69 Result(s)
within
Zhi Li
Artificial Intelligence
-
Article
WMBAL: weighted minimum bounds for active learning
In the present study, aimed at reliably acquiring difficult samples for object detection models from massive raw data, we propose a novel difficult sample mining strategy based on active learning with Weighted...
-
Article
Effective reversible data hiding scheme for interpolated images using an improved data encoding strategy
In 2021, Lu et al. proposed a reversible data hiding (RDH) scheme for interpolated images based on a multilayer center-folding strategy with a high embedding rate and image quality. However, their data encodin...
-
Article
Optimal neighborhood kernel clustering with adaptive local kernels and block diagonal property
The purpose of multiple kernel clustering (MKC) is usually to generate an optimal kernel by fusing the information of multiple base kernels. Among the methods of generating the optimal kernel, a neighborhood k...
-
Article
Joint contrastive learning and frequency domain defense against adversarial examples
Deep neural networks (DNNs) are vulnerable to being attacked by adversarial examples, leading to DNN misclassification. Perturbations in adversarial examples usually exist in the form of noise. In this paper, ...
-
Chapter and Conference Paper
A Short Overview on Low-Density Ablators for Unmanned Vehicle
With the development of small unmanned detector, unmanned reconnaissance aircraft, reusable unmanned testing machine to a higher speed, the thermal environment with high heat flux, high enthalpy and long aerod...
-
Chapter and Conference Paper
Semantic Relation Transfer for Non-overlapped Cross-domain Recommendations
Although cross-domain recommender systems (CDRSs) are promising approaches to solving the cold-start problem, most CDRSs require overlapped users, which significantly limits their applications. To remove the o...
-
Article
Open AccessTwitter-aided decision making: a review of recent developments
Twitter is one of the largest online platforms where people exchange information. In the first few years since its emergence, researchers have been exploring ways to use Twitter data in various decision making...
-
Article
Copper price movement prediction using recurrent neural networks and ensemble averaging
The motivation for this paper is to investigate the use of three promising types of recurrent neural networks (RNNs), i.e., the long short-term memory (LSTM) network, the bidirectional LSTM (BiLSTM), and gated...
-
Article
Dynamic radiomics: A new methodology to extract quantitative time-related features from tomographic images
At present, the feature extraction method of radiology is mainly based on static tomography images at a certain time. However, the occurrence and development of disease is a dynamic process, and the informatio...
-
Article
Improving knowledge graph completion via increasing embedding interactions
Knowledge graphs usually consist of billions of triplet facts describing the real world. Although most of the existing knowledge graphs are huge in scale, they are still far from completion. As a result, varie...
-
Chapter and Conference Paper
Analysis of Key Technologies and Application Status of Smart Logistics
At present, it is difficult to continue the development of traditional logistics industry, and smart logistics is becoming an important source for the trans-formation and upgrading of the logistics industry. T...
-
Chapter and Conference Paper
Application of Carbon Composites in Unmanned Aerial Vehicles: A Review
The lightweight demand of unmanned aerial vehicles (UAVs) has promoted the continuous upgrading of its body materials. After light metal materials such as aluminum alloy and titanium alloy, carbon fiber compos...
-
Chapter and Conference Paper
Analysis of Key Supporting Technologies and Applications of Smart City Construction
Smart city is an inevitable development trend in the future, which has a strong role in promoting urban development. Promoting the construction of smart city can not only improve people’s living standards and ...
-
Chapter and Conference Paper
Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRF
Recognizing useful named entities plays a vital role in medical information processing, which helps drive the development of medical area research. Deep learning methods have achieved good results in medical n...
-
Chapter and Conference Paper
Overview of Foreign Inertial Technology Development
Inertial navigation technology can provide high-precision position and acceleration information when satellite navigation is not available, and unmanned systems tend to use inertial navigation as an auxiliary ...
-
Chapter and Conference Paper
One-Hot Coding Similarity of Vehicle Routing Particle Swarm Optimizer
Aiming at the real-time problem of vehicle routing planning, an improved particle swarm optimization method, called AVSPSO, is proposed in this paper
-
Article
Design and implementation of wearable medical monitoring system on the internet of things
The purposes are to improve the detection efficiency of medical health data and make full use of the Internet of Things technology for the rapid acquisition of human medical data. The most frequently used Andr...
-
Chapter and Conference Paper
Head Detection Method for Indoor Scene
This paper proposes a trainable fully convolutional, end-to-end crowd head detector model, which is a single convolutional network architecture, applying for target bounding box prediction and classification t...
-
Chapter and Conference Paper
Judicial Case Determination Methods Based on Event Tuple
Judges have to consider the motives of the defendant’s side and the sequence of actions of all judicial subjects in the process of sentencing. Text analysis methods based on word vectors and deep neural networ...
-
Chapter and Conference Paper
Flow Fusion Method of Electromagnetic Flowmeter Based on Fuzzy Measure
The electromagnet flowmeter have been widely used in industrial manufacture, and Low power, portable are the development direction of it. In order to reducing measurement power consumption, this research analy...
