RF-Enabled Deep-Learning-Assisted Drone Detection and Identification: An End-to-End Approach.

The security and privacy risks posed by unmanned aerial vehicles (UAVs) have become a significant cause of concern in today's society. Due to technological advancement, these devices are becoming progressively inexpensive, which makes them convenient for many different applications. The massive number of UAVs is making it difficult to manage and monitor them in restricted areas. In addition, other signals using the same frequency range make it more challenging to identify UAV signals. In these circumstances, an intelligent system to detect and identify UAVs is a necessity. Most of the previous studies on UAV identification relied on various feature-extraction techniques, which are computationally expensive. Therefore, this article proposes an end-to-end deep-learning-based model to detect and identify UAVs based on their radio frequency (RF) signature. Unlike existing studies, multiscale feature-extraction techniques without manual intervention are utilized to extract enriched features that assist the model in achieving good generalization capability of the signal and making decisions with lower computational time. Additionally, residual blocks are utilized to learn complex representations, as well as to overcome vanishing gradient problems during training. The detection and identification tasks are performed in the presence of Bluetooth and WIFI signals, which are two signals from the same frequency band. For the identification task, the model is evaluated for specific devices, as well as for the signature of the particular manufacturers. The performance of the model is evaluated across various different signal-to-noise ratios (SNR). Furthermore, the findings are compared to the results of previous work. The proposed model yields an overall accuracy, precision, sensitivity, and F1-score of 97.53%, 98.06%, 98.00%, and 98.00%, respectively, for RF signal detection from 0 dB to 30 dB SNR in the CardRF dataset. The proposed model demonstrates an inference time of 0.37 ms (milliseconds) for RF signal detection, which is a substantial improvement over existing work. Therefore, the proposed end-to-end deep-learning-based method outperforms the existing work in terms of performance and time complexity. Based on the outcomes illustrated in the paper, the proposed model can be used in surveillance systems for real-time UAV detection and identification.

An energy and leakage current monitoring system for abnormality detection in electrical appliances.

Unsafe electrical appliances can be hazardous to humans and can cause electrical fires if not monitored, analyzed, and controlled. The purpose of this study is to monitor the system's condition, including the electrical properties of the appliances, and to diagnose fault conditions without deploying sensors on individual appliances and analyzing individual sensor data. Using historical data and an acceptable range of normal and leakage currents, we proposed a hybrid model based on multiclass support vector machines (MSVM) integrated with a rule-based classifier (RBC) to determine the changes in leakage currents caused by installed devices at a certain moment. For this, we developed a sensor-based monitoring device with long-range communication to store real-time data in a cloud database. In the modeling process, RBC algorithm is used to diagnose the constructed device fault and overcurrent fault where MSVM is applied for detecting leakage current fault. To conduct an operational field test, the developed device was integrated into some houses. The results demonstrate the effectiveness of the proposed system in terms of electrical safety monitoring and detection. All the collected data were stored in a structured database that could be remotely accessed through the Internet.

Real-Time Energy Data Acquisition, Anomaly Detection, and Monitoring System: Implementation of a Secured, Robust, and Integrated Global IIoT Infrastructure with Edge and Cloud AI.

The industrial internet of things (IIoT), a leading technology to digitize industrial sectors and applications, requires the integration of edge and cloud computing, cyber security, and artificial intelligence to enhance its efficiency, reliability, and sustainability. However, the collection of heterogeneous data from individual sensors as well as monitoring and managing large databases with sufficient security has become a concerning issue for the IIoT framework. The development of a smart and integrated IIoT infrastructure can be a possible solution that can efficiently handle the aforementioned issues. This paper proposes an AI-integrated, secured IIoT infrastructure incorporating heterogeneous data collection and storing capability, global inter-communication, and a real-time anomaly detection model. To this end, smart data acquisition devices are designed and developed through which energy data are transferred to the edge IIoT servers. Hash encoding credentials and transport layer security protocol are applied to the servers. Furthermore, these servers can exchange data through a secured message queuing telemetry transport protocol. Edge and cloud databases are exploited to handle big data. For detecting the anomalies of individual electrical appliances in real-time, an algorithm based on a group of isolation forest models is developed and implemented on edge and cloud servers as well. In addition, remote-accessible online dashboards are implemented, enabling users to monitor the system. Overall, this study covers hardware design; the development of open-source IIoT servers and databases; the implementation of an interconnected global networking system; the deployment of edge and cloud artificial intelligence; and the development of real-time monitoring dashboards. Necessary performance results are measured, and they demonstrate elaborately investigating the feasibility of the proposed IIoT framework at the end.

Deep learning based optimal energy management for photovoltaic and battery energy storage integrated home micro-grid system.

The development of the advanced metering infrastructure (AMI) and the application of artificial intelligence (AI) enable electrical systems to actively engage in smart grid systems. Smart homes with energy storage systems (ESS) and renewable energy sources (RES)-known as home microgrids-have become a critical enabling technology for the smart grid. This article proposes a new model for the energy management system of a home microgrid integrated with a battery ESS (BESS). The proposed dynamic model integrates a deep learning (DL)-based predictive model, bidirectional long short-term memory (Bi-LSTM), with an optimization algorithm for optimal energy distribution and scheduling of a BESS-by determining the characteristics of distributed resources, BESS properties, and the user's lifestyle. The aim is to minimize the per-day electricity cost charged by time-of-use (TOU) pricing while considering the day-basis peak demand penalty. The proposed system also considers the operational constraints of renewable resources, the BESS, and electrical appliances. The simulation results from realistic case studies demonstrate the validation and responsibility of the proposed system in reducing a household's daily electricity cost.

Formulation of a Hybrid Nanofertilizer for Slow and Sustainable Release of Micronutrients.

In this work, we have proposed a new formulation of a hybrid nanofertilizer (HNF) for slow and sustainable release of nutrients into soil and water. Urea-modified hydroxyapatite was synthesized, which is a rich source of nitrogen, calcium, and phosphate. Nanoparticles such as copper, iron, and zinc were incorporated into urea-modified hydroxyapatite to increase the efficiency of the proposed fertilizer. Different techniques including powder X-ray powder diffraction, Fourier-transform infrared spectroscopy, and scanning electron microscopy were used to get insight into the properties, morphology, and structure of the as-prepared fertilizer. The developed HNF was used in a field experiment on the ladies' finger (Abelmoschus esculentus) plant. The slow release of HNF was observed during leaching studies and confirmed the availability of Ca2+, PO4 3-, NO2-, NO3-, Cu2+, Fe2+, and Zn2+. Furthermore, the presence of Cu2+, Fe2+, and Zn2+ nutrients in ladies' finger was confirmed by the inductively coupled plasma-optical emission spectrometry (ICP-OES) experiment. A considerable increase in the physicochemical properties such as swelling ratio and water absorption and retention capacities of the proposed fertilizer was observed, which makes the fertilizer more attractive and beneficial compared with the commercial fertilizer. The composition of the proposed HNF was functionally valuable for slow and sustainable release of plant nutrients. The dose of prepared HNF applied was 50 mg/week, whereas the commercial fertilizer was applied at a dose of 5 g/week to A. esculentus. The obtained results showed a significant increase of Cu2+, Fe2+, and Zn2+ nutrient uptake in A. esculentus as a result of slow release from HNF.