Nanjing University of Information Science and Technology

About: Nanjing University of Information Science and Technology is a education organization based out in Nanjing, China. It is known for research contribution in the topics: Precipitation & Aerosol. The organization has 14129 authors who have published 17985 publications receiving 267578 citations. The organization is also known as: Nan Xin Da.

Attention-Based Convolutional Neural Network for Weakly Labeled Human Activities’ Recognition With Wearable Sensors

Abstract: Traditional methods of human activity recognition usually require a large amount of strictly labeled data for training classifiers. However, it is hard for one to keep a fixed activity when collecting desired activity data by wearable sensors, and the weakly labeled data inevitably occurs in the process of data collection. For now, human activity recognition methods have seldom been researched according to weakly labeled data, which deserves deep investigation. In this paper, we proposed a novel attention-based human activity recognition method to process the weakly labeled activity data. The traditional convolutional neural network (CNN)-based human activity recognition is modified by attention mechanism, which computes the compatibility between the global features extracted at the final fully connected layers and the local features extracted at a given convolutional layer. The attention-based CNN architecture can amplify the salient activity information and suppress the irrelevant and potentially confusing information by weighing up their compatibility. Our methods are compared with two state-of-the-art methods, CNN and DeepConvLSTM. The experimental results show that our model is comparably well on the traditional UCI HAR dataset and outperforms them on the weakly labeled dataset in accuracy. Our method can greatly facilitate the process of sensor data annotation and makes data collection easier.

Vehicle Detection in High-Resolution Aerial Images via Sparse Representation and Superpixels

Abstract: This paper presents a study of vehicle detection from high-resolution aerial images. In this paper, a superpixel segmentation method designed for aerial images is proposed to control the segmentation with a low breakage rate. To make the training and detection more efficient, we extract meaningful patches based on the centers of the segmented superpixels. After the segmentation, through a training sample selection iteration strategy that is based on the sparse representation, we obtain a complete and small training subset from the original entire training set. With the selected training subset, we obtain a dictionary with high discrimination ability for vehicle detection. During training and detection, the grids of histogram of oriented gradient descriptor are used for feature extraction. To further improve the training and detection efficiency, a method is proposed for the defined main direction estimation of each patch. By rotating each patch to its main direction, we give the patches consistent directions. Comprehensive analyses and comparisons on two data sets illustrate the satisfactory performance of the proposed algorithm.

Pricing decisions in closed-loop supply chains with marketing effort and fairness concerns

Abstract: We investigate closed-loop supply chains (CLSCs) under four reverse channel structures where a central planner, a manufacturer (M), a retailer (R) or a third party (T), respectively, serves as the ...

Comprehensive Pattern of Deep Convective Systems over the Tibetan Plateau–South Asian Monsoon Region Based on TRMM Data

Abstract: Diurnal and seasonal variation, intensity, and structure of deep convective systems (DCSs; with 20-dBZ echo tops exceeding 14 km) over the Tibetan Plateau–South Asian monsoon region from the Tibetan Plateau (TP) to the ocean are investigated using 14 yr of Tropical Rainfall Measuring Mission (TRMM) data. Four unique regions characterized by different orography are selected for comparison, including the TP, the southern Himalayan front (SHF), the South Asian subcontinent (SAS), and the ocean. DCSs and intense DCSs (IDCSs; with 40-dBZ echo tops exceeding 10 km) occur more frequently over the continent than over the ocean. About 23% of total DCSs develop into IDCSs in the SHF, followed by the TP (21%) and the SAS (15%), with the least over the ocean (2%). The average 20-dBZ echo-top height of IDCSs exceeds 16 km and 9% of them even exceed 18 km. DCSs and IDCSs are the most frequent over the SHF, especially in the westernmost SHF, where the intensity—in terms of strong radar echo-top (viz., 40 dBZ) he...

Introduction to Suomi national polar‐orbiting partnership advanced technology microwave sounder for numerical weather prediction and tropical cyclone applications

Abstract: [1] The Suomi National Polar-orbiting Partnership (NPP) satellite was successfully launched on 28 October 2011. On board the Suomi NPP, the Advanced Technology Microwave Sounder (ATMS) is a cross-track scanning instrument and has 22 channels at frequencies ranging from 23 to 183 GHz which allows for probing the atmospheric temperature and moisture under clear and cloudy conditions. ATMS inherited most of the sounding channels from its predecessors: Advanced Microwave Sounding Unit-A (AMSU-A) and Microwave Humidity Sounder (MHS) onboard NOAA and MetOp satellites. However, ATMS has a wider scan swath and has no gaps between two consecutive orbits. It includes one new temperature sounding channel and two water vapor sounding channels and provides more details of thermal structures in lower troposphere, especially for the storm conditions such as tropical cyclones. While ATMS temperature sounding channels have shorter integration time and therefore higher noise than AMSU-A, the ATMS observations from their overlapping field of views are resampled to produce AMSU-A-like measurements.