Online reviews have become a valuable resource for decision making. In recent years, analysis ofreviews has attracted significant attention. Individuals and organizations in making purchase and other organizational de...
详细信息
Online reviews have become a valuable resource for decision making. In recent years, analysis ofreviews has attracted significant attention. Individuals and organizations in making purchase and other organizational decisions are increasingly using online reviews. Positive reviews acclaim significant financial gains, fame and prestige for businesses in market. On the other end, this gives strong enticement to fraudulent to hypocrite the system by posting disingenuous reviews to promote or to vilify some target products and services, which is known as opinion spam. Therefore, we made this research effort as an initial impetus in the direction to identify the presence of fake reviews. We performed this experiment on Wallet Apps accessible through Google Play Store. To do so, we rate applications based on features availability existence in Google App based on App content and user reactions. We computed four major scores-Description score, Positive Store, Negative Store and Review Tag Score and finally assigned a cumulative normalized score to all Wallet Apps. Further, a comparative analysis has been done between cumulative normalized score and stated Google App rating. Significant deviation indicates a strong probability that application has an opinion spam.
Machine learning plays an important and growing role in molecular simulation. The newest version of the OpenMM molecular dynamics toolkit introduces new features to support the use of machine learning potentials. Arbi...
详细信息
In this paper we will offer a new symmetric-key cryptographic scheme which is based on the existence of exponentially distorted subgroups in arithmetic groups. Aside from this, we will also provide new examples of dis...
详细信息
Chromosome segmentation in metaphase images is a critical yet challenging task in cytogenetics and genomics due to the inherent complexity, variability in chromosome shapes, and the scarcity of high-quality annotated ...
详细信息
Chromosome segmentation in metaphase images is a critical yet challenging task in cytogenetics and genomics due to the inherent complexity, variability in chromosome shapes, and the scarcity of high-quality annotated datasets. This study proposes a robust instance segmentation framework that integrates an automated annotation pipeline with an enhanced deep learning architecture to address these challenges. A novel dataset is introduced, comprising metaphase images and corresponding karyograms, annotated with precise instance segmentation information across 24 chromosome classes in COCO format. To overcome the labor-intensive manual annotation process, a feature-based image registration technique leveraging SIFT and homography is employed, enabling the accurate mapping of chromosomes from karyograms to metaphase images and significantly improving annotation quality and segmentation performance. The proposed framework includes a custom Mask R-CNN model enhanced with an Attention-based Feature Pyramid Network (AttFPN), spatial attention mechanisms, and a LastLevelMaxPool block for superior multi-scale feature extraction and focused attention on critical regions of the image. Experimental evaluations demonstrate the model's efficacy, achieving a mean average precision (mAP) of 0.579 at IoU = 0.50:0.95, surpassing the baseline Mask R-CNN and Mask R-CNN with AttFPN by 3.94% and 5.97% improvements in mAP and AP50, respectively. Notably, the proposed architecture excels in segmenting small and medium-sized chromosomes, addressing key limitations of existing methods. This research not only introduces a state-of-the-art segmentation framework but also provides a benchmark dataset, setting a new standard for chromosome instance segmentation in biomedical imaging. The integration of automated dataset creation with advanced model design offers a scalable and transferable solution, paving the way for tackling similar challenges in other domains of biomedical and cytogenetic imagi
A complete emotional expression typically contains a complex temporal course in a natural conversation. Related research on utterance-level, segment-level and multi-level processing lacks understanding of the underlyi...
详细信息
ISBN:
(纸本)9781538656280;9781538656273
A complete emotional expression typically contains a complex temporal course in a natural conversation. Related research on utterance-level, segment-level and multi-level processing lacks understanding of the underlying relation of emotional speech. In this work, a convolutional neural network (CNN) with audio word-based embedding is proposed for emotion modeling. In this study, vector quantization is first applied to convert the low level features of each speech frame into audio words using k-means algorithm. Word2vec is adopted to convert an input speech utterance into the corresponding audio word vector sequence. Finally, the audio word vector sequences of the training emotional speech data with emotion annotation are used to construct the CNN- based emotion model. The NCKU-ES database, containing seven emotion categories: happiness, boredom, anger, anxiety, sadness, surprise and disgust, was collected and five-fold cross validation was used to evaluate the performance of the proposed CNN-based method for speech emotion recognition. Experimental results show that the proposed method achieved an emotion recognition accuracy of 82.34%, improving by 8.7% compared to the Long Short Term Memory (LSTM)- based method, which faced the challenging issue of long input sequence. Comparing with raw features, the audio word-based embedding achieved an improvement of 3.4% for speech emotion recognition.
In medicine, the diagnosis of diseases by means of image processing has had great acceptability and credibility, which is why it has been able to explore in depth the theme, taking advantage of mainly which is a non-i...
详细信息
Intensive care clinicians are presented with large quantities of patient information and measurements from a multitude of monitoring systems. The limited ability of humans to process such complex information hinders p...
详细信息
Psoriasis classification requires the accurate identification of the lesional types for the early and effective diagnosis and it is worth interesting that the normal and psoriasis cell tissues exhibit different gene e...
详细信息
Psoriasis classification requires the accurate identification of the lesional types for the early and effective diagnosis and it is worth interesting that the normal and psoriasis cell tissues exhibit different gene expression. Therefore, gene expression data is an effective source for psoriasis classification and there is a challenge regarding the selection of suitable gene signatures for its purpose. In this present study, the gene expression-based microarray data were used and 35 expression features linked with psoriasis were utilized to feed into our machine learning model. Overall, the performance of our model based on 35 mentioned-above features surpassed that of other state-of-the-art classifiers with an average accuracy of 98.3%, recall of 98.6%, and precision of 98% in 5-fold cross-validation tests. We also validate our model on two different sets of psoriasis and the performance results are significant. These results have suggested that our 35 expression signatures have been identified as key features for classifying samples between lesion and non-lesion. More specifically, the expression levels of few genes i.e., FABP5 , TGM1 , or BCAR3 are discovered as newly potential biomarkers for psoriasis classification and treatment with high confidence. This study, therefore, could shed light on developing the prediction models for psoriasis classification and treatment using gene expression profiles.
暂无评论