Significant evolution in deep learning took place in 2010, when software developers started using graphical processing units for general-purpose applications. From that date, the deep neural network ...(DNN) started progressive steps across different applications ranging from natural language processing to hyperspectral image processing. The convolutional neural network (CNN) mostly triggers the interest, as it is considered one of the most powerful ways to learn useful representations of images and other structured data. The revolution of DNNs in medical imaging (MI) came in 2012, when
Li
launched ImageNet, a free database of more than 14 million labeled medical images. This state-of-the-art work presents a comprehensive study for the recent DNNs research directions applied in MI analysis. Clinical and pathological analysis through a selected patch of most cited researches is introduced. It will be shown how DNNs are able to tackle medical problems: classification, detection, localization, segmentation, and automatic diagnosis. Datasets comprises a range of imaging technologies: X-Ray, MRI, CT, Ultrasound, PET, Fluorescene Angiography, and even photographic images. This work surveys different patterns of DNNs and focuses somehow on the CNN, which offers an outstanding percentage of solutions compared to other DNNs structures. CNN emphasizes image features and has well-known architectures. On the other hand, limitations beyond DNNs training and execution time will be explained. Problems related to data augmentation and image annotation will be analyzed among a multiple of high standard publications. Finally, a comparative study of existing software frameworks supporting DNNs and future research directions in the area will be presented. From all presented works it could be deduced that the use of DNNs in healthcare is still in its early stages, there are strong initiatives in academia and industry to pursue healthcare projects based on DNNs.
Automatic facial expression recognition (AFER), sometimes referred to as emotional recognition, is important for socializing. Automatic methods in the past two years faced challenges due to Covid-19 ...and the vital wearing of a mask. Machine learning techniques tremendously increase the amount of data processed and achieved good results in such AFER to detect emotions; however, those techniques are not designed for masked faces and thus achieved poor recognition. This paper introduces a hybrid convolutional neural network aided by a local binary pattern to extract features in an accurate way, especially for masked faces. The basic seven emotions classified into anger, happiness, sadness, surprise, contempt, disgust, and fear are to be recognized. The proposed method is applied on two datasets: the first represents CK and CK +, while the second represents M-LFW-FER. Obtained results show that emotion recognition with a face mask achieved an accuracy of 70.76% on three emotions. Results are compared to existing techniques and show significant improvement.
Infectious diseases are a major global threat that accounts for one of the leading causes of global mortality and morbidity. Prompt diagnosis is a crucial first step in the management of infectious ...threats, which aims to quarantine infected patients to avoid contacts with healthy individuals and deliver effective treatments prior to further spread of diseases. This review article discusses current advances of diagnostic systems using colloidal nanomaterials (e.g., gold nanoparticles, quantum dots, magnetic nanoparticles) for identifying and differentiating infectious pathogens. The challenges involved in the clinical translation of these emerging nanotechnology based diagnostic devices will also be discussed.
Students engagement level detection in online e-learning has become a crucial problem due to the rapid advance of digitalization in education. In this paper, a novel Videos Recorded for Egyptian ...Students Engagement in E-learning (VRESEE) dataset is introduced for students engagement level detection in online e-learning. This dataset is based on an experiment conducted on a group of Egyptian college students by video recording them during online e-learning sessions. Each recorded video is labeled with a value from 0 to 3 representing the level of engagement of each student during the online session. Moreover, three new hybrid end-to-end deep learning models have been proposed for detecting student's engagement level in an online e-learning video. These models are evaluated using the VRESEE dataset and also using a public Dataset for the Affective States in E-Environment (DAiSEE). The first proposed hybrid model uses EfficientNet B7 together with Temporal Convolution Network (TCN) and achieved an accuracy of 64.67% on DAiSEE and 81.14% on VRESEE. The second model uses a hybrid EfficientNet B7 along with Long Short Term Memory (LSTM) and reached an accuracy of 67.48% on DAiSEE and 93.99% on VRESEE. Finally, the third hybrid model uses EfficientNet B7 along with a Bidirectional LSTM and achieved an accuracy of 66.39% on DAiSEE and 94.47% on VRESEE. The results of the first, second and third proposed models outperform the results of currently existing models by 1.08%, 3.89%, and 2.8% respectively in students engagement level detection.
Hyperuricemia is an abnormal metabolic condition characterized by an increase in uric acid levels in the blood. It is the cause of gout, manifested by inflammatory arthritis, pain and disability. ...This study examined the possible ameliorative impacts of parsley (PAR) and celery (CEL) as hypouricemic agents at biochemical, molecular and cellular levels. PAR and CEL alone or in combination were orally administered to hyperuricemic (HU) mice and control mice for 10 consecutive days. Serum levels of uric acid and blood urea nitrogen (BUN), xanthine oxidase activity, antioxidants, inflammatory (IL-1β and TNF-α) and anti-inflammatory cytokines (IL-10) were measured. mRNA expression of urate transporters and uric acid excretion genes in renal tissues were examined using qRT-PCR (quantitative real time PCR). Normal histology and immunoreactivity of transforming growth factor-beta 1 (TGF-β1) in kidneys was examined. Administration of PAR and CEL significantly reduced serum BUN and uric acids in HU mice, ameliorated changes in malondialdehyde, catalase, and reduced glutathione, glutathione peroxidase (GPX), IL-1β, TNF-α and IL-10 in hyperuricemic mice. Both effectively normalized the alterations in mURAT-1, mGLUT-9, mOAT-1 and mOAT-3 expression, as well as changes in TGF-β1 immunoreactivity. Interestingly, combined administration of PAR and CEL mitigated all examined measurements synergistically, and improved renal dysfunction in the hyperuricemic mice. The study concluded that PAR and CEL can potentially reduce damaging cellular, molecular and biochemical effects of hyperuricemia both individually and in combination.
