Search

Skin melanoma is a potentially fatal form of cancer. If left untreated or allowed to spread, it can lead to death or serious disability. Therefore, early diagnosis is crucial for improving patient prognosis and outcomes. Recent advances in machine learning (ML) and deep learning (DL) have greatly contributed to the categorisation and identification of melanoma. The goal of this survey is to evaluate 60 publications that have been submitted in order to create an overview of the melanoma detection process. It examines several feature extraction techniques.The evaluation concentrates on different melanoma detection methods, including 'deep learning (DL)' and 'machine learning (ML)' models. The analysis includes performance metrics and a review of the results obtained from the PH2 dataset, which achieved a high accuracy of 96.5%. Finally, the survey addresses research gaps to facilitate future investigations into melanoma identification strategies. [ABSTRACT FROM AUTHOR]

Ya Shen,1,2,* Shun-Shun Cui,3,* Xiao-Bao Teng,2,* Ming-Feng Han,2 Yan-Bei Zhang1 1Department of Geriatric Respiratory and Critical Care Medicine, The First Affiliated Hospital of Anhui Medical University, Hefei, 230000, People’s Republic of China; 2Department of Respiratory and Critical Care Medicine, Fuyang Infectious Disease Clinical College of Anhui Medical University, Fuyang, 236000, People’s Republic of China; 3Department of Respiratory and Critical Care Medicine, Fuyang People’s Hospital, Fuyang, 236000, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yan-Bei Zhang, Department of Geriatric Respiratory and Critical Care Medicine, The First Affiliated Hospital of Anhui Medical University, No. 218 of Jixi Road, Shushan District, Hefei, 230000, People’s Republic of China, Tel +86-13093340370, Email zhangyanbeizyb@126.com Ming-Feng Han, Department of Respiratory and Critical Care Medicine, Fuyang Infectious Disease Clinical College of Anhui Medical University, No.1088 of Yinghexi Road, Yingzhou District, Fuyang, 236000, People’s Republic of China, Tel +86-16655800262, Email mingfeng_han@126.comObjective: The aim of this study was to assess the prevalence of Tropheryma whipplei (TW) infection in the population and to investigate the clinical symptoms, as well as the laboratory and imaging characteristics of patients testing positive for TW using next-generation sequencing (NGS).Methods: A retrospective review was conducted on 1346 bronchoalveolar lavage fluid (BALF) samples collected between January 2021 and September 2023. The case group comprised patients with TW detected using NGS while the control group included 65 randomly chosen Gram-positive bacterial infection patients without TW. Comparative analyses were carried out on the basic demographics, laboratory parameters, and imaging findings between the two groups. Additionally, the case group underwent an in-depth examination of underlying diseases, pathogens, final diagnoses, treatment strategies.Results: The case group comprised of 51 patients with TW, constituting 3.8% of the total. There was no significant difference in gender and age between the case and control groups (P = 0.84, P = 0.07). Symptoms such as coughing, expectoration, wheezing, fever, and hemoptysis are less commonly detected in the case group with a higher incidence of chest pain when compared to the control group (P > 0.05). The case group exhibited decreased albumin levels and increased C-reactive protein and D-dimer levels compared to normal levels. Imaging findings in the case group commonly included nodules, patchy images, and interstitial changes, the most common underlying disease is cardiovascular disease, and the most frequently co-occurring pathogen is the human herpesvirus. Among the case group, 27 patients received a final diagnosis of pneumonia, and 3 patients clinically diagnosed with Whipple’s disease demonstrated improvement in both symptoms and imaging after treatment.Conclusion: NGS revealed a relatively low overall detection rate of TW-positive patients using BALF. TW was more prevalent in middle-aged and elderly male patients characterized by symptoms such as cough, expectoration, shortness of breath, and fever. Chest imaging in these cases typically showed nodules and interstitial changes.Keywords: bronchoalveolar lavage fluid, feature, image, NGS, Tropheryma whipplei

Intelligent farming has been an ever-increasing trend in agricultural production, with the development of artificial intelligence (AI) and Internet of Things (IoT). Rapid and accurate identification of cattle identity is of great significance to prevent the insurance fraud for the live cattle loans in the cattle industry. Among them, computer vision can be expected for the cattle face recognition in the modernization transformation of the livestock industry. Smart devices and systems can also be integrated to achieve the intelligent cattle management, feeding, and disease prevention. However, the traditional identification (such as ear tags and collars) has limited the large-scale production in recent years, due to the small differences in facial features among different cattle, the deep layers of the FaceNet network, slow inference speeds, and insufficient classification accuracy. In this study, a cattle face recognition was proposed using FaceNet, called VanillaFaceNet. Firstly, the backbone feature extraction network of FaceNet was replaced with the latest simplified network. VanillaNet-13. Dynamic activation and enhanced linear transformation of activation functions were proposed to improve the non-linearity of the network. Specifically, dynamic activation was fully utilized the expressive power of activation functions during training when dynamically adjusting, in order to flexibly adapt the variations in data distribution at different stages of training. Dynamic activation was used to merge the convolutional layers during inference phase. The computational load was reduced to improve the inference speed of networks. The performance and efficiency of model were then enhanced during training and inference. Activation functions with linear transformations were significantly enhanced the non-linearity through parallel stacking. Multiple activation functions were stacked in parallel, thus enabling each layer to capture more complex features. Additionally, spatial context information was embedded within the activation functions. The spatial relationships among features were better utilized to fit the complex feature distributions. Non-linearity and integration of spatial context information were achieved in a more accurate and efficient model when processing complex data. Secondly, DBCA (Dual-Branch Coordinate Attention) module was added into the global maximum pooling. Global average pooling was used to aggregate significant features of cattle faces, in order better represent the differences among cattle facial features. Therefore, the accuracy network was improved to recognize the cattle. Finally, a center loss was introduced to train the network with the center-triplet loss joint supervision, because the triplet loss was only reduced the inter-class differences among cattle. The intra-class separability of cattle was improved to compactly aggregate the same category of cattle. Thus, the accuracy of comparisons was improved among the same identities of cattle. Cattle face videos were collected at the Otai Ranch in Hohhot, Inner Mongolia Autonomous Region. An image dataset was constructed to train and test the model for the cattle face recognition. The experimental results show that VanillaFaceNet was achieved an accuracy of 88.21% in the cattle recognition, with a frame rate of 26.23 frames per second (FPS). Compared with FaceNet, MobileFaceNet, CenterFace, CosFace, and ArcFace, the model was improved the recognition accuracy by 2.99%, 9.58%, 6.26%, 3.85%, and 4.49%, respectively, and the inference speed by 2.67, 0.77, 0.10, 1.28, and 0.94 frames/s, respectively. The recognition accuracy and speed were greatly improved to fully meet the requirements of the ranch for the accuracy and real-time performance of cattle recognition. The excellent performance was achieved in the cattle recognition, suitable for the deployment on embedded devices, such as Jetson AGX Xavier. A better balance was also gained between accuracy and inference speed of cattle facial recognition. [ABSTRACT FROM AUTHOR]

