scholarly journals Re-Identification in Urban Scenarios: A Review of Tools and Methods

2021 ◽  
Vol 11 (22) ◽  
pp. 10809
Author(s):  
Hugo S. Oliveira ◽  
José J. M. Machado ◽  
João Manuel R. S. Tavares
Keyword(s):  
Neural Networks ◽  
High Performance ◽  
Object Identification ◽  
Future Research ◽  
Great Effort ◽  
Data Limitations ◽  
Video Feed ◽  
Adversarial Training ◽  
Future Research Directions ◽  
Model Training

With the widespread use of surveillance image cameras and enhanced awareness of public security, objects, and persons Re-Identification (ReID), the task of recognizing objects in non-overlapping camera networks has attracted particular attention in computer vision and pattern recognition communities. Given an image or video of an object-of-interest (query), object identification aims to identify the object from images or video feed taken from different cameras. After many years of great effort, object ReID remains a notably challenging task. The main reason is that an object’s appearance may dramatically change across camera views due to significant variations in illumination, poses or viewpoints, or even cluttered backgrounds. With the advent of Deep Neural Networks (DNN), there have been many proposals for different network architectures achieving high-performance levels. With the aim of identifying the most promising methods for ReID for future robust implementations, a review study is presented, mainly focusing on the person and multi-object ReID and auxiliary methods for image enhancement. Such methods are crucial for robust object ReID, while highlighting limitations of the identified methods. This is a very active field, evidenced by the dates of the publications found. However, most works use data from very different datasets and genres, which presents an obstacle to wide generalized DNN model training and usage. Although the model’s performance has achieved satisfactory results on particular datasets, a particular trend was observed in the use of 3D Convolutional Neural Networks (CNN), attention mechanisms to capture object-relevant features, and generative adversarial training to overcome data limitations. However, there is still room for improvement, namely in using images from urban scenarios among anonymized images to comply with public privacy legislation. The main challenges that remain in the ReID field, and prospects for future research directions towards ReID in dense urban scenarios, are also discussed.

MetaLearning with Graph Neural Networks

2021 ◽  
Vol 23 (2) ◽  
pp. 13-22
Author(s):  
Debmalya Mandal ◽  
Sourav Medya ◽  
Brian Uzzi ◽  
Charu Aggarwal
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Future Research ◽  
Open Problems ◽  
Research Directions ◽  
Graph Problems ◽  
Meta Learning ◽  
Comprehensive Survey ◽  
Future Research Directions ◽  
Graph Neural Networks

Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems. However, GNNs on such applications are limited when there are few available samples. Meta-learning has been an important framework to address the lack of samples in machine learning, and in recent years, researchers have started to apply meta-learning to GNNs. In this work, we provide a comprehensive survey of different metalearning approaches involving GNNs on various graph problems showing the power of using these two approaches together. We categorize the literature based on proposed architectures, shared representations, and applications. Finally, we discuss several exciting future research directions and open problems.

scholarly journals Graphene-Based Thermal Interface Materials: An Application-Oriented Perspective on Architecture Design

Polymers ◽  
2018 ◽  
Vol 10 (11) ◽  
pp. 1201 ◽  
Author(s):  
Le Lv ◽  
Wen Dai ◽  
Aijun Li ◽  
Cheng-Te Lin
Keyword(s):  
Thermal Conductivity ◽  
High Performance ◽  
Electronic Devices ◽  
Point Of View ◽  
Future Research ◽  
Thermal Interface Materials ◽  
Research Directions ◽  
Thermal Interface ◽  
Future Research Directions ◽  
Interface Materials

With the increasing power density of electrical and electronic devices, there has been an urgent demand for the development of thermal interface materials (TIMs) with high through-plane thermal conductivity for handling the issue of thermal management. Graphene exhibited significant potential for the development of TIMs, due to its ultra-high intrinsic thermal conductivity. In this perspective, we introduce three state-of-the-art graphene-based TIMs, including dispersed graphene/polymers, graphene framework/polymers and inorganic graphene-based monoliths. The advantages and limitations of them were discussed from an application point of view. In addition, possible strategies and future research directions in the development of high-performance graphene-based TIMs are also discussed.

Managing Human Resources in Family Businesses

2014 ◽  
pp. 96-112 ◽  
Author(s):  
Santiago Gutiérrez-Broncano ◽  
Mercedes Rubio-Andrés ◽  
Pedro Jiménez Estévez
Keyword(s):  
Human Capital ◽  
Human Resources ◽  
High Performance ◽  
Negative Impact ◽  
Business Owners ◽  
Family Businesses ◽  
Future Research ◽  
Research Directions ◽  
Positive Effects ◽  
Future Research Directions

Although a lot of research has been carried out in the field of family businesses in recent years, not much of it has focused on human resource management. After compiling the major studies, both negative aspects (e.g. nepotism) and positive ones (e.g. employee commitment) have been identified. Therefore, the authors propose high-performance human resources practices to reduce the negative impact of family in business and boost the positive effects, increase their human capital, and achieve a competitive advantage in this field. Finally, the authors provide key insights for practitioners, family business owners, and managers, and they propose future research directions.

