Pallabi Sharma^1,*, Kangkana Bora², Kunio Kasugai³, Bunil Kumar Balabantaray¹

Oncologie, Vol.22, No.3, pp. 129-145, 2020, DOI:10.32604/oncologie.2020.013870

Abstract In this paper, we address a current problem in medical image processing, the detection of colorectal cancer from colonoscopy videos. According to worldwide cancer statistics, colorectal cancer is one of the most common cancers. The process of screening and the removal of pre-cancerous cells from the large intestine is a crucial task to date. The traditional manual process is dependent on the expertise of the medical practitioner. In this paper, a two-stage classification is proposed to detect colorectal cancer. In the first stage, frames of colonoscopy video are extracted and are rated as significant if More >

Yan Zhou, Lili Pan^*, Rongyu Chen, Weizhi Shao

Journal of Information Hiding and Privacy Protection, Vol.2, No.2, pp. 77-86, 2020, DOI:10.32604/jihpp.2020.010486 - 11 November 2020

Abstract In large-scale image retrieval, deep features extracted by Convolutional Neural Network (CNN) can effectively express more image information than those extracted by traditional manual methods. However, the deep feature dimensions obtained by Deep Convolutional Neural Network (DCNN) are too high and redundant, which leads to low retrieval efficiency. We propose a novel image retrieval method, which combines deep features selection with improved DCNN and hash transform based on high-dimension features reduction to gain lowdimension deep features and realizes efficient image retrieval. Firstly, the improved network is based on the existing deep model to build a… More >

Rongyu Chen, Lili Pan^*, Yan Zhou, Qianhui Lei

Journal of Information Hiding and Privacy Protection, Vol.2, No.2, pp. 67-76, 2020, DOI:10.32604/jihpp.2020.010472 - 11 November 2020

Abstract With the rapid development of information technology, the speed and efficiency of image retrieval are increasingly required in many fields, and a compelling image retrieval method is critical for the development of information. Feature extraction based on deep learning has become dominant in image retrieval due to their discrimination more complete, information more complementary and higher precision. However, the high-dimension deep features extracted by CNNs (convolutional neural networks) limits the retrieval efficiency and makes it difficult to satisfy the requirements of existing image retrieval. To solving this problem, the high-dimension feature reduction technology is… More >

Arnab Kumar De, Arijit Ghosh, Debabrata Dolui, Indraneel Saha, Malay Kumar Adak^*

Phyton-International Journal of Experimental Botany, Vol.89, No.4, pp. 999-1017, 2020, DOI:10.32604/phyton.2020.010828 - 09 November 2020

Abstract In the present experiment with ongoing concentration (0 µM, 100 µM, 250 µM, 500 µM and 1000 µM) of 2,4-D, the responses of Azolla pinnata R.Br. was evaluated based on cellular functions. Initially, plants were significantly tolerated up to 1000 µM of 2,4-D with its survival. This was accompanied by a steady decline of indole acetic acid (IAA) concentration in tissues with 78.8% over the control. Membrane bound H⁺ -ATPase activity was over expressed within a range of 1.14 to 1.25 folds with activator (KCl) and decreased within a range of 57.3 to 74.6% in response to… More >

Gundala Swathi^*

Computer Systems Science and Engineering, Vol.35, No.5, pp. 335-345, 2020, DOI:10.32604/csse.2020.35.335

Abstract Researches in wireless mobile ad hoc networks have an inherent challenge of vulnerable diagnosis due to the diverse behaviour pattern of the vulnerable nodes causing heterogeneous vtype1, vtype2, vtupe3 and vtype4 faults. This paper proposes a protocol for the diagnosis of vulnerability nodes with threephases of clustering, vulnerable detection and vulnerable fault classification in wireless networks. This protocol employs the technique of probabilistic neural network for classification of vulnerable nodes and detects vulnerable nodes through timeout mechanism and vtype3, vtype4, vtype1, vtype2 nodes through the method of analysis variance. Network simulator NS-2.3.35 is employed for More >

