving a balance between prediction performance and computing efficiency. The MVHS-LSTM model employs the Ordinary Least Squares (OLS) method to intelligently reduce factors and optimize cost efficiency. Additionally, it dynamically selects hyperparameters through a heuristic iteration process involving epoch, learning rate, and window length, ensuring adaptability and improved accuracy. Extensive simulations were conducted using real traffic flow data from Shanghai to evaluate the enhanced performance of MVHS-LSTM. The prediction results were compared with those of the ARIMA, SVM, and PSO-LSTM models, demonstrating the innovative capabilities and advantages of the proposed model. [ABSTRACT FROM AUTHOR]

Recent advances in knowledge graphs show great promise to link various data together to provide a semantic network. Place is an important part in the big picture of the knowledge graph since it serves as a powerful glue to link any data to its georeference. A key technical challenge in constructing knowledge graphs with location nodes as geographical references is the matching of place entities. Traditional methods typically rely on rule-based matching or machine-learning techniques to determine if two place names refer to the same location. However, these approaches are often limited in the feature selection of places for matching criteria, resulting in imbalanced consideration of spatial and semantic features. Deep feature-based methods such as deep learning methods show great promise for improved place data conflation. This paper introduces a Semantic-Spatial Aware Representation Learning Model (SSARLM) for Place Matching. SSARLM liberates the tedious manual feature extraction step inherent in traditional methods, enabling an end-to-end place entity matching pipeline. Furthermore, we introduce an embedding fusion module designed for the unified encoding of semantic and spatial information. In the experiment, we evaluate the approach to named places from Guangzhou and Shanghai cities in GeoNames, OpenStreetMap (OSM), and Baidu Map. The SSARLM is compared with several classical and commonly used binary classification machine learning models, and the state-of-the-art large language model, GPT-4. The results demonstrate the benefit of pre-trained models in data conflation of named places. [ABSTRACT FROM AUTHOR]

Building change detection (BCD) plays a vital role in city planning and development, ensuring the timely detection of urban changes near metro lines. Synthetic Aperture Radar (SAR) has the advantage of providing continuous image time series with all-weather and all-time capabilities for earth observation compared with optical remote sensors. Deep learning algorithms have extensively been applied for BCD to realize the automatic detection of building changes. However, existing deep learning-based BCD methods with SAR images suffer limited accuracy due to the speckle noise effect and insufficient feature extraction. In this paper, an attention-guided dual-branch fusion network (ADF-Net) is proposed for urban BCD to address this limitation. Specifically, high-resolution SAR images collected by TerraSAR-X have been utilized to detect building changes near metro line 8 in Shanghai with the ADF-Net model. In particular, a dual-branch structure is employed in ADF-Net to extract heterogeneous features from radiometrically calibrated TerraSAR-X images and log ratio images (i.e., difference images (DIs) in dB scale). In addition, the attention-guided cross-layer addition (ACLA) blocks are used to precisely locate the features of changed areas with the transformer-based attention mechanism, and the global attention mechanism with the residual unit (GAM-RU) blocks is introduced to enhance the representation learning capabilities and solve the problems of gradient fading. The effectiveness of ADF-Net is verified using evaluation metrics. The results demonstrate that ADF-Net generates better building change maps than other methods, including U-Net, FC-EF, SNUNet-CD, A2Net, DMINet, USFFCNet, EATDer, and DRPNet. As a result, some building area changes near metro line 8 in Shanghai have been accurately detected by ADF-Net. Furthermore, the prediction results are consistent with the changes derived from high-resolution optical remote sensing images. [ABSTRACT FROM AUTHOR]

The short‐term origin‐destination (OD) forecast in bus rapid transit (BRT) can provide future OD demand, which means that transport plan personnel can take measures in advance, such as adjusting the departure schedule, to avoid congestion. This emphasizes the importance of accurate and stable OD forecasting in real‐time. Deep learning methods have been widely applied due to their superior performance in capturing dynamic spatiotemporal and nonlinear features. However, current methods based on deep learning and data‐driven cannot simultaneously address the problems of data availability and sparsity, and their ability to capture dynamic spatiotemporal patterns is insufficient, which cannot provide satisfactory accuracy and stability. To address these problems, this paper proposes a method for forecasting the OD demand in BRT based on dual attention multi‐scale convolutional network (DAMSCN). Considering the three temporal properties of OD, that is, closeness, period and trend dependencies. DAMSCN uses multi‐scale convolution (MSC), dual attention mechanism (DAt) and stacked convolutional long short‐term memory networks (ConvLSTM) to model the three kinds of properties. The MSC module converts sparse OD information into dense useful features to solve the problem of data sparsity. The DAt and ConvLSTM module model the dependencies relationship in the spatial and temporal dimensions, which can improve the spatiotemporal features extraction ability. DAMSCN also combine inflow information to enhance data availability. The three properties are dynamically aggregated and further integrated with external influences (e.g. weather conditions etc.) to obtain the final forecasting result. The accuracy and stability are evaluated on the Xiamen BRT (XMBRT) and Shanghai Metro datasets (SHMetro). The experimental results show that the DAMSCN is superior to other method. Compared to the best baseline, on the XMBRT, MAE decreased by 8.60%, and RMSE decreased by 4.81%. On the SHMetro, MAE decreased by 7.22%, and RMSE decreased by 8.96%. [ABSTRACT FROM AUTHOR]

As a key component of rail vehicle operation, the running condition of the wheelset significantly affects the operational safety of track vehicles. The wheel diameter, flange thickness, and flange height are key dimensional parameters of the wheelset, which directly influence the correct position of wheelsets on the track, and the train needs to be continuously monitored during the passenger operation. A prediction model for the key parameters of the wheelset is established based on LSTM (long short-term memory) neural network, and real measured data of wheelsets from the Shanghai Metro vehicles are selected. The predicted results of the model are compared and analyzed, and the results show that the LSTM-based prediction model for key parameters of wheelsets performs well, with the mean absolute percentage errors (MAPEs) for wheel diameter, flange thickness, and flange height being 0.08%, 0.42%, and 0.44%, respectively, for the left wheel and 0.07%, 0.35%, and 0.44%, respectively, for the right wheel. The prediction model for the train wheelset parameters established in this paper has a good prediction accuracy. By predicting the key parameters of the wheelset, the faults and causes of the wheelset can be found and determined, which is helpful for engineers to overhaul the wheelset faults, make maintenance plans, and perform preventive maintenance. [ABSTRACT FROM AUTHOR]

The mixed ownership reform aims to improve the property rights structure of the state−owned enterprises (SOEs) and reduce agency costs, and the current mixed reform strategies mainly include equity blending by introducing external non−state capital, executive assignments, and employee stock ownership. In this paper, 953 valid data of A−shares listed in Shanghai and Shenzhen from 2008 to 2020 are used as samples to construct the indicators of mixed reform strategy by the literature statistics method. After obtaining multiple impact indicators, the regression impact model of corporate agency cost suppression strategy is constructed by MATLAB software using a machine learning algorithm. On this basis, the performance of multiple machine learning algorithms is compared, and it is found that the integrated optimization−based bag−boosting model is used to study the effect of hybrid reform strategy to reduce the agency costs of SOEs, and the proportional setting of indicators when the effect is optimal is also explored. Finally, the laws of different influencing factors on the agency costs of enterprises are explored separately by the eigenvalue method. The results of the study show that the proportion of shareholding of the first largest non−state shareholder is sin−functional with the agency costs of SOEs when non−state majority shareholders are introduced into SOEs' equity mix, and the agency costs tend to decrease after SOEs become privately held enterprises. The greater the number and proportion of supervisors appointed by non−state shareholders, the greater the supervisory restraint effect on SOE managers and the better the effect of suppressing agency costs. The participation of non−state−owned shareholders in the company's business decisions by appointed executives and the special resource advantages of SOEs intensify the occurrence of the self−interest of appointed executives and the increase of agency costs of SOEs. The implementation of an employee stock ownership plan plays the role of employee supervision and restraint on SOE managers, which reduces the agency costs of SOEs. Based on this, it can provide support for the government to improve the hybrid reform policy and promote the process layer by layer, and also provide theoretical reference for SOEs to deepen the equity mix, incentivize employee shareholding, and empower non−state shareholders to govern and thus reduce agency costs. [ABSTRACT FROM AUTHOR]