Addressing the challenge of radar detection of small targets under sea clutter, target detection methods based on a three-dimensional feature space have shown effectiveness. However, their application has revealed several problems, including high dependency on linear relationships between features for dimensionality reduction, unclear reduction objectives, and spatial divergence of target samples, which limit detection performance. To mitigate these challenges, we constructed a feature density distance metric employing copula functions to quantitatively describe the classification capability of multidimensional features to distinguish targets from sea clutter. On the basis of this, a lightweight nonlinear dimensionality reduction network utilizing a self-attention mechanism was developed, optimally re-expressing multidimensional features into a three-dimensional feature space. Additionally, a concave hull classifier using feature sample distance was proposed to mitigate the negative impact of target sample divergence in the feature space. Furthermore, multivariate autoregressive prediction was used to optimize features, reducing erroneous decisions caused by anomalous feature samples. Experimental results using the measured data from the SDRDSP public dataset demonstrated that the proposed detection method achieved a detection probability more than 4% higher than comparative methods under Sea State 5, was less affected by false alarm rates, and exhibited superior detection performance under different false alarm probabilities from 10−3 to 10−1. [ABSTRACT FROM AUTHOR]

Malware detection has become a critical aspect of ensuring the security and integrity of computer systems. With the ever-evolving landscape of malicious software, developing effective detection methods is of utmost importance. This study focuses on the identification of important features for malware detection methods, aiming to enhance the accuracy and efficiency of such systems. In this work, we propose an ensemble approach called FRAMC to identify the key features that contribute significantly to the detection of malware. The effectiveness of FRAMC is assessed using different types of classifiers on a number of real-world malware datasets. The outcomes of our analysis demonstrate that the proposed approach excels in terms of performance when compared to other methods. [ABSTRACT FROM AUTHOR]

The areas of research methodologies are continually developing, driven by the quest for more profound comprehension and more successful critical thinking. This theory examines the concept of exploring new paradigms of research practice, featuring the meaning of embracing advancement in the journey for information revelation. It looks at the reasoning behind the requirement for novel methodologies, focusing on the restrictions of conventional approaches and the open doors introduced by investigating new roads. By embracing new paradigms, researchers can be liberated from the limitations of regular reasoning and procedures, opening ways to new points of view and insights. This paper explores various examples of innovative research paradigms, ranging from interdisciplinary collaborations and data-driven approaches to participatory action research and qualitative synthesis methods. It discusses how these paradigms offer unique opportunities to address complex research questions and tackle emerging challenges in diverse fields. Besides, this paper talks about the likely advantages and difficulties related to taking on new research paradigms, including considerations connected with interdisciplinary collaboration, strategic exactness, and moral ramifications. It underscores the significance of encouraging a culture of trial and error and advancing within the research community to work with the investigation and reception of inventive methodologies. [ABSTRACT FROM AUTHOR]

Fabricating micro-pillars is a tough procedure as these features are highly debile. Wire Electro-Discharge Machining (WEDM) is a popular micromachining process to fabricate complex features on electrical conducting materials. SS304 stainless steel is commonly used in manufacturing of heating and cooling devices. A simple method of micro-pillars array fabrication on SS304 Stainless Steel material using WEDM was used through perpendicular crossed wire movement, keeping specified amount of step-over distance to form pillars. An analytical model for material removal rate prediction was developed using input parameters like spark duration, off time, voltage and current. Also, the influence of the process parameters was studied on depth and kerf width produced. Voltage and pulse-on time were found to be the major influencing parameters. Micro-featured surfaces fabricated for minimum kerf width and maximum feature depth were analysed using SEM and EDS along with the wettability study. The fabricated surfaces remained hydrophobic even after 100s. [ABSTRACT FROM AUTHOR]

