Port scanning attack is a common cyber-attack where an attacker directs packets with diverse port numbers to scan accessible services aiming to discover open/weak ports in a network. Hence, several detection/prevention techniques were developed to frustrate such cyber-attacks. In this paper, we propose a new inclusive discovery scheme that evaluate five supervised machine learning classifiers, including logistic regression, decision trees, linear/quadratic discriminant, naive Bayes, and ensemble boosted trees. We compared the performance of these models via detection accuracy using a contemporary dataset for port scanning attacks (PSA-2017). As a result, the best performance results have recorded for logistic regression based detection scheme with 99.4%, 99.9%, 99.4%, 99.7%, and 0.454 mu Sec registered for accuracy, precision, recall, F-score, and detection overhead. Lastly, the comparison with existing models exhibited the proficiency and advantage of our model with enhanced attack discovery speed.
Energy efficiency in industry provides some promising solutions for industrial decarbonization and reduction of negative environ-mental impacts. Nowadays, the digitalization of the industry offers an intelligent industrial work network, which allows the use of learning algorithms for the prediction of energy consumption in order to lower the energy bill. This paper investigates different approaches used to predict energy consumption in industry, including Multiple Linear Regression (MLR), Decision Tree (DT), Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN) based on data collected of meteorological conditions, energy consumption, and lighting in the industry. The review results indicate that the MLR approach is the best forecasting method.
This study investigates a Fuzzy-Sliding mode control (Fuzzy-SMC) scheme for a single-phase Voltage Source Inverter (VSI) interfacing a photovoltaic (PV) system. The suggested controller is developed to control the real and reactive power in a robust and smooth way and deal with the system parameter uncertainties and external disturbances. The stability of the obtained control laws is proved according to Lyapunov stability criterion. The effectiveness of the adopted strategy is validated through an experimental verification using a Dspace 1104 real-time implementation board. The experimental results, under different load levels, demonstrate that the Fuzzy-SMC provides enhanced transient performance and lower Total Harmonic Distortion (THD) of the output current and voltage in comparison with SMC.
The tremendous demand for water in the agricultural sector in Saudi Arabia poses a great challenge to the government. Bluntly regulating the water supply to farms as a solution for this challenge is not an option, because farming is one of the most important businesses, and it should not be threatened. A substantial percentage of that demanded water is wasted due to manual or inefficient farming, which does not utilize sensors and new technologies to conserve water consumption in the farming process. This project introduces the conspicuous solution, which is an automated, data logging farming system, to achieve efficient, water-conserving farming process. This project combines sensors and automation that introduce efficiency and convenience to a scalable system that will help not only the government and the industries, but also individuals who are interested in farming or simply want to have quick and inexpensive access to fresh crops. The project utilizes a soil moisture sensor to continuously measure the water content of the soil in the system, and supplies the plants with the exact amount of water they need, only when the moisture level is low. The system has been implemented and tested using an Arduino microcontroller that is connected to a webserver to record and retrieve data, into and from a database that is easy to access from anywhere in the world at any time.
In this work, a multiwall carbon nanotube time delay section (MWCNTDS) is presented. For this purpose transmission line model (TLM) of a multiwall carbon nanotube (MWCNT) is used. The results of the analysis of a MWCNTDS are examined and discussed in detail. The results show that while the distance from the ground plane of the outer shell increases, time delay of a MWCNTDS increases. Time delay decreases while the value of inner radius or the total number of shells increases. Since the diameter increases with the increasing values of inner radius and the total number of shells, time delay decreases with increasing diameter. While time delay increases with increasing length of MWCNTDS, it decreases with increasing frequency.