Stock forecasting is difficult because of its complexity and uncertainty. To better predict stock prices and then provide stockholders with reasonable suggestions, this paper proposes an improved time convolution network (TCN) model for predicting stock prices. The model used can make up for some of the shortcomings of the traditional neural network, use the trading data in the stock market, and put the preprocessed data of financial news into the model for training to improve the accuracy of prediction. Using the Shanghai Securities Exchange (SSE) 50 Index (Shanghai Securities Exchange 50 Index selects the most representative 50 stocks with large scale and good liquidity in Shanghai stock market as sample stocks) and news text crawled from financial web pages as samples, predict the direction of the SSE 50 Index's rise and fall. After using different network structure hyperparameters to adjust the model structure, the prediction effect is compared with other models, and it is found that the proposed improved TCN model can effectively improve the effect of predicting the rise and fall of the SSE 50 index, and can complete the model training and predict the stock price faster. [ABSTRACT FROM AUTHOR]

Accurate prediction of urban residential rents is of great importance for landlords, tenants, and investors. However, existing rents prediction models face challenges in meeting practical demands due to their limited perspectives and inadequate prediction performance. The existing individual prediction models often lack satisfactory accuracy, while ensemble learning models that combine multiple individual models to improve prediction results often overlook the impact of spatial heterogeneity on residential rents. To address these issues, this paper proposes a novel prediction model called GERPM, which stands for Geographically Weighted Stacking Ensemble Learning-Based Urban Residential Rents Prediction Model. GERPM comprehensively analyzes the influencing factors of residential rents from multiple perspectives and leverages a geographically weighted stacking ensemble learning approach. The model combines multiple machine learning and deep learning models, optimizes parameters to achieve optimal predictions, and incorporates the geographically weighted regression (GWR) model to consider spatial heterogeneity. By combining the strengths of deep learning and machine learning models and taking into account geographical factors, GERPM aims to improve prediction accuracy and provide robust predictions for urban residential rents. The model is evaluated using housing data from Nanjing, a major city in China, and compared with representative individual prediction models, the equal weight combination model, and the ensemble learning model. The experimental results demonstrate that GERPM outperforms other models in terms of prediction performance. Furthermore, the model's effectiveness and robustness are validated by applying it to other major cities in China, such as Shanghai and Hangzhou. Overall, GERPM shows promising potential in accurately predicting urban residential rents and contributing to the advancement of the rental market. [ABSTRACT FROM AUTHOR]

Sepsis is a life-threatening medical condition that is characterized by the dysregulated immune system response to infections, having both high morbidity and mortality rates. Early prediction of sepsis is critical to the decrease of mortality. This paper presents a novel early warning model called Double Fusion Sepsis Predictor (DFSP) for sepsis onset. DFSP is a double fusion framework that combines the benefits of early and late fusion strategies. First, a hybrid deep learning model that combines both the convolutional and recurrent neural networks to extract deep features is proposed. Second, deep features and handcrafted features, such as clinical scores, are concatenated to build the joint feature representation (early fusion). Third, several tree-based models based on joint feature representation are developed to generate the risk scores of sepsis onset that are combined with an End-to-End neural network for final sepsis detection (late fusion). To evaluate DFSP, a retrospective study was conducted, which included patients admitted to the ICUs of a hospital in Shanghai China. The results demonstrate that the DFSP outperforms state-of-the-art approaches in early sepsis prediction. [ABSTRACT FROM AUTHOR]

Aiming at the problems of crowd distribution, scale feature, and crowd feature extraction difficulties in exhibition centers, this paper proposes a crowd density estimation method using deep learning for passenger flow detection systems in exhibition centers. Firstly, based on the pixel difference symbol feature, the difference amplitude feature and gray feature of the central pixel are extracted to form the CLBP feature to obtain more crowd group description information. Secondly, use the LR activation function to add nonlinear factors to the convolution neural network (CNN) and use dense blocks derived from crowd density estimation to train the LR-CNN crowd density estimation model. Finally, experimental results show that the mean absolute error (MAE) and mean square error (MSE) of the proposed method in the UCF_CC_50 dataset are 325.6 and 369.4, respectively. Besides, MAE and MSE in part_A of the Shanghai Tech dataset are 213.5 and 247.1, respectively, and they in part_B are 85.3 and 99.7, respectively. The proposed method effectively improves the accuracy of crowd density estimation in exhibition centers. [ABSTRACT FROM AUTHOR]

For the earth pressure balance shield, the muck can reflect soil information at the tunnel face to track the change in geologic conditions. Thus, this paper presents a general framework for automatic detection of muck types based on the on‐site surveillance camera using deep learning algorithms. A simplified muck classification method and the corresponding muck recognition criteria are proposed for the muck detection task. The muck detection model (MDM) based on You Only Look Once v4, is established on the muck dataset for Shanghai (MSH) after some optimization treatments. The mean average precision value of 97.73% of MDM is twice that of the original model of 48.47%. The MDM is then applied to Metro Line 14 in Shanghai. Results show that The MDM performs well and meets the real‐time requirements with frames per second of 60, and it outperforms other state‐of‐the‐art detection models both in accuracy and speed. [ABSTRACT FROM AUTHOR]

High-rise building areas (HRBs) provide significant social and environmental services and play a crucial role in modern urbanization. The large-scale and long-term spatial distribution of HRBs is of great interest to many fields, such as urban planning and local climate analysis. While previous studies have confirmed the value of Sentinel-2 images in extracting HRBs and their changes, current work is limited to relatively local areas and short-term analysis. One reason is due to the fact that the earliest Sentinel-2 image can only date back to 2015. To address this research gap, this paper proposes an efficient procedure to intelligently extract HRBs and their changes from multitemporal Landsat-7 and Sentinel-2 images, using a specifically designed fully convolutional network. To validate the proposed method, we selected four typical cities in China, namely, Beijing, Shanghai, Guangzhou, and Zhengzhou, as study areas. We utilized Landsat-7 images acquired in 2000 and 2010, along with Sentinel-2 images acquired in 2020, as experimental data. We extracted and analyzed three periods of HRBs and their changes in the four cities, along with urban rail terminal data and gross domestic product (GDP) data in the same period. The results show that the proposed method can efficiently extract HRBs and their changes in the four cities over the past 20 years, with an overall accuracy of more than 90%. HRBs changes are primarily driven by urban planning policies and geographical factors. There is a strong positive correlation between the increase in HRBs and the increase in rail terminals, both in terms of quantity and spatial distribution. Additionally, there is a positive correlation between HRBs increase and GDP increase in terms of quantity, but the trend varies in different cities due to their diverse developing modes. Overall, the results indicate that the proposed method can be a potential operational tool to extract large-scale and long-term HRBs and their changes in China. [ABSTRACT FROM AUTHOR]

