scispace - formally typeset
Search or ask a question

Showing papers by "Mohamed Abdel-Nasser published in 2019"


Journal ArticleDOI
TL;DR: The use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems and offers a further reduction in the forecasting error compared with the other methods.
Abstract: Photovoltaic (PV) is one of the most promising renewable energy sources. To ensure secure operation and economic integration of PV in smart grids, accurate forecasting of PV power is an important issue. In this paper, we propose the use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems. The LSTM networks can model the temporal changes in PV output power because of their recurrent architecture and memory units. The proposed method is evaluated using hourly datasets of different sites for a year. We compare the proposed method with three PV forecasting methods. The use of LSTM offers a further reduction in the forecasting error compared with the other methods. The proposed forecasting method can be a helpful tool for planning and controlling smart grids.

443 citations


Journal ArticleDOI
TL;DR: This paper introduces a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution to improve discriminability between the lesion and non-lesion features.
Abstract: Skin lesion segmentation in dermoscopic images is still a challenge due to the low contrast and fuzzy boundaries of lesions. Moreover, lesions have high similarity with the healthy regions in terms of appearance. In this paper, we propose an accurate skin lesion segmentation model based on a modified conditional generative adversarial network (cGAN). We introduce a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution. The channel attention mechanism increases the discriminability between the lesion and non-lesion features by taking feature channel interdependencies into account. The 1-D factorized kernel block provides extra convolutions layers with a minimum number of parameters to reduce the computations of the higher-order convolutions. Besides, we use a multi-scale input strategy to encourage the development of filters which are scale-variant (i.e., constructing a scale-invariant representation). The proposed model is assessed on three skin challenge datasets: ISBI2016, ISBI2017, and ISIC2018. It yields competitive results when compared to several state-of-the-art methods in terms of Dice coefficient and intersection over union (IoU) score. The codes of the proposed model are publicly available at https://github.com/vivek231/Skin-Project.

47 citations


Journal ArticleDOI
TL;DR: This paper proposes a novel method to model the changes on temperatures in normal and abnormal breasts using a representation learning technique called learning-to-rank and texture analysis methods and produced competitive results when compared to other studies in the literature.
Abstract: Nowadays, breast cancer is one of the most common cancers diagnosed in women. Mammography is the standard screening imaging technique for the early detection of breast cancer. However, thermal infrared images (thermographies) can be used to reveal lesions in dense breasts. In these images, the temperature of the regions that contain tumors is warmer than the normal tissue. To detect that difference in temperature between normal and cancerous regions, a dynamic thermography procedure uses thermal infrared cameras to generate infrared images at fixed time steps, obtaining a sequence of infrared images. In this paper, we propose a novel method to model the changes on temperatures in normal and abnormal breasts using a representation learning technique called learning-to-rank and texture analysis methods. The proposed method generates a compact representation for the infrared images of each sequence, which is then exploited to differentiate between normal and cancerous cases. Our method produced competitive (AUC = 0.989) results when compared to other studies in the literature.

44 citations


Journal ArticleDOI
TL;DR: A fast yet accurate energy-loss assessment approach in distribution systems using machine learning that uses all data to estimate losses, which yields accurate results close to the exact solutions in a very short time.
Abstract: The penetration of photovoltaic (PV) has obviously been increased in distribution systems throughout the world. To sufficiently assess the energy losses with PV, comprehensive simulations with high time-resolution data are required. These simulations have a heavy computational burden, which makes it difficult to analyze distribution systems and evaluate PV impacts with fine resolutions. To cope with this issue, most related works down-sample, cluster, or quantize the full data to reduce the computational time on the expense of the accuracy. In this paper, we propose a fast yet accurate energy-loss assessment approach in distribution systems using machine learning. The unique feature of the proposed approach is that it uses all data to estimate losses, which yields accurate results close to the exact solutions in a very short time. The simulation results demonstrate that the proposed approach extremely reduces the computational time of energy-loss estimation with high accuracy rates. The speedup of the proposed approach with respect to power flow simulations for a yearlong at a 30-s time resolution is 28 691 (99.9965 $\%$ reduction in computational time). The effectiveness of the proposed approach is also illustrated by applying it to optimize the PV size for minimizing energy losses.

34 citations


Journal ArticleDOI
TL;DR: Artificial neural network (ANN) is used to evaluate gain parameters of static synchronous compensator (STATCOM) in order to improve the stability performance of CWF and results show that the performance ofCWF can be enhanced using STATCOM tuned by ANN more than MOGA and WOA.
Abstract: Although the wind farms based on squirrel cage induction generators (SCIG) is cheaper than the wind farms based on doubly fed induction generators (DFIG), it is always in desperate need for reactiv...

