Search

Additional file 2: Figure S1. [Kaplan-Meier curves of overall survival for the preoperative groups of CEA (a), CA19-9 (b), and CA125 (c) in colorectal cancer patients]. Figure S2. [Kaplan-Meier curves of overall survival for the first postoperative groups of CEA (a), CA1 -9 (b), and CA125 (c) in colorectal cancer patients]. Figure S3. [Longitudinal trajectories of CEA (a), CA19-9 (b) and CA125 (c) of survived and died patients]. Figure S4. [The eigenfunctions of FPCA for CEA (a), CA19-9 (b), and CA125 (c)]. Figure S5. [The first five eigenfunctions for CEA (a), CA19-9 (b), and CA125 (c) based on MFPCA of the three markers]. Figure S6. [Variable importance of preoperative CEA&CA19-9&CA125 model (a) and longitudinal CEA&CA19-9&CA125 model (b)]. Figure S7. [ROC curves of the preoperative, postoperative and longitudinal CEA&CA19-9&CA125 models at 60 months after surgery for internal validation (a) and external validation (b)]. Figure S8. [Personalized dynamic prediction for the survival probability of patient A (a), patient B (b) and patient C (c) based on longitudinal CEA&CA19-9&CA125 model]. Figure S9. [AUC (a) and BS (b) of the prediction models with MSI status at 24 to 60 months after surgery for external validation].

Recently, the world has witnessed the most severe pandemic (COVID-19) in this century. Studies on epidemic prediction and simulation have received increasing attention. However, the current methods suffer from three issues. First, most of the current studies focus on epidemic prediction, which can not provide adequate support for intervention policy making. Second, most of the current interventions are based on population groups rather than fine-grained individuals, which can not make the measures towards the infected people and may cause waste of medical resources. Third, current simulations are not efficient and flexible enough for large-scale complex systems. In this paper, we propose a new epidemic simulation framework called HMES to address the above three challenges. The proposed framework covers a full pipeline of epidemic simulation and enables comprehensive fine-grained control in a large scale. In addition, we conduct experiments on real COVID-19 data. HMES demonstrates more accurate modeling of disease transmission up to 300 million people and up to 3 times acceleration compared to the state-of-the-art methods., Comment: UIC-2022, code available at https://github.com/hygeng/humanflow

Additional file 1. Characteristics of the included and excluded patients in YNCH and SYSU6.

Background Profound heterogeneity in prognosis has been observed in colorectal cancer (CRC) patients with intermediate levels of disease (stage II–III), advocating the identification of valuable biomarkers that could improve the prognostic stratification. This study aims to develop a deep learning-based pipeline for fully automatic quantification of immune infiltration within the stroma region on immunohistochemical (IHC) whole-slide images (WSIs) and further analyze its prognostic value in CRC. Methods Patients from two independent cohorts were divided into three groups: the development group (N = 200), the internal (N = 134), and the external validation group (N = 90). We trained a convolutional neural network for tissue classification of CD3 and CD8 stained WSIs. A scoring system, named stroma-immune score, was established by quantifying the density of CD3+ and CD8+ T-cells infiltration in the stroma region. Results Patients with higher stroma-immune scores had much longer survival. In the development group, 5-year survival rates of the low and high scores were 55.7% and 80.8% (hazard ratio [HR] for high vs. low 0.39, 95% confidence interval [CI] 0.24–0.63, P Conclusions We proposed a stroma-immune score via a deep learning-based pipeline to quantify CD3+ and CD8+ T-cells densities within the stroma region on WSIs of CRC and further predict survival.

Traffic simulation provides interactive data for the optimization of traffic control policies. However, existing traffic simulators are limited by their lack of scalability and shortage in input data, which prevents them from generating interactive data from traffic simulation in the scenarios of real large-scale city road networks. In this paper, we present \textbf{C}ity \textbf{B}rain \textbf{Lab}, a toolkit for scalable traffic simulation. CBLab consists of three components: CBEngine, CBData, and CBScenario. CBEngine is a highly efficient simulator supporting large-scale traffic simulation. CBData includes a traffic dataset with road network data of 100 cities all around the world. We also develop a pipeline to conduct a one-click transformation from raw road networks to input data of our traffic simulation. Combining CBEngine and CBData allows researchers to run scalable traffic simulations in the road network of real large-scale cities. Based on that, CBScenario implements an interactive environment and a benchmark for two scenarios of traffic control policies respectively, with which traffic control policies adaptable for large-scale urban traffic can be trained and tuned. To the best of our knowledge, CBLab is the first infrastructure supporting traffic control policy optimization in large-scale urban scenarios. CBLab has supported the City Brain Challenge @ KDD CUP 2021. The project is available on GitHub:~\url{https://github.com/CityBrainLab/CityBrainLab.git}., Accepted by KDD2023 (Applied Data Science Track)

China is well known for its wide and increasing commercial use of mobile social media for various purposes in different areas, ranging from online shopping to social networking. Such a popular commercial use was insightfully examined in relation to social relationship in the age of mobile internet, which enables people of either weak or strong connections to socialize anywhere anytime, leading to scenarios where mobile social media can be leveraged for profits. In what way can user experiences be guaranteed while platforms' value-added targets be achieved at the same time? In addressing that question, the authors of this chapter examined the commercial use of mobile social media in the context of complicated social networks. It is expected from the editor that further studies are to be carried out to comprehensively and comparatively examine the same topic in different countries or cultures.