Fast insecurity early warning is the key technique to resist the dynamic insecurity risk, which becomes intractable due to the strong nonlinearity of hybrid AC/DC grids and the high uncertainty of wind generation. Considering dynamic security constraints and wind power uncertainty, this paper presents an insecurity early warning method based on decision tree (DT) and semi-supervised deep learning. First, semi-supervised deep learning is deployed to estimate the dynamic security limit of the critical interface of hybrid AC/DC grids. The system security is assessed by comparing the actual power transfer of the critical interface with the security limit. Then, operating conditions (OCs) are ranked into different insecure levels according to the type of preventive control actions that is needed to ensure the system security. Finally, oblique DT is utilized to identify insecurity classification boundaries in the wind power injection space. Insecure OC sets are constructed based on these classification boundaries. Simulation results of the real-life Jiangsu-Shanghai interconnected grid in east China demonstrate that the proposed method can fast construct the insecure OC sets corresponding to different insecure levels. [ABSTRACT FROM AUTHOR]

IPv6 geolocation is necessary for many location-based Internet services. However, the accuracy of the current IPv6 geolocation methods including machine-learning-based or deep-learning-based location algorithms are unsatisfactory for users. Strong geographic correlation is observed for measurement path features close to the target IP, so previous methods focused more on stable paths in the vicinity of the probe. Based on this, this paper proposes a new IPv6 geolocation algorithm, SubvectorS_Geo, which is mainly divided into three steps: firstly, it filters geographically relevant routing feature codes layer by layer to approximate the fine-grained trusted region of the target; secondly, it extracts delay vectors into the trusted region; thirdly, it evaluates the vector similarity to determine the final target geolocation information. The final experiments show that the median error distance range is 7.025 km to 9.709 km on three real datasets (Shanghai, New York State, and Tokyo). Compared with the advanced method, the median distance error distance is reduced by at least 6.8% and the average error distance is reduced by at least 9.2%. [ABSTRACT FROM AUTHOR]

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs. [ABSTRACT FROM AUTHOR]

With the rapid development of global trade, ports and terminals are playing an increasingly important role, and automatic guided vehicles (AGVs) have been used as the main carriers performing the loading/unloading operations in automated container terminals. In this paper, we investigate a multi-AGV dynamic scheduling problem to improve the terminal operational efficiency, considering the sophisticated complexity and uncertainty involved in the port terminal operation. We propose to model the dynamic scheduling of AGVs as a Markov decision process (MDP) with mixed decision rules. Then, we develop a novel adaptive learning algorithm based on a deep Q-network (DQN) to generate the optimal policy. The proposed algorithm is trained based on data obtained from interactions with a simulation environment that reflects the real-world operation of an automated in Shanghai, China. The simulation studies show that, compared with conventional scheduling methods using a heuristic algorithm, i.e., genetic algorithm (GA) and rule-based scheduling, terminal the proposed approach performs better in terms of effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

Urban functional zones are basic units for human socio-economic activities in cities. Urban functional zones play an important role in a wide range of urban studies, as they are fundamental to urban planning and management, urban resource allocation, as well as urban sustainable development evaluation. However, existing studies of urban functional zone modeling and mapping mainly employ state-of-the-art image segmentation and deep learning classification methods in computer science field to delineate and recognize urban functional zones, but ignore their heterogeneity, integration, multi-scale, and locality characteristics, so that the accuracy of urban functional zone modeling, mapping, and analysis is limited and interpretable, thus cannot comprehensively meet the requirements of downstream applications. This study, however, proposes a geoscene modeling and analysis framework for extracting urban functional zones, which first delineates urban functional zones by multiscale geoscene segmentation, then characterizes them by hierarchical semantic cognition, and finally recognizes their functional categories by linear Dirichlet mixture model. Although this paper does not present the detailed implementations of the geoscene modeling of urban functional zones, it illustrates the importance and the generally strategy of geoscene modeling in urban functional zone mapping and analysis. Additionally, urban functional zone mapping results of Baoshan District, Shanghai, in 2015 and 2020 are presented to verify the effectiveness of the proposed geoscene modeling strategy. [ABSTRACT FROM AUTHOR]

High-precision road detection from very high resolution (VHR) remote sensing images has broad application value. However, the most advanced deep learning based methods often fail to identify roads when there is a distribution discrepancy between the training samples and test samples, due to their limited generalization ability. In this paper, to address this problem, an open-source data-driven domain-specific representation (OSM-DOER) framework is proposed for cross-domain road detection. On the one hand, as the spatial structure information of the source and target domains is similar, but the texture information is different, the domain-specific representation (DOER) framework is proposed, which not only aligns the distributions of the spatial structure information, but also learns the domain-specific texture information. Furthermore, in order to enhance the representation of the target domain data distribution, open-source and freely available OpenStreetMap (OSM) road centerline data are utilized to generate target domain samples, which are then used in the network training as the supervised information for the target domain. Finally, to verify the superiority of the proposed OSM-DOER framework, we conducted extensive experiments with the public SpaceNet and DeepGlobe road datasets, and large-scale road datasets from Birmingham in the UK and Shanghai in China. The experimental results demonstrate that the proposed OSM-DOER framework shows obvious advantages over the mainstream road detection methods, and the use of OSM road centerline data has great potential for the road detection task. [ABSTRACT FROM AUTHOR]

In this paper, the LSTM model is used to predict the PM2.5 concentrations in five representative Chinese cities with the GDP exceeding 1 trillion Yuan, including Beijing, Chengdu, Shanghai, Shenzhen and Wuhan. The PM2.5 concentration data in 2015-2017 are selected for training, and the results are optimized to achieve an efficient solution by adjusting the parameters. Based on the optimized solution, a test is carried out to predict the PM2.5 concentration in 2018, and the results are compared with the real value obtained from the monitoring centre. According to the comparison results, the correlation coefficient of Wuhan and Chengdu is 0.86724 and 0.80070, which are the highest in these five cities. While the correlation coefficient of Shenzhen and Shanghai, are 0.78225, 0.72147, Beijing, as the capital city of China achieved the lowest correlation coefficient which is 0.64118. The LSTM-based predictive model has relatively good reliability and transferability. More effective predictive results can be achieved by implementing deep learning to analyse PM2.5 concentration. [ABSTRACT FROM AUTHOR]

Nowadays, the autonomous driving transportation systems are at the heart of both academic and industry research for the distinguished advantages including increased network capacity, enhanced punctuality, greater flexibility and improved overall safety level. With the responsibility of transporting passengers in a safe, comfortable and efficient way, the decision making method plays a critical position in the autonomous driving of high-speed trains. Focusing on solving the autonomous decision making problem, this paper proposes a novel learning based framework by combining the deep learning technology with the distributed tracking control approach. To cope with the data insufficiency problem in training the deep learning network, a generative adversarial network (GAN) based data argumentation scheme is proposed to generate data samples that have the same distribution with actual data samples, and a hybrid learning network is constructed to predict the speed trajectory from the multi-attribute data with both temporal sequences and static features. Then, based on the model predictive control (MPC) scheme, a distributed tracking control model is formulated to minimize the tracking deviations and balance the performance of punctuality, energy-efficiency and riding comfort. Further, the dual decomposition technique is adopted to deal with the coupling constraints for the safe distance headway such that the separation for the autonomous driving of high-speed trains is achieved. Finally, simulation experiments based on actual scenarios of the Beijing-Shanghai high-speed railway are conducted to illustrate the effectiveness of our methods. [ABSTRACT FROM AUTHOR]