Phishing URL is a type of cyberattack, based on falsified URLs. The number of phishing URL attacks continues to increase despite cybersecurity efforts. According to the Anti-Phishing Working Group (APWG), the number of phishing websites observed in 2020 is 1 520 832, doubling over the course of a year. Various algorithms, techniques and methods can be used to build models for phishing URL detection and classification. From our reading, we observed that Machine Learning (ML) is one of the recent approaches used to detect and classify phishing URL in an efficient and proactive way. In this paper, we evaluate eleven of the most adopted ML algorithms such as Decision Tree (DT), Nearest Neighbours (KNN), Gradient Boosting (GB), Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), Support Vector Machines (SVM), Neural Network (NN), Ex-tra_Tree (ET), Ada_Boost (AB) and Bagging (B). To do that, we compute detection accuracy metric for each algorithm and we use lexical analysis to extract the URL features.
With Pakistan being ranked as the 46th largest revenue generator in terms of the E-commerce industry, online frauds have increased proportionally. The process of online shopping has changed drastically as the seller and buyer can now communicate directly through social media applications without needing a specific platform. It implies that all fraud prevention techniques, already in place, fail in such scenarios as they are only applicable to their platform. So, for an easily attainable input to the fraud prevention pipeline, our research focuses on analyzing the fraudulent activities in this market by using commonly available customer, product, and seller traits, as features. For this research, a product-based fraud detection dataset was collected through a survey and various feature selection techniques and ML models were applied to it. In prospect, our approach can be used to develop a utility that automatically extracts relevant features, calculates risk scores, and facilitates customers in purchase decisions, given a threshold on the risk score.
Solar PV market is expected to expand significantly as the residential sector investments in this market have started increasing recently. This creates a golden opportunity for Saudi Arabia which aims to achieve 50% renewable penetration by 2030. However, the public is not yet confident of the financial gains of rooftop solar PV, so this rises the need for detailed feasibility study that considers local metrological data, prices, and regulations. In this paper, two different designs of grid-connected and standalone PV are studied, starting by evaluating the average electricity consumption of 3 houses and the utilization of standard load profile (SLP) concept to achieve reasonable hourly data. Then, local metrological data and system components pricings are collected. After that, HOMER is used to simulate and analyze system performance, and determining the feasibility of the system using two variables as references, which are levelized cost of electricity (LCOE) and payback period. The study showed that grid-connected PV system could provide 28% reduction in LCOE compared to grid-only case with a payback period of 14 years, while for the standalone case the LCOE is still relatively high. Eventually, the study successfully proved the feasibility of grid-connected rooftop PV system, but with long payback period.
This paper proposes a model for describing the avalanche breakdown voltage (BVDS). The model takes into account the gate-source voltage (VGS) dependence and the temperature (T) dependence. Both dependencies are due to different phenomena, therefore the product of two quadratic functions of independent variables (VGS and T) is considered to characterize BVDS. The coefficients of these functions are identified by nonlinear least-squares. A 650 V SiC MOSFET is characterized with the proposed technique. Results show a good agreement between experimental and predicted values.
This work is focused on a design of a circular patch antenna using a high frequency structure simulator (HFSS). It presents a robust example of design of circular patch antenna, in which we have, simulated and computed by three different feeding configurations in order to improve the parameters and to evaluate the range and the performances of such antennas. The substrate used is RT/duroid 5880 with a dielectric constant of 2.2 having low dielectric loss. The method of analysis considered is the cavity model with antenna having a patch of radius 10.9 mm and a grounded substrate of dimensions 30 mm × 30 mm at frequency of 5 GHz belonging to C band which is used for some Wi-Fi devices and weather radars. Comparison and interpretation of different antennas parameters and specially gains, have been achieved.
Recently, the electric vehicles search extracting energy from any possible energy source. It looks to its aerodynamic forces, to its inertial energy, and to the solar energy for help increasing its autonomy. Concentrating on who extracting energy from the photovoltaic panels, the electric car can have a better energetic performance and can help increasing the battery autonomy inside the vehicle. Therefore, the objective of this study is to build a robust control loop which extract the maximum of energy from these solar panels. So, finding the best control tool will help having a better performance for this renewable energy system. Referring to the existing literature, many algorithms can be used for extracting the maximum of energy. Perturb and observe, Incremental or Particle swarm optimization algorithms can give an acceptable solution. Studying these algorithms and compare their results can give a clear view about the performances of each one. So, initially, it is necessary to study correctly all these algorithms and define their variables and parameters that must be fixed, then implementing all these algorithms and control their outputs. MATLAB/Simulink is the used control tool.