Additional file 1: FigureS1. Association between preoperative CA19-9 status and overall survival. (a) overall population. (b) patients with normal preoperative CEA. (c) patientswith elevated preoperative CEA. Solid yellow lines are unadjustedhazard ratios, with dashed yellow lines showing 95% confidence intervalsderived from restricted cubic spline regressions. Reference lines for noassociation are indicated by the solid bold lines at a hazard ratio (HR) of 1.0. Dashed blue curves show the fraction of the population with different levels of preoperative CA19-9. Arrows indicate the concentration of preoperative CA19-9 with HR of 1.0. CA19-9, carbohydrate antigen 19-9; CEA, carcinoembryonic antigen; CI, confidence interval; E, number of events; HR, hazard ratio; N, number of patients. FigureS2. Kaplan‐Meier curves for overall survival according to the preoperative CA19-9 group. (a) overall population. (b) patients with normal preoperative CEA. (c) patientswith elevated preoperative CEA. CA19-9, carbohydrate antigen 19-9; CEA, carcinoembryonic antigen. FigureS3. Kaplan‐Meier curves according to the joint group of preoperative CEA and CA19-9 in colorectal cancer patients. (a) recurrence-free survival. (b) overall survival. CA19-9, carbohydrate antigen 19-9; CEA, carcinoembryonic antigen; OS, overall survival; RFS, recurrence-free survival. FigureS4. Forest plot for recurrence-free survival of preoperative CA 19-9 groups stratified by clinicopathological features based on the Cox models. P values for interaction were calculated using Cox regression model. HR and 95%CIs were given and visually represented by the squares and error bars. CA 19-9, carbohydrate antigen 19-9; CEA, carcinoembryonic antigen; CI, confidence interval; HR, hazard ratio. FigureS5. Forest plot for performance overallsurvival of preoperative CA19-9 groups stratified by clinicopathological features based on the Cox models. P values for interaction were calculated using Cox regression model. HR and 95%CIs were given and visually represented by the squares and error bars. CA19-9, carbohydrate antigen 19-9; CEA, carcinoembryonic antigen; CI, confidenceinterval; HR, hazard ratio. FigureS6. Kaplan‐Meier curves according to the joint group of preoperative CEA and CA19-9 in patients with stage II colorectal cancer. (a) recurrence-free survival.(b) overall survival. CA 19-9, carbohydrate antigen 19-9;CEA, carcinoembryonic antigen; OS, overall survival; RFS, recurrence-freesurvival.

Additional file 1. SI. Inclusion and exclusion criteria. SII. Annotation of ultrasound images. SIII. Details of theautomated segmentation model for breast ultrasound images. SIV. Data Standardization and Feature Extraction. SV. Feature Selection and Model Construction. SVI. Consistency evaluation of features by Bland-Altman. Fig. S1. Inclusion and exclusion criteria. Fig. S2. U-net architecture. Fig. S3. Flowchart of feature assessment and SUAS construction. Fig. S4. Principal component analysis plot and linear model for evaluating batch effect correction in three institutions. Fig. S5. Relative variable contribution in Model2 and Model3. Fig. S6. Clinical usefulness evaluation of Model2 and Model3. Fig. S7. The changing trend of entropy-related features in three institutions. Table S1. The ultrasonographic images acquisition parameters of the multiple centers. Table S2. Similarity and consistency evaluation between automated segmentation and manual segmentation. Table S3. Key features selected for construction of phasal signatures based on ultrasound images at each single time point. Table S4. Multivariate analysis of clinicopathological model, Model 2 (the early-treatment model) and Model 3 (the posttreatment model). Table S5. Prediction performance of the signatures. Table S6. AUCs of early-pretreatment model (Model 2) and post-treatment model (Model 3) in breast cancer subtypes. Table S7. NRI test for prediction improvements of SUAS compared to single-time signature in multiple cohorts. Table S8. IDI test for prediction improvements of SUAS compared to single-time signature in multiple cohorts. Table S9. Prediction performance of the signatures and SUAS in randomly split datasets.

Additional file 1.

Additional file 1: Note S1. Immunohistochemical staining. Table S1. The coding, partial regression coefficient and estimated 5-year baseline cumulative hazard of each prediction model. Figure S1. Comparison of automated and manual counting of positive cells. Figure S2. Determination of an optimal cut-off for CD3-score. Figure S3. Determination of an optimal cut-off for CD8-score. Figure S4. Kaplan-Meier curves of subgroup analyses

The COVID-19 pandemic has caused a dramatic reshaping of passenger risk perception for airline industry. The sharp increase in risk aversion by air passenger has caused a disastrous impact on the tourism service industry, particularly airline industry. Although the existing literature has provided a lot of studies on the impact of the pandemic on travel industry, there are very few studies discussing the impact of change in passenger risk perception on the stock market performance of airline industry. This study considers two types of airline companies, full-service and low-cost. In order to overcome the traditional problem of the Chow test, Quandt–Andrews test is used to identify structural change points during the pandemic in the stock prices of United States airline companies. The result shows that an industry-wide structural change in the stock market performance indeed is found to take place during the pandemic for United States airline companies. Meanwhile, no significant difference is found in the structural change date between the two types of airline companies. The selected airline companies are found to be clustered toward the end of 2020 (November and December) in their structural change dates. Although the strike of the COVID-19 pandemic on airline industry has proven to be widespread and profound, our investigation implies that air passengers have gradually adapted to the new normal of travel activities at some level and partly rebuild their sense of safety under the strict epidemic-control measures.