Currently, self-driving, emerging as a key automatic application, has brought a huge potential for the provision of in-vehicle services (e.g., automatic path planning) to mitigate urban traffic congestion and enhance travel safety. To provide high-quality vehicular services with stringent delay constraints, edge computing (EC) enables resource-hungry self-driving vehicles (SDVs) to offload computation-intensive tasks to the edge servers (ESs). In addition, caching highly reusable contents decreases the redundant transmission time and improves the quality of services (QoS) of SDVs, which is envisioned as a supplement to the computation offloading. However, the high mobility and time-varying requests of SDVs make it challenging to provide reliable offloading decisions while guaranteeing the resource utilization of content caching. To this end, in this paper we propose a collaborative computation offloading and content caching method, named CoPace, by leveraging deep reinforcement learning (DRL) in EC for self-driving system. Specifically, we first introduce OSTP to predict the future time-varying content popularity, taking into account the temporal-spatial attributes of requests. Moreover, a DRL-based algorithm is developed to jointly optimize the offloading and caching decisions, as well as the resource allocation (i.e., computing and communication resources) strategies. Extensive experiments with real-world datasets in Shanghai, China, are conducted to evaluate the performance, which demonstrates that CoPace is both effective and well-performed. [ABSTRACT FROM AUTHOR]

This paper proposes a meta-modeling workflow to forecast the cooling and heating loads of buildings at individual and district levels in the early design stage. Seven input variables, with large impacts on building loads, are selected for designing meta-models to establish the MySQL database. The load profiles of office, commercial, and hotel models are simulated with EnergyPlus in batches. A sequence-to-sequence (Seq2Seq) model based on the deep-learning method of a one-dimensional convolutional neural network (1D-CNN) is introduced to achieve rapid forecasting of all-year hourly building loads. The method performs well with the load effective hour rate (LEHR) of around 90% and MAPE less than 10%. Finally, this meta-modeling workflow is applied to a district as a case study in Shanghai, China. The forecasting results well match the actual loads with R2 of 0.9978 and 0.9975, respectively, for the heating and cooling load. The LEHR value of all-year hourly forecasting loads is 98.4%, as well as an MAPE of 4.4%. This meta-modeling workflow expands the applicability of building-physics-based methods and improves the time resolution of conventional data-driven methods. It shows small forecasting errors and fast computing speed while meeting the required precision and convenience of engineering in the building early design stage. [ABSTRACT FROM AUTHOR]

This paper aims to explore the status quo and basic laws of entrepreneurship education at the stage of social development in China, thereby providing a theoretical basis and practical guidance for the cultivation of innovative and entrepreneurial talents in colleges. First, a college entrepreneurship education model based on lean entrepreneurship theory and flipped classroom was established to provide the development of entrepreneurship education with a theoretical framework while improving the students' autonomous learning ability. Based on the theoretical basis of the influence of the locus of control on entrepreneurial motivation in the entrepreneurial process of college students, the students who participated in the basic education of entrepreneurship among the sophomores in the first semester of the 2018–2019 academic year of a college in Shanghai were selected as the research object. Then, the effect of lean entrepreneurship education under the flipped classroom mode was analyzed. Before the start of the entrepreneurial basic education course, there was no difference between the pretest scores of the research group and the control group students (P > 0.05). After the course, there was no difference between the posttest scores of the two groups of students (P > 0.05). It can be confirmed that, based on the flipped classroom education mode of halving the actual number of lectures by teachers, the effect of basic education on entrepreneurship for students is not different from the traditional teaching effect. Based on the flipped classroom mode, the number of people who have reached the level of "understanding" of the text target task is the highest, and the number of people who can reach the "comprehensive application" level of the high-order target is almost 0. It means that the realization of the high-order target still needs to be strengthened. Lean entrepreneurship education mode is based on lean iteration, which is conducive to promoting the development of entrepreneurship education in China. Therefore, the application of flipped classroom combined with locus of control analysis in lean entrepreneurship education for college students can ideally achieve the goal of deep learning, which is greatly significant for improving the effectiveness of entrepreneurship education. [ABSTRACT FROM AUTHOR]

• End-to-end single-lead ECG diagnosis with high accuracy and efficiency. • Multi-scale convolutions and hybrid RNNS for multi-angle ECG insights. • Imbalanced clinical datasets: realistic data distribution. • Segmentation and recombination: for large-scale datasets with varying lengths. Arrhythmia is a prevalent cardiovascular disease that can unveil various heart health issues. In recent times, the rise of wearable devices has garnered attention towards the advantages of portable single-lead ECG devices in heart health monitoring. Achieving end-to-end ECG automatic diagnosis through deep learning is essential due to the time-consuming and labour-intensive characteristics of manual diagnosis of ECG records. This paper presents the design of a hybrid residual recurrent convolutional neural network (HRRCNN) for automatically diagnosing single-lead ECG with multiple labels. Firstly, the convolutional layers and residual networks extract the spatial and short-term temporal features. Subsequently, a hybrid recurrent neural network (RNN) comprised of a double-layer bidirectional gated recurrent unit (GRU) and a bidirectional long short-term memory (LSTM) is employed to capture long and short-term temporal features. Finally, an output layer, comprising an attention layer and a fully connected layer, converts the extracted features into classification results. To evaluate the performance of HRRCNN, a dataset from the Shanghai First People's Hospital Affiliated to Shanghai JiaoTong University(Shanghai General Hospital, SGH) is utilized. The experimental results demonstrate that HRRCNN achieves an accuracy of 95.08 %, F1-macro of 87.22 %, Sensitivity of 88.51 %, and a positive prediction rate of 86.13 %. Comparative analysis with existing methods underscores the superior performance of HRRCNN, thereby establishing its potential as an out-of-hospital heart health monitoring tool and an auxiliary tool in clinical settings. [ABSTRACT FROM AUTHOR]

The primary objective of this study is to predict the short-term demand of free-floating bike sharing (FFBS) using deep learning approach. The FFBS trip data in Shanghai city are collected from the Mobike Company. Other datasets such as weather data and air quality data are also collected. The spatiotemporal patterns of FFBS demand indicates that the weekday rides exhibit an obvious commuting pattern while the weekend rides are usually involved with various trip purposes. Then, a hybrid deep learning neural network (HDL-net) is developed to predict the short-term FFBS demand for different time intervals including 15, 20 and 30 min. The proposed HDL-net exhibits better performance on morning peak than the evening peak and non-peak hours for all the three time intervals. Moreover, five benchmark methods are also used to compare with the proposed HDL-net. The results suggest that the proposed hybrid deep learning framework outperform the benchmarks in the prediction performance for all three time intervals. The results of this study could provide insightful suggestions for transportation authorities to develop effective rebalancing strategies and bike lanes planning schemes to promote the service level of cycling in an urban city. [ABSTRACT FROM AUTHOR]

In this paper, we propose a hybrid prediction model based on spatial-temporal data fusion to predict future tunnel traffic. Our approach consists of a local predictor, a global predictor, an outlier predictor, and a prediction integrator. Firstly, the local predictor forecast tunnel traffic based on the collected local data. It is more concerned with the historical and future traffic conditions, that is, the temporal correlation. Then, the global predictor uses data collected from peripheral road segments to predict tunnel volume, which models the spatial correlation based on a deep learning network. Thirdly, the prediction integrator dynamically integrates the prediction results of local and global predictors on the basis of the current weather conditions. In addition, we detect the abnormal traffic volume for training an individual outlier predictor. Finally, we integrate it with the output of the prediction integrator and accumulate the current tunnel traffic volume to calculate final prediction results. In our experiments, we collected the multisource urban-awareness data from Shanghai to evaluate the proposed hybrid prediction model. Our approach is obviously superior to the baseline when dealing with the general condition. The MREs of 30 min and 60 min tunnel traffic volume prediction are less than 6.5%. In addition, the outlier predictor of the proposed model significantly enhances the ability to predict the abnormal tunnel traffic under extreme weather conditions or unexpected traffic accidents. [ABSTRACT FROM AUTHOR]