The DCLL is an attractive breeding blanket concept that leads to a high-temperature (T∼700°C), high thermal efficiency (η>40%) blanket system. The key element of the concept is a flow channel insert ...(FCI) that serves as an electrical and thermal insulator to reduce the magnetohydrodynamic (MHD) pressure drop and to decouple the temperature-limited RAFM (reduced-activation ferritic/martensitic) steel wall from the flowing hot PbLi. The paper introduces the concept, reviews history of the development of the DCLL in the US and worldwide and then identifies critical R&D needs prior to fusion environment testing in four research areas important to the successful development of the DCLL concept: (1) PbLi MHD thermofluids, (2) fluid materials interaction, (3) tritium transport, and (4) FCI development and characterization. For these areas, the most important R&D results obtained in the US in the ITER DCLL TBM program (2005–2011) and more recently are reviewed, including experimental and computational studies of MHD PbLi flows, corrosion of RAFM, tritium permeation, and silicon carbide FCI fabrication and material qualification. We also discuss required features of non-fusion facilities for DCLL blanket testing, where current lab experiments and modeling could progress to multiple effects and partially-integrated studies that approach as nearly as possible prototypic, integrated blanket conditions prior to testing in a fusion environment.
Protein amino acid sequences can be used to determine the functions of the protein. However, determining the function of a single protein requires many resources and a tremendous amount of time. ...Computational Intelligence methods such as Deep learning have been shown to predict the proteins' functions. This paper proposes a hybrid deep neural network model to predict an unknown protein's functions from sequences. The proposed model is named Deep_CNN_LSTM_GO. Deep_CNN_LSTM_GO is an Integration between Convolutional Neural network (CNN) and Long Short-Term Memory (LSTM) Neural Network to learn features from amino acid sequences and outputs the three different Gene Ontology (GO). The gene ontology represents the protein functions in the three sub-ontologies: Molecular Functions (MF), Biological Process (BP), and Cellular Component (CC). The proposed model has been trained and tested using UniProt-SwissProt's dataset. Another test has been done using Computational Assessment of Function Annotation (CAFA) on the three sub-ontologies. The proposed model outperforms different methods proposed in the field with better performance using three different evaluation metrics (Fmax, Smin, and AUPR) in the three sub-ontologies (MF, BP, CC).
Display omitted
Aluminium nitride piezoelectric thin films grown on sapphire are strong candidates for high-temperature surface acoustic wave (SAW) sensors, due to their thermal stability, large bandgap, high ...acoustic velocity and suitable electromechanical coupling. However, thin-film resonators need more design efforts than those based on bulk crystals, due to the usually limited thickness of the piezoelectric films, and to acoustic properties disparities between the latters and their host substrate. This work presents an optimization of AlN/Sapphire-based SAW resonators with high quality factors for high-temperature applications. It combines specifically grown, <inline-formula> <tex-math notation="LaTeX">3~\mu \text{m} </tex-math></inline-formula>-thick aluminium nitride films, with the use of aluminium electrodes for their low density and resistivity, as an alternative to heavier electrodes like Pt. These electrodes allow for much lower mechanical losses and higher quality factors, in spite of needing passivation for increased lifetime. A standard resonator design is first presented and used for preliminary tests, in order to monitor the AlN/Sapphire structure with unprotected aluminium electrodes, for temperatures up to 600°C. A quasi-synchronous, optimized design is then proposed for higher quality factors and wireless sensing compliance. The high temperature characterizations confirmed that much larger quality factors can be retrieved from this optimized design. The quasi-synchronous resonators proposed in this study remain well-tuned for temperatures up to 400°C, and show high quality factors, as high as 3400 at 400°C.
Abstract The increasing occurrence of antimicrobial resistance among bacteria is a global problem that requires the development of alternative techniques to eradicate these superbugs. Herein, we used ...a combination of thermosensitive biocompatible polymer and gold nanorods to specifically deliver, preserve and confine heat to the area of interest. Our data demonstrates that this technique can be used to kill both Gram positive and Gram negative antimicrobial resistant bacteria in vitro. Our approach significantly reduces the antimicrobial resistant bacteria load in experimentally infected wounds by 98% without harming the surrounding tissues. More importantly, this polymer-nanocomposite can be prepared easily and applied to the wounds, can generate heat using a hand-held laser device, is safe for the operator, and does not have any adverse effects on the wound tissue and healing process.