Wyniki wyszukiwania - BazTech

1

Hybrid binary whale optimization algorithm based on taper shaped transfer function for software defect prediction

Alnaish Zakaria A. Hamed, Hasoon Safwan O.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2023

|

T. 13, nr 4

85--92

EN

Reliability is one of the key factors used to gauge software quality. Software defect prediction (SDP) is one of the most important factors which affectsmeasuring software's reliability. Additionally, the high dimensionality of the features has a direct effect on the accuracy of SDP models.The objective of this paper is to propose a hybrid binary whale optimization algorithm (BWOA) based on taper-shape transfer functions for solving feature selection problems and dimension reduction with a KNN classifier as a new software defect prediction method. In this paper, the values of a real vector that representsthe individual encoding have been converted to binary vector by using the four types of Taper-shaped transfer functionsto enhance the performance of BWOA to reduce the dimension of the search space. The performance of the suggestedmethod (T-BWOA-KNN)was evaluatedusing eleven standard software defect prediction datasets from the PROMISE and NASA repositories depending on the K-Nearest Neighbor (KNN) classifier. Seven evaluation metrics have been used to assess the effectiveness of the suggested method. The experimental results have shownthat the performanceof T-BWOA-KNNproduced promising results compared to other methods including ten methods from the literature, four typesof T-BWOAwith the KNN classifier. In addition, the obtained results are compared and analyzed with other methods from the literature in termsof the average numberof selected features (SF) and accuracy rate (ACC) using the Kendall W test. In this paper, a new hybrid software defect prediction methodcalledT-BWOA-KNNhas been proposed which is concerned with the feature selection problem. The experimental results have provedthatT-BWOA-KNN produced promising performance compared with other methods for most datasets.

PL

Niezawodność jest jednym z kluczowych czynników stosowanych do oceny jakości oprogramowania.Przewidywanie defektów oprogramowania SDP (ang. Software Defect Prediction) jest jednym z najważniejszych czynników wpływających na pomiar niezawodności oprogramowania. Dodatkowo, wysoka wymiarowość cech ma bezpośredni wpływ na dokładność modeli SDP.Celemartykułu jest zaproponowanie hybrydowego algorytmu optymalizacji BWOA (ang. Binary Whale Optimization Algorithm) w oparciu o transmitancję stożkową do rozwiązywania problemów selekcji cech i redukcji wymiarów za pomocą klasyfikatora KNN jako nowej metody przewidywania defektów oprogramowania.W artykule, wartości wektora rzeczywistego, reprezentującego indywidualne kodowanie zostały przekonwertowane na wektor binarny przy użyciu czterech typów funkcji transferu w kształcie stożka w celu zwiększenia wydajności BWOA i zmniejszenia wymiaru przestrzeni poszukiwań.Wydajność sugerowanej metody (T-BWOA-KNN) oceniano przy użyciu jedenastu standardowych zestawów danych do przewidywania defektów oprogramowania z repozytoriów PROMISE i NASA w zależności od klasyfikatora KNN. Do oceny skuteczności sugerowanej metody wykorzystano siedemwskaźników ewaluacyjnych. Wyniki eksperymentów wykazały, że działanie rozwiązania T-BWOA-KNN pozwoliło uzyskaćobiecujące wyniki w porównaniu z innymi metodami, w tym dziesięcioma metodami na podstawie literatury, czterema typami T-BWOA z klasyfikatorem KNN. Dodatkowo, otrzymane wyniki zostały porównanei przeanalizowane innymi metodami z literatury pod kątem średniej liczby wybranych cech (SF) i współczynnika dokładności (ACC), z wykorzystaniem testu W.Kendalla. W pracy, zaproponowano nową hybrydową metodę przewidywania defektów oprogramowania, nazwaną T-BWOA-KNN, która dotyczy problemu wyboru cech. Wyniki eksperymentów wykazały, że w przypadku większości zbiorów danych T-BWOA-KNN uzyskała obiecującą wydajnośćw porównaniu z innymi metodami.