Time series prediction has been widely applied to the finance industry in applications such as stock market price and commodity price forecasting. Machine learning methods have been widely used in financial time series prediction in recent years. How to label financial time series data to determine the prediction accuracy of machine learning models and subsequently determine final investment returns is a hot topic. Existing labeling methods of financial time series mainly label data by comparing the current data with those of a short time period in the future. However, financial time series data are typically non-linear with obvious short-term randomness. Therefore, these labeling methods have not captured the continuous trend features of financial time series data, leading to a difference between their labeling results and real market trends. In this paper, a new labeling method called "continuous trend labeling" is proposed to address the above problem. In the feature preprocessing stage, this paper proposed a new method that can avoid the problem of look-ahead bias in traditional data standardization or normalization processes. Then, a detailed logical explanation was given, the definition of continuous trend labeling was proposed and also an automatic labeling algorithm was given to extract the continuous trend features of financial time series data. Experiments on the Shanghai Composite Index and Shenzhen Component Index and some stocks of China showed that our labeling method is a much better state-of-the-art labeling method in terms of classification accuracy and some other classification evaluation metrics. The results of the paper also proved that deep learning models such as LSTM and GRU are more suitable for dealing with the prediction of financial time series data. [ABSTRACT FROM AUTHOR]

Forecasting urban metro flow accurately plays an important role for station management and passenger safety. Owing to the limitations of non-linearity and complexity of traffic flow data, traditional methods cannot satisfy the requirements of effectively capturing spatiotemporal dependencies at the metro network level, which makes it difficult to demonstrate high performance. In this paper, a novel deep learning method is proposed based on Graph Neural Networks (GNN), named STGCN-Metro (SpatioTemporal Graph Convolutional Network based on Metro network), to forecast the short-term inflow and outflow volumes of metro passengers. The proposed model is composed of two spatiotemporal convolutional blocks, which is integrated with the Dilated Convolutional Neural Network (DCNN) and Cluster-Graph Convolutional Network (Cluster-GCN). The DCNN is employed with different dilation rates to capture temporal dependence in larger receptive field. In addition, compare with GCN, the Cluster-GCN is applied the graph clustering algorithms to reduce computational resources considering spatial heterogeneity. A real-world dataset collected in Shanghai metro stations is conducted for validation, and the results demonstrate that the proposed model achieves higher performance, outperforming some well-known baseline models. [ABSTRACT FROM AUTHOR]

Accurate subway passenger flow prediction is crucial to operation management and line scheduling. It can also promote the construction of intelligent transportation systems (ITS). Due to the complex spatial features and time-varying traffic patterns of subway networks, the prediction task is still challenging. Thus, a hybrid neural network model, GCTN (graph convolutional and comprehensive temporal neural network), is proposed. The model combines the Transformer network and long short-term memory (LSTM) network to capture the global and local temporal dependency. Besides, it uses a graph convolutional network (GCN) to capture the spatial features of the subway network. For the sake of the stability and accuracy for long-term passenger flow prediction, we enhance the influence of the station itself and the global station and combine the convolutional neural networks (CNN) and Transformer. The model is verified by the passenger flow data of the Shanghai Subway. Compared with some typical data-driven methods, the results show that the proposed model improves the prediction accuracy in different time intervals and exhibits superiority in prediction stability and robustness. Besides, the model has a better performance in the peak value and the period when passenger flow changes quickly. [ABSTRACT FROM AUTHOR]

Understanding solar radiation in urban street spaces is crucial for comprehending residents' environmental experiences and enhancing their quality of life. However, existing studies rarely focus on the patterns of urban street solar radiation over time and across different urban and suburban areas. In this study, street view images from the summers of 2013 and 2019 in Shanghai were used to calculate solar radiation in urban street spaces. The results show a general decrease in street solar radiation in 2019 compared to 2013, with an average drop of 12.34%. The decrease was most significant in October (13.47%) and least in May (11.71%). In terms of solar radiation data gathered from street view sampling points, 76.57% showed a decrease, while 23.43% showed an increase. Spatially, solar radiation decreased by 79.66% for every additional 1.5 km from the city centre. In summary, solar radiation generally shows a decreasing trend, with significant variations between different areas. These findings are vitally important for guiding urban planning, optimising green infrastructure, and enhancing the urban ecological environment, further promoting sustainable urban development and improving residents' quality of life. [ABSTRACT FROM AUTHOR]

Street quality plays a crucial role in promoting urban development. There is still no consensus on how to quantify human street quality perception on a large scale or explore the relationship between street quality and street composition elements. This study investigates a new approach for evaluating and comparing street quality perception and accessibility in Shanghai and Chengdu, two megacities with distinct geographic characteristics, using street-view images, deep learning, and space syntax. The result indicates significant differences in street quality perception between Shanghai and Chengdu. In Chengdu, there is a curvilinear distribution of the highest positive perceptions along the riverfront space and a radioactive spatial distribution of the highest negative perceptions along the ring road and main roads. Shanghai displays a fragmented cross-aggregation and polycentric distribution of the streets with the highest positive and negative perceptions. Thus, it is reasonable to hypothesize that street quality perception closely correlates with the urban planning and construction process of streets. Moreover, we used multiple linear regression to explain the relationship between street quality perception and street elements. The results show that buildings in Shanghai and trees, pavement, and grass in Chengdu were positively associated with positive perceptions. Walls in both Shanghai and Chengdu show a consistent positive correlation with negative perceptions and a consistent negative correlation with other positive perceptions, and are most likely to contribute to the perception of low street quality. Ceilings were positively associated with negative perceptions in Shanghai but are not the major street elements in Chengdu, while the grass is the opposite of the above results. Our research can provide a cost-effective and rapid solution for large-scale, highly detailed urban street quality perception assessments to inform human-scale urban planning. [ABSTRACT FROM AUTHOR]

Numerous efforts have been made to address the section‐level travel speed prediction problem. However, section‐level predictions can hardly be used for fine‐grained applications, such as lane management and lane‐level navigation. The main reason for this is that significant speed heterogeneity exists among the lanes within one section. Thus, this study proposes a three‐dimensional (3D) dual attention convolution‐based deep learning model for predicting the lane‐level travel speed. 3D convolutions are designed to learn high‐dimensional spatiotemporal traffic flow features, that is, the relationships between different sections, lanes, and periods. Dual attention modules are used to focus on the traffic flow propagation patterns and to explain the model's mechanisms. To evaluate the proposed model, an indicator is introduced to assess the spatio‐temporal learning ability, based on targeting the lane‐level case. Evaluation experiments are conducted based on loop detector data in Shanghai, China. The results show that high accuracy is obtained by the proposed model, with a 2.9 km/h mean absolute error, thereby outperforming several existing methods. Finally, an in‐depth analysis is provided regarding the attention coefficients and interpretation of real‐world lane‐level traffic flow propagation patterns, so as to gain insights into the model's mechanism when capturing dynamic lane‐level traffic flow. [ABSTRACT FROM AUTHOR]