Artificial Intelligence Review

2019 ◽  
pp. 23-39
Author(s):  
Amal Kilani ◽  
Ahmed Ben Hamida ◽  
Habib Hamam
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Fuzzy Logic ◽  
Intelligent System ◽  
Route Planning ◽  
Turing Test ◽  
Future Research ◽  
Interaction Data ◽  
Research Directions ◽  
Future Research Directions

In this chapter, the authors present a profound literature review of artificial intelligence (AI). After defining it, they briefly cover its history and enumerate its principal fields of application. They name, for example, information system, commerce, image processing, human-computer interaction, data compression, robotics, route planning, etc. Moreover, the test that defines an artificially intelligent system, called the Turing test, is also defined and detailed. Afterwards, the authors describe some AI tools such as fuzzy logic, genetic algorithms, and swarm intelligence. Special attention will be given to neural networks and fuzzy logic. The authors also present the future research directions and ethics.

A review on the mechanical properties of textile structural composite T-beams

2019 ◽  
Vol 90 (5-6) ◽  
pp. 710-727 ◽  
Author(s):  
Yiwei Ouyang ◽  
Xianyan Wu
Keyword(s):  
Mechanical Properties ◽  
High Performance ◽  
Raw Materials ◽  
Research Progress ◽  
Future Research ◽  
Research Directions ◽  
Structural Composite ◽  
Delamination Resistance ◽  
Application Potential ◽  
Future Research Directions

In order to review the most effective ways to improve the mechanical properties of composite T-beams and further increase their application potential, research progress on the mechanical properties of textile structural composite T-beams was summarized based on two-dimensional (2-D) ply structure composite T-beams, delamination resistance enhanced 2-D ply structure T-beams, and three-dimensional (3-D) textile structural composite T-beams; future research directions for composite T-beams were also considered. From existing literature, the research status and application bottlenecks of 2-D ply structure composite T-beams and T-beams with enhanced delamination resistance performance were described, as were the specific classification, research progress, and mechanical properties of 3-D textile structural composite T-beams. In addition, the superior mechanical properties of 3-D braided textile structural composite T-beams, specifically their application potential based on excellent delamination resistance capacity, were highlighted. Future research directions for composite T-beams, that is, the applications of high-performance raw materials, locally enhanced design, structural blending enhancement, functionality, and intelligence are presented in this review.

A STATE-OF-THE-ART REVIEW OF NEURAL NETWORKS FOR PERMEABILITY PREDICTION

2000 ◽  
Vol 40 (1) ◽  
pp. 341 ◽  
Author(s):  
A.G. Bruce ◽  
P.M. Wong ◽  
Y. Zhang ◽  
H.A. Salisch ◽  
C.C. Fung ◽  
...  
Keyword(s):  
Neural Networks ◽  
Oil And Gas ◽  
State Of The Art ◽  
Future Research ◽  
Good Prediction ◽  
New Era ◽  
Multiple Networks ◽  
Permeability Prediction ◽  
Future Research Directions ◽  
Oil And Gas Companies

This paper reviews the state-of-the-art of neural networks for permeability prediction from well logs. Good prediction of permeability is necessary for reservoir characterisation and is important for improving the reliability of the asset value of oil and gas companies. Two particular models, known as backpropagation and radial basis function networks, have been applied. From previous work, six innovative aspects are identified:choice of inputs;outlier detection and removal;data splitting;scaling;multiple networks; andprediction confidence.We have also provided a list of future research directions in the area, reflecting the current deficiencies of the use of neural networks. The topics are:the quality and quantity of core data;the maximum use of the logs;the compatibility of scales;the use of soft computing; andthe management of prediction confidence.The current applications are certainly the beginning of a new era. It is important for petrophysicists to take advantage of the advanced technologies.

