Optimal Artificial Intelligence Based Automated Skin Lesion Detection and Classification Model

Skin lesions have become a critical illness worldwide, and the earlier identification of skin lesions using dermoscopic images can raise the survival rate. Classification of the skin lesion from those dermoscopic images will be a tedious task. The accuracy of the classification of skin lesions is improved by the use of deep learning models. Recently, convolutional neural networks (CNN) have been established in this domain, and their techniques are extremely established for feature extraction, leading to enhanced classification. With this motivation, this study focuses on the design of artificial intelligence (AI) based solutions, particularly deep learning (DL) algorithms, to distinguish malignant skin lesions from benign lesions in dermoscopic images. This study presents an automated skin lesion detection and classification technique utilizing optimized stacked sparse autoencoder (OSSAE) based feature extractor with backpropagation neural network (BPNN), named the OSSAE-BPNN technique. The proposed technique contains a multi-level thresholding based segmentation technique for detecting the affected lesion region. In addition, the OSSAE based feature extractor and BPNN based classifier are employed for skin lesion diagnosis. Moreover, the parameter tuning of the SSAE model is carried out by the use of sea gull optimization (SGO) algorithm. To showcase the enhanced outcomes of the OSSAE-BPNN model, a comprehensive experimental analysis is performed on the benchmark dataset. The experimental findings demonstrated that the OSSAE-BPNN approach outperformed other current strategies in terms of several assessment metrics.     

Correction to: Enhanced TOA Estimation Using OFDM over Wide-Band Transmission Based on a Simulated Model

Wireless Personal Communications -     

Probabilistic quality-aware routing in cognitive radio networks under dynamically varying spectrum opportunities

In this paper, we introduce a probabilistic routing metric that considers the peculiar characteristics of the operating environment of cognitive radio networks (CRNs). This metric captures the dynamic changes in channel availabilities due to the randomness of primary user’s activity and the rich channel diversity due to the fact that a CRN is expected to operate over highly separated frequency channels with different propagation characteristics. Our metric, Probability of Success (PoS), statistically quantifies the chances of a successful cognitive radio (CR) packet transmission over a given channel. Based on the PoS metric, we propose a joint probabilistic routing and channel assignment protocol for multi-hop CRNs that attempts at selecting the path with the maximum probability of success among all possible paths for a given CR source-destination pair. Selecting such a path results in minimizing the number of disruptions to CR packet transmissions, which consequently improves network throughput. Simulation results verify the significant throughput improvement achieved by our protocol compared to reference CRN routing protocols.     

Evaluation of copy-move forgery detection: datasets and evaluation metrics

Creating copy-move forgery became even easier using a wide range of software and platforms. Many algorithms have been proposed to solve the problem, but each one of those algorithms has its own drawbacks. Researchers face many challenges in developing copy-move detection algorithms, and in this paper, we focus on two challenges. The first is the benchmark dataset, and the second involves evaluation metrics. In this paper, we investigate the available copy-move datasets and their advantages and disadvantages. In addition, we discuss the different metrics that have been used by researchers to evaluate the copy-move forgery detection (CMFD) algorithms. On that basis, we suggest the standard specifications of the appropriate copy-move dataset and the metrics that should be used to evaluate the detection algorithms. The findings of this paper will help researchers evaluate their algorithms effectively and fairly essential for developing reliable algorithms.     

The effects of different noise types and mobility on error rate of digital modulation schemes over millimeter-wave Weibull fading channels

Wireless Networks - Millimeter (mm-wave) communication is a prominent candidate to support the evolution towards fifth generation (5G) wireless systems. As such, in this paper, we study the impact...     

Design methodology for barrier‐based two phase flow distributor

The barrier‐based distributor is a multiphase flow distributor for a multichannel microreactor which assures flow uniformity and prevents channeling between the two phases. For N number of reaction channels, the barrier‐based distributor consists of a gas manifold, a liquid manifold, N barrier channels for the gas, N barrier channels for the liquid, and N mixers for mixing the phases before the reaction channels. The flow distribution is studied numerically using a method based on the hydraulic resistive networks (RN). The single phase hydraulic RN model (Commenge et al., 2002;48:345–358) is extended for two phases gas‐liquid Taylor flow. For Re_GL <30, the accuracy for the model was above 90%. The developed‐model was used to study the effects of fabrication tolerance and barrier channel dimensions. A design methodology has been proposed as an algorithm to determine the required hydraulic resistance in the barrier channels and their dimensions. This methodology is demonstrated using a numerical example. © 2012 American Institute of Chemical Engineers AIChE J, 2012     

Novel Homozygous Missense Variant in GJA3 Connexin Domain Causing Congenital Nuclear and Cortical Cataracts

Congenital cataracts (CC) are responsible for approximately one-tenth of childhood blindness cases globally. Here, we report an African American family with a recessively inherited form of CC. The proband demonstrated decreased visual acuity and bilateral cataracts, with nuclear and cortical cataracts in the right and left eye, respectively. Exome sequencing revealed a novel homozygous variant (c.563A > G; p.(Asn188Ser)) in GJA3, which was predicted to be pathogenic by structural analysis. Dominantly inherited variants in GJA3 are known to cause numerous types of cataracts in various populations. Our study represents the second case of recessive GJA3 allele, and the first report in African Americans. These results validate GJA3 as a bona fide gene for recessively inherited CC in humans.     

LCZ696 Protects against Diabetic Cardiomyopathy-Induced Myocardial Inflammation,ER Stress,and Apoptosis through Inhibiting AGEs/NF-κB and PERK/CHOP Signaling Pathways

The present study is designed to determine the effect of LCZ696 on DCM in rats and investigate the underlying mechanism involved. Diabetes was induced by feeding rats with a high-fat diet for six weeks following a single injection of STZ (30 mg/kg). Diabetic rats were divided into three groups (n = 10). LCZ696 and valsartan treatment was started two weeks after diabetic induction and continued for eight weeks. At the end of the treatment, serum and cardiac tissues were analyzed by RT-PCR, Western blot, and ELISA kits. LCZ696 and valsartan ameliorated DCM progression by inhibiting AGEs formation at activity levels; pro-apoptotic markers (BAX/Bcl2 ratio and caspase-3) in mRNA and protein expressions, the NF-κB at mRNA; and protein levels associated with the restoration of elevated proinflammatory cytokines such as the TNF-α, IL-6, and IL-1β at the activity level. Furthermore, LCZ696 and valsartan contribute to restoring the induction of ER stress parameters (GRP78, PERK, eIF2a, ATF4, and CHOP) at mRNA and protein levels. LCZ696 and valsartan attenuated DCM by inhibiting the myocardial inflammation, ER stress, and apoptosis through AGEs/NF-κB and PERK/CHOP signaling cascades. Collectively, the present results reveal that LCZ696 had a more protective solid effect against DCM than valsartan.