With the global whisky market reaching $65.6 billion in 2024 and projected to reach $89.48 billion by the end of 2029, the incentives for fraud in relation to (and adulteration of) this alcoholic beverage are self-evident. Law enforcement agencies worldwide have taken actions against crimes of this nature, with forensic scientists playing crucial roles (mainly through expert testimonies on sample authenticities) during legal proceedings. Important issues associated with Scotch whisky authentication include: (a) understanding the typical manufacturing process; (b) acquisition of reference samples; and (c) effective utilization of instrumentations to characterize features derived from the manufacturing process and strategic approaches for the interpretation of analytical findings. Following a brief review of the definition/classification, manufacturing, and adulteration/counterfeiting of Scotch whiskies, this review focuses on the characterization of manufacturing-derived features and interpretation of analytical findings as grouped into: (a) quantitative analysis of single compounds; (b) qualitative analysis and intensity ratio of multiple compounds; (c) chemometric analysis of selected multi-compounds; and (d) quantitative analysis of selected elements. Finally, a flowchart for conducting the authentication process, from various significantly different perspectives, is proposed. [ABSTRACT FROM AUTHOR]

Due to the fast-modeling speed and high accuracy, deep learning has attracted great interest in the field of fault diagnosis in building energy systems in recent years. However, the black-box nature makes deep learning models generally difficult to interpret. In order to compensate for the poor interpretability of deep learning models, this study proposed a fault diagnosis method based on interpretable graph neural network (GNN) suitable for building energy systems. The method is developed by following three main steps: (1) selecting NC-GNN as a fault diagnosis model for building energy systems and proposing a graph generation method applicable to the model, (2) developing an interpretation method based on InputXGradient for the NC-GNN, which is capable of outputting the importance of the node features and automatically locating the fault related features, (3) visualizing the results of model interpretation and validating by matching with expert knowledge and maintenance experience. Validation was performed using the public ASHRAE RP-1043 chiller fault data. The diagnosis results show that the proposed method has a diagnosis accuracy of over 96%. The interpretation results show that the method is capable of explaining the decision-making process of the model by identifying fault-discriminative features. For almost all seven faults, their fault-discriminative features were correctly identified. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Peer-to-peer (P2P) lending platforms are growing significantly, and users always leave comments on the application to provide ratings. User comments are important to analyze to see the needs and constraints of fintech users. The Purpose of the research is to create an analytical model that effectively addresses the problem of limited accuracy in classification due to data imbalance in P2P Lending platforms. The research aims to improve feature detection and overall model quality by effectively managing imbalanced data. The design involves a combination of techniques. First, the Latent Dirichlet Allocation (LDA) method is used to organize topics and label data. To address the data imbalance, the study employs Random Over Sampling (ROS) and Neighborhood Cleaning Rule (NCL). The final classification is performed using Convolutional Neural Networks (CNN). Additionally, a comparative analysis with other algorithms like LSTM and CNN-LSTM is carried out to validate the effectiveness of the proposed approach. The Findings reveal that the CNN-ROS-NCL model is capable of managing imbalanced data, which improves class distribution and enhances the model's quality by reducing noise and misleading samples. The CNN model achieved a classification accuracy of 94.66% on 10 feature classes, suggesting a significant improvement in feature detection and classification performance on the P2P Lending platform. The Originality of this research lies in the innovative integration of LDA for topic analysis with CNN for classification a novel approach in the context of fintech feature development. This combination has not previously been used in fintech and offers a new way to automatically detect features in Fintech P2P Lending user comment datasets by identifying key topics. The research contributes to the enhancement of fintech applications and services by providing a model that improves the understanding and processing of user comments on P2P platforms. [ABSTRACT FROM AUTHOR]

Abstract Neuromarketing is an emerging research field that aims to understand consumers’ decision-making processes when choosing which product to buy. This information is highly sought after by businesses looking to improve their marketing strategies by understanding what leaves a positive or negative impression on consumers. It has the potential to revolutionize the marketing industry by enabling companies to offer engaging experiences, create more effective advertisements, avoid the wrong marketing strategies, and ultimately save millions of dollars for businesses. Therefore, good documentation is necessary to capture the current research situation in this vital sector. In this article, we present a systematic review of EEG-based Neuromarketing. We aim to shed light on the research trends, technical scopes, and potential opportunities in this field. We reviewed recent publications from valid databases and divided the popular research topics in Neuromarketing into five clusters to present the current research trend in this field. We also discuss the brain regions that are activated when making purchase decisions and their relevance to Neuromarketing applications. The article provides appropriate illustrations of marketing stimuli that can elicit authentic impressions from consumers' minds, the techniques used to process and analyze recorded brain data, and the current strategies employed to interpret the data. Finally, we offer recommendations to upcoming researchers to help them investigate the possibilities in this area more efficiently in the future.

In this paper, we introduce a facial recognition system comprising two key components: face detection and localization, and facial recognition. For face detection and localization, the RetinaFace method is employed to accurately identify facial regions within images and to separate them from intricate backgrounds, thus facilitating facial detection based on isolated facial imagery. In the domain of facial recognition, we address the limitations of conventional convolutional neural networks (CNNs), which are typically constrained to recognizing known categories. To overcome this limitation, in our study, we leverage a Siamese network rooted in metric learning as the central architecture for facial recognition. The primary objective of this architecture is to acquire image features. It operates by minimizing the feature distance between similar images and maximizing the feature distance between dissimilar ones. Consequently, images can be directly fed into the Siamese network to extract corresponding features, followed by similarity calculation to ascertain their presence within the database. Diverging from the conventional approach of directly classifying individuals using models, we significantly inhibit the need for model retraining owing to personnel changes in the differentiation of members and nonmembers. Furthermore, the model does not increase in size with the growth of the personnel dataset. The study outcomes demonstrate that the attained average values for accuracy, recall rate, precision, and F1-Score all surpass 96%. These results robustly demonstrate the feasibility and superior performance of this approach. [ABSTRACT FROM AUTHOR]