This paper represents the 0.18 µm CMOS technology-based implementation of wideband (0.1 - 4 GHz) LNA for cellular services, terrestrial communication and satellite navigation. Here, a wideband operation is achieved by the design of the current reuse methodology and negative feedback between the drain and gate terminal of the device to be operated in a common source (CS) configuration. The proposed design improves the transconductance and reduces the drain current by half due to the scaling of the device geometry using the W/L ratio. The implanted design provides greater than 30 dB gain in three cascaded stages with input-output return loss better than -12 dB throughout the band and a noise figure less than 3 dB. The formulated design consumes 18 mA power from a 1.8 V source.
Conventional kerosene dependent light, battery dependent television, and light bulb in the rural areas which is being used to replace by Solar Home System (SHS) from 1998 in Bangladesh. The remarkable growth of rural electrification is based on the Solar Home System (SHS). In 2003, Rural Electrification and Renewable Energy Development Project (REREDP) was introduced in Bangladesh. The achievement of the primary goal of 50,000 SHS implementation had been completed in off-grid locations by 2.5 years; the estimated time was three years. 4.5 million SHS has been installed, and 13 million people are taking advantage of SHS systems. But maximum drawbacks and complaints regarding the installed SHS such as lifetime and battery-related difficulty, technological-advancement deficiency, bulb-related difficulties, high cost and implement associated challenges, social and other barriers have created a perplexing condition. The main goal of this research work is to find out the challenges of SHS deployment and compare it with the new model (CP model). In addition, the requirement of the customer is rising remarkably with the advancement of technology. A possible technique is needed to generate enough power utilizing green energy sources at consumers' locations. Here “Consumer is Producer” showed a unique method for providing stable power to the customer, where also the energy will be produced and utilized by the customer.
Stream-flow forecasting is one of the major aspects in improving the efficiency of water resource planning and management for the water reservoirs in various geographical regions. Different forecasting techniques have been implemented for forecasting the inflow rate in the past with Support Vector Machine (SVM) being very popular and accurate among them. Similarly, the outflow forecasting is essential to estimate the usage and also encompasses different models for forecasting. Muskingum model is found to be prevalent in forecasting outflow but it has the limitation of inefficiency in taking care nonlinearity. In this paper, both inflow and outflow rate prediction is done by Auto-Regressive Integral Moving Average (ARIMA) model as prediction of stream flow was never modelled as ARIMA in the literature earlier. The performance evaluation parameter considered is the root mean square error (RMSE) for comparison with the existing SVM models. It is found that in case of inflow rate, RMSE obtained by ARIMA model shows a decrease of 36% in the best case and increase of 4.3% in the worst case when compared with the SVM models. Likewise, the outflow rate RMSE when compared with Muskingum model gives better results taking non-linearity into consideration. The results of this study will help in not only planning efficient water resource management but also prediction of flood frequency in future.
Multitask networks version of the conventional Incremental Least Mean Square (ILMS) is developed and implemented over Wireless Sensor Networks (WSN). The concept of Code Division Multiple Access (CDMA) is adopted to extract a particular task or estimate solution successfully among different clusters. In addition, diffusion-based approaches of ILMS CDMA algorithm called the Combine-Then-Adapt (CTA) and the Adapt-Then-Combine (ATC) are developed which allow data exchanging among the neighbouring nodes to enhance the performance. As expected, the simulation results of ILMS CDMA topology consisting of 7 nodes that grouped in 3 clusters converged to -35 dB of Mean Square Error (MSE) and -47.75 dB of Mean Square Deviation (MSD), while the MSD performance of CTA and ATC approaches settled down to -50.32 dB and -51.52 dB, respectively, indicating performance enhancement of -2.6 dB and -3.8 dB.
