Search

The segmentation of dermoscopic‐based skin lesion images is considered to be challenging owing to various factors. Some of the most tangible reasons include poor contrast near the affected skin lesion, the fuzzy and unpredictable lesion limits, the presence of variations in noise, and capturing images under different conditions. This paper aims to develop an efficient segmentation model for dermoscopic images of different skin lesions based on deep learning. This paper proposes the 11‐layer convolutional deep neural network with two segmentation models trained from start to finish and do not depend on any previous information about the data. The viability, efficiency, and speculation ability of the models are evaluated on the ISIC2018 database. The proposed model achieves 0.903 accuracy and 0.820 Jaccard index in the segmentation of skin lesions. The model shows better performance compared to other image segmentation techniques from the leaderboards of ISIC2018 using deep learning. [ABSTRACT FROM AUTHOR]

This document is an editorial published in the journal Frontiers in Electronics. It discusses the topic of re-electrification technology and the application of energy consumption terminals. The editorial highlights emerging technologies such as energy harvesting and wireless power transfer, as well as the low-carbon operation of integrated energy systems. The document includes three original research articles that cover the influences of metal foreign objects on wireless power transmission, the coil configuration scheme of wireless power transmission, and the low carbon and efficient operation of integrated energy systems. The research topic has received attention and provides innovative conclusions in these areas. [Extracted from the article]

This paper discusses about the new approach of multiple object tracking relative to background information. The concept of multiple object tracking through background learning is based upon the theory of relativity, that involves a frame of reference in spatial domain to localize and/or track any object. The field of multiple object tracking has seen a lot of research, but researchers have considered the background as redundant. However, in object tracking, the background plays a vital role and leads to definite improvement in the overall process of tracking. In the present work an algorithm is proposed for the multiple object tracking through background learning. The learning framework is based on graph embedding approach for localizing multiple objects. The graph utilizes the inherent capabilities of depth modelling that assist in prior to track occlusion avoidance among multiple objects. The proposed algorithm has been compared with the recent work available in literature on numerous performance evaluation measures. It is observed that our proposed algorithm gives better performance. [ABSTRACT FROM AUTHOR]

Vehicle detection plays an important role in the development of an autonomous driving system. Fast processing and accurate detection are two major aspects of generating the autonomous vehicle detection system. This paper proposes a novel computer vision-based cost-effective vehicle detection system. Here, a Gentle Adaptive Boosting algorithm is trained with Haar-like features to generate the hypothesis of vehicles. Haar-like feature generates hypotheses very fast but may detect false vehicle candidates. The support vector machine algorithm is trained with the histogram of oriented gradient features to filter out the generated false hypothesis. The histogram of oriented gradients descriptor utilizes the shape and outlines of the vehicles, hence detects vehicles more accurately. Haar-Likes features and histogram of oriented gradients features are organized to accomplish the aspects of autonomous driving. The performance of the proposed vehicle detector is evaluated for day time and night time captured images and compared with three different existing vehicle detectors. The average precision of the proposed system for day time captured image is 0.97 and for night time captured image is 0.94. The proposed system requires 15 times less training time as compared to the existing technique for the same number of image data and on the same CPU. [ABSTRACT FROM AUTHOR]

Electricity market economics is one of the vital factors which play a key role in achieving the efficient operation of the power system. Economic operation along with secure & reliable operation is must for ensuring optimum utilization of the resources in order to maximize social welfare. This article presents a method for achieving economic operation of electricity market in case of congestion occurring in the system. The generator sensitivity (GS) method alone can manage the system congestion, however it does not consider the economic benefits which can be achieved by considering the bids submitted by the generators and as a result it leads to situation of market power. To avoid such scenario, bid sensitivity factor (BSF) is proposed to select the generators to participate and regulate their real power generation for alleviating congestion from the system optimally. The BSF takes into account the GS as well as bids of the generators. In this paper, the effectiveness of the proposed method in eliminating market power is realized by changing the bids of the generators. The proposed method is tested on IEEE 30‐bus system and IEEE 118‐bus system. The obtained results show an encouraging pattern for managing the congestion more optimally and economically. [ABSTRACT FROM AUTHOR]

This paper includes a design analysis of an inductorless low-power (LP) low-noise amplifier (LNA) with active load for Ultra Wide Band (UWB) applications. The proposed LNA consists of two parallel paths, one is the common source (CS) path and second is the CG path. The CG path has the edge advantage of improving overall Noise figure (NF) due to wide band impedance matching in UWB, while the CS path provides high power gain. A method for noise cancellation is adopted, to reduce the noise of CS path with the help of CG path. The proposed LNA successfully simulated in 90 nm CMOS technology. The results of proposed work indicate optimization at frequency 5.70 GHz with 3 dB bandwidth of 4.3 GHz–8.9 GHz. All simulations have been done for a range of frequency 03 GHz–13 GHz in Cadence virtuoso software. The results quoted 1.15 dB NF, −18.12 dB S11, 13.7 dB S21, maximum operating power gain (GP) 11.756 dB at frequency 5.7 GHz and available power gain (GA) is 10.17 dB at frequency 8.61 GHz, with 0.6 V, 0.92 mW broad band LNA. [ABSTRACT FROM AUTHOR]