Classification is a significant step in many applications like image classifications, text recognition, categorization of speech, facial expression classification and so on. And the features fed to the classifier affects the accuracy or performance. The components or patterns of an item in a picture that assist to identify it are termed as features of an item. In computer vision and image processing, the feature carries the information about the content of an image. In classification challenges, the process of extracting features from an object is essential. There are several techniques or features which are used. This paper gives an explanation of different types of feature extraction techniques or methodologies that are used to extract the features out of an image along with classification. Here the facial expressions images are taken. Support vector machine and K-Nearest Neighbor classifier are taken to classify the facial expressions images. The image features used here are local binary pattern (LBP), entropy and histogram of oriented gradients (HOG). The CK+ 48 image dataset is taken here and the MATLAB software is used to obtain the results. The features are extracted and fed to the classifiers. The results show a better accuracy when one feed the three features (LBP, HOG, and entropy) simultaneously. According to the results it is concluded that the accuracy or performance of a classifier depends on the selection of the features of an image or we can say that the classification results are dependent on selected features and classifiers. [ABSTRACT FROM AUTHOR]

Neuromarketing is an emerging research field that aims to understand consumers' decision-making processes when choosing which product to buy. This information is highly sought after by businesses looking to improve their marketing strategies by understanding what leaves a positive or negative impression on consumers. It has the potential to revolutionize the marketing industry by enabling companies to offer engaging experiences, create more effective advertisements, avoid the wrong marketing strategies, and ultimately save millions of dollars for businesses. Therefore, good documentation is necessary to capture the current research situation in this vital sector. In this article, we present a systematic review of EEG-based Neuromarketing. We aim to shed light on the research trends, technical scopes, and potential opportunities in this field. We reviewed recent publications from valid databases and divided the popular research topics in Neuromarketing into five clusters to present the current research trend in this field. We also discuss the brain regions that are activated when making purchase decisions and their relevance to Neuromarketing applications. The article provides appropriate illustrations of marketing stimuli that can elicit authentic impressions from consumers' minds, the techniques used to process and analyze recorded brain data, and the current strategies employed to interpret the data. Finally, we offer recommendations to upcoming researchers to help them investigate the possibilities in this area more efficiently in the future. [ABSTRACT FROM AUTHOR]

We consider the problem of feature detection in the presence of clutter in spatial point processes. Classification methods have been developed in previous studies. Among these, Byers and Raftery (J Am Stat Assoc 93(442):577–584, 1998) models the observed Kth nearest neighbour distances as a mixture distribution and classifies the clutter and feature points consequently. In this paper, we enhance such approach in two manners. First, we propose an automatic procedure for selecting the number of nearest neighbours to consider in the classification method by means of segmented regression models. Secondly, with the aim of applying the procedure multiple times to get a "better" end result, we propose a stopping criterion that minimizes the overall entropy measure of cluster separation between clutter and feature points. The proposed procedures are suitable for a feature with clutter as two superimposed Poisson processes on any space, including linear networks. We present simulations and two case studies of environmental data to illustrate the method. [ABSTRACT FROM AUTHOR]

The anti-oxidant proteins have a closer relation to disease control. Hence an accurate classification of antioxidant proteins by automated analysis is an essential process for the expansion of drugs for various diseases. Wet-lab experimental approaches are generally expensive and inefficient for the identification of anti-oxidant proteins. Novel methodologies like Physiochemical and Conjoint-Quad (PCQ) feature composition using the physio-chemical features combined with moment-based features is proposed in this work for the accurate classification of anti-oxidant proteins. In this proposed work, four techniques namely, proposed PCQ, k-spaced Amino Acid Pairs (CKSAAP), g-gap, and N-gram (N = 3) were applied to create different hybrid features from the anti-oxidant proteins efficiently. The Pearson Kernel-based Supervised Principal Component Analysis (PKSPCA) is proposed for the dimension reduction of the features and effective classification. To evaluate the proposed technique, ten-fold cross-validation and independent test datasets were utilized. On the testing data, the proposed method attained the best performance when compared with the previous techniques. This proposed method achieves 99% accuracy, sensitivity of 98% and specificity of 91% during the classification of the anti-oxidant proteins. [ABSTRACT FROM AUTHOR]

The digital economy refers to the economic activities that emerge from connecting individuals, businesses, devices, data, and operations through digital technology. It includes online transactions across multiple sectors and technologies, such as the Internet, mobile technology, big data, and information and communications technology. The digital economy differs from a traditional economy because it relies on digital technology, online transactions, and its transformative effect on traditional industries Digital innovations such as the Internet of Things (IoT), Artificial Intelligence (AI), Virtual Reality, Blockchain, and autonomous vehicles all play a part in creating a digital economy. For this study, various papers on "Digital Economy" and "Industry 4.0" are identified from Scopus, Google Scholar and other research platforms and further studied briefly. This review paper has been developed after studying the digital economy and its needs in the Industry 4.0 Environment. The defining trends, key enablers, features and challenges associated with the digital economy towards Industry 4.0 are discussed briefly. Finally, the paper identifies and discusses the significant requirements of Industry 4.0 fulfilled through the digital economy. Today, customers are becoming aware of goods and services online and are turning to the industry for long-term solutions by deploying digital technologies. The digital economy is built on hyper connectivity, the growing interconnectedness of individuals, organisations, and machines due to the Internet, mobile technologies, and the IoT. Industry 4.0 technologies are automation, data exchange, cloud computing, robotics, big data, AI, the IoT, and other technological trends are all part of the industrial sector's digital transformation, which aims to achieve industrial objectives and intelligent manufacturing practices that engage with customers, emerging technologies, and innovation. The economy is becoming more digital, changing how products and services are provided and consumed. A new road map is being provided by Industry 4.0 services to help many industries adapt their conventional methods and support the new revolution. In the digital economy, scaled-up, integrated ecosystems that leverage software platforms to generate value, build resilience, and stimulate innovation via networked goods, assets, people, and processes rapidly replace old, linear value chains with partner participation. [ABSTRACT FROM AUTHOR]

