14 research outputs found
Mammographic mass classification according to Bi‐RADS lexicon
No full textThe goal of this study is to propose a computer‐aided diagnosis system to differentiate between four breast imaging reporting and data system (Bi‐RADS) classes in digitised mammograms. This system is inspired by the approach of the doctor during the radiologic examination as it was agreed in BI‐RADS, where masses are described by their form, their boundary and their density. The segmentation of masses in the authors’ approach is manual because it is supposed that the detection is already made. When the segmented region is available, the features extraction process can be carried out. 22 visual characteristics are automatically computed from shape, edge and textural properties; only one human feature is used in this study, which is the patient's age. Classification is finally done using a multi‐layer perceptron according to two separate schemes; the first one consists of classify masses to distinguish between the four BI‐RADS classes (2, 3, 4 and 5). In the second one the authors classify abnormalities on two classes (benign and malign). The proposed approach has been evaluated on 480 mammographic masses extracted from the digital database for screening mammography, and the obtained results are encouraging
Sheeran succeeds in ‘Shape of You’ music copyright infringement claim
No full textCopyright © The Author(s) 2022. Sheeran & Ors v Chokri & Ors [2022] EWHC 187 (Ch), 6 April 2022.
This case involved an assessment of UK copyright infringement, including the application of the question of independent creation and substantial similarity in relation to the copying of a musical work
Extraction of Scores and Average From Algerian High-School Degree Transcripts
No full textA system for extracting scores and average from Algerian High School Degree Transcripts is proposed. The system extracts the scores and the average based on the localization of the tables gathering this information and it consists of several stages. After preprocessing, the system locates the tables using ruling-lines information as well as other text information. Therefore, the adopted localization approach can work even in the absence of certain ruling-lines or the erasure and discontinuity of lines. After that, the localized tables are segmented into columns and the columns into information cells. Finally, cells labeling is done based on the prior knowledge of the tables structure allowing to identify the scores and the average. Experiments have been conducted on a local dataset in order to evaluate the performances of our system and compare it with three public systems at three levels, and the obtained results show the effectiveness of our system
Tones in Khezha noun constructions
No full textKhezha is one of the minor Naga languages of the Tibeto-Burman family, spoken by about 25,000 people in and outside Nagaland (about 20.000 in Nagaland and 5,000 in Manipur). The region in which its speakers live is also called Khezha. Scholars have classified Naga languages into three groups, viz. Western, Central and Eastern. According to this classification, Khezha, along with Angami. Chokri, Mao, Rengma, Sema and Pochuri, constitute the Eastern (or Southern) group. In recent years, some scholars have attempted to study some of the Naga languages. However, no one has done any significant work on Khezha; only small data samples have been collected for comparative analysis with other Naga languages. Within Khezha, each village has its own dialect identity (this is a common characteristic of all Naga languages). The present study was conducted on the Pfutsero dialect of Khezha, of which the author is a native speaker.Published versio
Conventional Machine Learning versus Deep Learning for Magnification Dependent Histopathological Breast Cancer Image Classification: A Comparative Study with Visual Explanation
No full textBreast cancer is a serious threat to women. Many machine learning-based computer-aided diagnosis (CAD) methods have been proposed for the early diagnosis of breast cancer based on histopathological images. Even though many such classification methods achieved high accuracy, many of them lack the explanation of the classification process. In this paper, we compare the performance of conventional machine learning (CML) against deep learning (DL)-based methods. We also provide a visual interpretation for the task of classifying breast cancer in histopathological images. For CML-based methods, we extract a set of handcrafted features using three feature extractors and fuse them to get image representation that would act as an input to train five classical classifiers. For DL-based methods, we adopt the transfer learning approach to the well-known VGG-19 deep learning architecture, where its pre-trained version on the large scale ImageNet, is block-wise fine-tuned on histopathological images. The evaluation of the proposed methods is carried out on the publicly available BreaKHis dataset for the magnification dependent classification of benign and malignant breast cancer and their eight sub-classes, and a further validation on KIMIA Path960, a magnification-free histopathological dataset with 20 image classes, is also performed. After providing the classification results of CML and DL methods, and to better explain the difference in the classification performance, we visualize the learned features. For the DL-based method, we intuitively visualize the areas of interest of the best fine-tuned deep neural networks using attention maps to explain the decision-making process and improve the clinical interpretability of the proposed models. The visual explanation can inherently improve the pathologist’s trust in automated DL methods as a credible and trustworthy support tool for breast cancer diagnosis. The achieved results show that DL methods outperform CML approaches where we reached an accuracy between 94.05% and 98.13% for the binary classification and between 76.77% and 88.95% for the eight-class classification, while for DL approaches, the accuracies range from 85.65% to 89.32% for the binary classification and from 63.55% to 69.69% for the eight-class classification
Wavelet Neural Networks for DNA Sequence Classification Using the Genetic Algorithms and the Least Trimmed Square
