ARTICLE | doi:10.20944/preprints201812.0022.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Image retrieval, color features, shape features, low-level features combination
Online: 3 December 2018 (13:33:45 CET)
Due to an increase in the number of image achieves, Content-Based Image Retrieval (CBIR) has gained attention for research community of computer vision. The image visual contents are represented in a feature space in the form of numerical values that is considered as a feature vector of image. Images belonging to different classes may contain the common visuals and shapes that can result in the closeness of computed feature space of two different images belonging to separate classes. Due to this reason, feature extraction and image representation is selected with appropriate features as it directly affects the performance of image retrieval system. The commonly used visual features are image spatial layout, color, texture and shape. Image feature space is combined to achieve the discriminating ability that is not possible to achieve when the features are used separately. Due to this reason, in this paper, we aim to explore the low-level feature combination that are based on color and shape features. We selected color moments and color histogram to represent color while shape is represented by using invariant moments. We selected this combination, as these features are reported intuitive, compact and robust for image representation. We evaluated the performance of our proposed research by using the Corel, Coil and Ground Truth (GT) image datasets. We evaluated the proposed low-level feature fusion by calculating the precision, recall and time required for feature extraction. The precision, recall and feature extraction values obtained from the proposed low-level feature fusion outperforms the existing research of CBIR.
ARTICLE | doi:10.20944/preprints202009.0330.v1
Subject: Medicine & Pharmacology, Pediatrics Keywords: bullying; dentofacial features; physical features; schoolchildren
Online: 15 September 2020 (04:48:47 CEST)
Context: bullying among schoolchildren is a serious phenomenon and a leading health concern. Aim: to determine the prevalence of bullying, its forms, and its effect on academic abilities and school attendance, as well as associated sociodemographic, physical, and dentofacial features among Saudi schoolchildren. Methods: this cross-sectional study recruited a sample of 1131 parents of schoolchildren 8-18 years old and requested them to complete internationally accepted questionnaires for their children. Chi-square test and logistic regression analysis were used to analyze the data (p<0.05). Results: a majority (89.2%) of schoolchildren were bully victims. Physical bullying (48.9%) was the most common form of bullying. The youngest schoolchildren (8-11 years), those who disliked school classes or neither liked nor hated them, as well as those who were truant from school were more likely to be victims. In addition, those who had worse grades because of bullying, and those who were very often bullied because of good grades or because they showed an interest in school were more likely to be victims. With regards to targeted physical features, teeth were the number one target, followed by the shape of the lips and strength, while teeth shape and color was the most common dentofacial target, followed by anterior open bite and protruded anterior teeth. Boys and the youngest schoolchildren were more often subjected to bullying because of these features (p<0.05). Conclusions: the prevalence of bullying, mainly in a physical form, was high among Saudi schoolchildren, with a negative influence on students’ academic abilities. Problems related to teeth, in particular, which can be treated, were targets, mainly for boys and the youngest schoolchildren. More studies are required in Saudi Arabia to explore the issue further among schoolchildren, themselves.
ARTICLE | doi:10.20944/preprints202008.0396.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: crowd analysis; tracking; people safety; crowd features; localized features
Online: 19 August 2020 (07:49:37 CEST)
The safety of people is an important phenomenon nowadays. This importance arises due to the crowded places including subway station, universities, colleges, airport, shopping mall and square, and city squares. Therefore, the development of an effective system based on physical characteristics of crowd layout is of significant demand. In this paper, we proposed a novel automated and intelligent systems for crowd event analysis based on a set of physical elements. For this purpose, we take into account optical flow and spatial-time gradient, contour features, and Gaussian processes. Our method combine these characteristics into a unique model to deal with the challenging problem of crowd event analysis. For evaluating our proposed method, we consider a benchmark dataset and a number of different performance metrics. These analysis demonstrate the robustness and effectiveness of our proposed method.
ARTICLE | doi:10.20944/preprints202211.0488.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Capsule network; differential features; deep learning; micro-expression recognition; spatiotemporal features
Online: 28 November 2022 (03:12:12 CET)
Micro-expression (ME) is one of the key psychological stress reactions. It is a modest, spontaneous facial mechanism. ME has significant applicability in a variety of psychologically-related sectors because to its precision and unpredictability with regard to psychological manifestations. Nevertheless, the current Micro-expression recognition (MER) algorithms have poor accuracy and a limited quantity of ME data, and this study issue has not been thoroughly investigated. Therefore, we present an approach for deep learning based on a Spatio-temporal capsule network (STCP-Net). STCP-Net has four components: a jitter reduction module, a differential feature extraction module, an STCP module, and a fully linked layer. The first two modules are aimed to extract diversifying differential features more precisely and to limit the influence of head jitter. The STCP module is used to extract Spatio-temporal features layer by layer, taking the temporal and geographical connection between features into account. This research runs sufficient trials using the Leave One Subject Out (LOSO) methodology for cross-validation using the CASMEII dataset. The conclusion and analysis demonstrate that the algorithm is innovative and efficient.
ARTICLE | doi:10.20944/preprints201701.0102.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: facial expression recognition; fusion features; salient facial areas; hand-crafted features; feature correction
Online: 24 January 2017 (03:28:51 CET)
In pattern recognition domain, deep architectures are widely used nowadays and they have achieved fine grades. However, these deep architectures need special demands, especially big datasets and GPU. Aiming to gain better grades without deep networks, we propose a simplified algorithm framework using fusion features extracted from the salient areas of faces. Furthermore, the proposed algorithm has achieved a better result than some deep architectures. For extracting more effective features, this paper firstly defines the salient areas on the faces. This paper normalizes the salient areas of the same location in the faces to the same size, therefore it can gain more similar features from different subjects. LBP and HOG features are extracted from the salient areas, fusion features’ dimensions are reduced by Principal Component Analysis( PCA) and we apply softmax to classify the six basic expressions at once. This paper proposes a salient areas definitude method which uses peak expressions frames to compare with their neutral faces. This paper also proposes and applies the idea of normalizing the salient areas to align the specific areas which express the different expressions. This makes the salient areas found from different subjects have the same size. Besides, gamma correction method is firstly applied on LBP features in our algorithm framework which improves our recognition rates significantly. By applying this algorithm framework, our research has gained state-of-the-art performances on CK+ database and JAFFE database.
ARTICLE | doi:10.20944/preprints201906.0166.v1
Subject: Mathematics & Computer Science, Information Technology & Data Management Keywords: MRI image; Texture Features; GLCM
Online: 18 June 2019 (05:36:29 CEST)
This paper presented a feature vector using a different statistical texture analysis of brain tumor from MRI image. The statistical feature texture is computed using GLCM (Gray Level Co-occurrence Matrices) of Brain Nodule structure. For this paper, the brain nodule segmented using strips method to implemented marker watershed image segmentation based on PSO (Particle Swarm Optimization) and Fuzzy C-means clustering (FCM). Furthermore, the four angles 0o, 45o, 90o and 135o are calculated the segmented brain image in GLCM. The four angular directions are calculated using texture features are correlation, energy, contrast and homogeneity. The texture analysis is performed a different types of images using past years. So the algorithm proposed statistical texture features are calculated for iterative image segmentation. These results show that MRI image can be implemented in a system of brain cancer detection.
TECHNICAL NOTE | doi:10.20944/preprints201806.0343.v1
Subject: Engineering, Biomedical & Chemical Engineering Keywords: Lesion classification; statistical features; mammograms
Online: 21 June 2018 (15:46:03 CEST)
Breast cancer is the second cause of fatality among all cancers for women. Automatic classification of breast cancer lesions in mammograms is a challenging task due to the irregularity and complexity of the location, size, shape, and texture of these lesions. The intensity dissimilarity has been found between breast cancer tissues and normal tissues, when a multi-spectral anatomical mammographic screening scans have been done. In this work, two approaches have been evaluated to classify the breast tumor lesions. The first one is through Gabor wavelet features and the second one is Statistical features. Subsequently, support vector machine, Multilayer Perceptron and KNN classifiers have been used with computer based method for breast tumor classification.
ARTICLE | doi:10.20944/preprints202108.0433.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: Speech emotion recognition; Feature extraction; Heterogeneous parallel network; Spectral features; Prosodic features; Multi-feature fusion
Online: 23 August 2021 (12:16:40 CEST)
Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.
ARTICLE | doi:10.20944/preprints202003.0058.v1
Online: 4 March 2020 (10:22:09 CET)
Objective:The Glioma brain tumor detection and segmentation methods are proposed in this paper using machine learning approaches. Methods:The boundary edge pixels are detected using Kirsch’s edge detectors and then contrast adaptive histogram equalization method is applied on the edge detected pixels. Then, Ridgelet transform is applied on this enhanced brain image in order to obtain the Ridgelet multi resolution coefficients. Further, features are derived from the Ridgelet transformed coefficients and the features are optimized using Principal Component Analysis (PCA) method and these optimized features are classified into Glioma or non-Glioma brain images using Co-Active Adaptive Neuro Fuzzy Expert System (CANFES) classifier.Results:The proposed method with PCA and CANFES classification approach obtains 97.6% of se, 98.56% of sp, 98.73% of Acc, 98.85% of Pr, 98.11% of FPR and 98.185 of FNR, then the proposed Glioma brain tumor detection method using CANFES classification approach only.
