Search

Summary: In this paper, we developed an object detection and identification framework to bolster public safety. Before developing the proposed framework, several existing frameworks were analyzed to bolster public safety. The other models were carefully observed for their strengths and weaknesses based on the machine learning and deep learning algorithms they operate on. All these were kept in mind during the development of the proposed model. The proposed framework consists of an unmanned aerial vehicle (UAV) utilized for data collection that constantly monitors and captures the images of the designated areas. A convolutional neural network (CNN) model is developed to recognize a threat and identifies various handheld objects, such as guns and knives, which facilitate criminals to commit crimes. The proposed CNN model comprises 16 layers with input, convolutional, dense, max‐pool, and flattened layers of different dimensions. For that, a benchmarked dataset, that is, small objects handled similarly to a weapon (SOHAs), a weapon detection dataset is used. It comprises six classes of 8945 images, with 5947 used for training, 1699 used for testing, and 849 used for validation. Once the CNN model accomplishes the object identification and classification, that is, the person is criminal or non‐criminal, the criminal is forwarded to various law enforcement agencies and non‐criminal data are again forwarded to the CNN model for improvising its accuracy rate. As a result, the proposed CNN model outperforms several pre‐trained models with an accuracy of 0.8352 and a validation accuracy of 0.7758. In addition, the proposed model gives a minimal loss of 0.83 with a validation loss of 0.97. The proposed framework decreases the burden on crime‐fighting agencies and increases the accuracy of crime detection. Additionally, it ensures fairness and operates at a meager computational cost compared to similar pre‐trained models. [ABSTRACT FROM AUTHOR]

Summary: In this article, we exploit the huge advantages of full‐duplex (FD) transmission, nonorthogonal multiple access (NOMA) technique, unmanned aerial vehicle (UAV), and millimeter‐wave (mmWave) communications in an Internet of things (IoT) sensor network. Specifically, the UAV operates as a FD amplify‐and‐forward (AF) relay to aid communications between an IoT sensor and multiple NOMA users. Moreover, the FD‐UAV (FDU) adopts both fixed and variable gains. We obtain exact expressions of outage probability (OP) and throughput of IoT‐FDU‐NOMA‐mmWave network with fixed and variable gains at FDU over Nakagami‐m$$ m $$ fading channels. Numerical illustrations clearly show that the OP and throughput performance of the IoT‐FDU‐NOMA‐mmWave network with variable gain are considerably higher than those with fixed gain. Since mmWave bands are used, the OP and throughput of the IoT‐FDU‐NOMA‐mmWave network are greatly affected by carrier frequency and communication distances. Consequently, when the carrier frequency or/and the distances between the IoT sensor and the users increase, the transmit power of the IoT sensor and the FDU should be increased to maintain the network performance. On the other hand, the effects of residual loop interference (LI) induced by FD transmission are remarkable. Thus, more efforts to reduce the residual LI power have to be continuously performed. Moreover, the specific impacts of the key parameters such as fading order m$$ m $$, the positions of the FDU, and data rates are clarified. More importantly, in practice, according to the fixed gain or the variable gain that is used, we can locate the position of FDU to achieve the best performance for the IoT‐FDU‐NOMA‐mmWave network. [ABSTRACT FROM AUTHOR]

Hyperspectral imagery from an Unmanned Aerial Vehicle (UAV) has been used to predict soil organic carbon (SOC) content. This study compared UAV hyperspectral imagery with Sentinel-2A multispectral imagery and soil spectra in the laboratory to predict the SOC content in Suaeda salsa (S. salsa) coastal wetland. Characteristic variables were determined through correlation analysis comparing observed SOC with constructed spectral indices of SOC, index variables, and spectral bands. Predict Models of SOC were constructed by multilayer perceptron (MLP), the prediction accuracy was evaluated and the spatial maps of SOC were produced. The results showed that estimating SOC using UAV, Sentinel imagery, and laboratory spectra has great potential when using MLP algorithm. The SOC content can be accurately predicted by the laboratory spectra without spatial map. The accuracy of SOC estimation was better when based on Sentinel-2A imagery than UAV imagery, with the model determination coefficients (R2) of 0.838 and 0.638, the root mean square error (RMSE) of 0.398 and 0.596 g kg−1, ratio of performance to deviations (RPD) of 2.485 and 1.660, and bias of − 0.028 and 0.085 g kg−1, respectively. The SOC estimation model using Sentinel-2A imagery demonstrated better stability than that using UAV imagery, with the mean uncertainty standard deviations (SD) of 0.226 and 0.291 g kg−1, respectively. The spatial SOC maps generated from both UAV and Sentinel-2A imagery presented more subtle variation information when compared with the spatial interpolation results. Although the prediction accuracy of SOC from UAV was lower than that from Sentinel-2A, UAV imagery could disclose more fine distribution information of SOC at the local level. The UAV imagery can be used to estimate SOC in coastal wetlands but with a higher cost than freely available Sentinel images. We recommend using sentinel imagery to predict SOC at regional, national, or even global levels. [ABSTRACT FROM AUTHOR]

Sweep coverage (SC) is an NP-hard problem that needs to be solved with a small number of mobile sensors (sensor nodes) to monitor or observe targets in wireless sensor networks (WSNs) over a period of time. One of the proposed solutions to optimize the lifetime of WSNs is to monitor targets in the area of interest (AoI) by path planning of the sensor nodes. Considering the applications of unmanned aerial vehicles (UAVs) in military and civilian fields, in this study, we model multiple UAVs to solve the SC problem based on non-uniformly distributed targets in the AoI. In this modeling, we conduct effective coverage path planning for UAVs by performing an SC task for targets in the AoI with multiple asynchronously flying UAVs. To this end, we propose a new approach, which we call Weighted Targets Sweep Coverage, based on the metaheuristic Crow Search Algorithm and the heuristic Greedy algorithm. In our proposed approach, we define a new objective function by considering the UAV task completion time and the AoI coverage rate as metrics. In the Monte Carlo simulations that we perform to measure the performance, we run 5 different scenarios considering the number of targets defined for AoI and the alpha parameters defined for the objective function. The results of the scenario studies show that the proposed approach outperforms the other algorithms by up to 21% and 50% in terms of UAV task completion time and AoI coverage rate, respectively. [ABSTRACT FROM AUTHOR]