2

Application of entropy method for estimating factor weights in mining-method selection for development of novel mining-method selection system

Manjate Pansilvania Andre Manjate, Saadat Mahdi, Toriya Hisatoshi, Inagaki Fumiaki, Kawamura Youhei

Journal of Sustainable Mining

|

2021

|

Vol. 20, iss. 4

296--308

EN

Mining-method selection (MMS) is one of the most critical and complex decision making processes in mine planning. Therefore, it has been a subject of several studies for many years culminating with the development of different systems. However, there is still more to be done to improve and/or create more efficient systems and deal with the complexity caused by many influencing factors. This study introduces the application of the entropy method for feature selection, i.e., select the most critical factors in MMS. The entropy method is applied to assess the relative importance of the factors influencing MMS by estimating their objective weights to then select the most critical. Based on the results, ore strength, host-rock strength, thickness, shape, dip, ore uniformity, mining costs, and dilution were identified as the most critical factors. This study adopts the entropy method in the data preparation step (i.e., feature selection) for developing a novel-MMS system that employs recommendation system technologies. The most critical factors will be used as main variables to create the dataset to serve as a basis for developing the model for the novel-MMS system. This study is a key step to optimize the performance of the model.

3

An Empirical Study on Application of Word Embedding Techniques for Prediction of Software Defect Severity Level

Kumar Lov, Kumar Mukesh, Bhanu Murthy Lalita, Misra Sanjay, Kocher Vipul, Padmanabhuni Srinivas

Annals of Computer Science and Information Systems

|

2021

|

Vol. 25

477--484

EN

This work aims to develop defect severity level prediction models that have the ability to assign severity level of defects based on bugs report. In this work, seven different word embedding techniques are applied to defect description to represent the word, not just as a number but as a vector in n-dimensional space. Further, three feature selection techniques have been applied to find the right set of relevant vectors. The effectiveness of these word embedding techniques and different sets of vectors are evaluated using different classification techniques with SMOTE to overcome the class imbalance problem.

4

Schizophrenia detection using Multivariate Empirical Mode Decomposition and entropy measures from multichannel EEG signal

Krishnan Palani Thanaraj, Joseph Raj Alex Noel, Balasubramanian Parvathavarthini, Chen Yuanzhu

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

1124--1139

EN

Multivariate analysis of the EEG signal for the detection of Schizophrenia condition is proposed here. Multivariate Empirical Mode Decomposition (MEMD) is used to decompose the EEG signal into Intrinsic Mode Functions (IMF) signal. The randomness measure of the IMF signal is determined by computing the entropy of the signal. Five entropy measures such as Approximate entropy, Sample entropy, Permutation entropy, Spectral entropy, and Singular Value Decomposition entropy are measured from the IMF signal. These entropy measures showed a significant difference ( p < 0.01) between the healthy controls (HC) and Schizophrenia (SZ) subjects. Many state-of-the-art (SoA) machine learning classifiers are trained on the feature matrix obtained from entropy values of the IMF signal, amongst them Support Vector Machine based on Radial Basis Function (SVM-RBF) provided the highest accuracy and F1-score of 93% for the 95 features. The area under the curve (AUC) value of 0.9831 was obtained using this classifier. These performance metrics suggests that computation of randomness measure such as entropy in the multivariate IMF domain provided better discriminating power in detection of Schizophrenia condition from the multichannel EEG signal.