The traditional weighing and selling process of non-barcode items requires manual service, which not only consumes manpower and material resources but is also more prone to errors or omissions of data. This paper proposes an intelligent self-service vending system embedded with a single camera to detect multiple products in real-time performance without any labels, and the system realizes the integration of weighing, identification, and online settlement in the process of non-barcode items. The system includes a self-service vending device and a multi-device data management platform. The flexible configuration of the structure gives the system the possibility of identifying fruits from multiple angles. The height of the system can be adjusted to provide self-service for people of different heights; then, deep learning skill is applied implementing product detection, and real-time multi-object detection technology is utilized in the image-based checkout system. In addition, on the multi-device data management platform, the information docking between embedded devices, WeChat applets, Alipay, and the database platform can be implemented. We conducted experiments to verify the accuracy of the measurement. The experimental results demonstrate that the correlation coefficient R 2 between the measured value of the weight and the actual value is 0.99, and the accuracy of non-barcode item prediction is 93.73%. In Yangpu District, Shanghai, a comprehensive application scenario experiment was also conducted, proving that our system can effectively deal with the challenges of various sales situations. [ABSTRACT FROM AUTHOR]

• Public ecological aesthetic perception basically follows a three-step process (seeing ecological elements—concept perception processing—aesthetic experience). • Ecological and aesthetic perceptions vary in terms of conceptual relevance and processing. • Natural landscape elements are more likely to contribute to positive ecosystem aesthetic perception. • Evaluation models developed using Bayesian networks combined with deep learning and eye-tracking have practical applications. Public perceptions of ecological aesthetics are a crucial component in evaluations of the quality of urban green spaces (UGSs) and in guiding urban planning, design and renewal practices. In this paper, we propose a novel methodological framework that combines deep learning and eye-tracking to investigate the relationships between landscape elements, features, visual focus and public ecosystem aesthetic perceptions of UGSs. Our Public Ecosystem Aesthetic Perceptions (PEAP) model emphasises interactions between ecosystem quality and landscape aesthetic quality. To validate the model, we conducted a study in Shanghai, China, where we selected 54 representative UGSs for photography, perception surveys, and image processing. The results demonstrated that visual focus acts as a mediator between landscape stimuli (landscape elements and features) and perceptions of ecosystem aesthetics. Notably, we found that natural elements elicited significantly stronger visual focus than artificial elements. Thus, our PEAP approach can enhance understanding of aesthetic qualities of landscapes and ecological qualities of urban ecosystems, enabling creation of more aesthetically pleasing and ecologically sustainable UGSs. [ABSTRACT FROM AUTHOR]

It is critical for the management and control of urban rail transit (URT) to be able to predict passenger flow accurately and in real time. Considering that the high-resolution data aggregated by the automatic fare collection (AFC) system is wasted, this paper analyzes the problem of applying a multi-time granularity passenger flow data fusion forecasting process. First, we examine the challenge of constructing a dataset of passenger flow data with different time granularities. Thus, an algorithm is proposed for selecting passenger flow datasets with multi-time granularity. Furthermore, a multi-time granularity dense residual network (Mul-DesLSTM) with a dense residual structure and LSTM (long short-term memory) as the predictor is constructed, inspired by a residual network. Using Mul-DesLSTM, finer-grained passenger flow features can be fused layer by layer while maintaining the accuracy of traditional single-granularity passenger flow predictions. Lastly, Mul-DesLSTM is applied to the URT system of Shanghai, China, and compared with baselines. As a result, the proposed Mul-DesLSTM outperforms the baselines with LSTM as a predictor and state-of-the-art model. When the predicted time granularity is 30 min, compared to the single-time granularity LSTM network, the mean absolute error, root mean square error, and symmetric mean absolute percentage error can be reduced by 51%, 63%, and 15%, respectively. The results can serve as a reference and basis for the operation and management of URT systems. [ABSTRACT FROM AUTHOR]

Building height serves as an essential feature of urban morphology that provides valuable insights into human socio-cultural behaviors and their impact on the environment in an urban milieu. However, openly accessible building height information at the individual building level is still lacking and remains sorely limited. Previous studies have shown that the ICESat-2′s ATL03/08 products are of good accuracy for urban building heights retrieval, however, these studies are limited to areas with available data coverage. To this end, we propose a method for extracting urban building height by using ICESat-2 ATL03 photons and high-resolution remote sensing images. We first extracted the information of building roof to footprint offsets and building shadows from high resolution imagery using multitasking CNN frameworks. Using the building height samples calculated from ICESat-2 ATL03 photons, we developed a building height estimation method that combines building offset and shadow length information. We assessed the efficacy of the proposed method in the Wujiaochang area of Shanghai city, China. The results indicated that the proposed method is able to extract building height with a MAE of 4.7 m, and outperforms the traditional shadow-based and offset-based method. We believe that the proposed method is a good candidate for accurately retrieving building heights on a city-wide scale. [ABSTRACT FROM AUTHOR]

Building façade colors play an important role in influencing urban imageability, attraction and citizens' experience. However, the relations between street functions and the building façade color distribution, color harmony and color diversity have not been thoroughly examined. We obtained the dominant colors of building façades in Changning District, Shanghai, utilizing Baidu street view images, image semantic segmentation technology and the K-means algorithm. The variations in building façades' dominant colors, color harmony and diversity across different types of functional streets were examined through logistic regression and ANOVA analyses. The results indicate that, compared to industrial streets, red hues are more common in science education streets, residential streets and mixed functional streets. Business streets are more likely to have hues of green, red and red–purple. Residential streets' saturation is overall higher than that of industrial streets. In business streets, the medium–high value occurs less frequently than other streets. Moreover, we found that the street building façade colors in industrial streets were more harmonious and less diversified than that in other functional streets. This study has implications for urban color planning practices. Color harmony and color diversity should be well considered in future planning. The role of street functions should also be addressed in building façade color planning, to improve existing planning frameworks as well as related strategies. [ABSTRACT FROM AUTHOR]

Objective: To analyze the cranial computed tomography (CT) imaging features of patients with primary ciliary dyskinesia (PCD) who have exudative otitis media (OME) and sinusitis using a deep learning model for early intervention in PCD. Methods: Thirty-two children with PCD diagnosed at the Children’s Hospital of Fudan University, Shanghai, China, between January 2010 and January 2021 who had undergone cranial CT were retrospectively analyzed. Thirty-two children with OME and sinusitis diagnosed using cranial CT formed the control group. Multiple deep learning neural network training models based on PyTorch were built, and the optimal model was trained and selected to observe the differences between the cranial CT images of patients with PCD and those of general patients and to screen patients with PCD. Results: The Swin-Transformer, ConvNeXt, and GoogLeNet training models had optimal results, with an accuracy of approximately 0.94; VGG11, VGG16, VGG19, ResNet 34, and ResNet 50, which are neural network models with fewer layers, achieved relatively strong results; and Transformer and other neural networks with more layers or neural network models with larger receptive fields exhibited a relatively weak performance. A heat map revealed the differences in the sinus, middle ear mastoid, and fourth ventricle between the patients with PCD and the control group. Transfer learning can improve the modeling effect of neural networks. Conclusion: Deep learning-based CT imaging models can accurately screen for PCD and identify differences between the cranial CT images. [ABSTRACT FROM AUTHOR]