Additional file 2: Table S1.Baseline characteristics by participant site. Table S2.Multivariate analyses of recurrence-free survival in total population (Cox model). Table S3.Multivariate analyses of overall survival in total population (Cox model). Table S4.Interaction between preoperative CEA and CA19-9 with risk of outcomes. Table S5.Multivariate analyses of recurrence-free survival in colorectal cancer subgroup with CEA < 5 ng/ml (Cox model). Table S6.Multivariate analyses of recurrence-free survival in colorectal cancer subgroup with CEA ≥ 5 ng/ml (Cox model). Table S7. Multivariate analyses of overall survival in colorectal cancer subgroup with CEA < 5 ng/ml (Cox model). Table S8.Multivariate analyses of overall survival in colorectal cancer subgroup with CEA ≥ 5 ng/ml (Cox model). Table S9.A frailty model analysis of preoperative CA19-9 (cutoff: 37 U/ml) on colorectal cancer outcomes in total population. TableS10.Cox proportional hazard regression analysis of preoperative CA19-9 (cutoff:74 U/ml) on colorectal cancer outcomes in total population. Table S11.Relationship between preoperative CA19-9 and benefit from adjuvant chemotherapyin patients with stage II colorectal cancer.

Background. Poor balance is one of the risk factors for falls in patients with knee osteoarthritis (KOA), which is related to the symptoms. Electroacupuncture (EA) is one of the traditional Chinese conservative methods commonly used to improve the symptoms in patients with KOA. Objective. To assess whether EA increases the dynamic balance during stair negotiation among patients with KOA. Methods. A total of 40 KOA patients were assigned to two groups randomly (true electroacupuncture vs. mock electroacupuncture). Acupoints around the knee were selected in the true electroacupuncture (TEA) group with electrical stimulation (2 Hz). In the mock electroacupuncture (MEA) group, about 2 cm next to the above acupoints, the needles were inserted superficially without electrical stimulation. All the participants received 11 sessions of stimulation treatment in three weeks. The primary outcome was margin of stability (MOS). Secondary outcomes included hip kinematics and kinetics as well as pain. Results. There was no significant difference between the two groups for self-reported pain (p=0.585). During ascent, there was no difference between groups in MOS value in both directions, which was the anterior-posterior (A/P) direction and medial-lateral (M/L) direction at initial contact and toe-off as well as the midstance in the gait cycle, and no difference for the hip kinematics and kinetics between the groups was detected (p>0.05). For descent, at the toe-off event, the TEA group was more unstable as compared to the MEA group in the A/P direction (p=0.029) but not in the M/L direction, and the hip showed a larger internal rotator moment (p=0.049); at the midstance, the TEA group showed a lower abductor moment than the MEA group (p=0.003). Conclusions. Based on the assessment results from the chosen patients with KOA, the TEA did not demonstrate a significant effect in improving the dynamic balance during stair negotiation in comparison with the MEA. This finding does not support EA as a conservative treatment to improve the dynamic balance in such patients.

Traffic simulators act as an essential component in the operating and planning of transportation systems. Conventional traffic simulators usually employ a calibrated physical car-following model to describe vehicles' behaviors and their interactions with traffic environment. However, there is no universal physical model that can accurately predict the pattern of vehicle's behaviors in different situations. A fixed physical model tends to be less effective in a complicated environment given the non-stationary nature of traffic dynamics. In this paper, we formulate traffic simulation as an inverse reinforcement learning problem, and propose a parameter sharing adversarial inverse reinforcement learning model for dynamics-robust simulation learning. Our proposed model is able to imitate a vehicle's trajectories in the real world while simultaneously recovering the reward function that reveals the vehicle's true objective which is invariant to different dynamics. Extensive experiments on synthetic and real-world datasets show the superior performance of our approach compared to state-of-the-art methods and its robustness to variant dynamics of traffic., Accepted for publication by IJCAI 2021

In this paper, a hierarchical energy management strategy (EMS) based on low-pass filter and equivalent consumption minimization strategy (ECMS) is proposed in order to lift energy sources lifespan, power performance and fuel economy for hybrid electrical vehicles equipped with fuel cell, battery and supercapacitor. As for the considered powertrain configuration, fuel cell serves as main energy source, and battery and supercapacitor are regarded as energy support and storage system. Supercapacitor with high power density and dynamic response acts during great power fluctuations, which relives stress on fuel cell and battery. Meanwhile, battery is used to lift the economy of hydrogen fuel. In higher layer strategy of the proposed EMS, supercapacitor is employed to supply peak power and recycle braking energy by using the adaptive low-pass filter method. Meantime, an ECMS is designed to allocate power of fuel cell and battery such that fuel cell can work in a high efficient range to minimize hydrogen consumption in lower layer. The proposed EMS for hybrid electrical vehicles is modeled and verified by advisor-simulink and experiment bench. Simulation and experiment results are given to confirm effectiveness of the proposed EMS of this paper.

In this paper, in order to extend battery lifespan and lift power performance in hybrid batteries/supercapacitors electrical vehicles, a new energy management strategy is proposed based on...

Additional file 1: Supplementary Methods.

Additional file 1: Figure S1. Study profile and IHC tiles dataset generation. Figure S2���S4. Kaplan���Meier survival analysis for patients stratified by TNM stage, age, sex, tumor site, MSI status, and treatment modalities. Figure S5. Using the pipeline to predict the prognosis of one patient with CD3 and CD8 WSIs. Figure S6. Kaplan���Meier survival curve of overall survival of stroma-low vs. stroma-high groups. Figure S7. Stroma-immune score vs. intraepithelial-immune score.