ARTICLE | doi:10.20944/preprints201809.0449.v1
Subject: Engineering, Electrical & Electronic Engineering Keywords: motion; superpixel; temporal features; video classification
Online: 24 September 2018 (09:54:01 CEST)
Superpixels are a representation of still images as pixel grids because of their more meaningful information compared with atomic pixels. However, their usefulness for video classification has been given little attention. In this paper, rather than using spatial RGB values as low-level features, we use optical flows mapped into hue-saturation-value (HSV) space to capture rich motion features over time. We introduce motion superpixels, which are superpixels generated from flow fields. After mapping flow fields into HSV space, independent superpixels are formed by iteration of seeded regions. Every grid of a motion superpixel is tracked over time using nearest neighbors in the histogram of flow (HOF) for consecutive flow fields. To define the temporal representation, the evolution of three features within the superpixel region, namely the HOF, HOG, and the center of superpixel mass are used as descriptors. The bag of features algorithm is used to quantify final features, and generalized histogram-kernel support vector machines are used as learning algorithms. We evaluate the proposed superpixel tracking on first-person videos and action sports videos.
Subject: Engineering, Electrical & Electronic Engineering Keywords: coronavirus; COVID-19; diagnosis; deep features; SVM
Online: 22 April 2020 (05:58:22 CEST)
The detection of coronavirus (COVID-19) is now a critical task for the medical practitioner. The coronavirus spread so quickly between people and approaches 100,000 people worldwide. In this consequence, it is very much essential to identify the infected people so that prevention of spread can be taken. In this paper, the deep feature plus support vector machine (SVM) based methodology is suggested for detection of coronavirus infected patient using X-ray images. For classification, SVM is used instead of deep learning based classifier, as the later one need a large dataset for training and validation. The deep features from the fully connected layer of CNN model are extracted and fed to SVM for classification purpose. The SVM classifies the corona affected X-ray images from others. The methodology consists of three categories of Xray images, i.e., COVID-19, pneumonia and normal. The method is beneficial for the medical practitioner to classify among the COVID-19 patient, pneumonia patient and healthy people. SVM is evaluated for detection of COVID-19 using the deep features of different 13 number of CNN models. The SVM produced the best results using the deep feature of ResNet50. The classification model, i.e. ResNet50 plus SVM achieved accuracy, sensitivity, FPR and F1 score of 95.33%,95.33%,2.33% and 95.34% respectively for detection of COVID-19 (ignoring SARS, MERS and ARDS). Again, the highest accuracy achieved by ResNet50 plus SVM is 98.66%. The result is based on the Xray images available in the repository of GitHub and Kaggle. As the data set is in hundreds, the classification based on SVM is more robust compared to the transfer learning approach. Also, a comparison analysis of other traditional classification method is carried out. The traditional methods are local binary patterns (LBP) plus SVM, histogram of oriented gradients (HOG) plus SVM and Gray Level Co-occurrence Matrix (GLCM) plus SVM. In traditional image classification method, LBP plus SVM achieved 93.4% of accuracy.
ARTICLE | doi:10.20944/preprints202101.0526.v1
Subject: Biology, Anatomy & Morphology Keywords: Asaia; paratransgenesis; symbiotic traits; Anopheles stephensi; genome features
Online: 26 January 2021 (08:19:00 CET)
Asaia bacteria commonly comprise part of the microbiome of many mosquito species in the genera Anopheles and Aedes, including important vectors of infectious agents. Their close association with multiple organs and tissues of their mosquito hosts enhances the potential for paratransgenesis for delivery of anti-malaria or anti-virus effectors. The molecular mechanisms involved in the interactions between Asaia and mosquito hosts, as well as Asaia and other bacterial members of the mosquito microbiome, remained unexplored. Here, we determined the genome sequence of the strain W12 isolated from Anopheles stephensi mosquitoes, compared them to other Asaia species associated with plants or insects, and investigated some properties of the bacteria relevant to their symbiosis with host mosquitoes. The assembled genome of strain W12 has a size of 3.94 MB, which is the largest among Asaia spp studied so far. At least 3,585 coding sequences were predicted. The insect-associated Asaia including strain W12 carried more glycoside hydrolase (GH) encoding genes (31 per genome) than those isolated from plants (22 per genome). W12 had the most predicted regulatory protein components (213) among the selected Asaia (ranging from 131 to 211), indicating its great capability to adapt to frequent environmental changes in the mosquito gut. Two complete operons encoding cytochrome bo3-type ubiquinol terminal oxidases (cyoABCD-1 and cyoABCD-2) were found in most of Asaia genomes, which possibly offer alternative terminal oxidases and allow the flexible transition of respiratory pathways. Genes involved in the production of acetoin and 2,3-butandiol have been identified in Asaia sp. W12.
REVIEW | doi:10.20944/preprints202004.0453.v1
Subject: Medicine & Pharmacology, Clinical Neurology Keywords: neurology; clinical features; coronavirus; stroke; encephalitis; headache; delirium
Online: 25 April 2020 (02:36:21 CEST)
The Coronavirus disease due to SARS-CoV-2 emerged in Wuhan city, China in December 2019 and rapidly spread more than 200 countries as a global health pandemic. There are more 3 million confirmed cases and around 207,000 fatalities. The primary manifestation is respiratory and cardiac but neurological manifestations are being reported in the literature as case reports and case series. The most common reported symptoms to include headache and dizziness followed by encephalopathy and delirium. Among the complications noted are Cerebrovascular accident, Guillian barre syndrome, acute transverse myelitis, and acute encephalitis. The most common peripheral manifestation was hyposmia. It is further noted that sometimes the neurological manifestations can precede the typical features like fever and cough and later on typical manifestations develop in these patients. Hence a high index of suspicion is required for timely diagnosis and isolation of cases to prevent the spread in neurology wards. We present a narrative review of the neurological manifestations and complications of COVID-19. Our aim is to update the neurologists and physicians working with suspected cases of COVID-19 about the possible neurological presentations and the probable neurological complications resulting from this novel virus infection.
ARTICLE | doi:10.20944/preprints201905.0350.v1
Subject: Keywords: Support vector machine, motion descriptor, features, human behaviors
Online: 29 May 2019 (11:19:19 CEST)
Identifying human actions in complex scenes is widely considered as a challenging research problem due to the unpredictable behaviors and variation of appearances and postures. For extracting variations in motion and postures, trajectories provide meaningful way. However, simple trajectories are normally represented by vector of spatial coordinates. In order to identify human actions, we must exploit structural relationship between different trajectories. In this paper, we propose a method that divides the video into N number of segments and then for each segment we extract trajectories. We then compute trajectory descriptor for each segment which capture the structural relationship among different trajectories in the video segment. For trajectory descriptor, we project all extracted trajectories on the canvas. This will result in texture image which can store the relative motion and structural relationship among the trajectories. We then train Convolution Neural Network (CNN) to capture and learn the representation from dense trajectories. . Experimental results shows that our proposed method out performs state of the art methods by 90.01% on benchmark data set.
ARTICLE | doi:10.20944/preprints202207.0384.v1
Subject: Medicine & Pharmacology, Pediatrics Keywords: SARS-CoV-2; COVID-19; children; clinical features; comorbidities; male genderSARS-CoV-2, COVID-19, children, clinical features, comorbidities, male gender
Online: 26 July 2022 (04:43:02 CEST)
Background: Given the potential for additional development to clarify a better knowledge of the overall impact of COVID-19 on the pediatric population, the clinical symptoms of SARS-CoV-2 infection in children and adolescents are still being explored. Morbidity in children is characterized by a variable clinical course. Our study's goal was to compare clinical aspects of 230 pediatric patients who tested positive for SARS-CoV-2 and were hospitalized between April 2020 and March 2022. Methods: In a retrospective analysis, we compared two groups hospitalized in the infectious diseases clinical ward IX at the National Institute for Infectious Diseases "Prof. Dr. Matei Bals," Bucharest, Romania. The first group of 88 patients was admitted between (April–December 2020) and their clinical manifestations were compared with the second group of 142 children followed between July 2021 and March 2022. Results: Of 230 children, the median age was 4.5 (interquartile range 0.6-17) years, 53.9% were male. 88 (36.21%) patients (first group) were admitted during the second wave in Romania, mostly aged < 5 years old, and experienced digestive manifestations like fever (p=0.001), and diarrhoea (p=0.004). The second group experienced different clinical signs when compared with the first group, with higher temperature and increased respiratory symptoms analogous to those of acute respiratory viral infections. The proportion in the second group increased, and 64.5% had symptoms for a median interval of 5 days; age (0-4 -years old) and length of stay were both proportionally inversely (p<0.01) and with correlation with hospital admission (p = 0.04). We report two Paediatric Inflammatory Multisystem Syndrome (PIMS) in the second group, with favourable evolution under treatment. Comorbidities were risk factors for complications appear (p < 0.001) in both groups. All paediatric cases admitted to our clinic evolved favourably and no death was recorded. Conclusions: In the first group children experienced digestive symptoms, whereas the second group experienced mild and moderate respiratory symptoms. We confirmed risk factors for severe cases as manifestations across the age spectrum, 0-4 (digestive symptoms) and 5-12 years old (for respiratory symptoms), associated comorbidities, fever, and male gender. The potential effects of COVID-19 infection in children older than 5 years should encourage caregivers to vaccinate and improve the prognosis among pediatric patients at risk.
ARTICLE | doi:10.20944/preprints202109.0081.v1
Subject: Chemistry, Food Chemistry Keywords: rootstocks; untargeted metabolomics; features; grafted; multivariate analysis; volatile compounds
Online: 6 September 2021 (09:52:40 CEST)
To allow for a broad survey of subtle metabolic shifts in wine caused by rootstock and irrigation, an integrated metabolomics-based workflow followed by quantitation was developed. This workflow was particularly useful when applied to a poorly studied variety cv. Chambourcin. Allowing volatile metabolites that otherwise may have been missed with a targeted analysis to be included, this approach allowed deeper modeling of treatment differences which then could be used to identify important compounds. Wines produced on a per vine basis, over two years, were analyzed using SPME-GC-MS/MS. From the 382 and 221 features that differed significantly among rootstocks in 2017 and 2018 respectively, we tentatively identified 94 compounds by library search and retention index, with 22 confirmed and quantified using authentic standards. Own-rooted Chambourcin differed from other root-systems for multiple volatile compounds with fewer dif-ferences among grafted vines. For example, the average concentration of β-Damascenone present in own-rooted vines (9.49 µg/L) was significantly lower in other rootstocks (8.59 µg/L), whereas mean Linalool was significantly higher in 1103P rootstock compared to own-rooted. β-Damascenone was higher in regulated deficit irrigation (RDI) than other treatments. The workflow outlined not only was shown to be useful for scientific investigation, but also in creating a protocol for analysis that would ensure differences of interest to industry are not missed.