Grapes are one of the important agricultural products that are consumed both fresh and dried. By drying grapes in different conditions, various raisins are produced. After raisin production in the field, it is delivered to raisin production factories in order to wash and remove bad grains and remove thorns and weeds. Pricing and determining the quality of bulk raisins at this stage is one of the most important challenges between the seller and the buyer, who is the factory owner. In this research, using the machine vision method, 15 different classes of bulk raisins were investigated based on the composition of good and bad seeds and dry wood. The texture features of the images were used for classification, and the best combination of image texture extraction algorithms was evaluated using the particle swarm optimization (PSO) method. Three different classifier by name support vector machine (SVM), linear discriminate analysis (LDA) and K-nearest neighborhood were used for modeling. The results showed that the combination of several texture feature extraction methods using PSO improves the classification accuracy for all classifiers. The best results were achieved using SVM and LDA modeling as 99.33% and 99.73%, respectively. Since the number of algorithms used in LDA modeling was less than SVM, so the LDA model was selected as a best model. Results showed that the machine vision system can be used successfully for quality evaluation of bulk raisin pricing. [ABSTRACT FROM AUTHOR]

In this paper, for the classification of images, the observed cooperative classification method is proposed with the aim of reducing the semantic vacuum. Because most classification methods are sensitive to cluster centers at initialization, the algorithm converges optimally locally if the quantification is not done correctly. It is also very difficult to combine the results of the classification due to the fact that the labels of the work centers are not clear. Supervised semi-classification is used to solve these problems. To achieve the highest performance, the system classification results are combined with different color space and similarity criteria with multiple features as a semi-supervised cooperative. When the number of features is effective, the relevant feedback is used for its semi-regulatory classification. One of the most important parts of an image retrieval system and a classification algorithm is to determine the appropriate similarity between images. In this study, two methods of classification of cases have been used, which include k-NN and PNN classification, which according to the results in all proposed methods, a better response from k-NN classification than PNN has been observed. The proposed algorithm is very suitable for classifying large image databases due to the reduction of time complexity. Also, in image retrieval in different color spaces and using different similarity criteria, different classifications are obtained. Better results can be achieved if the classification results are combined.

Abstract Background Circular RNAs (circRNAs) can regulate microRNA activity and are related to various diseases, such as cancer. Functional research on circRNAs is the focus of scientific research. Accurate identification of circRNAs is important for gaining insight into their functions. Although several circRNA prediction models have been developed, their prediction accuracy is still unsatisfactory. Therefore, providing a more accurate computational framework to predict circRNAs and analyse their looping characteristics is crucial for systematic annotation. Results We developed a novel framework, CircDC, for classifying circRNAs from other lncRNAs. CircDC uses four different feature encoding schemes and adopts a multilayer convolutional neural network and bidirectional long short-term memory network to learn high-order feature representation and make circRNA predictions. The results demonstrate that the proposed CircDC model is more accurate than existing models. In addition, an interpretable analysis of the features affecting the model is performed, and the computational framework is applied to the extended application of circRNA identification. Conclusions CircDC is suitable for the prediction of circRNA. The identification of circRNA helps to understand and delve into the related biological processes and functions. Feature importance analysis increases model interpretability and uncovers significant biological properties. The relevant code and data in this article can be accessed for free at https://github.com/nmt315320/CircDC.git .

It is possible to refer to the pioneer of modern Egyptian sculpture, Mahmoud Mokhtar, who took the Egyptian identity as a starting point for expression and sculptural creativity and pushed it to the world. From his fame Mukhtar and the gathering of the Egyptian public around him, his pride in his identity in a period of time when Egypt was under the British occupation and the Egyptian people were searching for their identity in their resistance against the British occupier, searching for it in their language, religion and in art, to begin the movement of Egyptianization that ends with the revolution of 1919 affecting the form The arts and the development of literature in the following decade. For Mukhtar and the Egyptian people to meet under the banner of national identity, where the Egyptian people found in Mukhtar's sculpture an image of belonging and patriotism, so that the spectrum of society united and gathered around his sculptural works. Although Mukhtar studied Western sculpture models, his talent, vision, and search for self and identity, which were not absent from his vision in his artistic works, prompted him to benefit from what he learned to be inspired after that from the cultural heritage of Egypt in his works, in which he found endless art, these works that were not an imitation of sculptures. And a culture that disappeared decades ago, but rather it was a civilization with an Egyptian identity, the life of the Egyptian people

In this paper, a scalable end-to-end tree boosting system called XGBoost has been applied for predicting the magnitude of an earthquake from the early part of earthquake waveform data. This model uses the features extracted from the early P wave phase of the records as an input. The model's effectiveness has been verified by using data on earthquakes occurring in the Eurasian plate of Japan Islands from 1996 to 2021. Feature engineering has given 29 new features identified from the early P wave phase of the record, which show a high correlation with the magnitude of an earthquake. The comparison of predicted and actual magnitude shows that a trained XGboost model, which uses a single input record for magnitude prediction, gives an average prediction error of 0.004 ± 0.57 for earthquakes in the test dataset. In contrast, the average prediction error of –1.1 ± 0.80 and –0.65 ± 0.69 has been obtained for the magnitude estimated from conventional τc and Pd methods using the same test dataset. It is further seen that the average predicted magnitude of a single earthquake of magnitude 4.5 and 6.1 (MJMA) obtained by using multiple nearfield records using XGBoost model is 4.58 ± 0.33 and 6.32 ± 0.29, which is close to the actual magnitude of the earthquake. The results presented in this paper clearly show that the structured data can be effectively used by complex machine learning or deep learning models to predict earthquake magnitude from single or multiple records. [ABSTRACT FROM AUTHOR]