5

Entropies for automated detection of coronary artery disease using ECG signals: A review

Acharya U. R., Hagiwara Y., Koh J. E. W., Oh S. L., Tan J. H., Adam M., Tan R. S.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

373--384

EN

Coronary artery disease (CAD) develops when coronary arteries are unable to supply oxygen-rich blood to the heart due to the accumulation of cholesterol plaque on the inner walls of the arteries. Chronic insufficient blood flow leads to the complications, including angina and heart failure. In addition, acute plaque rupture may lead to vessel occlusion, causing a heart attack. Thus, it is encouraged to have regular check-ups to diagnose CAD early and avert complications. The electrocardiogram (ECG) is a widely used diagnostic tool to study the electrical activity of the heart. However, ECG signals are highly chaotic, complex, and non-stationary in their behaviour. It is laborious, and requires expertise, to visually interpret these signals. Hence, the computer-aided detection system (CADS) is developed to assist clinicians to interpret the ECG signals fast and reliably. In this work, we have employed sixteen entropies to extract the various hidden signatures from ECG signals of normal healthy persons as well as patients with CAD. We observed that the majority of extracted entropy features showed lower values for CAD patients compared to normal subjects. We believe that there is one possible reason which could be the decreased in the variability of ECG signals is associated with reduced heart pump function.

6

Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform

Kumar M., Pachori R. B., Rajendra Acharya U.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

564--573

EN

Atrial fibrillation (AF) is the most common type of sustained arrhythmia. The electrocardiogram (ECG) signals are widely used to diagnose the AF. Automated diagnosis of AF can aid the clinicians to make a more accurate diagnosis. Hence, in this work, we have proposed a decision support system for AF using a novel nonlinear approach based on flexible analytic wavelet transform (FAWT). First, we have extracted 1000 ECG samples from the long duration ECG signals. Then, log energy entropy (LEE), and permutation entropy (PEn) are computed from the sub-band signals obtained using FAWT. The LEE and PEn features are extracted from different frequency bands of FAWT.We have found that LEE features showed better classification results as compared to PEn. The LEE features obtained maximum accuracy, sensitivity, and specificity of 96.84%, 95.8%, and 97.6% respectively with random forest (RF) classifier. Our system can be deployed in hospitals to assist cardiac physicians in their diagnosis.

7

Estimating the Shapes of Gravity Sources through Optimized Support Vector Classifier (SVC)

Hekmatian M. E., Ardestani V. E., Riahi M. A., Bagh A. M. K., Amini J.

Acta Geophysica

|

2015

|

Vol. 63, no. 4

1000--1024

EN

In gravity interpretation methods, an initial guess for the approximate shape of the gravity source is necessary. In this paper, the support vector classifier (SVC) is applied for this duty by using gravity data. It is shown that using SVC leads us to estimate the approximate shapes of gravity sources more objectively. The procedure of selecting correct features is called feature selection (FS). In this research, the proper features are selected using inter/intra class distance algorithm and also FS is optimized by increasing and decreasing the number of dimensions of features space. Then, by using the proper features, SVC is used to estimate approximate shapes of sources from the six possible shapes, including: sphere, horizontal cylinder, vertical cylinder, rectangular prism, syncline, and anticline. SVC is trained using 300 synthetic gravity profiles and tested by 60 other synthetic and some real gravity profiles (related to a well and two ore bodies), and shapes of their sources estimated properly.

8

Document content mining for authors’ identification task

Łukasik Sz., Haręza M., Kaczor M.

Czasopismo Techniczne. Automatyka

|

2013

|

R. 110, z. 1-AC

3--15

EN

This paper deals with automatic authorship attribution through documents content analysis. This approach is based on selecting sets of suitable features relying on specific use of grammar, punctuation or vocabulary and in the next step – executing given classification algorithm. The contribution first overviews various text characteristics which can be employed for that purpose, then presents the results of experiments involving feature selection and examines classifier performance for author identification problem. The paper concludes with discussion and proposals for further research.

PL

Przedmiotem niniejszego artykułu jest problem identyfikacji autora na podstawie analizy treści dokumentów. Podejście to opiera się na wyborze odpowiednich cech związanych ze specyficznym użyciem struktur gramatycznych, interpunkcji oraz słownika, a następnie – użycie wybranego algorytmu klasyfikacji. W artykule przedstawiono najpierw różne charakterystyki tekstu, które mogą być użyte w omawianym zagadnieniu, a następnie załączono wyniki eksperymentów obliczeniowych obejmujących wybór cech i badanie skuteczności klasyfikacji w problemie identyfikacji autorów. Artykuł podsumowano wnioskami oraz propozycjami dalszych prac w rozważanej tematyce badawczej.