ARTICLE | doi:10.20944/preprints202001.0123.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: static features extraction; dynamic environments; 3D reconstruction; monocular SLAM
Online: 12 January 2020 (15:12:52 CET)
Many classic visual monocular SLAM systems have been developed over the past decades, however, most of them will fail when dynamic scenarios dominate. DM-SLAM is proposed for handling dynamic objects in environments based on ORB-SLAM. The article mainly concentrates on two aspects. Firstly, DLRSAC is proposed to extract static features from the dynamic scene based on awareness of nature difference between motion and static, which is integrated into initialization of DM-SLAM. Secondly, we design candidate map points selection mechanism based on neighborhood mutual exclusion to balance the accuracy of tracking camera pose and system robustness in motion scenes. Finally, we conduct experiments in the public dataset and compare DM-SLAM with ORB-SLAM. The experiments verify the superiority of the DM-SLAM.
ARTICLE | doi:10.20944/preprints201912.0086.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: action recognition; spatio-temporal features; convolution network; transfer learning
Online: 7 December 2019 (00:57:34 CET)
This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D CNNs, 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is to fuse the convolution layers from 2D and 3D CNNs to allow temporal encoding with fewer parameters than 3D CNNs. We adopt transfer learning from pre-trained 2D CNNs for spatial extraction, followed by temporal encoding, before connecting to 3D convolution layers at the top of the architecture. We construct our fusion architecture, semi-CNN, based on three popular models: VGG-16, ResNets and DenseNets, and compare the performance with their corresponding 3D models. Our empirical results evaluated on the action recognition dataset UCF-101 demonstrate that our fusion of 1D, 2D and 3D convolutions outperforms its 3D model of the same depth, with fewer parameters and reduces overfitting. Our semi-CNN architecture achieved an average of 16 – 30% boost in the top-1 accuracy when evaluated on an input video of 16 frames.
ARTICLE | doi:10.20944/preprints201810.0718.v1
Subject: Engineering, Electrical & Electronic Engineering Keywords: event-driven processing; ECG; cardiac diseases; features extraction; classification
Online: 30 October 2018 (09:15:43 CET)
The aim of this paper is to develop an intelligent event-driven Electrocardiogram (ECG) processing module in order to achieve an efficient solution for diagnosis of the cardiac diseases. The suggested method acquires the signal with an event-driven A/D converter (EDADC). The output of EDADC is passed through the activity selection and interpolation blocks. It allows focusing only on the important signal parts and resampling it uniformly. Later on, the signal is de-noised. The autoregressive (AR) method is used to extract the classifiable features of the de-noised signal. Afterwards, the output is classified by employing different robust classification techniques such as support vector machines (SVMs), K- Nearest Neighbor (KNN) and Artificial Neural Network (ANN). The event-driven feature enables to adapt the system processing load according to the signal temporal variations. This interesting feature of the devised system aptitudes a drastic reduction in its processing activity and therefore in the power consumption as compared to the traditional ones. A comparison of the performance of different classifiers is also made in terms of accuracy. Results show that the proposed system is a potential candidate for an automatic diagnosis of the cardiac diseases.
ARTICLE | doi:10.20944/preprints201810.0494.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: unsupervised training; features learning; deep learning; time series forecasting
Online: 22 October 2018 (12:24:43 CEST)
A continuous Deep Belief Network (cDBN) with two hidden layers is proposed in this paper, focusing on the problem of weak feature learning ability when dealing with continuous data. In cDBN, the input data is trained in an unsupervised way by using continuous version of transfer functions, the contrastive divergence is designed in hidden layer training process to raise convergence speed, an improved dropout strategy is then implemented in unsupervised training to realize features learning by de-cooperating between the units, and then the network is fine-tuned using back propagation algorithm. Besides, hyper-parameters are analysed through stability analysis to assure the network can find the optimal. Finally, the experiments on Lorenz chaos series, CATS benchmark and other real world like CO2 and waste water parameters forecasting show that cDBN has the advantage of higher accuracy, simpler structure and faster convergence speed than other methods.
ARTICLE | doi:10.20944/preprints201704.0165.v1
Subject: Engineering, Electrical & Electronic Engineering Keywords: synthetic aperture radar; features extraction; saliency detection; image fusion
Online: 26 April 2017 (06:06:19 CEST)
Saliency detection in synthetic aperture radar (SAR) image is a difficult problem. This paper proposed a multitask saliency detection (MSD) model for the saliency detection task of SAR image. Firstly, we extract four features of SAR image as the input of the MSD model, which include the intensity, orientation, uniqueness and global contrast. Then, the saliency map is generated by the multitask sparsity pursuit (MTSP) which integrates the multiple features collaboratively. Subjective and objective evaluation of the MSD model verifies its effectiveness. Based on the saliency maps of the source images, an image fusion method is proposed for the SAR and color optical image fusion. The experimental results of real data show the proposed image fusion method is superior to the presenting methods in terms of several universal quality evaluation indexes, as well as in the visual quality. The salient areas in the SAR image can be highlighted and the spatial and spectral details of color optical image can also be preserved in the fusion result.
ARTICLE | doi:10.20944/preprints202008.0330.v1
Subject: Keywords: Skin Detection; Color Space Model; Aggregated Channel Features (ACF) Detector; Histogram Oriented Gradient (HOG) Features Detection; Bootstrap Aggregation Decision Tree Classifier; Spot Detection
Online: 15 August 2020 (03:28:51 CEST)
Human Face and facial parts are the most significant parts as it reveals a person’s true identity. It plays an important role in various biometric applications like crowd analysis, human tracking, photography, cosmetic surgery, etc. There are many techniques are available to detect a facial image. Among them, skin detection is the most popular one. The aim of this paper is to detect first the person's identity from facial image and finally check any spot present the the detected person. The first step is to detect the maximum skin region based on a combination method of RGB and HSV color space model. Next it is to verify the skin areas of human through machine learning approach. The Aggregated Channel Features (ACF) detector is used to identify the different facial parts like eye pairs, nose, and mouth. Bootstrap aggregation decision tree classifier is applied to classify the person’s identity based on Histogram Oriented Gradient (HOG) features value. The experimental results show that the proposed method gives the average 97% accuracy.
ARTICLE | doi:10.20944/preprints202211.0039.v1
Subject: Life Sciences, Genetics Keywords: Staphylococcus aureus, MRSA ST239, osteomyelitis, genome features, adaptation; chronic infection
Online: 2 November 2022 (03:34:29 CET)
Abstract. The increasing frequency of isolation of methicillin-resistant Staphylococcus aureus (MRSA) limits the chances of effective antibacterial therapy of staphylococcal diseases and results in development of persistent infection such as bacteremia and osteomyelitis. The aim of this study was to identify features of the MRSAST239 0943-1505-2016 (SA943) genome, that contribute to the formation of both acute and chronic musculoskeletal infections. The analysis was performed using comparative genomics data of the dominant epidemic S. aureus lineages namely ST1, ST8, ST30, ST36, ST239. SA943 genome encodes proteins that provide resistance to the host immune system, suppress immunological memory and form biofilms. The molecular mechanisms of adaptation responsible for development of persistent infection were as follows: amino acid substitution in PBP2 and PBP2a, providing resistance to ceftaroline; loss of a large part of prophage DNA and restoration of nucleotide sequence of beta-hemolysin, that greatly facilitates escape of phagocytosed bacteria from phagosome and formation of biofilms; dysfunction of the AgrA system due to the presence of psm-mec and several amino acid substitutions in the AgrC; partial deletion of nucleotide sequence in genomic island vSAβ resulting in the loss of two proteases of Spl - operon; deletion of SD repeats in SdrE amino acid sequence.
ARTICLE | doi:10.20944/preprints202107.0014.v1
Subject: Medicine & Pharmacology, Clinical Neurology Keywords: EEG; music therapy; acoustic features; machine learning; emotional-response predictions
Online: 1 July 2021 (11:12:19 CEST)
Music has the ability to evoke a wide variety of emotions in human listeners. Research has shown that treatment for depression and mental health disorders is significantly more effective when it is complemented by music therapy. However, because each human experiences music-induced emotions differently, there is no systematic way to accurately predict how people will respond to different types of music at an individual level. In this experiment, a model is created to predict humans’ emotional responses to music from both their electroencephalographic data (EEG) and the acoustic features of the music. By using recursive feature elimination (RFE) to extract the most relevant and performing features from the EEG and music, a regression model is fit and accurately correlates the patient’s actual music-induced emotional responses and model’s predicted responses. By reaching a mean correlation of r = 0.788, this model is significantly more accurate than previous works attempting to predict music-induced emotions (e.g. a 370% increase in accuracy as compared to Daly et al. (2015)). The results of this regression fit suggest that accurately predicting how people respond to music from brain activity is possible. Furthermore, by testing this model on specific features extracted from any musical clip, music that is most likely to evoke a happier and pleasant emotional state in an individual can be determined. This may allow music therapy practitioners, as well as music-listeners more broadly, to select music that will improve mood and mental health.