Anorectal malformations (ARMs) of the rectoperineal and rectovestibular fistula type (RPF/RVF) generally have a good prognosis but may be accompanied by bowel dysfunction, especially constipation. Bowel dysfunction in preschoolers may persist into adolescence and adulthood, exerting a negative effect on their quality of life. This study was designed to evaluate bowel function and identify the features of bowel dysfunction in preschoolers with RPF/RVF across type and sex differences. A total of 159 preschoolers with RPF/RVF (male RPF group, n = 95; female RPF group, n = 26; RVF, n = 38) and 128 normal control preschoolers (control group, n = 128; female control group, n = 35), according to the bowel function score (BFS) obtained through a questionnaire survey, the BFS items in the questionnaire, and the clinical characteristics of patients were compared among groups. The rates of bowel dysfunction (BFS < 17) were 27.2% and 50.0% in the RPF and RVF groups, respectively. Normal rates of BFS items, namely, ability to hold back defecation, feels/reports of the urge to defecate, frequency of defecation, and constipation, in the RPF and RVF groups were significantly lower than those in the control and female control groups (all p < 0.05). After subgroup analysis among the male RPF, female RPF, and RVF groups, higher rates of normal bowel function and ability to hold back defecation were found in the male RPF group than in the female RPF and RVF groups (p < 0.05). Normal rates of feels/reports of the urge to defecate were higher in the male and female RPF groups than in the RVF group (all p < 0.05). The rate of never soiling in the male RPF group was significantly higher than that in the RVF group (p < 0.05). Conclusions: In patients with RPF/RVF, bowel dysfunction is still prevalent, characterized by inadequate ability to hold back defecation, inability to feel/report the urge to defecate, soil, less frequent defecation, and constipation. However, male RPF patients had better overall bowel function than female RPF or RVF patients, including more adequate ability to hold back defecation and feels/reports of the urge to defecate and slighter soiling, which may be linked to early age at surgery, low occurrences of low sacral ratio, and tethered cord in male RPF. Trial registration: This study was retrospectively registered in ClinicalTrials.gov on 09/01/2023 (NCT05716230). What is Known: • Rectoperineal and rectovestibular fistula (RPF/RVF) of the anorectal malformation (ARM) type has a good prognosis but may cause bowel dysfunction, especially constipation. • Bowel dysfunction at preschool age may lead to social and psychological disorders that undermine the quality of life in adolescence and adulthood. What is New: • Bowel function in preschoolers with RPF/RVF was deeply evaluated in a relatively large number of patients and normal control children. • Features of bowel dysfunction in RPF/RVF preschoolers across type and gender differences were identified in this study. [ABSTRACT FROM AUTHOR]

Objectives: The aim was to explore the magnetic resonance imaging (MRI) features of stage-I intravenous leiomyomatosis (IVL). Materials and methods: From January 2019 to January 2023, clinical, pathological, and MRI data were collected from 19 cases confirmed by surgical pathology. Two radiologists retrospectively measured the tumor sizes, T1WIs, T2WIs, and ADC values and evaluated contrast-enhanced T1WIs, DWIs, complications and parauterine infiltrations. The number of tumor cells and the total nuclear area were measured. The percentage of tumor cell area out of the total area was used as the tumor cell density. Results: Nineteen patients with stage-I IVL aged 33 to 66 years (mean age: 46 ± 7.6 years) were included in this study. All 19 cases were located in the myometrium or parametrium, with a mean diameter of 11.2 ± 4.8 cm. Among these cases, 14 (73.6%) were associated with leiomyoma, and six (31.6%) involved the broad ligament. Isointensity was observed in the T1WIs of 12 cases (63.2%), while slight hypointensity was seen in five patients (26.3%). Isointensity was observed in the on T2WIs of four cases (21.1%), and iso- or slight hyperintensity was observed in 15 cases (78.9%). A significant difference was detected between the normalized T2WIs of IVL and myometrium (p < 0.001). A Pearson correlation test showed demonstrated a negative correlation between the ADC and tumor cell density values (r = − 0.946, p < 0.001). Tortuous vessels were present in 17 cases (89.5%) within or next to the lesions, and multiple winding cord-like filling defects were seen in 11 cases (57.9%) within the tortuous vessels on the T2WIs. Conclusion: Identifying the characteristic MRI features of stage-I IVL helped improve the diagnostic accuracy achieves for this rare tumor. Stage-I IVL often presents as a large mass accompanied by leiomyoma, and it easily invades the broad ligament. TIWI signals exhibited isointensity, and T2WI signals contained iso- or slight hyperintensity. Tortuous vessels were present within or next to the lesions, and multiple winding cord-like filling defects were observed within the tortuous vessels on the T2WIs. [ABSTRACT FROM AUTHOR]

Highway safety researchers focus on crash injury severity, utilizing deep learning--specifically, deep neural networks (DNN), deep convolutional neural networks (D-CNN), and deep recurrent neural networks (D-RNN)--as the preferred method for modeling accident severity. Deep learning's strength lies in handling intricate relationships within extensive datasets, making it popular for accident severity level (ASL) prediction and classification. Despite prior success, there is a need for an efficient system recognizing ASL in diverse road conditions. To address this, we present an innovative Accident Severity Level Prediction Deep Learning (ASLP-DL) framework, incorporating DNN, D-CNN, and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent. The framework optimizes hidden layers and integrates data augmentation, Gaussian noise, and dropout regularization for improved generalization. Sensitivity and factor contribution analyses identify influential predictors. Evaluated on three diverse crash record databases--NCDB 2018-2019, UK 2015-2020, and US 2016-2021--the D-RNN model excels with an ACC score of 89.0281%, a Roc Area of 0.751, an F-estimate of 0.941, and a Kappa score of 0.0629 over the NCDB dataset. The proposed framework consistently outperforms traditional methods, existing machine learning, and deep learning techniques. [ABSTRACT FROM AUTHOR]

