Forecasting the short-term metro ridership is an important issue for operation management of systems. However, it cannot be solved well by single long memory (LSTM) neural network alone irregular fluctuation caused various factors. This paper proposes a hybrid algorithm (STL-LSTM) which combines addition mode Seasonal-Trend decomposition based on Loess (STL) and LSTM to mitigate influences improve performance prediction. First, original series decomposed into three sub-series STL. Then,...

Abstract Although the flexibility of quasi−solid polymer electrolyte favors its surface conformal to electrode, interfacial damage originating from side reactions between and electrode remains dominant for battery failure. The design electrolytes compatible with both aggressive nickel−rich cathode lithium metal anode persists critical application high−voltage batteries (LMBs). Herein, a chemical/electrochemical response strategy is proposed construct simultaneously stable cathodic anodic...

Climate change has caused more frequent instances of extreme climatic events around the world, being an influential factor on occurrence wildfires in China large scale. However, impact changes climate different zones remains unclear. In present study, 26 indices were selected to analyze thereof relationship with wildfire occurrences from 2005 2018 regions China. Wildfires primarily occur south, a measurable presence north. On annual scale, southwestern show stronger correlations mean...

This brief presents an ultra-low voltage split-data-aware 10T and 8T (SDA-10T-8T) embedded static random access memory (SRAM) design for MPEG-4 video processors. Without additional complex peripheral circuits, the proposed enables a reliable operation at 0.36 V under process variation aging effect. The experimental results based on 45-nm CMOS technology show that, as compared to conventional SRAM design, our can achieve 95% reduction in active power, with no significant degradation frame...

Taxi is an indispensable mode in the urban public transportation. Although many studies have explored travel patterns of taxi trips, few combined and subway to reveal their intermodal relationship. To bridge gap, this study utilized taxi’s trajectory data investigate its relationship with subway. Considering multifaceted between operation, trips are categorized into three types, namely, subway-competing, subway-extending, subway-complementing trips. The characteristics each type reflect...

Aggressive driving is a common phenomenon with potential safety hazards. The primary aim of this study to investigate the relationship among skill, behavior and aggressiveness. A questionnaire survey consisting three subscales was conducted. Subscale 1 about skill; 2 associated daily behavior, while 3 focuses on aggressive behaviors. total 239 licensed drivers completed survey. five-factor structure extracted by factor analysis. Then, correlation analysis method used explore between these...

Accessibility has drawn extensive attention from city planners and transportation researchers for decades. With the benefits of large-scale varying time, this study aims to combine taxi global positioning system (GPS) data with a cumulative opportunity measure calculate accessibility in Beijing, China. As traffic conditions vary significantly over time space, we select four typical periods introduce grid-based method divide area into grid cells. Both GPS signals opportunities that include...

The online car-hailing system developed rapidly in recent years. This paper introduces the concept of user value and develops a machine learning framework for modeling dynamic transformation passenger system. Specifically, during engagement process, four types representing status were captured based on both consumption travel attributes. Additionally, we modeled conversion prediction throughout seamlessly integrating benefits features enhancement time series prediction. Experiments using...

Driving behavior studies based on electroencephalography (EEG) have mostly investigated the relationship between various risky driving behaviors and brain activity, while only a few discussed ordinary (drivers’ in normal situations) activity. To bridge gap, we conducted simulator experiment to collect data behavior, including acceleration, space headway, speed, time lane deviation, amplitude of steering wheel movements. At same time, amplitude, log-transformed power (LTP), spectral density...

To improve first/last mile travel services between metro stations and communities, this study modeled analyzed four kinds of feeder bus operation strategies in terms time accessibility. The analytical modeling was used to compare the times simulation experiments were accessibilities different strategies. results showed that when ratio length width area increases, number stops for fixed route transit with will increase. When demand is low, responsive separate routes has highest high, provides...

This paper presents a low power embedded SRAM memory design for MPEG-4 video processors. Considering both of the process variation and aging effect, proposed adopts an optimal high voltage spatial scaling to achieve efficiency. Simulations in FreePDK 45nm CMOS technology show that our technique can 85%, 90%, 79% reduction write power, read leakage current, respectively, with graceful degradation (~5.6%) quality, as compared conventional design.

In recent years, customized bus as an innovative mode has become important choice of public transport. It helps to change transportation structure and alleviate traffic congestion, which great efficiency for energy conservation emission reduction. However, it is relatively simple cannot be well integrated into the intelligent system. Therefore, this paper discusses dispatching strategies on basis dynamic information. Finally, example given confirm effectiveness these strategies. We...

The superpixel, as an important pre‐processing technique, has been successfully used in many vision applications. Introduced is a fast superpixel method called iterative edge refinement (IER). image was first initialised regular grids, and then concentration on unstable pixels relabelling them iteratively so pixels, are around the moving boundary. It found that decrease rapidly during process, which results high speed‐up. Experimental Berkeley BSDS500 dataset show IER achieves segmentation...

As industry moves towards many core chips, conventional bus and crossbar interconnections often struggle to meet the multi-core communication requirement. Network on Chip (NoC) has been proposed replace global alleviate this problem. In NoC, routers are used exchange data between IPs. So router performance directly impacts efficiency of entire system. The key components a modern include Route Computation (RC), Virtual-channel Allocation (VA), Switch (SA) Traversal (ST). paper, we present new...

Abstract Extreme weather events, such as typhoon and hurricane, have characteristics of high uncertainty, large destructiveness, extensiveness, which threat the daily life cause apparent perturbations to human mobility. In order investigate perturbation on mobility, this study collects metro transaction data before during a event in Fuzhou, China, conduct analyses. The ridership is innovatively compared at system, station origin-destination level. Besides, it novelty examine travel time...

The normal studies on air traffic departure scheduling problem (DSP) mainly deal with an independent airport in which the is not affected by surrounded airports, which, however, a consistent case. In reality, there still exist cases where several commercial airports are closely located and one of them possesses higher priority. During peak hours, activities lower-priority usually required to give way those higher-priority airport. These giving-way requirements can inflict set changes...