ARTICLE | doi:10.20944/preprints201904.0244.v1
Subject: Keywords: salient object; local binary pattern; histogram features; conditional random field
Online: 22 April 2019 (11:40:11 CEST)
We propose a novel method for salient object detection in different images. Our method integrates spatial features for efficient and robust representation to capture meaningful information about the salient objects. We then train a conditional random field (CRF) using the integrated features. The trained CRF model is then used to detect salient objects during the online testing stage. We perform experiments on two standard datasets and compare the performance of our method with different reference methods. Our experiments show that our method outperforms the compared methods in terms of precision, recall, and F-Measure.
ARTICLE | doi:10.20944/preprints201811.0436.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: sentiment analysis; opinion mining; linguistic features; classification; very negative opinions
Online: 19 November 2018 (09:35:13 CET)
In this paper, we examine the performance of several classifiers in the process of searching for very negative opinions. More precisely, we do an empirical study that analyzes the influence of three types of linguistic features (n-grams, word embeddings, and polarity lexicons) and their combinations when they are used to feed different supervised machine learning classifiers: Support Vector Machine (SVM), Naive Bayes (NB), and Decision Tree (DT).
ARTICLE | doi:10.20944/preprints201801.0017.v1
Subject: Mathematics & Computer Science, Information Technology & Data Management Keywords: Wikipedia; Polish; information quality; linguistic features; linguistics; data mining; NLP
Online: 3 January 2018 (02:03:51 CET)
Wikipedia is the most popular and the largest user-generated source of knowledge on the Web. Quality of the information in this encyclopedia is often questioned. Therefore, Wikipedians have developed an award system for high quality articles, which follows the specific style guidelines. Nevertheless, more than 1.2 million articles in Polish Wikipedia are unassessed. This paper considers over 100 linguistic features to determine the quality of Wikipedia articles in Polish language. We evaluate our models on 500,000 articles of Polish Wikipedia. Additionally, we discuss the importance of linguistic features for quality prediction.
ARTICLE | doi:10.20944/preprints202211.0304.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: CGAN; Styles & Features Renovation; Street Façade; world heritage city; Wuyi area
Online: 16 November 2022 (09:55:23 CET)
With the development of society and the economy, the unified planning of architectural style has become a difficult problem in the competition between urban expansion and the protection of tra-ditional buildings in villages and towns. At the same time, it also allows people to re-examine the appearance and quality of life of traditional village buildings. In this paper, the Conditional Gen-erative Adversarial Network (CGAN) is used to construct a method of building facade generation in villages and towns, so as to gradually realize the governance of the style of villages and towns. At the same time, it has also reduced the restoration of the facades of villages and towns and the graphic design of rural tourism products, showing its application value and potential in the field of planning and design. In the research, taking villages and towns in the Wuyishan area of China as an example, the method is used to carry out model training, image generation, and comparison of the derivation results of different assumed building contours and product contours. The research shows that: (1) CGAN can be used to derive and design the facades of conventional civil buildings in villages and towns. (2) In terms of product graphic design, especially the common tourist cultural products fans and water cups, show significant potential. (3) The construction of this method is not only applicable to villages and towns under the World Heritage City, but can be further promoted and used in the future for cities and villages that have a demand for architectural style consistency.
REVIEW | doi:10.20944/preprints202012.0479.v1
Subject: Mathematics & Computer Science, Algebra & Number Theory Keywords: Image classification; Texture image analysis; Discriminant features; Combination methods; texture operators
Online: 18 December 2020 (16:21:50 CET)
In many image processing and computer vision applications, the main aim is to describe image contents. So, different visual properties such as color, texture and shape are extracted to make aim. In this respect, texture information play important role in image description and visual pattern classification. Texture is referred to a specific local distribution of intensities that is repeated throughout the image. Since now different operations or descriptors have been proposed to analysis texture characteristics. In the multi object images specific texture operators usually doesn’t provide accurate results. So, in many cases, combination of texture operators are used to achieve more discriminant features. In this paper, some combination methods are survived to analysis effect of combinational texture features in image content description. Also, in the result part, different related methods are compared in terms of accuracy and computational complexity.
ARTICLE | doi:10.20944/preprints202002.0378.v3
Subject: Medicine & Pharmacology, Other Keywords: Coronavirus Disease 2019; SARS-CoV-2; clinical features; laboratory; outcomes; epidemic.
Online: 11 March 2020 (10:35:01 CET)
Introduction: An epidemic of Coronavirus Disease 2019 (COVID-19) begun in December 2019 in China, causing a Public Health Emergency of International Concern. Among raised questions, clinical, laboratory, and imaging features have been partially characterized in some observational studies. No systematic reviews have been published on this matter. Methods: We performed a systematic literature review with meta-analysis, using three databases to assess clinical, laboratory, imaging features, and outcomes of COVID-19 confirmed cases. Observational studies, and also case reports, were included and analyzed separately. We performed a random-effects model meta-analysis to calculate the pooled prevalence and 95% confidence interval (95%CI). Results: 660 articles were retrieved (1/1/2020-2/23/2020). After screening by abstract/title, 27 articles were selected for full-text assessment. Of them, 19 were finally included for qualitative and quantitative analyses. Additionally, 39 case report articles were included and analyzed separately. For 656 patients, fever (88.7%, 95%CI 84.5-92.9%), cough (57.6%, 40.8-74.4%) and dyspnea (45.6%, 10.9-80.4%) were the most prevalent manifestations. Among the patients, 20.3% (95%CI 10.0-30.6%) required intensive care unit (ICU), with 32.8% presenting acute respiratory distress syndrome (ARDS) (95%CI 13.7-51.8), 6.2% (95%CI 3.1-9.3) with shock and 13.9% (95%CI 6.2-21.5%) of hospitalized patients with fatal outcomes (case fatality rate, CFR).Conclusion: COVID-19 brings a huge burden to healthcare facilities, especially in patients with comorbidities. ICU was required for approximately 20% of polymorbid, COVID-19 infected patients and this group was associated with a CFR of over 13%. As this virus spreads globally, countries need to urgently prepare human resources, infrastructure, and facilities to treat severe COVID-19.
ARTICLE | doi:10.20944/preprints201812.0250.v3
Subject: Earth Sciences, Geoinformatics Keywords: Built-settlements; urban features; spatial growth; , random forest; dasymetric modelling; population
Online: 9 October 2019 (10:48:20 CEST)
Mapping settlement extents at the annual time step has a wide variety of applications in demography, public health, sustainable development, and many other fields. Recently, while more multitemporal urban feature or human settlement datasets have become available, issues still exist in remotely-sensed imagery due to coverage, adverse atmospheric conditions, and expenses involved in producing such feature sets. These challenges make it difficult to increase temporal coverage while maintaining high fidelity in the spatial resolution. Here we demonstrate an interpolative and flexible modeling framework for producing annual built-settlement extents. We use a combined technique of random forest and spatio-temporal dasymetric modeling with open source subnational data to produce annual 100m x 100m resolution binary settlement maps in four test countries of varying environmental and developmental contexts for test periods of five-year gaps. We find that in the majority of years, across all study areas, the model correctly identified between 85-99% of pixels that transition to built-settlement. Additionally, with few exceptions, the model substantially out performed a model that gave every pixel equal chance of transitioning to the category “built” in each year. This modelling framework shows strong promise for filling gaps in cross-sectional urban feature datasets derived from remotely-sensed imagery, provide a base upon which to create future built/settlement extent projections, and further explore the relationships between built area and population dynamics.
ARTICLE | doi:10.20944/preprints202212.0405.v1
Subject: Earth Sciences, Geoinformatics Keywords: hyperspectral data; few-shot learning; deep features; convolution kernels; edge-preserving filtering
Online: 22 December 2022 (01:44:48 CET)
In recent years, different deep learning frameworks were introduced for hyperspectral image (HSI) classification. However, the proposed network models have a higher model complexity and do not provide high classification accuracy if few-shot learning is used. This paper pre-sents an HSI classification method that combines random patches network (RPNet) and re-cursive filtering (RF) to obtain informative deep features. The proposed method first convolves image bands with random patches to extract multi-level deep RPNet features. Thereafter, the RPNet feature set is subjected to dimension reduction through principal component analysis (PCA) and the extracted components are filtered using the RF procedure. Finally, HSI spectral features and the obtained RPNet-RF features are combined to classify the HSI using a support vector machine (SVM) classifier. In order to test the performance of the proposed RPNet-RF method, some experiments were performed on three widely known datasets using a few training samples for each class and classification results were compared with those obtained by other advanced HSI classification methods adopted for small training samples. The comparison showed that the RPNet-RF classification is characterized by higher values of such evaluation metrics as overall accuracy and Kappa coefficient (https://github.com/UchaevD/RPNet-RF).
ARTICLE | doi:10.20944/preprints202104.0736.v1
Subject: Engineering, Automotive Engineering Keywords: forest fire; image recognition; graph neural network; convolutional neural network; dynamic features
Online: 28 April 2021 (09:58:49 CEST)
Forest fire identification is important for forest resource protection. Effective monitoring of forest fires requires the deployment of multiple monitors with different viewpoints, while most traditional recognition models can only effectively recognize images from a single source, often because they ignore the correlation information between images from different viewpoints, resulting in inaccurate visual similarity estimation for multiple source samples and generating the problems of missed and high false alarm rates. In order to solve the problems, a similarity-guided graph neural network model based on the dynamic characteristics of images is proposed in this paper. The method converts the input features of the nodes on the graph into relational features of different gallery pairs by establishing pairs (nodes) that represent different viewpoint images and gallery images. The dynamic feature update of the image gallery using the new feature-bank relationship enables the estimation of the similarity between images and improves the image recognition rate of the model. Besides, to reduce the complicated pre-processing process and extract the key features in the images effectively, this paper also proposes a dynamic feature extraction method for fire regions based on image segment ability. By setting the threshold value of HSV color space, the fire region is segmented from the image and the fire region frames are calculated for dynamic feature extraction. The experimental results on the open-source forest fire dataset and our collected forest fire dataset show that the performance of the method in this paper is improved by 4% compared with Resnet, the theme during this paper may be tailored to totally different fire eventualities and has sensible generalization and interference resistance.