胸骨腹側面の形状を, 胸骨吻（吻外棘）, 切痕数, 内側窓数, その他の特徴の4点に分けて観察し た.胸骨吻（吻外棘）はI, U, Y形の3つ,切痕数では1対のものと2対のもの,内側窓数は1対,その他の 特徴では, 胸骨吻（吻内棘）のあるものや, 全体の形状に相違が認められた．胸骨は, 分類群によって形 態的な特徴が認められ,胸骨を用いて種不明標本の種推定を行うことがある程度可能である.. [ABSTRACT FROM AUTHOR]

The clinical assessment of depression is based on observation and subjective patient complaints of almost all psychiatric disorders. Psychomotor retardation is one of the leading symptoms of depression, and as an indicator of this, physical activity is reduced in depressed patients. In this study, we aimed to develop a machine learning-based objective diagnostic support method for diagnosing depression using a dataset of daily physical activity data of individuals with and without depression as a reference. After detailed feature searches, we identified the four best features by Fisher Feature Selection. Using the Ensemble Bagged Tree method, we achieved a better classification result than the reference study, with an accuracy of 0.88. In addition, we found that the accuracy exceeded 0.90 when more than the four features we limited to compare with the reference study were selected. Thus, we could distinguish between individuals with and without depression with high accuracy with the machine learning-based method, which we developed using physical activity data. This study has shown promising results that activity data can be used as a diagnostic tool for depression. Our results show that different biomarkers, such as physical activity, when used with machine learning, can potentially overcome the lack of objective diagnostic support criteria in psychiatric evaluation. [ABSTRACT FROM AUTHOR]

Abstract: Over recent years, with the rapid development and increasing popularity of social media, we have seen a massive growth in the volume and variety of fake news. This phenomenon has profound effects on individuals and society. Verification is a widely used method to counter the negative effects of fake news. But this method is not efficient when analyzing huge amount of data. Therefore, advanced machine learning models and feature-based approaches are used to automatically identify fake news. At the same time, the large number of models and the heterogeneity of features used in the literature often create limitations for researchers trying to improve model performance. For this reason, in the present study a comprehensive framework of the features used in the detection of fake news is presented with a systematic review method. In order to carry out this systematic review, using the guide provided by Okoli and Schabram, all studies conducted in the field of fake news using related keywords were taken from ScienceDirect, Springer, Emerald, IEEE, ACM, Wiley, Sage databases, JSTOR, Taylor and WOS and finally 72 related articles were analyzed. As a result of the analysis of related articles, the features were placed in two main categories of news content and news context. News content includes linguistic and semantic features, visual features and style-based features. The news context also includes features based on user, post and network. The obtained results showed that the most used features in detecting fake news are features based on user profile, features of statistical stylistic, writing pattern and readability. Due to the high variety of available features, it is suggested that a wide evaluation of features, models and their performance in multiple data sets should be done and in this way the performance of different models and feature sets should be compared in order to find the best combination of features in different conditions to be determined. [ABSTRACT FROM AUTHOR]

Accurately classifying petrol and diesel fuel using an image processing method is crucial for fuel-related industries such as petrol pumps, refineries, and fuel storage facilities. However, distinguishing between these fuels using traditional methods can be challenging due to their similar visual characteristics. This article introduces a novel multi-scale and multi-level modified histogram of oriented gradients (MHOG) feature descriptors for robust classification of fuel images. Our proposed method involves extracting distinctive features from the images using the novel multi-scale and multi-level MHOG feature descriptor. These features are then utilized to train a range of machine learning classifiers with different hyperparameter settings for an ablation study. To the best of our knowledge, this is the first ablation study for this fuel classification application. To evaluate the effectiveness of our approach, we conduct experiments on a carefully labeled dataset consisting of petrol and diesel fuel images. The results demonstrate the high accuracy of our proposed method, achieving a classification accuracy of 98% using the light gradient boosting machine (LGBM). Furthermore, our method surpasses existing state-of-the-art techniques for fuel image classification. With its superior performance, this approach holds great potential for efficient and effective fuel classification in diverse fuel-related industries. [ABSTRACT FROM AUTHOR]

Formal approaches to bi- and multilingual grammars rely on two important claims: (i) the grammatical architecture should be able to deal with mono- and bi-/multilingual data without any specific constraints for the latter, (ii) features play a pivotal role in accounting for patterns across and within grammars. In the present paper, it is argued that an exoskeletal approach to grammar, which clearly distinguishes between the underlying syntactic features and their morphophonological realizations (exponents), offers an ideal tool to analyze data from bi- and multilingual speakers. Specifically, it is shown that this framework can subsume the specific mechanism of Feature Reassembly developed by Donna Lardiere since the late 1990's. Three case studies involving different languages and language combinations are offered in support of this claim, demonstrating how an exoskeletal approach can be employed without any additional constraints or mechanisms. [ABSTRACT FROM AUTHOR]