In Internet of Things (IoT) applications and wireless sensor networks(WSNs), ultra low power receivers are commonly used. The methodologies and circuits used to achieve ultra-low power receivers are compared in this research. The supply voltage scaling and current reuse techniques discussed in this paper are widely used. The current reuse technique is used to design the low noise converter (LNC), self oscillating mixer (SOM), low noise amplifier-mixer-VCO (LMV), LMV-filter architecture, and QLMVF architecture. This paper describes how to overcome design challenges in order to obtain exceptionally low-power building blocks.
The increasing number of distributed energy resources (DER) and the increasing penetration of intermittent renewable generation impose a significant challenge in ensuring the reliability of the electricity grid. Orchestration of virtual power plants (VPP) and demand response (DR) programs provides flexibility in the grid and improves grid reliability. The deployment of 5G will significantly improve the performance of VPP and DR by providing reliable and low-latency communication solutions. In this paper, the advantages and challenges of using 5G in the orchestration of VPP and DR are discussed. The study shows that 5G technology can address many of the current limitations in orchestration of VPP and DR programs. Furthermore, the main challenges of 5G in large scale operations of VPP and DR programs are discussed.
In recent years, there have been increasing demands for applications of image storage, sharing and transmission across data networks. For these data-intensive and sensitive applications, it is imperative to perform both image compression and encryption. In this paper, two different approaches of image compression and encryption were studied and compared. In the first approach, image compression was followed by encryption; while, in the second approach, image encryption was followed by compression. Both approaches were implemented based on standard schemes, i.e., JPEG 2000 lossless compression and DES encryption. Experiments were conducted for two different types of testing images: a natural image and a medical image. The efficiency performance of the two approaches was compared based on key parameters such as MSE, PSNR, entropy, image file size, compression ratio and time consumption. We found that the first approach outperformed the second for both testing images. The results are presented and analysed along with recommendations for related future work.
Convolutional neural networks (CNN) are a very powerful tool for many different applications. This capability is highly demanded in the field of embedded systems for video surveillance, speech recognition, and image analysis. Due to its high computational intensity, the application of CNN is limited to real-time research areas where computational speed is extremely important. Therefore, an appropriate accelerator is required to fulfill the requirements of these limitations. On the one hand, GPUs are widely used to accelerate the CNN under high power dissipation. On the other hand, the trend for FPGA implementation is increasing rapidly due to its low power consumption and facile re-configurability. In this work, we evaluate the inference performance of 10 classification models and 9 object detection models using the OpenVINO toolkit. In addition, we analyzed the implementation of these models on the DE5a-Net DDR4 equipped with an Arria 10 GX FPGA. The results show that the performance of Full-Precision FP32 classification models on a heterogeneous architecture FPGA/CPU is on average 3.6X faster than the CPU.
This paper deals with the control of parallel voltage source inverters (VSI) in microgrid islanded mode while sharing the active and reactive power required by the load. Firstly, an islanded microgrid composed of n distributed energy resources (DER) connected to each other through VSI and nonlinear load is modelled. Thereafter, a master slave based control strategy is proposed. One of the VSI is designated as a master and it is responsible for controlling the microgrid AC bus voltage and responsible, also, for setting the reference current to be supplied by the slave VSI. In the other hand, the slaves are responsible for controlling their output currents following the references received from the master VSI; in that way, the active and reactive power are shared among all the DER proportionally to their rated generated power. The control of the VSI voltage and current is ensured applying the backstepping technique. Using Lyapunov theory, the closed loop system is globally asymptotically stable. From the simulation case study, the proposed control strategy ensures the voltage control of the n parallel VSI as well as the power sharing between the n DER without being overloaded.