Growing evidence links intra-urban gradients in atmospheric fine particles (PM2.5), a complex and variable cocktail of toxic chemicals, to adverse health outcomes. Here, we propose an improved hierarchical deep learning model framework to estimate the hourly variation of PM2.5 mass concentration at the street level. By using a full-year monitoring data (including meteorological parameters, hourly concentrations of PM2.5, and gaseous precursors) from multiple stations in Shanghai, the largest city in China, as a training dataset, we first apply a convolutional neural network to obtain cross-domain and time-series features so that the inherent features of air quality and meteorological data associated with PM2.5 can be effectively extracted. Next, a Gaussian weight calculation layer is used to determine the potential interaction effects between different regions and neighboring stations. Finally, a long and short-term memory model layer is used to efficiently extract the temporal evolution characteristics of PM2.5 concentrations from the previous output layer. Further comparative analysis reveals that our proposed model framework significantly outperforms previous benchmark methods in terms of the stability and accuracy of PM2.5 prediction, which has important implications for the intra-urban health assessment of PM2.5-related pollution exposures. [ABSTRACT FROM AUTHOR]

The accurate forecasts of carbon prices can help policymakers and enterprises further understand the laws of carbon price fluctuations and formulate related policies and investment strategies. Nowadays, many carbon price prediction models have been proposed. However, some models ignore the time–frequency relationship when considering exogenous variables and fail to measure their importance to the forecasting results, leading to unsatisfactory results. Therefore, this study proposes a novel hybrid model for carbon price forecasting on the basis of advanced multidimensional time series decomposition techniques and interpretable multifactor models. In the proposed model, multivariate fast iterative filtering is used to decompose carbon price and its exogenous variable sequence into several intrinsic mode functions, which can overcome the nonlinearity and nonstationarity of carbon prices and obtain their intrinsic characteristics. Meanwhile, temporal fusion transform (TFT) is used to interpret predictions for multivariate time series. TFT is a new attention‐based deep learning model combining high‐performance multihorizon prediction and interpretability and can adaptively select the optimal features for carbon price prediction. Five carbon markets in Guangdong, Beijing, Shanghai, Hubei, and Shenzhen are selected for experimental studies. Empirical results indicate that the proposed model outperforms the compared benchmark models in all performance metrics. In the interpretable output of TFT, the prediction of the high‐frequency part requires the participation of exogenous variables and has a long time dependence; for the middle and low‐frequency part, only using the carbon price itself and a short time step can lead to good results. This finding can inform future research on carbon price forecasting and help policymakers. [ABSTRACT FROM AUTHOR]

China implemented a strict lockdown policy to prevent the spread of COVID-19 in the worst-affected regions, including Wuhan and Shanghai. This study aims to investigate impact of these lockdowns on air quality index (AQI) using a deep learning framework. In addition to historical pollutant concentrations and meteorological factors, we incorporate social and spatio-temporal influences in the framework. In particular, spatial autocorrelation (SAC), which combines temporal autocorrelation with spatial correlation, is adopted to reflect the influence of neighbouring cities and historical data. Our deep learning analysis obtained the estimates of the lockdown effects as − 25.88 in Wuhan and − 20.47 in Shanghai. The corresponding prediction errors are reduced by about 47% for Wuhan and by 67% for Shanghai, which enables much more reliable AQI forecasts for both cities. [ABSTRACT FROM AUTHOR]

Sensor data are gaining increasing global attention due to the advent of Internet of Things (IoT). Reasoning is applied on such sensor data in order to compute prediction. Generating a health warning that is based on prediction of atmospheric pollution, planning timely evacuation of people from vulnerable areas with respect to prediction of natural disasters, etc., are the use cases of sensor data stream where prediction is vital to protect people and assets. Thus, prediction accuracy is of paramount importance to take preventive steps and avert any untoward situation. Uncertainties of sensor data is a severe factor which hampers prediction accuracy. Belief Rule Based Expert System (BRBES), a knowledge-driven approach, is a widely employed prediction algorithm to deal with such uncertainties based on knowledge base and inference engine. In connection with handling uncertainties, it offers higher accuracy than other such knowledge-driven techniques, e.g., fuzzy logic and Bayesian probability theory. Contrarily, Deep Learning is a data-driven technique, which constitutes a part of Artificial Intelligence (AI). By applying analytics on huge amount of data, Deep Learning learns the hidden representation of data. Thus, Deep Learning can infer prediction by reasoning over available data, such as historical data and sensor data streams. Combined application of BRBES and Deep Learning can compute prediction with improved accuracy by addressing sensor data uncertainties while utilizing its discovered data pattern. Hence, this paper proposes a novel predictive model that is based on the integrated approach of BRBES and Deep Learning. The uniqueness of this model lies in the development of a mathematical model to combine Deep Learning with BRBES and capture the nonlinear dependencies among the relevant variables. We optimized BRBES further by applying parameter and structure optimization on it. Air pollution prediction has been taken as use case of our proposed combined approach. This model has been evaluated against two different datasets. One dataset contains synthetic images with a corresponding label of PM2.5 concentrations. The other one contains real images, PM2.5 concentrations, and numerical weather data of Shanghai, China. We also distinguished a hazy image between polluted air and fog through our proposed model. Our approach has outperformed only BRBES and only Deep Learning in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

The role of the stock market in the whole financial market is indispensable. How to obtain the actual trading income and maximize the interests in the trading process has been a problem studied by scholars and financial practitioners for a long time. Deep learning network can extract features from a large number of original data, which has potential advantages for stock market prediction. Based on the Shanghai and Shenzhen stock markets from 2019 to 2021, we use LSTM models, optimized on in-sample period and tested on out-of-sample period, using rolling window approach. We select the right hyperparameters at the beginning of our tests, use RBM pre-processing data, then use LSTM model to obtain expected stock return, to effectively predict future stock market analysis and predictive behavior. Finally, we perform a sensitivity analysis of the main parameters and hyperparameters of the model. [ABSTRACT FROM AUTHOR]

Obtaining crowd flow distribution with recognized human intention is extremely valuable for a series of applications for metropolitan cities. Previous solutions look at spatial correlation and temporal periodicity based on historical crowd flow information to calculate future crowd flow distribution. However, these mechanisms cannot recognize the intention behind crowd flow. We address this problem by leveraging a key insight – people's intention behind their movement is highly correlated with the point-of-interest (POI) distribution of the corresponding regions and adjacent regions. Therefore, we propose DeepFlowGen to model the complicated relationship between crowd flow, POI, check-ins, and time to generate intention-aware crowd flow. Specifically, we solve the conflict between dynamic crowd flow and static POI distribution by fusing the information in both time and POI domains. Besides, we employ a sequence of residual blocks in DeepFlowGen to address the challenges of modeling the diverse temporal rhythms and heterogeneous influence of POI. Furthermore, we examine the generated intention-aware crowd flow from two aspects to substantiate the reasonability of DeepFlowGen. Extensive experiments demonstrate that our model outperforms the state-of-the-art solutions by at most 30 percent in terms of NRMSE of total crowd flow. Moreover, the correlation between the generated intention-aware crowd flow and the check-in distribution across different categories of POIs is as high as 0.90 and 0.80 in Beijing and Shanghai. Combined with extensive case studies, we demonstrate the strong ability of our model in generating intention-aware crowd flow. [ABSTRACT FROM AUTHOR]