Simulation of the real-world traffic can be used to help validate the transportation policies. A good simulator means the simulated traffic is similar to real-world traffic, which often requires dense traffic trajectories (i.e., with a high sampling rate) to cover dynamic situations in the real world. However, in most cases, the real-world trajectories are sparse, which makes simulation challenging. In this paper, we present a novel framework ImInGAIL to address the problem of learning to simulate the driving behavior from sparse real-world data. The proposed architecture incorporates data interpolation with the behavior learning process of imitation learning. To the best of our knowledge, we are the first to tackle the data sparsity issue for behavior learning problems. We investigate our framework on both synthetic and real-world trajectory datasets of driving vehicles, showing that our method outperforms various baselines and state-of-the-art methods., Comment: Accepted by ECML-PKDD 2020, Best Applied Data Science Paper. 16 pages, 6 figures

The heavy traffic and related issues have always been concerns for modern cities. With the help of deep learning and reinforcement learning, people have proposed various policies to solve these traffic-related problems, such as smart traffic signal control systems and taxi dispatching systems. People usually validate these policies in a city simulator, since directly applying them in the real city introduces real cost. However, these policies validated in the city simulator may fail in the real city if the simulator is significantly different from the real world. To tackle this problem, we need to build a real-like traffic simulation system. Therefore, in this paper, we propose to learn the human routing model, which is one of the most essential part in the traffic simulator. This problem has two major challenges. First, human routing decisions are determined by multiple factors, besides the common time and distance factor. Second, current historical routes data usually covers just a small portion of vehicles, due to privacy and device availability issues. To address these problems, we propose a theory-guided residual network model, where the theoretical part can emphasize the general principles for human routing decisions (e.g., fastest route), and the residual part can capture drivable condition preferences (e.g., local road or highway). Since the theoretical part is composed of traditional shortest path algorithms that do not need data to train, our residual network can learn human routing models from limited data. We have conducted extensive experiments on multiple real-world datasets to show the superior performance of our model, especially with small data. Besides, we have also illustrated why our model is better at recovering real routes through case studies.

Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads. In this paper, we study how to efficiently construct historical features through counting features. The key challenge of such problem lies in how to automatically identify counting keys. We propose a tree-based method for counting key selection. The intuition is that a decision tree naturally provides various combinations of features, which could be used as counting key candidate. In order to select personalized counting features, we train one decision tree model per user, and the counting keys are selected across different users with a frequency-based importance measure. To validate the effectiveness of proposed solution, we conduct large scale experiments on Twitter video advertising data. In both online learning and offline training settings, the automatically identified counting features outperform the manually curated counting features., 7 pages, KDD'19 AutoML Workshop

Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has shown its effectiveness in online scenarios by continuously updating the model with the learned prior. However, current online meta-learning algorithms are limited to learn a globally-shared meta-learner, which may lead to sub-optimal results when the tasks contain heterogeneous information that are distinct by nature and difficult to share. We overcome this limitation by proposing an online structured meta-learning (OSML) framework. Inspired by the knowledge organization of human and hierarchical feature representation, OSML explicitly disentangles the meta-learner as a meta-hierarchical graph with different knowledge blocks. When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks. Through the meta-knowledge pathway, the model is able to quickly adapt to the new task. In addition, new knowledge is further incorporated into the selected blocks. Experiments on three datasets demonstrate the effectiveness and interpretability of our proposed framework in the context of both homogeneous and heterogeneous tasks., Accepted by NeurIPS 2020

Based on a large number of data generated by the application of the Internet of things, the data information is processed and processed. The contents and methods of data processing in three-tier IOT structure are different. Upper layer: data communication and data communication; data acquisition and application. The data processing process reflects the purpose and mode of data processing in the Internet of things system. A large number of experiments have proved that the data processing methods and forms used in this paper have practical significance.