ARTICLE | doi:10.20944/preprints202101.0468.v1
Subject: Materials Science, Biomaterials Keywords: selective laser melting; Ti6Al4V; acid etching; chemical oxidation; thermochemical treatment; surface features.
Online: 25 January 2021 (10:12:21 CET)
Ti6Al4V samples obtained by selective laser melting were subjected to acid treatment, chemical oxidation in hydrogen peroxide solution and subsequent thermochemical treatment. The effect of temperature and time of acid etching of Ti6Al4V samples on surface roughness, morphology, topography and chemical and phase composition after the thermochemical treatment was studied. The surfaces were characterized using scanning electron microscopy, energy dispersive X-ray spectroscopy, X-ray diffraction and contact profilometry. Pore and protrusion sizes were measured. Acid etching modified the elemental composition and surface roughness of the alloy. Temperature had a greater influence on the morphology, topography and surface roughness of samples than time. Increases in roughness values were observed when applying successive chemical oxidation and thermochemical treatment compared to the values observed on surfaces with acid etching. After the thermochemical treatment, the samples with acid etching at a temperature of 80 °C showed a multiscale topography. In addition, a network-shaped structure was obtained on all surfaces, both on their protrusions and pores previously formed during the acid etching.
ARTICLE | doi:10.20944/preprints201705.0027.v2
Subject: Social Sciences, Geography Keywords: remote sensing; image registration; multiple image features; different viewpoint; non-rigid distortion
Online: 13 June 2017 (09:52:10 CEST)
Remote sensing image registration plays an important role in military and civilian fields, such as natural disaster damage assessment, military damage assessment and ground targets identification, etc. However, due to the ground relief variations and imaging viewpoint changes, non-rigid geometric distortion occurs between remote sensing images with different viewpoint, which further increases the difficulty of remote sensing image registration. To address the problem, we propose a multi-viewpoint remote sensing image registration method which contains the following contributions. (i) A multiple features based finite mixture model is constructed for dealing with different types of image features. (ii) Three features are combined and substituted into the mixture model to form a feature complementation, i.e., the Euclidean distance and shape context are used to measure the similarity of geometric structure, and the SIFT (scale-invariant feature transform) distance which is endowed with the intensity information is used to measure the scale space extrema. (iii) To prevent the ill-posed problem, a geometric constraint term is introduced into the L2E-based energy function for better behaving the non-rigid transformation. We evaluated the performances of the proposed method by three series of remote sensing images obtained from the unmanned aerial vehicle (UAV) and Google Earth, and compared with five state-of-the-art methods where our method shows the best alignments in most cases.
ARTICLE | doi:10.20944/preprints201703.0152.v1
Subject: Mathematics & Computer Science, Information Technology & Data Management Keywords: deep convolutional neural networks; identification; semi-verification; multi-scale features; face verification
Online: 20 March 2017 (09:06:18 CET)
Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks(CNN) for face verification. In this work, we explore to use identification signal to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose to use different landmarks of faces to solve the problems caused by poses. And the final face representation is formed by the concatenating feature of each deep CNN after PCA reduction. What's more, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on LFW dataset.
ARTICLE | doi:10.20944/preprints202203.0403.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: behavioral change prediction; learned features; deep feature learning; handcrafted features; bidirectional long-short term memory; autoencoders; temporal convolutional neural network; clinical decision support system; multisensory stimulation therapy; physiological signals.
Online: 31 March 2022 (08:38:58 CEST)
Predicting change from multivariate time series has relevant applications ranging from medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient’s behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aims to predict changes in behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a Temporal Convolutional Network, and the behavioral state was predicted through Bidirectional Long Short-Term Memory Auto-Encoder, operating jointly. From the comparison with the state-of-the-art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.
Subject: Medicine & Pharmacology, General Medical Research Keywords: COVID-19; SARS-CoV-2; epidemic dynamics; disease control; clinical features; tropical area
Online: 8 July 2020 (12:30:52 CEST)
Objective: The objective of this study is to determine the epidemic dynamics and clinical features of COVID-19 in southern Hainan Island, China, and provide experience for other tropical areas of the world. Methods: This retrospective study included confirmed cases of COVID-19 in southern Hainan. All enrolled patients were treated in Sanya, and data on epidemiological and clinical features of the disease and infection prevention and control measures adopted by the local government during the epidemic were collected. Results: Of the 74 cases, 71 (95.95%) were imported from Wuhan, Hubei Province (47, 63.51%), other cities in Hubei Province (11, 14.86%), or provinces other than Hubei and Hainan (13, 17.57%). Three (4.06%) patients were infected in southern Hainan, including one autochthonous case in Sanya. Fifty-four cases (72.97%) were detected in Sanya, and 27 cases (27.03%) were diagnosed in other cities. The rate of severe or critical cases was 28.38% (21/74), and mortality was 2.7% (2/74). The serum lactate levels and base excess of severe-critical patients were higher than those of patients with mild-moderate disease. Multivariate logistic regression analysis showed that chronic conditions were risk factors for severe and critical COVID-19. Seventy-four patients were diagnosed with COVID-19 over a 22-day period in Sanya, and the epidemic period in the city was 48 days. The outbreak was controlled rapidly because the local government adopted strict infection prevention and control measures. Conclusions: The clinical characteristics of COVID-19 in Hainan Island were similar to those reported in other regions. In Sanya, the rate of severe and very severe cases was higher than in other regions; however, most cases were imported, and there was only one autochthonous case. The rapid control of the outbreak in Sanya may be related to the tropical climate, adoption of strict infection prevention and control measures, daily reporting of new cases, increased public awareness about the epidemic, and other emergency actions implemented by the local government.
ARTICLE | doi:10.20944/preprints202210.0081.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: CNN; AI; Causality; Understandability; Object Features; Excitation Weight; Multi-model Neural Network; Model Selection
Online: 7 October 2022 (14:58:09 CEST)
Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.
ARTICLE | doi:10.20944/preprints202012.0237.v1
Subject: Mathematics & Computer Science, Algebra & Number Theory Keywords: Biometrics; Face Recognition; Single Sample Face Recognition; Binarized Statistical Image Features; K-Nearest Neighbors
Online: 9 December 2020 (18:25:02 CET)
Single sample face recognition (SSFR) is a computer vision challenge. In this scenario, there is only one example from each individual on which to train the system, making it difficult to identify persons in unconstrained environments, particularly when dealing with changes in facial expression, posture, lighting, and occlusion. This paper suggests a different method based on a variant of the Binarized Statistical Image Features (BSIF) descriptor called Multi-Block Color-Binarized Statistical Image Features (MB-C-BSIF) to resolve the SSFR Problem. First, the MB-C-BSIF method decomposes a facial image into three channels (e.g., red, green, and blue), then it divides each channel into equal non-overlapping blocks to select the local facial characteristics that are consequently employed in the classification phase. Finally, the identity is determined by calculating the similarities among the characteristic vectors adopting a distance measurement of the k-nearest neighbors (K-NN) classifier. Extensive experiments on several subsets of the unconstrained Alex & Robert (AR) and Labeled Faces in the Wild (LFW) databases show that the MB-C-BSIF achieves superior results in unconstrained situations when compared to current state-of-the-art methods, especially when dealing with changes in facial expression, lighting, and occlusion. Furthermore, the suggested method employs algorithms with lower computational cost, making it ideal for real-time applications.
ARTICLE | doi:10.20944/preprints201810.0739.v1
Subject: Engineering, Electrical & Electronic Engineering Keywords: Event-Driven Processing, Speech recognition, Adaptive Resolution Analysis, Features extraction, Dynamic Time Warping, Classification
Online: 31 October 2018 (08:14:15 CET)
This paper proposes a novel approach, based on the adaptive rate processing and analysis, for the isolated speech recognition. The idea is to smartly combine the event-driven signal acquisition and windowing along with adaptive rate processing, analysis and classification for realizing an effective isolated speech recognition. The incoming speech signal is digitized with an event-driven A/D converter (EDADC). The output of EDADC is windowed with an activity selection process. These windows are later on resampled uniformly with an adaptive rate interpolator. The resampled windows are de-noised with an adaptive rate filter and their spectrum are computed with an adaptive resolution short time Fourier transform (ARSTFT). Later on, the magnitude, Delta and Delta-Delta spectral coefficients are extracted. The Dynamic Time Warping (DTW) technique is employed to compare these extracted features with the reference templates. The comparison outcomes are used to make the classification decision. The system functionality is tested for a case study and results are presented. An 8.2 times reduction in acquired number of samples is achieved by the devised approach as compared to the classical one. It aptitudes a significant computational gain and power consumption reduction of the proposed system over the counter classical ones. An average subject dependent isolated speech recognition accuracy of 96.8% is achieved. It shows that the proposed approach is a potential candidate for the automatic speech recognition applications like rehabilitation centers, smart call centers, smart homes, etc.