9

Analyzing feature trajectories for audio content discrimination

Mąka T.

Elektronika : konstrukcje, technologie, zastosowania

|

2011

|

Vol. 52, nr 10

157-159

EN

The paper presents an approach to classification of audio data using properties derived from low-level features. The new descriptors based on peakiness of the feature trajectory, and the crossing points between two selected trajectories. Calculated features are exploited in wrapper-based selection process and Support Vector Machines are employed to the speech/music classification problem. The obtained results show that proposed approach can be applied to perform audio classification in efficient manner.

PL

Podejście do klasyfikacji akustycznej przedstawione w pracy wykorzystuje charakterystykę zmienności cech niskopoziomowych. Wykorzystano własności występowania szczytów w trajektoriach cech oraz własności punktów przecięć pomiędzy dwoma wybranymi trajektoriami cech. Uzyskane w ten sposób deskryptory poddano selekcji z użyciem algorytmu wykorzystującego maszyny wektorów nośnych SVM dla problemu klasyfikacji sygnałów mowy i muzyki. Pokazano, że proponowane podejście i użyte cechy pozwalają uzyskać wysoką skuteczność klasyfikacji.

10

Facial feature extraction from a monochromatic picture

Rafiński L.

Poznan University of Technology Academic Journals. Electrical Engineering

|

2010

|

No. 61

207-213

EN

Face pose determination represents an important area of research in Human Machine Interaction. In this paper, I describe a new method of extracting facial feature locations from a single monochromatic monocular camera for the purpose of estimating and tracking the three dimensional pose of human face and eye-gaze direction.

11

Application of Support Vector Machines in automatic human face recognition

Kawulok M.

Journal of Medical Informatics & Technologies

|

2005

|

Vol. 9

143--150

EN

This paper presents the possibilities of applying the Support Vector Machines (SVM) in the process of automatic human face recognition. It is described how the existing methods of face recognition can be improved by the SVM. Moreover, a new approach to the multi-method fusion utilising the SVM is proposed. Usefulness of all the methods described in the paper improving the face recognition effectiveness by the SVM is confirmed by the experimental results.

12

Feature extraction using indicators of cyclostationarity for a mechanical diagnosis purpose

Raad A., Antoni J., Sidahmed M.

Computer Assisted Mechanics and Engineering Sciences

|

2005

|

Vol. 12, No. 2-3

223-230

EN

This paper focuses on features extraction based on cyclostationarity for diagnosis purpose. The objective is to derive new indicators for the diagnosis of rotating machinery. These indicators are based on cyclic higher order statistics and generalize some existing ones for the second order statistics. A comprehensive methodology is proposed for obtaining a diagnosis objective; a crucial example is presented, relating to vibration signals of a gearbox. Results demonstrate the effectiveness of these features to detect spalling in gearbox.

13

Selekcja cech w cyfrowej analizie obrazów biologicznych

Cytowski J., Sakowski T.

Prace Instytutu Podstaw Informatyki Polskiej Akademii Nauk

|

1998

|

nr 871

3-32

PL

W pracy przedstawiamy zastosowanie metody decyzyjno-teoretycznrgo rozpoznawania wzorców do analizy obrazów biologicznych. Rozważamy problem wyboru cech obrazów. Na podstawie analizy statystycznej wyznaczamy zbiór cech przydatnych w rozpoznawaniu obrazów biologicznych.

EN

This paper discuss the implementation of a DTPR (decision-theoretical pattern recognition) method for a analysis of a biological images. We discuss in detail the problem of images attributes selection. The paper contains statistical analysis of attributes for biological images recognition.