Decades on emergency decision-making: a bibliometric analysis and literature review

Complex & Intelligent Systems, Journal Year: 2021, Volume and Issue: 7(6), P. 2819 - 2832

Published: July 27, 2021

When an emergency occurs, effective decisions should be made in a limited time to reduce the casualties and economic losses as much possible. In past decades, decision-making (EDM) has become research hotspot lot of studies have been conducted for better managing events under tight constraint. However, there is lack comprehensive bibliometric analysis literature on this topic. The objective paper provide academic community with complete EDM researches generate global picture developments, focus areas, trends field. A total 303 journal publications published between 2010 2020 were identified analyzed using VOSviewer regard cooperation network, co-citation keyword co-occurrence network. findings indicate that annual field increased rapidly since 2014. Based network analyses, most productive influential countries, institutions, researchers, their networks identified. Using analysis, landmark articles core journals area are found out. With help hotspots development domain determined. According current blind spots literature, possible directions further investigation finally suggested EDM. review results valuable information new insights both scholars practitioners grasp situation, future agenda

Language: Английский

---

Lane detection in intelligent vehicle system using optimal 2- tier deep convolutional neural network

Multimedia Tools and Applications, Journal Year: 2022, Volume and Issue: 82(5), P. 7293 - 7317

Published: Aug. 18, 2022

Language: Английский

---

Facial Mask Detection Using Depthwise Separable Convolutional Neural Network Model During COVID-19 Pandemic

Frontiers in Public Health, Journal Year: 2022, Volume and Issue: 10

Published: March 7, 2022

Deep neural networks have made tremendous strides in the categorization of facial photos last several years. Due to complexity features, enormous size picture/frame, and severe inhomogeneity image data, efficient face classification using deep convolutional remains a challenge. Therefore, as data volumes continue grow, effective mobile context utilizing advanced learning techniques is becoming increasingly important. In recent past, some Learning (DL) approaches for identify images been designed; many them use (CNNs). To address problem mask recognition images, we propose Depthwise Separable Convolution Neural Network based on MobileNet (DWS-based MobileNet). The proposed network utilizes depth-wise separable convolution layers instead 2D layers. With limited datasets, DWS-based performs exceptionally well. decreases number trainable parameters while enhancing performance by adopting lightweight network. Our technique outperformed existing state art when tested benchmark datasets. When compared Full baseline methods, results this study reveal that Convolution-based significantly improves (Acc. = 93.14, Pre. 92, recall F -score 92).

Language: Английский

---

Bio-Inspired Swarm Intelligence Optimization Algorithm-Aided Hybrid TDOA/AOA-Based Localization

Biomimetics, Journal Year: 2023, Volume and Issue: 8(2), P. 186 - 186

Published: April 29, 2023

A TDOA/AOA hybrid location algorithm based on the crow search optimized by particle swarm optimization is proposed to address challenge of solving nonlinear equation time arrival (TDOA/AOA) in non-line-of-sight (NLoS) environment. This keeps its mechanism basis enhancing performance original algorithm. To obtain a better fitness value throughout process and increase algorithm’s accuracy, function maximum likelihood estimation modified. In order speed up convergence decrease needless global without compromising population diversity, an initial solution simultaneously added starting location. Simulation findings demonstrate that suggested method outperforms other comparable algorithms, including Taylor, Chan, PSO, CPSO, basic CSA algorithms. The approach performs well terms robustness, speed, node positioning accuracy.

Language: Английский

---

A Novel Machine Learning–Based Hand Gesture Recognition Using HCI on IoT Assisted Cloud Platform

Computer Systems Science and Engineering, Journal Year: 2023, Volume and Issue: 46(2), P. 2123 - 2140

Published: Jan. 1, 2023

Machine learning is a technique for analyzing data that aids the construction of mathematical models. Because growth Internet Things (IoT) and wearable sensor devices, gesture interfaces are becoming more natural expedient human-machine interaction method. This type artificial intelligence requires minimal or no direct human intervention in decision-making predicated on ability intelligent systems to self-train detect patterns. The rise touch-free applications number deaf people have increased significance hand recognition. Potential recognition research span from online gaming surgical robotics. location hands, alignment fingers, hand-to-body posture fundamental components hierarchical emotions gestures. Linguistic gestures may be difficult distinguish nonsensical motions field In this scenario, it overcome segmentation uncertainty caused by accidental trembling. When user performs same dynamic gesture, shapes speeds each user, as well those often generated vary. A machine-learning-based Gesture Recognition Framework (ML-GRF) recognizing beginning end sequence continuous stream suggested solve problem distinguishing between meaningful scattered generation. We recommended using similarity matching-based classification approach reduce overall computing cost associated with identifying actions, we shown how an efficient feature extraction method can used thousands single information four binary digit codes. findings simulation support accuracy, precision, recognition, sensitivity, efficiency rates. Learning-based had accuracy rate 98.97%, precision 97.65%, 98.04%, sensitivity 96.99%, 95.12%.

Language: Английский

---