The digital economy refers to the economic activities that emerge from connecting individuals, businesses, devices, data, and operations through digital technology. It includes online transactions across multiple sectors and technologies, such as the Internet, mobile technology, big data, and information and communications technology. The digital economy differs from a traditional economy because it relies on digital technology, online transactions, and its transformative effect on traditional industries Digital innovations such as the Internet of Things (IoT), Artificial Intelligence (AI), Virtual Reality, Blockchain, and autonomous vehicles all play a part in creating a digital economy. For this study, various papers on ”Digital Economy” and ”Industry 4.0” are identified from Scopus, Google Scholar and other research platforms and further studied briefly. This review paper has been developed after studying the digital economy and its needs in the Industry 4.0 Environment. The defining trends, key enablers, features and challenges associated with the digital economy towards Industry 4.0 are discussed briefly. Finally, the paper identifies and discusses the significant requirements of Industry 4.0 fulfilled through the digital economy. Today, customers are becoming aware of goods and services online and are turning to the industry for long-term solutions by deploying digital technologies. The digital economy is built on hyper connectivity, the growing interconnectedness of individuals, organisations, and machines due to the Internet, mobile technologies, and the IoT. Industry 4.0 technologies are automation, data exchange, cloud computing, robotics, big data, AI, the IoT, and other technological trends are all part of the industrial sector’s digital transformation, which aims to achieve industrial objectives and intelligent manufacturing practices that engage with customers, emerging technologies, and innovation. The economy is becoming more digital, changing how products and services are provided and consumed. A new road map is being provided by Industry 4.0 services to help many industries adapt their conventional methods and support the new revolution. In the digital economy, scaled-up, integrated ecosystems that leverage software platforms to generate value, build resilience, and stimulate innovation via networked goods, assets, people, and processes rapidly replace old, linear value chains with partner participation.

Over recent years, with the rapid development and increasing popularity of social media, we have seen a massive growth in the volume and variety of fake news. This phenomenon has profound effects on individuals and society. Verification is a widely used method to counter the negative effects of fake news. But this method is not efficient when analyzing huge amount of data. Therefore, advanced machine learning models and feature-based approaches are used to automatically identify fake news. At the same time, the large number of models and the heterogeneity of features used in the literature often create limitations for researchers trying to improve model performance. For this reason, in the present study, a comprehensive framework of the features used in the detection of fake news is presented with a systematic review method. In order to carry out this systematic review, using the guide provided by Okuli and Schabram, all studies conducted in the field of fake news using related keywords were taken from ScienceDirect, Springer, Emerald, IEEE, ACM, Wiley, Sage databases. , JSTOR, Taylor and WOS were extracted and finally 72 related articles were analyzed. As a result of the analysis of related articles, the features were placed in two main categories of news content and news context. News content includes linguistic and semantic features, visual features and style-based features. The news field also includes features based on user, post and network. The obtained results showed that the most used features in detecting fake news are features based on user profile, features of statistical style, writing pattern and readability. Due to the high variety of available features, it is suggested that a wide evaluation of features, models and their performance in multiple data sets should be done and in this way the performance of different models and feature sets should be compared in order to find the best combination of features in different conditions. to become clear.

Background and Aim: The Hospital Information System is a complete one to provide high-quality patient care and enhance community health, so it must be designed and produced accordingly. In this regard, the current research was carried out with the aim of providing the document of standards for producing Hospital Information System software for Iran. Materials and Methods: In this study, following extraction of the features and services of the Hospital Information System from the texts, they were matched with the generalities of the document of standards compiled by the Statistical Data Management and Information Technology Office of the Ministry of Health, Treatment, and Medical Education (SDMITO). Also, the Hospital Information System was reviewed observationally, all defects of document of standards were identified, and the document was amended throughout. After providing the proposed document of standards, it was consulted by a group of experts, which included ten health information management professors, ten medical informatics professors (with at least seven years of experience as members of the academic staff), and five heads of the information technology field of the Ministry of Health. An agreement coefficient of 85% was considered to accept and approve the document of standards. After obtaining the agreement coefficient, The Hospital Information System software production document of standards was provided. Results: The document of standards provided for the production of Hospital Information System software includes the Hospital Information System design meta model, Hospital Information System subtypes, standards for the structure and content of Electronic Health Record, information terminology standards, data classification standards, security data standards, data exchange standards, clinical services, and management services, which were placed in the four areas of “features”, “services”, “documentation requirements” and “rules and policies”. Conclusion: The application of this document of standards leads to the production of a higher quality, efficient, and standard Hospital Information System software, which is effective in improving the health level of society and provides the conditions for the implementation of Electronic Health Record.

Copyright of Journal of Hubei Open Vocational College is the property of Journal of Hubei Open Vocational College Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Addressing the challenge of radar detection of small targets under sea clutter, target detection methods based on a three-dimensional feature space have shown effectiveness. However, their application has revealed several problems, including high dependency on linear relationships between features for dimensionality reduction, unclear reduction objectives, and spatial divergence of target samples, which limit detection performance. To mitigate these challenges, we constructed a feature density distance metric employing copula functions to quantitatively describe the classification capability of multidimensional features to distinguish targets from sea clutter. On the basis of this, a lightweight nonlinear dimensionality reduction network utilizing a self-attention mechanism was developed, optimally re-expressing multidimensional features into a three-dimensional feature space. Additionally, a concave hull classifier using feature sample distance was proposed to mitigate the negative impact of target sample divergence in the feature space. Furthermore, multivariate autoregressive prediction was used to optimize features, reducing erroneous decisions caused by anomalous feature samples. Experimental results using the measured data from the SDRDSP public dataset demonstrated that the proposed detection method achieved a detection probability more than 4% higher than comparative methods under Sea State 5, was less affected by false alarm rates, and exhibited superior detection performance under different false alarm probabilities from 10−3 to 10−1.