Yoann Perreux¹, Marie Alexandre Chaix², Anna Kamp³, François-Pierre Mongeon², Magali Pham², Loïc Boussel¹, Roland Henaine¹, Annie Dore², Blandine Mondésert², Sylvie Di-Filippo¹, Paul Khairy², Francis Bessiere^1,*

Congenital Heart Disease, Vol.15, No.6, pp. 473-482, 2020, DOI:10.32604/CHD.2020.013032 - 02 November 2020

Abstract Sudden cardiac death and heart failure are well known long-term complications after atrial switch for D-transposition of the great arteries (D-TGA). Right systemic ventricular dysfunction is common and myocardial ischemia has been implicated as a putative mechanism for sudden death, with coronary anomalies prevalent in 30% of cases. We sought to assess an association between adverse events and coronary anomalies in patients with D-TGA and atrial switch surgery. An observational study was conducted in 3 tertiary centers (Montreal Heart Institute, Canada, Nationwide Children’s hospital, Chicago, USA and Hopital cardiologique Louis Pradel de Lyon, France). Adults… More >

D. Menaga¹, M. Premkumar², R. Sowmya^1,*, S. Narasimman³

Energy Engineering, Vol.117, No.6, pp. 481-495, 2020, DOI:10.32604/EE.2020.013282 - 16 October 2020

Abstract The proposed controller accompanies with different sliding surfaces. To understand maximum power point extraction as opposed to nonlinear uncertainties and unknown disturbance of a grid-connected photovoltaic system to various control inputs (u_d, u_q) is designed. To extract maximum power from a solar array and maintain unity power flow in a grid by controlling the voltage across the dclink capacitor (V_pvdc) and reactive current (i_q). A multiple input-output with multiple uncertainty constraints have considered designing proposed sliding mode controllers to validated their robustness performance. An innovative controller verifies uncertain inputs, constant and changes in irradiances, and temperature of More >

Shafiqur Rehman¹, Umar T. Salman^2,*, Luai M. Alhems¹

Energy Engineering, Vol.117, No.6, pp. 343-365, 2020, DOI:10.32604/EE.2020.011471 - 16 October 2020

Abstract Renewable energy has received much attention in the last few decades and more investment is being attracted across the world to boost its contribution towards the existing energy mix. In the Kingdom of Saudi Arabia (KSA), many studies have been conducted on the potential of renewable energy sources (RES), such as wind, solar, and geothermal. Many of these studies have revealed that the Kingdom is blessed with an abundance of RES with wind energy being the best after solar. This paper presents an analysis of windfarm distributed generation (WFDG) for energy management strategy in the… More >

S. Velliangiri^1,*, J. Premalatha²

CMES-Computer Modeling in Engineering & Sciences, Vol.125, No.2, pp. 625-645, 2020, DOI:10.32604/cmes.2020.010869 - 12 October 2020

Abstract Different devices in the recent era generated a vast amount of digital video. Generally, it has been seen in recent years that people are forging the video to use it as proof of evidence in the court of justice. Many kinds of researches on forensic detection have been presented, and it provides less accuracy. This paper proposed a novel forgery detection technique in image frames of the videos using enhanced Convolutional Neural Network (CNN). In the initial stage, the input video is taken as of the dataset and then converts the videos into image frames. More >

Jingfa Li¹, Bo Yu^1,*, Qianqian Shao², Dongliang Sun¹

CMES-Computer Modeling in Engineering & Sciences, Vol.125, No.2, pp. 541-563, 2020, DOI:10.32604/cmes.2020.011835 - 12 October 2020

Abstract In this work, the drag-reducing mechanism of high-Reynoldsnumber turbulent channel flow with surfactant additives is investigated by using large eddy simulation (LES) method. An N-parallel finitely extensible nonlinear elastic model with Peterlin’s approximation (FENE-P) is used to describe the rheological behaviors of non-Newtonian fluid with surfactant. To close the filtered LES equations, a hybrid subgrid scale (SGS) model coupling the spatial filter and temporal filter is applied to compute the subgrid stress and other subfilter terms. The finite difference method and projection algorithm are adopted to solve the LES governing equations. To validate the correctness More >