No full textAbstractThis paper presents a structure of the Wavelet Neural Networks used to classify the DNA sequences. The satisfying performance of the Wavelet Neural Networks (WNN) depends on an appropriate determination of the WNN structure optimization problem. In this paper we present a new method to solve this problem based on Genetic Algorithm (GA) and the Least Trimmed Square (LTS). The GA is used to solve the structure and the learning of the WNN and the LTS algorithm is applied to select the important wavelets. First, the scale of the WNN is managed by using the time-frequency locality of wavelet. Furthermore, this optimization problem can be solved efficiently by Genetic Algorithm as well as the LTS method to improve the robustness. The performance of the Wavelet Networks is investigated by detecting the simulating and the real signals in white noise. The main advantage of this method can guarantee the optimal structure of the WNN. The experimental results have indicated that the proposed method (WNN-GA) with the k-means algorithm is more precise than other methods. The proposed method has been able to optimize the wavelet neural network and classify the DNA sequences. Our goal is to construct a predictive approach that is highly accurate results. In fact, our approach allows avoiding the complex problem of form and structure in different groups of organisms. The experimental results are showed that the WNN-GA model outperformed the other models in terms of both the clustering results and the running time. In this study, we present our system which consists of three phases. The first one is the transformation, is composed of two sub steps; the binary codification of the DNA sequences and the Power Spectrum Signal Processing. The second step is the approximation; it is empowered by the use of the Multi Library Wavelet Neural Networks (MLWNN). Finally, the third one is the clustering of the DNA sequences, is realized by applying the algorithm of the k-means algorithm
Mathematical analysis and solution methodology for an inverse spectral problem arising in the design of optical waveguides
No full textInternational audienceWe analyze mathematically the problem of determining refractive index pro-les from some desired/measured guided waves propagating in optical bers. We establish the uniqueness of the solution of this inverse spectral problem assuming that only one guided mode is known. We then propose an iterative computational procedure for solving numerically the considered inverse spectral problem. Numerical results are presented to illustrate the potential of * corresponding author: [email protected] 1 the proposed regularized Newton algorithm to eciently and accurately retrieve the refractive index proles even when the guided mode measurements are highly noisy
Mathematical analysis and solution methodology for an inverse spectral problem arising in the design of optical waveguides
No full textInternational audienceWe analyze mathematically the problem of determining refractive index pro-les from some desired/measured guided waves propagating in optical bers. We establish the uniqueness of the solution of this inverse spectral problem assuming that only one guided mode is known. We then propose an iterative computational procedure for solving numerically the considered inverse spectral problem. Numerical results are presented to illustrate the potential of * corresponding author: [email protected] 1 the proposed regularized Newton algorithm to eciently and accurately retrieve the refractive index proles even when the guided mode measurements are highly noisy
Exotericising through Translation: Style and its Effects on Arabic Readers
No full textTranslated esoteric texts that are originally written for a specific ‘discourse community’ (Swales 1990) in the source language are unlikely to attract readers from outside that community in the target language due to their specialised content and style. The present thesis is based on the hypothesis that adopting a different style in the translation of a non-literary text in the target language will increase its readability and accessibility among a wider readership. It attempts to measure the reader’s response to style in a translated text and assess the ability of stylistic shifts to broaden its horizons in the host culture.
To test this hypothesis, excerpts from Sent before my Time: a Child Psychotherapist’s View of Life on a Neonatal Intensive Care Unit by Margaret Cohen (2003) have been translated into Arabic in two versions that are stylistically different. While the first version recreates the source text style, the second adopts a different approach that borrows stylistic features usually found in fiction and thus opens up the psychotherapeutic discourse implied in the source text. This study uses qualitative and quantitative methods. A total of 150 participants divided into two groups named Professionals and Laypeople took part in a reading experiment in which they were invited to register their response to two versions of the Arabic translation and choose which version they liked best. Surprisingly, the results show that not only the group of Laypeople responded more favourably to the second version but also the group of Professionals who were members of the discourse community addressed by the source text author. The implications of this study are potentially considerable. Stylistic shifts are capable of turning an esoteric text into an exoteric one and thus increasing its chances of being read by a wider readership in the target language
Exotericising through Translation: Style and its Effects on Arabic Readers
No full textTranslated esoteric texts that are originally written for a specific ‘discourse community’ (Swales 1990) in the source language are unlikely to attract readers from outside that community in the target language due to their specialised content and style. The present thesis is based on the hypothesis that adopting a different style in the translation of a non-literary text in the target language will increase its readability and accessibility among a wider readership. It attempts to measure the reader’s response to style in a translated text and assess the ability of stylistic shifts to broaden its horizons in the host culture.
To test this hypothesis, excerpts from Sent before my Time: a Child Psychotherapist’s View of Life on a Neonatal Intensive Care Unit by Margaret Cohen (2003) have been translated into Arabic in two versions that are stylistically different. While the first version recreates the source text style, the second adopts a different approach that borrows stylistic features usually found in fiction and thus opens up the psychotherapeutic discourse implied in the source text. This study uses qualitative and quantitative methods. A total of 150 participants divided into two groups named Professionals and Laypeople took part in a reading experiment in which they were invited to register their response to two versions of the Arabic translation and choose which version they liked best. Surprisingly, the results show that not only the group of Laypeople responded more favourably to the second version but also the group of Professionals who were members of the discourse community addressed by the source text author. The implications of this study are potentially considerable. Stylistic shifts are capable of turning an esoteric text into an exoteric one and thus increasing its chances of being read by a wider readership in the target language