Predicting the passenger flow of metro networks is of great importance for traffic management and public safety. However, such predictions are very challenging, as passenger flow is affected by complex spatial dependencies (nearby and distant) and temporal dependencies (recent and periodic). In this paper, we propose a novel deep-learning-based approach, named STGCNNmetro (spatiotemporal graph convolutional neural networks for metro), to collectively predict two types of passenger flow volumes—inflow and outflow—in each metro station of a city. Specifically, instead of representing metro stations by grids and employing conventional convolutional neural networks (CNNs) to capture spatiotemporal dependencies, STGCNNmetro transforms the city metro network to a graph and makes predictions using graph convolutional neural networks (GCNNs). First, we apply stereogram graph convolution operations to seamlessly capture the irregular spatiotemporal dependencies along the metro network. Second, a deep structure composed of GCNNs is constructed to capture the distant spatiotemporal dependencies at the citywide level. Finally, we integrate three temporal patterns (recent, daily, and weekly) and fuse the spatiotemporal dependencies captured from these patterns to form the final prediction values. The STGCNNmetro model is an end-to-end framework which can accept raw passenger flow-volume data, automatically capture the effective features of the citywide metro network, and output predictions. We test this model by predicting the short-term passenger flow volume in the citywide metro network of Shanghai, China. Experiments show that the STGCNNmetro model outperforms seven well-known baseline models (LSVR, PCA-kNN, NMF-kNN, Bayesian, MLR, M-CNN, and LSTM). We additionally explore the sensitivity of the model to its parameters and discuss the distribution of prediction errors. [ABSTRACT FROM AUTHOR]

The increasing free access of the Internet provides us with favorable circumstances to investigate search engine index reflecting more and more personal behavior information. Part of valuable travel search information can assist us to achieve more robust and reliable prediction of metro passenger flow. Inspired by this, the paper develops a new multi-source time series fusion and direct interval prediction approach to grasp the dynamic law of metro passenger flow effectively. Multi-source index regarding metro travel from three major search engines (Baidu, Sogou and 360) in China are screened out and fused into the powerful predictors. By integrating an optimized multivariate mode decomposition strategy and long short-term memory model, lower and upper bounds of prediction interval are estimated directly by a multi-objective framework that combines the advantages of both the deep learning models long short-term memory and the ensemble learning approach. Especially, two sets of real experiment data of Beijing and Shanghai metro systems are employed to test our approach. Findings show that fusion of multi-source index information promotes the predictability of metro passenger flow, contributing to improving operation management and service quality. [Display omitted] • Fusing multi-source search data from three search engines based on query popularity. • Developing a new multivariate preprocessing technique MOHHOMVMD. • Proposing a direct multi-objective interval prediction approach LSTM-based LUBE. • Verifying the superiority of our approach over six benchmark models in two cases. [ABSTRACT FROM AUTHOR]

Travel recommendations form a major part of tourism service. Traditional collaborative filtering and Markov model are not appropriate for expressing the trajectory features, for travel preferences of tourists are dynamic and affected by previous behaviors. Inspired by the success of deep learning in sequence learning, a personalized recurrent neural network (P-RecN) is proposed for tourist route recommendation. It is data-driven and adaptively learns the unknown mapping of historical trajectory input to recommended route output. Specifically, a trajectory encoding module is designed to mine the semantic information of trajectory data, and LSTM neural networks are used to capture the sequence travel patterns of tourists. In particular, a temporal attention mechanism is integrated to emphasize the main behavioral intention of tourists. We retrieve a geotagged photo dataset in Shanghai, and evaluate our model in terms of accuracy and ranking ability. Experimental results illustrated that P-RecN outperforms other baseline approaches and can effectively understand the travel patterns of tourists. [ABSTRACT FROM AUTHOR]

Severe haze or low-visibility events caused by abundant atmospheric aerosols have become a serious environmental issue in many countries. A framework based on deep convolutional neural networks containing more than 20 million parameters called HazeNet has been developed to forecast the occurrence of such events in two Asian megacities: Beijing and Shanghai. Trained using time-sequential regional maps of up to 16 meteorological and hydrological variables alongside surface visibility data over the past 41 years, the machine has achieved a good overall performance in identifying haze versus non-haze events, and thus their respective favorable meteorological and hydrological conditions, with a validation accuracy of 80 % in both the Beijing and Shanghai cases, exceeding the frequency of non-haze events or no-skill forecasting accuracy, and an F1 score specifically for haze events of nearly 0.5. Its performance is clearly better during months with high haze frequency, i.e., all months except dusty April and May in Beijing and from late autumn through all of winter in Shanghai. Certain valuable knowledge has also obtained from the training, such as the sensitivity of the machine's performance to the spatial scale of feature patterns, that could benefit future applications using meteorological and hydrological data. Furthermore, an unsupervised cluster analysis using features with a greatly reduced dimensionality produced by the trained HazeNet has, arguably for the first time, successfully categorized typical regional meteorological–hydrological regimes alongside local quantities associated with haze and non-haze events in the two targeted cities, providing substantial insights to advance our understandings of this environmental extreme. Interesting similarities in associated weather and hydrological regimes between haze and false alarm clusters or differences between haze and missing forecasting clusters have also been revealed, implying that factors, such as energy-consumption variation and long-range aerosol transport, could also influence the occurrence of hazes, even under unfavorable weather conditions. [ABSTRACT FROM AUTHOR]

The automatic detection and extraction of road pothole distress is an important issue regarding healthy road structures, monitoring, and maintenance. In this paper, a new algorithm that integrates the mobile point cloud and images is proposed for the detection of road potholes. The algorithm includes three steps: 2D candidate pothole extraction from the images using a deep learning method, 3D candidate pothole extraction via a point cloud, and pothole determination by depth analysis. Because the texture features of the pothole and asphalt or concrete patches greatly differ from those of a normal road, pothole or patch distress images are used to establish a training set and train and test the deep learning system. Subsequently, the 2D candidate pothole is extracted from the images and labeled via the trained DeepLabv3+, a state-of-the-art pixel-wise classification (semantic segmentation) network. The edge of the candidate pothole in the image is then used to establish the relationship between the mobile point cloud and images. The original road point cloud around the edge of the candidate pothole is categorized into two groups, that is, interior and exterior points, according to the relationship between the point cloud and images. The exterior points are used to fit the road plane and calculate the accurate 3D shape of the candidate potholes. Finally, the interior points of a candidate pothole are used to analyze the depth distribution to determine if the candidate pothole is a pothole or patch. To verify the proposed method, two cases, including real and simulation cases, are selected. The real case is an expressway in Shanghai with a length of 26.4 km. Based on the proposed method, 77 candidate potholes are extracted by the DeepLabv3+ system; 49 potholes and 28 patches are finally filtered. The affected lanes and pothole locations are analyzed. The simulation case is selected to verify the geometric accuracy of the detected potholes. The results show that the mean accuracy of the detected potholes is ∼1.5–2.8 cm. [ABSTRACT FROM AUTHOR]

Many studies have explored the relationship between housing prices and environmental characteristics using the hedonic price model (HPM). However, few studies have deeply examined the impact of scene perception near residential units on housing prices. This article used house purchasing records from and open access geolocation data (including massive street view pictures, point of interest (POI) data and road network data) and proposed a framework named “open-access-dataset-based hedonic price modeling (OADB-HPM)” for comprehensive analysis in Beijing and Shanghai, China. A state-of-the-art deep learning framework and massive Baidu street view panoramas were employed to visualize and quantify three major scene perception characteristics (greenery, sky and building view indexes, abbreviated GVI, SVI and BVI, respectively) at the street level. Then, the newly introduced scene perception characteristics were combined with other traditional characteristics in the HPM to calculate marginal prices, and the results for Beijing and Shanghai were explored and compared. The empirical results showed that the greenery and sky perceptual elements at the property level can significantly increase the housing price in Beijing (RMB 39,377 and 6011, respectively) and Shanghai (RMB 21,689 and 2763, respectively), indicating an objectively higher willingness by buyers to pay for houses that provide the ability to perceive natural elements in the surrounding environment. This study developed quantification tools to help decision makers and planners understand and analyze the interaction between residents and urban scene components. [ABSTRACT FROM AUTHOR]