Zhenhui Li,1,* Shaoyou Li,2,* Yun Liang,3,* Hongjiang Pu,4 Changling Tu,5 Zhenyu Wu,6 Dingyun You7,8 1Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming 650118, People’s Republic of China; 2Department of Medical Oncology, The First Affiliated Hospital of Kunming Medical University, Kunming 650032, People’s Republic of China; 3Department of Hepatobiliary Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming 650032, People’s Republic of China; 4Department of Colorectal Surgery, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming 650118, People’s Republic of China; 5Department of Cadres Medical Oncology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming 650118, People’s Republic of China; 6Department of Biostatistics, School of Public Health, Key Laboratory of Public Health Safety and Collaborative Innovation Center of Social Risks Governance in Health, Fudan University, Shanghai 200032, People’s Republic of China; 7The Department of Epidemiology & Biostatistics, School of Public Health, Kunming Medical University, Kunming, Yunnan 650500, People’s Republic of China; 8Yunnan Key Laboratory of Laboratory Medicine, Kunming Medical University, Kunming, Yunnan 650500, People’s Republic of China*These authors contributed equally to this workCorrespondence: Dingyun YouYunnan Key Laboratory of Laboratory Medicine, Kunming Medical University, No. 1168 Chunrongxi Road, Chenggong District, Kunming, Yunnan 650500, People’s Republic of ChinaTel/ Fax +86 871-5922935Email youdingyun@qq.comZhenyu WuDepartment of Biostatistics, School of Public Health, Key Laboratory of Public Health Safety and Collaborative Innovation Center of Social Risks Governance in Health, Fudan University, 130 Dongan Road, Shanghai, People’s Republic of ChinaTel/ Fax +86 21‐33563913Email nc.ude.naduf@wyzObjective: Association of postoperative peripheral CD4+ T cells percentage and recurrence in colorectal cancer (CRC) remains to be explored. Therefore, we aimed to investigate the association between the postoperative peripheral CD4+ T cells percentage and recurrence in CRC patients.Patients and Methods: Consecutive stage I–III CRC patients without neoadjuvant treatment undergoing curative resection from January 2010 to July 2016 were identified in two Chinese centers. The association between the postoperative CD4+ T cells percentage, measured within 12 weeks after surgery, and recurrence-free survival (RFS) was analyzed.Results: A total of 1028 patients were identified (training set: 913 patients, validation set: 115 patients). In the training set, the 5-year RFS rate of the 441 patients with abnormal postoperative CD4+ T cells percentage was significantly lower than that of those with normal percentage (70.3% [95% CI 65.7– 75.2%] vs 77.6% [95% CI 73.7– 81.7%] and unadjusted hazard ratio [HR] 1.36 [95% CI 1.04– 1.78], P= 0.02). The result was confirmed in the validation set. Multivariable Cox regression analysis demonstrated that the association of postoperative CD4+ T cells percentage with 5-year RFS was independent both in the training and validation sets. In propensity score matching analysis, patients with normal postoperative CD4+ T cells percentage were found to have a favourable response to adjuvant chemotherapy (HR 0.29 [95% CI 0.12– 0.72], P=0.008).Conclusion: Postoperative peripheral CD4+ T cells percentage is a predictive biomarker for RFS in patients with CRC, which can identify those who will benefit from adjuvant chemotherapy.Keywords: recurrence, peripheral CD4+ T cells, colorectal cancer, adjuvant chemotherapy, propensity score matching analysis

Connecting consumers with relevant products is a very important problem in both online and offline commerce. In physical retail, product placement is an effective way to connect consumers with products. However, selecting product locations within a store can be a tedious process. Moreover, learning important spatial patterns in offline retail is challenging due to the scarcity of data and the high cost of exploration and experimentation in the physical world. To address these challenges, we propose a stochastic model of spatial demand in physical retail. We show that the proposed model is more predictive of demand than existing baselines. We also perform a preliminary study into different automation techniques and show that an optimal product allocation policy can be learned through Deep Q-Learning., 8 pages, The AAAI-20 Workshop on Intelligent Process Automation

IntroductionStair ascent and descent require complex integration between sensory and motor systems; individuals with knee osteoarthritis (KOA) have an elevated risk for falls and fall injuries, which may be in part due to poor dynamic postural control during locomotion. Tai chi exercise has been shown to reduce fall risks in the ageing population and is recommended as one of the non-pharmocological therapies for people with KOA. However, neuromuscular mechanisms underlying the benefits of tai chi for persons with KOA are not clearly understood. Postural control deficits in performing a primary motor task may be more pronounced when required to simultaneously attend to a cognitive task. This single-blind, parallel design randomised controlled trial (RCT) aims to evaluate the effects of a 12-week tai chi programme versus balance and postural control training on neuromechanical characteristics during dual-task stair negotiation.Methods and analysisSixty-six participants with KOA will be randomised into either tai chi or balance and postural control training, each at 60 min per session, twice weekly for 12 weeks. Assessed at baseline and 12 weeks (ie, postintervention), the primary outcomes are attention cost and dynamic postural stability during dual-task stair negotiation. Secondary outcomes include balance and proprioception, foot clearances, self-reported symptoms and function. A telephone follow-up to assess symptoms and function will be conducted at 20 weeks. The findings will help determine whether tai chi is beneficial on dynamic stability and in reducing fall risks in older adults with KOA patients in community.Ethics and disseminationEthics approval was obtained from the Ethics Committee of the Affiliated Rehabilitation Hospital of Fujian University of Traditional Chinese Medicine (#2018KY-006–1). Study findings will be disseminated through presentations at scientific conferences or publications in peer-reviewed journals.Trial registration numberChiCTR1800018028.

In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones. However, a critical challenge in meta-learning is the task heterogeneity which cannot be well handled by traditional globally shared meta-learning methods. In addition, current task-specific meta-learning methods may either suffer from hand-crafted structure design or lack the capability to capture complex relations between tasks. In this paper, motivated by the way of knowledge organization in knowledge bases, we propose an automated relational meta-learning (ARML) framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph. When a new task arrives, it can quickly find the most relevant structure and tailor the learned structure knowledge to the meta-learner. As a result, the proposed framework not only addresses the challenge of task heterogeneity by a learned meta-knowledge graph, but also increases the model interpretability. We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines., Comment: Accepted by ICLR 2020

In the face of growing needs for water and energy, a fundamental understanding of the environmental impacts of human activities becomes critical for managing water and energy resources, remedying water pollution, and making regulatory policy wisely. Among activities that impact the environment, oil and gas production, wastewater transport, and urbanization are included. In addition to the occurrence of anthropogenic contamination, the presence of some contaminants (e.g., methane, salt, and sulfate) of natural origin is not uncommon. Therefore, scientists sometimes find it difficult to identify the sources of contaminants in the coupled natural and human systems. In this paper, we propose a technique to simultaneously conduct source detection and prediction, which outperforms other approaches in the interdisciplinary case study of the identification of potential groundwater contamination within a region of high-density shale gas development., 8 pages, 4 figures, 1 table