A new type of electrode design (jigsaw in shape) is presented for actuating inner electrodes in electrowetting-on-dielectric devices containing large two-dimensional array of electrodes. Electrodes are diagonally connected with one external pin to the voltage supply. Each electrode-pad is made by carving (or cutting) out two triangular sections from the sides and adding two triangular sections on the top and bottom of the traditional square electrode. This modification in electrode shape creates an imbalance of electromechanical force at the three-phase contact line on applying the supply voltage to the actuating electrode. Droplet moves towards either horizontal or vertical directions depending on the direction of the dominant force. The scheme requires a single layer of metal thin film deposition for device fabrication and also reduces the number of external pin connections to the power supply. [ABSTRACT FROM AUTHOR]

Fault diagnosis and condition monitoring are important to increase the efficiency and reliability of photovoltaic modules. This paper reviews the challenges and limitations associated with fault diagnosis of solar modules. A thorough analysis of various faults responsible for failure of solar modules has been discussed. After reviewing relevant work, a monitoring tool is designed using thermography and artificial intelligent systems that allows the detection of various types of faults in PV modules and at the same time the designed tool aims to filter the nonsignificant anomalies. A neural network (NN) classifier is applied to the transfer characteristics (I‐V data) of the faulty PV module for the diagnosis which adapts multilayer perceptron (MLP) networks to identify the type and location of occurring faults. The Discrete wavelet transform (DWT) based signal processing technique is utilized in the feature extraction process to reduce the NN input size. The developed detection algorithm is adapted for 24/7 automated surveillance. For a given fault condition, the average fault detection time is observed to be <9 seconds, which is lower than the previous work done. The developed algorithm achieved 100% accuracy when tested on a predetermined fault data set. [ABSTRACT FROM AUTHOR]

In this paper, authors propose an efficient system for the segmentation of lesions in digital mammograms. The proposed detection system comprises three steps. In the first step, efficient pre-processing technique is developed using top-hat morphological transform, wavelet transform, and morphological opening-closing reconstruction filter followed by median filter. In the second step, threshold selection procedure is developed using a combination of Fuzzy C-means (FCM) clustering and Otsu global thresholding method. Finally, computed threshold is used to binarize the pre-processed image thereby yielding the suspicious mass regions from it. The free response operating characteristics (FROC) curve is used to evaluate the performance of the proposed method. Proposed system achieved the sensitivity of 94% at the rate of 1.30 false positives per image. [ABSTRACT FROM AUTHOR]

Railway track monitoring is a challenging task to avoid railway accidents due to track failures. There are lot many issues involved in the railway accidents but the major involvement is the use of defective railway tracks. The aim of this paper is to present a novel visual inspection technique for detection, marking, and visualization of defected portion in railway tracks. In this paper, maximally stable extremal region technique is used to identify and visualize the geometrical features of the defected regions on the rail head surface in railway track images. Here, three classes of surface defects have been taken. The results are very promising and comprise all the aspects. [ABSTRACT FROM PUBLISHER]

The Wireless Sensor Networks (WSN) are the basic building blocks of today's modern internet of Things (IoT) infrastructure in smart buildings, smart parking, and smart cities. The WSN nodes suffer from a major design constraint in that their battery energy is limited and can only work for a few days depending upon the duty cycle of operation. The main contribution of this research article is to propose an efficient solar energy harvesting solution to the limited battery energy problem of WSN nodes by utilizing ambient solar photovoltaic energy. Ideally, the Optimized Solar Energy Harvesting Wireless Sensor Network (SEH-WSN) nodes should operate for an infinite network lifetime (in years). In this paper, we propose a novel and efficient solar energy harvesting system with pulse width modulation (PWM) and maximum power point tracking (MPPT) for WSN nodes. The research focus is to increase the overall harvesting system efficiency, which further depends upon solar panel efficiency, PWM efficiency, and MPPT efficiency. Several models for solar energy harvester system have been designed and iterative simulations were performed in MATLAB/SIMULINK for solar powered DC-DC converters with PWM and MPPT to achieve optimum results. From the simulation results, it is shown that our designed solar energy harvesting system has 87% efficiency using PWM control and 96% efficiency (η s y s) by using the MPPT control technique. Finally, an experiment for PWM controlled SEH-WSN is performed using Scientech 2311 WSN trainer kit and a Generic LM2575 DC-DC buck converter based solar energy harvesting module for validation of simulation results. [ABSTRACT FROM AUTHOR]