ARTICLE | doi:10.20944/preprints201711.0115.v1
Subject: Social Sciences, Marketing Keywords: FMCG; retail sales; geography methods; mesoscopic sales features; goods distribution strategy; development of economy
Online: 17 November 2017 (17:15:34 CET)
With the rapidly increasing of people’s purchasing power, the fast moving consumer goods (FMCG) industry is supposed to grow dramatically. In order to gain more market access and profile, it is important for the FMCG manufacturers and retailers to find the preferences and provincial characteristics of consumers, to develop more suitable goods distribution strategy. Based on retails marketing data with geographic characteristics, this paper proposes a new combination of geography methods to solve the problems in distribution of FMCG. Via multiple K-means clustering and cross validation of KNN half off, the mesoscopic sales features are extracted through the classification of retails, which can indirectly grasp the consumer behavior characteristics. Based on space division and Moran’ I spatial autocorrelation arithmetic, two strategies are developed to satisfy consumer’s needs and promote sales, including conservative and positive strategies. According to our analysis, the total sales volume of the regions will increase by 5.1% and 10.3%. This study can be applied to the provide purchase strategies for FMCG retails according to their locations. The research can explore the consumption potential of different areas, thus improving the profile of retails and the development of economy in more mesoscopic scale.
ARTICLE | doi:10.20944/preprints202010.0168.v2
Subject: Mathematics & Computer Science, Algebra & Number Theory Keywords: Genetic Programming; Evolutionary Computation; Machine Learning; Classification; Multiclass Classification; Feature Construction; Hyper-features; Spectral Indices
Online: 24 December 2020 (08:59:19 CET)
Genetic Programming (GP) is a powerful Machine Learning (ML) algorithm that can produce readable white-box models. Although successfully used for solving an array of problems in different scientific areas, GP is still not well known in Remote Sensing. The M3GP algorithm, a variant of the standard GP algorithm, performs Feature Construction by evolving hyper-features from the original ones. In this work, we use the M3GP algorithm on several sets of satellite images over different countries to create hyper-feature from satellite bands to improve the classification of land cover types. We add the evolved hyper-features to the reference datasets and observe a significant improvement of the performance of three state-of-the-art ML algorithms (Decision Trees, Random Forests and XGBoost) on multiclass classifications and no significant effect on the binary classifications. We show that adding the M3GP hyper-features to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI and NBR. We also compare the performance of the M3GP hyper-features in the binary classification problems with those created by other Feature Construction methods like FFX and EFS.
ARTICLE | doi:10.20944/preprints202001.0219.v1
Subject: Life Sciences, Virology Keywords: protruding features; spherical virus; point arrays; surface modifications; VLP; drug delivery; icosahedral; nanomedicine; ligand binding
Online: 20 January 2020 (06:59:09 CET)
Since its introduction, the Triangulation number has been the most successful and ubiquitous scheme for classifying spherical viruses. However, despite its many successes, it fails to describe the relative angular orientations of proteins, as well as their radial mass distribution within the capsid. It also fails to provide any insight into critical sites of stability, modifications or possible mutations. We show how classifying spherical viruses using icosahedral point arrays, introduced by Keef and Twarock, unveils new geometric rules and constraints for understanding virus stability and key locations for exterior and interior modifications. We present a modified fitness measure which classifies viruses in an unambiguous and rigorous manner, irrespective of local surface chemistry, steric hinderance, solvent accessibility or triangulation number. We then utilize these point arrays to explain the immutable surface loops of bacteriophage MS2, the relative reactivity of surface lysines in CPMV and the non-quasiequivalent flexibility of the HBV dimers. We explain how using sister and double point arrays can function as predictive tools for site directed modifications in other systems. This success builds on our previous work showing that viruses place their protruding features along the great circles of the asymmetric unit, demonstrating that viruses indeed adhere to these geometric constraints.
ARTICLE | doi:10.20944/preprints201710.0017.v1
Subject: Biology, Forestry Keywords: forest stand parameters; SPOT-5 satellite image; textural and spectral features; topographic information; estimation model
Online: 3 October 2017 (16:33:25 CEST)
In recent years, remote sensing technology has been widely used to predict forest stand parameters. In order to compare the effects of different features of remote sensing images and topographic information on the prediction of forest stand parameters, multivariate stepwise regression analysis method was used to build estimation models for important forest stand parameters by using textural and spectral features as well as topographic information of SPOT-5 satellite images in northeastern Heilongjiang Province in China as independent variables. The study results show that the optimal window to predict forest stand parameters using textural features of SPOT-5 satellite image is 9×9; the ability of textural features was better than that of spectral features in terms of predicting forest stand parameters; with the inclusion of topographic information, the accuracy of prediction of all models was improved, of which elevation has the most significant effect. The highest accuracy was achieved when predicting the stand volume (SV) (R2adj=0.820), followed by basal area (BA) (R2adj =0.778), accuracy of both above models exceeded 75%. The results show that models combined use of textural, spectral features and topographic information of SPOT-5 images have a good application prospect in predicting forest stand parameters.
ARTICLE | doi:10.20944/preprints201706.0036.v1
Subject: Mathematics & Computer Science, Information Technology & Data Management Keywords: two-factor authentication; online training; biological and behavioral features; mimic control method with sound intensity
Online: 6 June 2017 (09:04:47 CEST)
This study examines the evolution of the two-factor authentication method and its adaptability to the online education system. Two-factor authentication is a security measure used especially in areas where information such as banking is valuable. Parallel to technological developments, it has developed as much as daily. It aims to take security one step forward because it is composed of two phases. Today, banking, IOT devices, public transport tickets and many other areas are used. Two-factor authentication methods against security attacks in the field of information are also being updated. In recent years, new technologies such as biometric (iris pattern, retinal pattern, etc.) or behavioral biometry (location tracking, walking information, touch speed etc.) were studied. Instead of physically studying somewhere like going to a course in modern society, online trainings become more advantageous. Most of these online trainings are given certificates such as participation certificate, success certificate, etc. The main problem here is whether the person who is being certified is true. In the study conducted in line with these details, there is a proposal for the application of the Mimic Control Method with Sound Intensity (MCMSI) method for on-line training by examining the two-factor authentication techniques up to the day.
ARTICLE | doi:10.20944/preprints201910.0213.v1
Subject: Mathematics & Computer Science, Computational Mathematics Keywords: Quasi Extended Chebyshev space; optimal normalized totally positive basis; high-order continuity; shape preserving; shape features
Online: 18 October 2019 (11:33:13 CEST)
Firstly, a new set of Quasi-Cubic Trigonometric Bernstein basis with two tension shape parameters is constructed, and we prove that it is an optimal normalized totally basis in the framework of Quasi Extended Chebyshev space. And the Quasi-Cubic Trigonometric Bézier curve is generated by the basis function and the cutting algorithm of the curve are given, the shape features (cusp, inflection point, loop and convexity) of the Quasi-Cubic Trigonometric Bézier curve are analyzed by using envelope theory and topological mapping; Next we construct the non-uniform Quasi-Cubic Trigonometric B-spline basis by assuming the linear combination of the optimal normalized totally positive basis have partition of unity and continuity, and its expression is obtained. And the non-uniform B-spline basis is proved to have totally positive and high-order continuity. Finally, the non-uniform Quasi Cubic Trigonometric B-spline curve and surface are defined, the shape features of the non-uniform Quasi-Cubic Trigonometric B-spline curve are discussed, and the curve and surface are proved to be continuous.
ARTICLE | doi:10.20944/preprints201711.0198.v2
Subject: Life Sciences, Virology Keywords: human coronavirus; MERS-CoV; clinical features; upper respiratory tract infections; lower respiratory tract infections; respiratory viruses
Online: 30 January 2018 (09:52:03 CET)
Human coronaviruses cause both upper and lower respiratory tract infections in humans. In 2012 a sixth human coronavirus (hCoV) was isolated from a patient presenting with severe respiratory illness. The 60-year-old man died as a result of renal and respiratory failure after admission to a hospital in Jeddah, Saudi Arabia. The aetiological agent was eventually identified as a coronavirus and designated Middle East respiratory syndrome coronavirus (MERS-CoV). MERS-CoV has now been reported in more than 27 countries across the Middle East, Europe, North Africa and Asia. As of July 2017, 2040 MERS-CoV laboratory confirmed cases, resulting in 712 deaths, were reported globally, with a majority of these cases from the Arabian Peninsula. This review summarises the current understanding of MERS-CoV, with special reference to the (i) genome structure, (ii) clinical features, (iii) diagnosis of infection and (iv) treatment and vaccine development.
ARTICLE | doi:10.20944/preprints201710.0181.v1
Subject: Mathematics & Computer Science, Analysis Keywords: ultrasound image analysis; speckle noise; synthetic ultrasound images; texture features; local binary patterns; image quality assessment
Online: 30 October 2017 (09:37:59 CET)
Speckle noise reduction is an important area of research in the field of ultrasound image processing. Several algorithms for speckle noise characterization and analysis have been recently proposed in the area. Synthetic ultrasound images can play a key role in noise evaluation methods as they can be used to generate a variety of speckle noise models under different interpolation and sampling schemes, and can also provide valuable ground truth data for estimating the accuracy of the chosen methods. However, not much work has been done in the area of modelling synthetic ultrasound images, and in simulating speckle noise generation to get images that are as close as possible to real ultrasound images. An important aspect of simulated synthetic ultrasound images is the requirement for extensive quality assessment for ensuring that they have the texture characteristics and gray-tone features of real images. This paper presents texture feature analysis of synthetic ultrasound images using local binary patterns (LBP) and demonstrates the usefulness of a set of LBP features for image quality assessment. Experimental results presented in the paper clearly show how these features could provide an accurate quality metric that correlates very well with subjective evaluations performed by clinical experts.