Traffic signal control is an important and challenging real-world problem, which aims to minimize the travel time of vehicles by coordinating their movements at the road intersections. Current traffic signal control systems in use still rely heavily on oversimplified information and rule-based methods, although we now have richer data, more computing power and advanced methods to drive the development of intelligent transportation. With the growing interest in intelligent transportation using machine learning methods like reinforcement learning, this survey covers the widely acknowledged transportation approaches and a comprehensive list of recent literature on reinforcement for traffic signal control. We hope this survey can foster interdisciplinary research on this important topic., 32 pages

The analysis of customer journeys is a subject undergoing an intense study recently . The increase in understanding of customer behaviour serves as an important source of success to many organizations. Current research is however mostly focussed on visualizing these customer journeys to allow them to be more interpretable by humans. A deeper use of customer journey information in prediction and recommendationprocesses has not been achieved. This paper aims to take a step forward into that direction by introducing the Order-Aware Recommendation Approach (OARA). The main scientific contributions showcased by this approach are (i) increasing performance on prediction and recommendation tasks by taking into account the explicit order of actions in the customer journey, (ii) showing how a visualization of a customer journey can play an important role during predictions and recommendations, and (iii) introducing a way of maximizing recommendations for any tailor-made Key Performance Indicator (KPI) instead of the accuracy-based metrics traditionally used for this task. Anextensive experimental evaluation study highlights the potential of OARA against state-of-the-art approaches using a real dataset representing a customer journey of upgrading with multiple products.

With the increasing availability of traffic data and advance of deep reinforcement learning techniques, there is an emerging trend of employing reinforcement learning (RL) for traffic signal control. A key question for applying RL to traffic signal control is how to define the reward and state. The ultimate objective in traffic signal control is to minimize the travel time, which is difficult to reach directly. Hence, existing studies often define reward as an ad-hoc weighted linear combination of several traffic measures. However, there is no guarantee that the travel time will be optimized with the reward. In addition, recent RL approaches use more complicated state (e.g., image) in order to describe the full traffic situation. However, none of the existing studies has discussed whether such a complex state representation is necessary. This extra complexity may lead to significantly slower learning process but may not necessarily bring significant performance gain. In this paper, we propose to re-examine the RL approaches through the lens of classic transportation theory. We ask the following questions: (1) How should we design the reward so that one can guarantee to minimize the travel time? (2) How to design a state representation which is concise yet sufficient to obtain the optimal solution? Our proposed method LIT is theoretically supported by the classic traffic signal control methods in transportation field. LIT has a very simple state and reward design, thus can serve as a building block for future RL approaches to traffic signal control. Extensive experiments on both synthetic and real datasets show that our method significantly outperforms the state-of-the-art traffic signal control methods.

In this paper, an energy management strategy (EMS) for hybrid batteries and supercapacitor (SCs) electric vehicles (HBSEV) is considered for extending the batteries lifespan and lifting the power performance of HBSEV. In detail, firstly, vehicle dynamics model and hybrid energy storage source (HESS) models including batteries and SCs are adapted and simplified as fundamental of model prediction control (MPC) approach. Secondly, the EMS of HBSEV is designed for reducing batteries power variation and maintaining SCs SOC in a proper value based on MPC method combining adaptive method. That can enhance batteries lifespan and power performance. Finally, simulation results based on the proposed EMS are given, which show batteries lifespan and power performance for HBSEV are improved obviously compared with a real time average (RTA) strategy. Meanwhile, the SOC of batteries and SCs are maintained in a proper range.

Given a large collection of urban datasets, how can we find their hidden correlations? For example, New York City (NYC) provides open access to taxi data from year 2012 to 2015 with about half million taxi trips generated per day. In the meantime, we have a rich set of urban data in NYC including points-of-interest (POIs), geo-tagged tweets, weather, vehicle collisions, etc. Is it possible that these ubiquitous datasets can be used to explain the city traffic? Understanding the hidden correlation between external data and traffic data would allow us to answer many important questions in urban computing such as: If we observe a high traffic volume at Madison Square Garden (MSG) in NYC, is it because of the regular peak hour or a big event being held at MSG? If a disaster weather such as a hurricane or a snow storm hits the city, how would the traffic be affected? While existing studies may utilize external datasets for prediction task, they do not explicitly seek for direct explanations from the external datasets. In this paper, we present our results in attempts to understand taxi traffic dynamics in NYC from multiple external data sources. We use four real-world ubiquitous urban datasets, including POI, weather, geo-tagged tweet, and collision records. To address the heterogeneity of ubiquitous urban data, we present carefully-designed feature representations for various datasets. Extensive experiments on real data demonstrate the explanatory power on taxi traffic by using external datasets. More specifically, our analysis suggests that POIs can well describe the regular traffic patterns. At the same time, geo-tagged tweets can explain irregular traffic caused by big events and weather can explain the abnormal traffic drop., This manuscript is an extended version of the paper "Interpreting Traffic Dynamics using Ubiquitous Urban Data", Fei Wu, Hongjian Wang, Zhenhui Li, in Proceedings of the 24th ACM International Conference on Advances in Geographical Information Systems (SIGSPATIAL'16)

Hospitals often set protocols based on well defined standards to maintain quality of patient reports. To ensure that the clinicians conform to the protocols, quality assurance of these reports is needed. Patient reports are currently written in free-text format, which complicates the task of quality assurance. In this paper, we present a machine learning based natural language processing system for automatic quality assurance of radiology reports on breast cancer. This is achieved in three steps: we i) identify the top level structure of the report, ii) check whether the information under each section corresponds to the section heading, iii) convert the free-text detailed findings in the report to a semi-structured format. Top level structure and content of report were predicted with an F1 score of 0.97 and 0.94 respectively using Support Vector Machine (SVM). For automatic structuring, our proposed hierarchical Conditional Random Field (CRF) outperformed the baseline CRF with an F1 score of 0.78 vs 0.71. The third step generates a semi-structured XML format of the free-text report, which helps to easily visualize the conformance of the findings to the protocols. This format also allows easy extraction of specific information for other purposes such as search, evaluation and research.

