第一篇论文创新点寻找 - 预参考文献
参考论文
| 期刊、年份 | 标题 | 作者 | 说明 |
|---|---|---|---|
| 2019 - ITSC | Reinforcement Learning with Explainability for Traffic Signal Control | Sanjay Chawla | |
| 2019 - Artificial Intelligence | Ridesharing car detection by transfer learning | Qiang Yang | |
| 2020 - AAAI | Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development | 刘伟 | |
| 2019 - ITSC | Spatial Analysis of Taxi Speeding Event Using GPS Trajectory Data | Chuanyun Fu | |
| 2020 - MDPI Sensors | Forecasting Pedestrian Movements Using Recurrent Neural Networks: An Application of Crowd Monitoring Data. | Guangxing Wang | |
| 2020 - UbiComp | CityGuard: Citywide Fire Risk Forecasting Using A MachineLearning Approach | Bin Guo | |
| 2019 - CIKM | Matrix Factorization for Spatio-Temporal Neural Networks with Applications to Urban Flow Prediction. | Zheyi Pan | |
| 2019 - CIKM | CityTraffic: Modeling Citywide Traffic via Neural Memorization and Generalization Approach | Xiuwen Yi | |
| 2019 - KDD | Urban Traffic Prediction from Spatio-Temporal Data using Deep Meta Learning | Zheyi Pan | |
| 2019 - IEEE TKDE | Interactive Bike Lane Planning using Sharing Bikes’ Trajectories | Tianfu He | |
| 2019 - IEEE TKDE | Citywide Bike Usage Prediction in a Bike-Sharing System | Yexin Li | |
| 2019 - IEEE TKDE | Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning | Junbo Zhang | |
| 2018 - CIKM | DeepCrime: Attentive Hierarchical Recurrent Networks for Crime Prediction | Chao Huang | |
| 2020 - UbiComp | Dynamic Public Resource Allocation based on Human Mobility Prediction | Yu Zheng | |
| 2020 - WWW | What is the Human Mobility in a City? Transfer Mobility Knowledge Across Cities | Yu Zheng | |
关注学者
| 姓名 | 身份 | 说明 |
|---|---|---|
| 郑宇 链接二 |
京东智能城市研究院院长 | 大量论文值得参考 |
| 杨强 | 香港科技大学计科系主任 | 少量论文可参考 |
| 李瑞远 | 京东城市JUST团队负责人 京东智能城市研究院研究员 |
大量论文值得参考 |
创新点
京东智能城市研究所
从京东智能城市研究所看创新突破口
| 创新点 | 源头 | 说明 |
|---|---|---|
| 交通流量预测 | ||
| 公交路线规划 | ||
| 智能选址 | ||
| 人流量预测 | ||
| 出租车司机乘客智能匹配 | ||
| 地铁客流预测 | ||
| 公交客流估计 | ||
| 公交到站时间预测 | ||
| 公交地铁线路规划 | ||
| 自行车道划分 | ||
| 交通态势判断 | ||
| 交通信号灯配时优化 | ||
| 共享单车需求预测/智能调度 | ||
| 空气质量分析预测 | ||
| 城市噪声分析预测 | ||
| 环境污染风险预测 | ||
| 公共资源选址（充电桩、加油站、广告牌） | ||
| IOT站点选址（空气，水质，土壤） | ||
| 公共服务站点规划（警局、救护车） | ||
| 商业选址（商场，酒店，饭店） | ||
| 不合理道路检测 | ||
| 案发趋势预测 | ||
| 共享单车交通情况预测 | ||
| 通过人流检测城市黑洞 | ||
| 交通异常检测与诊断 | ||
数据集
| 数据集名称 | 链接 | 简介 | 看法 |
|---|---|---|---|
| T-Drive Taxi Trajectroies | 链接 | This is a sample of T-Drive trajectory dataset that contains a one-week trajectories of 10,357 taxis. The total number of points in this dataset is about 15 million and the total distance of the trajectories reaches 9 million kilometers. | |
| Geolife GPS trajectory dataset | 链接 | This GPS trajectory dataset was collected in (Microsoft Research Asia) Geolife project by 178 users in a period of over four years (from April 2007 to October 2011). A GPS trajectory of this dataset is represented by a sequence of time-stamped points, each of which contains the information of latitude, longitude and altitude. This dataset contains 17,621 trajectories with a total distance of 1,251,654 kilometers and a total duration of 48,203 hours. These trajectories were recorded by different GPS loggers and GPS-phones, and have a variety of sampling rates. 91 percent of the trajectories are logged in a dense representation, e.g. every 1~5 seconds or every 5~10 meters per point. | |
| Taxi request simulator | 链接 | This simulator can generate people’s request for taxicabs on different road segments, using the knowledge mined from a large-scale real taxi trajectories. Each query consists of an origin, destination, and a timestamp. | |
| Check-in data from Foursquare | 链接 | Each check-in includes a venue ID, the category of the venue, a timestamp, and a user ID. | |