FORECASTING FOREIGN EXCHANGE RATES WITH ARTIFICIAL NEURAL NETWORKS: A REVIEW

2004 ◽  
Vol 03 (01) ◽  
pp. 145-165 ◽  
Author(s):  
WEI HUANG ◽  
K. K. LAI ◽  
Y. NAKAMORI ◽  
SHOUYANG WANG
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Exchange Rates ◽  
Network Architecture ◽  
Future Research ◽  
Promising Alternative ◽  
Practical Applications ◽  
Future Research Directions ◽  
Artificial Neural ◽  
Input Variables

Forecasting exchange rates is an important financial problem that is receiving increasing attention especially because of its difficulty and practical applications. Artificial neural networks (ANNs) have been widely used as a promising alternative approach for a forecasting task because of several distinguished features. Research efforts on ANNs for forecasting exchange rates are considerable. In this paper, we attempt to provide a survey of research in this area. Several design factors significantly impact the accuracy of neural network forecasts. These factors include the selection of input variables, preparing data, and network architecture. There is no consensus about the factors. In different cases, various decisions have their own effectiveness. We also describe the integration of ANNs with other methods and report the comparison between performances of ANNs and those of other forecasting methods, and finding mixed results. Finally, the future research directions in this area are discussed.

scholarly journals Graph Neural Networks: Taxonomy, Advances, and Trends

2022 ◽  
Vol 13 (1) ◽  
pp. 1-54
Author(s):  
Yu Zhou ◽  
Haixia Zheng ◽  
Xin Huang ◽  
Shufeng Hao ◽  
Dengao Li ◽  
...  
Keyword(s):  
Neural Networks ◽  
Real World ◽  
Research Community ◽  
Future Research ◽  
Research Directions ◽  
Comprehensive Review ◽  
Future Research Directions ◽  
Graph Neural Networks ◽  
Low Dimensional

Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks. Up to now, there have been several surveys on this topic. However, they usually lay emphasis on different angles so that the readers cannot see a panorama of the graph neural networks. This survey aims to overcome this limitation and provide a systematic and comprehensive review on the graph neural networks. First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 327 relevant literatures to show the panorama of the graph neural networks. All of them are classified into the corresponding categories. In order to drive the graph neural networks into a new stage, we summarize four future research directions so as to overcome the challenges faced. It is expected that more and more scholars can understand and exploit the graph neural networks and use them in their research community.

scholarly journals Single-photon sources with quantum dots in III–V nanowires

Nanophotonics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 747-769 ◽  
Author(s):  
Henrik Mäntynen ◽  
Nicklas Anttu ◽  
Zhipei Sun ◽  
Harri Lipsanen
Keyword(s):  
Quantum Dots ◽  
High Performance ◽  
Single Photon ◽  
Future Research ◽  
Research Directions ◽  
Photon Sources ◽  
Future Research Directions ◽  
And Performance ◽  
Quantum Photonics ◽  
System Designs

AbstractSingle-photon sources are one of the key components in quantum photonics applications. These sources ideally emit a single photon at a time, are highly efficient, and could be integrated in photonic circuits for complex quantum system designs. Various platforms to realize such sources have been actively studied, among which semiconductor quantum dots have been found to be particularly attractive. Furthermore, quantum dots embedded in bottom-up-grown III–V compound semiconductor nanowires have been found to exhibit relatively high performance as well as beneficial flexibility in fabrication and integration. Here, we review fabrication and performance of these nanowire-based quantum sources and compare them to quantum dots in top-down-fabricated designs. The state of the art in single-photon sources with quantum dots in nanowires is discussed. We also present current challenges and possible future research directions.

scholarly journals Progress in ZnO Nanosensors

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5502
Author(s):  
Miaoling Que ◽  
Chong Lin ◽  
Jiawei Sun ◽  
Lixiang Chen ◽  
Xiaohong Sun ◽  
...  
Keyword(s):  
High Performance ◽  
Room Temperature ◽  
Wide Bandgap ◽  
Synthetic Methods ◽  
Superior Performance ◽  
Future Research ◽  
Electronic Systems ◽  
Research Directions ◽  
Photoelectric Sensor ◽  
Future Research Directions

Developing various nanosensors with superior performance for accurate and sensitive detection of some physical signals is essential for advances in electronic systems. Zinc oxide (ZnO) is a unique semiconductor material with wide bandgap (3.37 eV) and high exciton binding energy (60 meV) at room temperature. ZnO nanostructures have been investigated extensively for possible use as high-performance sensors, due to their excellent optical, piezoelectric and electrochemical properties, as well as the large surface area. In this review, we primarily introduce the morphology and major synthetic methods of ZnO nanomaterials, with a brief discussion of the advantages and weaknesses of each method. Then, we mainly focus on the recent progress in ZnO nanosensors according to the functional classification, including pressure sensor, gas sensor, photoelectric sensor, biosensor and temperature sensor. We provide a comprehensive analysis of the research status and constraints for the development of ZnO nanosensor in each category. Finally, the challenges and future research directions of nanosensors based on ZnO are prospected and summarized. It is of profound significance to research ZnO nanosensors in depth, which will promote the development of artificial intelligence, medical and health, as well as industrial, production.

Sign in / Sign up

Export Citation Format

Share Document