In order to improve fuel economy further, an equivalent consumption minimization strategy (ECMS) is designed for the parallel hybrid electric vehicle (PHEV). Firstly, based on the relations among the battery state of charge (SOC) and the equivalent factor and fuel consumption, the equivalent fuel consumption minimization objective function is constructed. Secondly, a variable equivalent factor over real-time driving cycle is obtained by introducing the Pontryagin's Minimum Principle (PMP) and the penalty function of SOC. Finally, the simulation results show that compared with ECMS based on a PI controller, the ICE efficiency increases by 2% and the fuel consumption to travel 100 km decreases by 4 % with ECMS based on a variable equivalent factor.

The unique structures and properties of nanocarbons will provide fascinating applications in biomedicine. Here we report a new strategy to combine C60 with graphene for targeting phototherapy. Folic acid (FA) and polyethylene glycol (PEG) were conjugated onto graphene oxide (GO) via an imide linkage. Using nucleophilic addition, the FA–GO–PEG/C60 nanohybrid was then prepared. The versatile platform of FA–GO–PEG for C60 dramatically improved tumor targeting, which has been demonstrated by a cellular uptake assay. Owing to the doping effect and the inhibition of aggregation, the hybridization process also significantly enhanced the phototoxicity of FA–GO–PEG/C60. More importantly, the photothermal therapy (PTT) of FA–GO–PEG/C60 can cause obvious cell damage, which may further enhance the photodynamic therapy (PDT) efficacy against cancer cells. As expected, the combined PDT and PTT treatment with FA–GO–PEG/C60 showed remarkably improved and synergistic effects compared to PTT or PDT alone. This study presents the potential of nanocarbons for synergistic phototherapy of cancer.

The superlarge Jinchang gold deposit is located in the joint area between the Taipingling uplift and the Laoheishan depression of the Xingkai Block in both eastern Jilin and eastern Heilongjiang Province. Wall rocks of the gold deposits are the Neoproterozoic Huangsong Group of metamorphic rocks. Yanshanian magmatism in this region can be divided into 5 phases, the diorite, the graphic granite, the granite, the granite porphyry and the diorite porphyrite, which resulted in the magmatic domes and cryptoexplosive breecia chimney followed by large-scale hydrothermal alteration. Gold mineralization is closely related to the fourth and fifth phase of magmatism. According to the occurrences, gold ores can be subdivided into auriferous pyritized quartz vein, auriferous quartz-pyrite vein, auriferous polymetallic sulfide quartz vein and auriferous pyritized calcite vein. The ages of the gold deposit are ranging from 122.53 to 119.40 Ma. The ore bodies were controlled by a uniform tectono-magmatic hydrothermal alteration system that the ore-forming materials were deep derived from and the ore-forming fluids were dominated by magmatic waters with addition of some atmospheric water in the later phase of mineralization. Gold mineralization took place in an environment of medium to high temperatures and medium pressures. Ore-forming fluids were the K+-Na+-Ca2+-Cl−-SO42- type and characterized by medium salinity or a slightly higher, weak alkaline and weak reductive. Au in the ore-forming fluids was transported as complexes of [Au (HS)2]−, [AuCl2]−, [Au(CO2)]− and [Au(HCO3)2]−. Along with the decline of temperatures and pressures, the ore-forming fluids varied from acidic to weak acidic and then to weak alkaline, which resulted in the dissociation of the complex and finally the precipitation of the gold.

The electrical equipment loss caused by the lightning and power’s increasing demand is reduced by monitoring the extent of the surge protector failure through measuring its leakage current on-line. Proposed a method of monitoring the surge protector’s failure degree online based on mutual inductance current sensor, established its mathematical model, analyzed the influence of coil turns, load resistance and stray capacitance on the amplitude-frequency and phase-frequency characteristic. And used impact and sinusoidal signal to composite a motivic signal to test the optimized current sensor’s time-domain response feature by simulation. Experiments show: while the range of measured current is 0.2~9 mA, the mutual inductance current sensor designed can resist the impact of 50 kA high current, the current measurement error can be less than 0.11 mA, meet requirement of the leakage current on-line monitoring.

Fisher score is one of the most widely used supervised feature selection methods. However, it selects each feature independently according to their scores under the Fisher criterion, which leads to a suboptimal subset of features. In this paper, we present a generalized Fisher score to jointly select features. It aims at finding an subset of features, which maximize the lower bound of traditional Fisher score. The resulting feature selection problem is a mixed integer programming, which can be reformulated as a quadratically constrained linear programming (QCLP). It is solved by cutting plane algorithm, in each iteration of which a multiple kernel learning problem is solved alternatively by multivariate ridge regression and projected gradient descent. Experiments on benchmark data sets indicate that the proposed method outperforms Fisher score as well as many other state-of-the-art feature selection methods.