| Air quality data of Beijing and Shanghai | 链接 | The data set is comprised of one-year (2013-2-8 to 2014-2-8) air quality data from air quality monitoring stations in Beijing and Shanghai. | |
| Traffic and geographical features of each road segments | 链接 | The package is comprised of six parts of data that were extracted from the GPS trajectories of taxicabs, road networks, POIs of Beijing, and video clips recording real traffic on roads. | |
| Noise complaint data and geographical data of NYC | 链接 | This package is comprised of three parts of data. 1) tensors representing the 311 complaints on urban noise; 2) geographical feature of each region in NYC; 3) Real noise levels of 36 locations in NYC. Please cite the following two papers when using the dataset. | |
| Air quality data, meteorological data and weather forecasts of 43 cities in China | 链接 | The dataset was used for air quality forecast and real-time inference. It also can be used for test cross-domain data fusion methods. | |
| Bike Sharing data coupled with weather conditions | 链接 | The dataset contains bike usage (denoted by the number of check-outs and check-ins) at each bike sharing station in NYC and Chicago. The weather condition data during the period, in which the bike sharing data is collected, is also shared. | |
| Three datasets for detecting collective anomalies | 链接 | This dataset is comprised of five parts of data, named Taxi Trip Data, Bike sharing data, 311 data, POIs and road network data of NYC. | |
| Inflow and outflow of crowds in each and every region of a city | 链接 | This data set consists of two types of crowd flows. One is a five-year taxis flow in Beijing. The other is bike usage in a bike sharing system in New York City. A research on predicting flow of crowds have been conducted based on this dataset. Please cite the following paper when using the dataset. (code)(data)(system) | |
其他与本论文无关的想法
私は思います
数据集：Peking Taxi 5 days GPS Trajectories (T-Drive Taxi Trajectroies)
该数据集包括：Taxi id, datetime, latitude, lontitude
两次采样间，时间、距离不定。其间隔，时间大多在5分钟之内，距离大多在3000内。
平均采样间隔：时间（177秒，约合3min），距离（623m）
相关领域及现有论文：
-
Spatial Analysis of Taxi Speeding Event Using GPS Trajectory Data：分析空间特征对出租车超速的影响，实验证明grid内道路数量、平均道路限制速度对超速有显著影响。（2019 IEEE Intelligent Transportation Systems Conference (ITSC)）
-
Matrix Factorization for Spatio-Temporal Neural Networks with Applications to Urban Flow Prediction：基于矩阵分解的方式，对城市(人/车)流量进行预测。其相对于其他模型的优势在于考虑了地区特异性。 (Conference on Information and Knowledge Management (CIKM) 2019 - CCF B类会议) ← 可作文章
-
Forecasting Pedestrian Movements Using Recurrent Neural Networks: An Application of Crowd Monitoring Data. (2020 - MDPI Sensors) 水文、参考意义不大
-
CityTraffic: Modeling Citywide Traffic via Neural Memorization and Generalization Approach (2019 CIKM) ← 跟上面似乎场景类似，可以参考
-
Urban Traffic Prediction from Spatio-Temporal Data using Deep Meta Learning (2019 - KDD - 数据挖掘top1会议) 同上
-
Interactive Bike Lane Planning using Sharing Bikes’ Trajectories (2019 IEEE TKDE - CCF A类会议) 用自行车的数据，换汤不换药
-
Citywide Bike Usage Prediction in a Bike-Sharing System (2019 IEEE TKDE) 同上，也可参考
-
Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning (2019 IEEE TKDE) 同上
-
DeepCrime: Attentive Hierarchical Recurrent Networks for Crime Prediction (2018 CIKM - CCF B类会议) 有点老了，但同样分析犯罪数据，是否可以换成交通，毕竟还有个搞火灾预测的在2020年发了
-
Dynamic Public Resource Allocation based on Human Mobility Prediction (2020 UbiComp) 智能选址京东还没大规模做，现在借助大量数据集是否有实现的可能性
-
What is the Human Mobility in a City? Transfer Mobility Knowledge Across Cities (2020 WWW - CCF A类会议) 到2020还在做人类流动性分析，只是技术变了，那么透过流动性分析选址呢
前面无所列论文领域
- 司乘匹配：有预测出租车目的地的，也有预测出租车需求的，那么为何不合起来做司乘匹配呢？核心也在出租车目的地预测。
- 公交路线规划：根据出租车路线，推荐公交线路 - 借助根据GPS轨迹绘制地图的思想，可以获得哪些地区出租车走得特别多
- 自行车路线规划 - 同上，自行车走得比较多的路线 - 同样有共享单车需求预测
- 交通态势判断：车流预测的一种
- 选址！ - 加油站、广告牌、充电桩、监测点、救护车、警察局、商场、酒店、饭店
- 城市区域功能划分 - 不限类别的聚类，倒是可以考虑加入时间维度，人群聚集分析
想法
- 预测交通流，从而对交通异常进行检测 - 至少交通流发生了异常，从中考虑对城市区域功能进行划分