ARTICLE | doi:10.20944/preprints202106.0016.v2
Subject: Engineering, Biomedical & Chemical Engineering Keywords: brain-computer interface; EEG signal; artificial neural networks, LabVIEW application; features extraction; eye-blinks detection; EEG headset
Online: 4 January 2022 (17:56:46 CET)
This paper proposes several LabVIEW applications to accomplish the data acquisition, processing, features extraction and real-time classification of the electroencephalographic (EEG) signal detected by the embedded sensor of the NeuroSky Mindwave Mobile headset. The LabVIEW applications are aimed at the implementation of a Brain-Computer Interface system, which is necessary to people with neuromotor disabilities. It is analyzed a novel approach regarding the preparation and automatic generation of the EEG dataset by identifying the most relevant multiple mixtures between selected EEG rhythms (both time and frequency domains of raw signal, delta, theta, alpha, beta, gamma) and extracted statistical features (mean, median, standard deviation, route mean square, Kurtosis coefficient and others). The acquired raw EEG signal is processed and segmented into temporal sequences corresponding to the detection of the multiple voluntary eye-blinks EEG patterns. The main LabVIEW application accomplished the optimal real-time artificial neural networks techniques for the classification of the EEG temporal sequences corresponding to the four states: 0 - No Eye-Blink Detected; 1 - One Eye-Blink Detected; 2 – Two Eye-Blinks Detected and 3 – Three Eye-Blinks Detected. Nevertheless, the application can be used to classify other EEG patterns corresponding to different cognitive tasks, since the whole functionality and working principle could estimate the labels associated with various classes.
REVIEW | doi:10.20944/preprints202102.0319.v2
Subject: Medicine & Pharmacology, Other Keywords: SARS-CoV-2; COVID-19; Non-Communicable Chronic Diseases (NCCDs); Clinical features; Institucionalized or hospitalized elderly; meta-analisys.
Online: 1 July 2021 (11:21:00 CEST)
Abstract: The objective of this meta-analysis was to evaluate the factors associated with mortality of elderly Italians diagnosed with the new coronavirus who resided in institutions or who were hospitalized as a result of the disease. Methods: A systematic review following the recommenda-tions of The Joanna Briggs Institute (JBI), where the PEO strategy was utilized - Population, Exposure and Outcome. P, being the elderly over 65 years old. E, the SARS-CoV_2 pandemic. O, mortality. The NCBI / PubMed, LILACS, EMBASE and CINAHL databases were used until July 31, 2020.; Results: Five Italian studies were included in the meta-analysis, with the number of elderly people varying between 18 and 1591 patients. The main morbidities presented by the elderly in the studies were: dementia, diabetes, chronic kidney disease and hypertension. Conclusions: The factors as-sociated with the mortality of elderly Italian people diagnosed with SARS-CoV-2 who lived in in-stitutions or who were hospitalized because of the disease were evaluated. It was found that de-mentia, diabetes, chronic kidney disease and hypertension are the main the main diagnosed dis-eases for mortality in elderly people with Covid-19.
ARTICLE | doi:10.20944/preprints202001.0220.v1
Subject: Mathematics & Computer Science, Artificial Intelligence & Robotics Keywords: heart disease; coronary artery disease; machine learning; deep learning; predictive features; coronary artery disease diagnosis; health informatics
Online: 20 January 2020 (09:11:14 CET)
Heart disease is one of the most common diseases in middle-aged citizens. Among the vast number of heart diseases, coronary artery disease (CAD) is considered a common cardiovascular disease with a high death rate. The most popular tool for diagnosing CAD is the use of medical imaging, e.g., angiography. However, angiography is known for being costly and also associated with a number of side effects. Hence, the purpose of this study is to increase the accuracy of coronary heart disease diagnosis by selecting significant predictive features in order of their ranking. In this study, we propose an integrated method using machine learning. The machine learning methods of random trees (RTs), the decision tree of C5.0, support vector machine (SVM), the decision tree of Chi-squared automatic interaction detection (CHAID) are used in this study. The proposed method shows promising results and the study confirms that the RTs model outperforms other models.
ARTICLE | doi:10.20944/preprints201905.0344.v1
Subject: Social Sciences, Other Keywords: religious pluralism; decolonization of mind; semi-structured interview; psychological features; Hinduism; Indian culture; religious rights of human
Online: 29 May 2019 (05:03:27 CEST)
This article presents the study of religious pluralism and decolonization of Indian mind in Russia. The paper analyzes the investigation results concerning psychological features of modern Indian students from universities in Russia and India. For measuring of connection between religious pluralism and decolonization of Indian mind we made socio-psychological investigation of Indian students. We made 254 semi-structured interview with Indian students who are studying in Russia and India. According to the result of investigation that decolonization of Indian mind is connected with the level of religious pluralism. Among the values principles of religious pluralism get more significance and importance in decolonizing mind of Indian students.
ARTICLE | doi:10.20944/preprints201809.0390.v1
Subject: Engineering, Other Keywords: Ovarian Cancer; Features Classification; Self-Organizing Map; Optimal Neural Networks; Adaptive Harmony Search Optimization; Internet of Things
Online: 19 September 2018 (16:15:56 CEST)
Ovarian Cancer (OC) is a type of cancer that affects ovaries in women, and is difficult to detect at initial stage due to which it remains as one of the leading causes of cancer death. The ovarian cancer data generated from the Internet of Medical Things (IoMT) was used and a novel approach was proposed for distinguishing the ovarian cancer by utilizing Self Organizing Maps (SOM) and Optimal Recurrent Neural Networks (ORNN). SOM algorithm was utilized for better feature subset selection and was also utilized for separating profitable, understood and intriguing data from huge measures of medical data. In supervised learning techniques, the SOM-based feature selection seems to be a tougher challenge because of the absence of class labels that would guide the search for relevant information to the classifier model. The classification approach can identify ovarian cancer data as benign/malignant. The ovarian cancer detection process can be improved by optimizing the weights of RNN structure using Adaptive Harmony Search Optimization (AHSO). The proposed model in this study can be used to detect cancer at early stages with high accuracy and low Root Mean Square Error (RMSE).
ARTICLE | doi:10.20944/preprints201806.0282.v1
Subject: Earth Sciences, Geoinformatics Keywords: land-use/land-cover; multi-decadal change analysis; irrigation ponds; textural features; supervised classification; multi-source data
Online: 18 June 2018 (16:40:31 CEST)
A multi-decadal change analysis of the irrigation ponds in Taoyuan, Taiwan was conducted by using multi-source data including digitized ancient maps, declassified single-band CORONA satellite images, and multispectral SPOT images. Supervised LULC classifications were conducted using four textural features derived from the single-band CORONA images and spectral features derived from SPOT images. Post-classification analysis revealed that the number of irrigation ponds in the study area decreased during the post-World War II farmland consolidation period (1945 – 1965) and the subsequent industrialization period (1970 – 2000). However, efforts on restoration of irrigation ponds in recent years have resulted in gradual increases in the number (9%) and total area (12%) of irrigation ponds in the study area.
COMMUNICATION | doi:10.20944/preprints202011.0720.v1
Subject: Biology, Anatomy & Morphology Keywords: Papillary thyroid cancer; noninvasive follicular thyroid neoplasm with papillary-like nuclear features; follicular adenoma; telomere-related genomic instability
Online: 30 November 2020 (11:37:22 CET)
Papillary thyroid carcinoma (PTC) has two main histologic variants: classical-PTC (CL-PTC) and follicular variant PTC (FV-PTC). Recently, due to its similar features to benign lesions, the encapsulated FV-PTC variant was reclassified as noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP). Nonetheless, specific molecular signatures are not yet available. It is well known that telomere-related genome instability is caused by inappropriate DNA repair of dysfunctional telomeres and that mechanisms involved in the damaged telomere repair processing may led to detrimental outcomes, altering the 3D nuclear telomere and genome organization in cancer cells. This pilot study aimed to evaluate whether a specific nuclear telomere architecture might characterize NIFTP, potentially distinguishing it from other PTC histologic variants. Our findings demonstrate that 3D telomere profiles of CL-PTC and FV-PTC were different from NIFTP and that NIFTP more closely resembles follicular thyroid adenoma (FTA). NIFTP has longer telomeres than CL-PTC and FV-PTC samples and telomere length overlaps in NIFTP and FTA. There was no association between BRAF expression and telomere length in all tested samples. Our data showing that 3D nuclear telomere organization is altered differently in thyroid cancer variants, suggest that this parameter might guide clinical management of NIFTP. Although further investigations in a larger cohort of patients are necessary to corroborate our observations, telomere-related genomic instability might be of value in the diagnosis of NIFTP and allow for a more appropriate selection of the correct treatment.
ARTICLE | doi:10.20944/preprints201811.0156.v1
Subject: Mathematics & Computer Science, Information Technology & Data Management Keywords: Unmanned Aerial Vehicle (UAV), Haar-like features, real time, Geographic Information Systems (GIS), human detection, geolocation error, OpenCV
Online: 7 November 2018 (09:41:39 CET)
Human detection from Unmanned Aerial Vehicles (UAV) is gaining popularity in the field of disaster management, crowd counting, people monitoring. Real time human detection from UAV is a challenging task, because of many constraints involved. This study proposes a system for real time detection of humans on videos captured from UAVs addressing three of these constraints namely, flying height, computation time and scale of viewing. The proposed method integrated an android application with a binary classifier based on Haar-features to automatically detect human / non-human class from UAV images. The video frames were parsed and detected humans from image frames were geo-localized and visualized on Google Earth. The performance was evaluated for geo-localization accuracy, computation time and detection accuracy, considering human coverage – pixel size relationship for various heights and scale factor. Based on flying height - human size relationship and tradeoff between detection accuracy vs computation time, the study came up with optimal parameters for OpenCV’s cv2.cascadeClassifier. detectMultiScale function. This paper establishes a strong ground for further research relating to real time human detection from UAV.