Rivaroxaban is a novel Xa inhibitor with an encouraging anti-thrombosis effect. The aim of this study is to assess whether rivaroxaban is superior to enoxaparin in venous thromboembolism prevention after knee- or hip-joint replacement.We searched for reports of randomized controlled trials on rivaroxaban versus enoxaparin in venous thromboembolism prophylaxis after knee- or hip-joint replacement in the Cochrane library, Embase, Pubmed, the Ovid database, and Chinese databases including VIP, CNKI, and CBM. Correlated data was extracted and analyzed.Eight studies involving 15246 patients were included, and all were randomized controlled studies. The methodological quality of six of the trials was generally moderate, while that of the remaining two was considered high quality. 10mg rivaroxaban daily is more effective than 40 mg/30 mg enoxaparin daily after the joint replacement in respect of the incidence of venous thromboembolism (P0.0001, RR = 0.38; P = 0.05, RR = 0.77, respectively). No significant difference between 10mg rivaroxaban daily and 40 mg/30 mg enoxaparin daily were found in major postoperative bleeding (P = 0.45, RR = 1.31;P = 0.34, RR = 1.61, respectively). With respect to other outcomes, rivaroxaban is not inferior to enoxaparin, while extended therapy with rivaroxaban (30 d) is more effective than short-term therapy (15 d) in relation to the incidence of venous thromboembolism (1.36% versus 10.13%).Rivaroxaban is superior to enoxaparin in venous thromboembolism prophylaxis after hip- or knee-joint replacement. Extended therapy--longer than 30 d--is recommended.

Measuring instrument for compensating brake master cylinder is mainly to measure the place, dimension and figure of the compensated hole and at the same time to measure the quality of machining and foundry by image for inner exterior of brake master cylinder. The measuring instrument adopt high differentiate rate image technique of CCD and using high precision drive framework to finish the measure assignment. It has some virtues, such as easy to handle, precision is high, automatous degree is good, and eliminate the influence of subjective complication. It is high-powered exactitude measuring instrument which gathered optics, mechanics, electronics and computer language. The measuring instrument for compensating brake master cylinder is made up of computer data acquire and process system, control system, CCD system, optical grating bit shift sensor and micro-machine drive system. The whole system adopt human-computer interactive measurement, when the cylinder was retracting ,we can install the workpiece to be measure to orientation fixture, and then the cylinder hold out and compaction the workpiece to be measure. To the effect that the orientation surface of workpiece to be measure can close to orientation fixture, then the step motor drive ball leading screw circumgyrate, then drive the endoscopy to move, meanwhile worm gear drive the bar circumgyrate, bases on the result of image CCD, then confirm the place of sampling point, note the information of grating ruler, save the quality information of cylinder inner exterior, by way of the member content of the date-base.

CCTV News, the first national 24-hour news channel in China, was launched in 2003. Three years later, it has become the leading 24-hour news channel in China, a milestone in the history of TV news broadcast in China. The results of this study show that the Chinese government has given much leeway to the news media at the micro level, but it has not given up its media control at the macro level. Although the news media in China have become more and more compatible with the global practices, the fundamental principle of sticking to the party line has not changed. And it will remain influential in determining what to broadcast and what not to broadcast for years to come as long as the fundamental political system does not change. ​Master of Mass Communication

A C60-polydopamine-graphene nanohybrid is prepared by a facile approach via polydopamine chemistry. The hybrid displays synergistic photodynamic and photothermal cancer cell killing effects under single light irradiation.

Frequent itemset mining (FIM) is a method for finding regularities in transaction databases. It has several application areas, such as market basket analysis, genome analysis, and drug design. Finding frequent itemsets allows further analysis to focus on a small subset of the data. For large datasets the number of frequent itemsets can also be very large, defeating their purpose. Therefore, several extensions to FIM have been studied, such as adding high-utility (or low-cost) constraints and only finding closed (or maximal) frequent itemsets. This paper presents a constraint programming based approach that combines arbitrary side constraints with closed frequent itemset mining. Our approach allows arbitrary side constraints to be expressed in a high level and declarative language which is then translated automatically for efficient solution by a SAT solver. We compare our approach with state-of-the-art algorithms via the MiningZinc system (where possible) and show significant contributions in terms of performance and applicability. Postprint

Most outlier detection algorithms are based on lazy learning or imply quadratic complexity. Both characteristics make them unsuitable for big data and stream data applications and preclude their applicability in systems that must operate autonomously. In this paper we propose a new algorithm-called SDO (Sparse Data Observers)-to estimate outlierness based on low density models of data. SDO is an eager learner; therefore, computational costs in application phases are severely reduced. We perform tests with a wide variation of synthetic datasets as well as the main datasets published in the literature for anomaly detection testing. Results show that SDO satisfactorily competes with the best ranked outlier detection alternatives. The good detection performance coupled with a low complexity makes SDO highly flexible and adaptable to stand-alone frameworks that must detect outliers fast with accuracy rates equivalent to lazy learning algorithms.

The rise of big data, especially social media data (e.g., Twitter, Facebook, Youtube), gives new opportunities to the understanding of human behavior. Consequently, novel computing methods for mining patterns in social media data are therefore desired. Through applying these approaches, it has become possible to aggregate public available data to capture triggers underlying events, detect on-going trends, and forecast future happenings. This thesis focuses on developing methods for social media analysis. Specifically, five directions are proposed here: 1) semi-supervised detection for targeted-domain events, 2) topical interaction study among multiple datasets, 3) discriminative learning about the identifications for common and distinctive topics, 4) epidemics modeling for flu forecasting with simulation via signals from social media data, 5) storyline generation for massive unorganized documents. Ph. D.