18 citations


Posted Content
TL;DR: An atrous convolution layer is proposed to be added to the conditional generative adversarial network (cGAN) segmentation model to learn tumor features at different resolutions of BUS images to automatically re-balance the relative impact of each of the highest level encoded features.
Abstract: This paper proposes an efficient solution for tumor segmentation and classification in breast ultrasound (BUS) images. We propose to add an atrous convolution layer to the conditional generative adversarial network (cGAN) segmentation model to learn tumor features at different resolutions of BUS images. To automatically re-balance the relative impact of each of the highest level encoded features, we also propose to add a channel-wise weighting block in the network. In addition, the SSIM and L1-norm loss with the typical adversarial loss are used as a loss function to train the model. Our model outperforms the state-of-the-art segmentation models in terms of the Dice and IoU metrics, achieving top scores of 93.76% and 88.82%, respectively. In the classification stage, we show that few statistics features extracted from the shape of the boundaries of the predicted masks can properly discriminate between benign and malignant tumors with an accuracy of 85%$

15 citations


Proceedings ArticleDOI
20 Feb 2019
TL;DR: A matching approach in order to detect correspondences between some candidate points from multiple mammographic views corresponding to the same patient, using a Scale Invariant Feature Transform detector and a combination between texture features.
Abstract: Matching candidate points from multiple mammographic views corresponding to the same patient may lead to an improvement in the accuracy of Computer Aided Diagnosis systems and it can help the radiologists to detect breast cancer in early stages, leading to a reduction of the percentage of mortality. In this paper, we propose a matching approach in order to detect correspondences between some candidate points from multiple mammographic views. Initially, a Scale Invariant Feature Transform detector is used to determine some candidate points in the mammographic views, then a combination between texture features is proposed to check the abnormality of the local region that surrounds each candidate point. The candidate points can be matched by integrating the information given by the texture analysis, the distance from the nipple and the location of the candidate points relative to the nipple. Some experiments are presented to show the effectiveness of the proposed approach.

9 citations


Posted Content
TL;DR: SLSNet as discussed by the authors combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model to achieve precise skin lesion segmentation with minimum resources.
Abstract: The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation algorithms are expensive in terms of computational time and memory. Consequently, running such segmentation algorithms requires a powerful GPU and high bandwidth memory, which are not available in dermoscopy devices. Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model. The 1-D kernel factorized network reduces the computational cost of 2D filtering. The position and channel attention modules enhance the discriminative ability between the lesion and non-lesion feature representations in spatial and channel dimensions, respectively. A multiscale block is also used to aggregate the coarse-to-fine features of input skin images and reduce the effect of the artifacts. SLSNet is evaluated on two publicly available datasets: ISBI 2017 and the ISIC 2018. Although SLSNet has only 2.35 million parameters, the experimental results demonstrate that it achieves segmentation results on a par with the state-of-the-art skin lesion segmentation methods with an accuracy of 97.61%, and Dice and Jaccard similarity coefficients of 90.63% and 81.98%, respectively. SLSNet can run at more than 110 frames per second (FPS) in a single GTX1080Ti GPU, which is faster than well-known deep learning-based image segmentation models, such as FCN. Therefore, SLSNet can be used for practical dermoscopic applications.

6 citations



Proceedings ArticleDOI
25 Feb 2019
TL;DR: A data-driven deep learning pooling policy based on multi-scale feature maps extraction at different scales (called FinSeg) and a novel aggregation layer is introduced in this model, in which the features maps generated at each scale is weighted using a fully connected layer.
Abstract: Image semantic segmentation is in the center of interest for computer vision researchers. Indeed, huge number of applications requires efficient segmentation performance, such as activity recognition, navigation, and human body parsing, etc. One of the important applications is gesture recognition that is the ability to understanding human hand gestures by detecting and counting finger parts in a video stream or in still images. Thus, accurate finger parts segmentation yields more accurate gesture recognition. Consequently, in this paper, we highlight two contributions as follows: First, we propose data-driven deep learning pooling policy based on multi-scale feature maps extraction at different scales (called FinSeg). A novel aggregation layer is introduced in this model, in which the features maps generated at each scale is weighted using a fully connected layer. Second, with the lack of realistic labeled finger parts datasets, we propose a labeled dataset for finger parts segmentation (FingerParts dataset). To the best of our knowledge, the proposed dataset is the first attempt to build a realistic dataset for finger parts semantic segmentation. The experimental results show that the proposed model yields an improvement of 5% compared to the standard FCN network.

2 citations


Posted Content
TL;DR: The proposed method qualitatively and quantitatively outperforms state-of-the-art vessel segmentation methods using DRIVE and STARE datasets.
Abstract: In this paper, we propose an efficient blood vessel segmentation method for the eye fundus images using adversarial learning with multiscale features and kernel factorization. In the generator network of the adversarial framework, spatial pyramid pooling, kernel factorization and squeeze excitation block are employed to enhance the feature representation in spatial domain on different scales with reduced computational complexity. In turn, the discriminator network of the adversarial framework is formulated by combining convolutional layers with an additional squeeze excitation block to differentiate the generated segmentation mask from its respective ground truth. Before feeding the images to the network, we pre-processed them by using edge sharpening and Gaussian regularization to reach an optimized solution for vessel segmentation. The output of the trained model is post-processed using morphological operations to remove the small speckles of noise. The proposed method qualitatively and quantitatively outperforms state-of-the-art vessel segmentation methods using DRIVE and STARE datasets.