ARTICLE | doi:10.20944/preprints202106.0482.v3
Subject: Mathematics & Computer Science, Algebra & Number Theory Keywords: COVID-19 Infodemic; Text Classification; TFIDF Features; Network Training modes; Supervised Learning; Misinformation; News Classification; False Publications; PubMed; Anomaly Detection
Online: 26 July 2021 (12:06:04 CEST)
The spread of the Coronavirus pandemic has been accompanied by an infodemic. The false information that is embedded in the infodemic affects people’s ability to have access to safety information and follow proper procedures to mitigate the risks. This research aims to target the falsehood part of the infodemic, which prominently proliferates in news articles and false medical publications. Here, we present NeoNet, a novel supervised machine learning text mining algorithm that analyzes the content of a document (news article, a medical publication) and assigns a label to it. The algorithm is trained by TFIDF bigram features which contribute a network training model. The algorithm is tested on two different real-world datasets from the CBC news network and Covid-19 publications. In five different fold comparisons, the algorithm predicted a label of an article with a precision of 97-99 %. When compared with prominent algorithms such as Neural Networks, SVM, and Random Forests NeoNet surpassed them. The analysis highlighted the promise of NeoNet in detecting disputed online contents which may contribute negatively to the COVID-19 pandemic.
REVIEW | doi:10.20944/preprints201808.0295.v1
Subject: Medicine & Pharmacology, Pediatrics Keywords: NICU; Physio-features; Neonatal imaging; Infrared thermography; Optical coherence tomography; Tissue optics; Near-infrared imaging; Short-wave infrared imaging; Visible light imaging
Online: 17 August 2018 (02:27:17 CEST)
The monitoring of sick newborns is a challenging task that health care providers in Neonatal Intensive Care Units (NICU) must contend with each day. Conventionally, newborns are monitored via probes that are affixed to their skin and attached to processing monitors (Fig.1). However, an alternative exists in contactless imaging to record such physiological signals (Physio-Markers), surface changes and internal structures which can be used independently of, or in conjunction with conventional monitors. Advantages of contactless monitoring methods include: i) quick data generation; ii) lack of contact with skin, which reduces skin breakdown and decreases risk of infection; and iii) minimizing the number of probes and monitors affixed to the skin, which allows greater body surface-area for other care. This paper is an attempt to build a foundation for and to provide a vision of the potential neonatal clinical applications of technologies that use non-contact modalities such as Visible Light Imaging (VLI), Near InfraRed Spectrum (NIRS), and Thermal Imaging (TI) using InfraRed Spectrum (IRS).
ARTICLE | doi:10.20944/preprints202105.0272.v1
Subject: Engineering, Automotive Engineering Keywords: real-time quality prediction; spatio-temporal features; feature importance; recurrent neural network; high-speed infrared imaging; convolutional neural network; lack of fusion (false friends)
Online: 12 May 2021 (13:55:12 CEST)
An effective process monitoring strategy is a requirement for meeting the challenges posed by increasingly complex products and manufacturing processes. To address these needs, this study investigates a comprehensive scheme based on classical machine learning methods, deep learning algorithms, and feature extraction and selection techniques. In a first step, a novel deep learning architecture based on convolutional neural networks (CNN) and gated recurrent units (GRU) is introduced to predict the local weld quality based on mid-wave infrared (MWIR) and near-infrared (NIR) image data. The developed technology is used to discover critical welding defects including lack of fusion (false friends), sagging and lack of penetration, and geometric deviations of the weld seam. Additional work is conducted to investigate the significance of various geometrical, statistical, and spatio-temporal features extracted from the keyhole and weld pool regions. Furthermore, the performance of the proposed deep learning architecture is compared to that of classical supervised machine learning algorithms, such as multi-layer perceptron (MLP), logistic regression (LogReg), support vector machines (SVM), decision trees (DT), random forest (RF) and k-Nearest Neighbors (kNN). Optimal hyperparameters for each algorithm are determined by an extensive grid search. Ultimately, the three best classification models are combined into an ensemble classifier that yields the highest detection rates and achieves the most robust estimation of welding defects among all classifiers studied, which is validated on previously unknown welding trials.
ARTICLE | doi:10.20944/preprints202006.0165.v2
Subject: Life Sciences, Virology Keywords: Conserved signature indels (CSIs) specific for SARS and SARS-CoV-2-related viruses. Molecular markers distinguishing different clades of Sarbecovirus, Evolutionary relationships between SARS and SARS-CoV-2-related viruses, Origin of SARS-CoV-2 and Pangolin CoV_MP789 viruses, Novel sequence and structural features of spike and nucleocapsid proteins. Genetic recombination.
Online: 26 August 2020 (10:17:16 CEST)
Both SARS-CoV-2 (COVID-19) and SARS coronaviruses (CoVs) are members of the subgenus Sarbecovirus. To understand the origin of SARS-CoV-2, protein sequences from sarbecoviruses were analyzed to identify highly-specific molecular markers consisting of conserved inserts or deletions (termed CSIs) in the spike (S) and nucleocapsid (N) proteins that are specific for either particular clusters/lineages of these viruses or are commonly shared by specific lineages. Three novel CSIs in the N-terminal domain of the spike protein S1-subunit (S1-NTD) are uniquely shared by the SARS-CoV-2, BatCoV-RaTG13 and most pangolin CoVs, distinguishing this cluster of viruses (SARS-CoV-2r) from all others. In the same positions, where these CSIs are found, related CSIs are also present in two other sarbecoviruses (viz. CoVZXC21 and CoVZC45 forming CoVZC cluster), which form an out group of the SARS-CoV-2r cluster. These three CSIs are not found in the SARS-CoVs. However, both SARS and SARS-CoV-2r CoVs contain two large CSIs in the C-terminal domain of S1 (S1-CTD), which binds the human ACE-2 receptor, that are absent in the CoVZC cluster of CoVs. These results indicate that while the S1-NTD of the SARS-CoV-2r viruses possesses the sequence characteristics of the CoVZC cluster of CoVs, their S1-CTD resembles the SARS viruses. Thus, the spike protein of SARS-CoV-2r viruses has likely originated from a recombination event between the S1-NTD of the CoVZC viruses and the S1-CTD of SARS viruses. This inference is also supported by the amino acid sequence similarity of the S1-NTD and S1-CTD from SARS-CoV-2 compared to the CoVZC and SARS CoVs. We also present evidence that one of the pangolin-CoV_MP789, whose receptor-binding domain is most similar to the SARS-CoV-2, is also derived by a recent recombination between the S1-NTD of the CoVZC CoVs and the S1-CTD of a SARS-CoV-2 related virus. Several other identified CSIs are specific for others clusters of sarbecoviruses including a clade consisting of bat SARS-CoVs (BM48-31/BGR/2008 and SARS_BtKY72). Structural mappings studies show that the identified CSIs are located within surface-exposed loops and form distinct patches on the surface of the spike protein. These surface loops/patches are predicted to interact with other host components and play important role in the biology/pathology of SARS-CoV-2 virus. Lastly, the CSIs specific for the SARS-CoV-2r clade provide novel means for development of new diagnostic and therapeutic targets for these viruses.
ARTICLE | doi:10.20944/preprints201810.0088.v1
Subject: Materials Science, Biomaterials Keywords: There are many molecules used as drug carrier. TUD-1 is a newly synthesized mesoporous silica (SM) molecule possess two important features; consists of mesoporous so it is very suitable to be drug carrier in addition to that it has the ability to induce apoptosis in cancer cells. However, the effect of TUD-1 appears to act as cell death inducer, regardless of whether it is necrosis or apoptosis. Unfortunately, recent studies indicate that a proportion of cells undergo necrosis rather than apoptosis, which limits the use of TUD-1 as a secure treatment. On the other hand, lithium considered as necrosis inhibitor element. Hence, current study based on the idea of production a new Li/TUD-1 by incorporated mesoporous silica (TUD-1 type) with lithium in order to produce a new compound that has the ability to activate apoptosis by mesoporous silica (TUD-1 type) and at the same time can inhibit the activity of necrosis by lithium. Herein, lithium was incorporated in TUD-1 mesoporous silica by
Online: 4 October 2018 (15:54:02 CEST)
There are many molecules used as drug carrier. TUD-1 is a newly synthesized mesoporous silica (SM) molecule possess two important features; consists of mesoporous so it is very suitable to be drug carrier in addition to that it has the ability to induce apoptosis in cancer cells. However, the effect of TUD-1 appears to act as cell death inducer, regardless of whether it is necrosis or apoptosis. Unfortunately, recent studies indicate that a proportion of cells undergo necrosis rather than apoptosis, which limits the use of TUD-1 as a secure treatment. On the other hand, lithium considered as necrosis inhibitor element. Hence, current study based on the idea of production a new Li/TUD-1 by incorporated mesoporous silica (TUD-1 type) with lithium in order to produce a new compound that has the ability to activate apoptosis by mesoporous silica (TUD-1 type) and at the same time can inhibit the activity of necrosis by lithium. Herein, lithium was incorporated in TUD-1 mesoporous silica by using sol-gel technique in one step synthesis procedure. Moreover, lithium was incorporated in TUD-1 with different loading in order to form different active sites such as isolated lithium ions, nanoparticles of Li2O, and bulky crystals of Li2O. The ability of the new compounds to induce apoptosis and prevent necrosis was evaluated on three different types of cancer cell lines which are; liver HepG-2, Breast MCF-7 and colon HCT116. The obtained results show that Li/TUD-1has the ability to control necrosis and thus reduce the side effects of treatments containing silica in the case of lithium has been added to them, especially in chronic cases. This has been demonstrated by the significant increase in the IC50 value and cell viability comparing to control groups. Consequently, the idea is new, so it definitely needs more develop and test with materials that have more apoptotic impact than silica in order to induce apoptosis without induction of necrosis.