Papers by Keyword: Classification

Abstract: The construction of Yogyakarta International Airport (YIA), driven by the limitations of land use at the former Adisutjipto Airport, is a key focal point of this research. The development of YIA has led to significant land cover changes in 2016 to 2021, transforming predominantly agricultural and fisheries land into built-up areas. Numerous studies have utilized remote sensing data to analyze land cover and land use (LULC) changes in Kulonprogo Regency, applying a range of remote sensing analytical methods. The most substantial LULC changes have been observed in Temon District, where agricultural land has sharply decreased, coinciding with the expansion of built-up areas. This study aims to further examine land use changes in Temon District, employing object-based classification techniques to enhance the accuracy of land cover analysis. In this study, OBIA classified land cover with 80% accuracy for the 2016 image (scale 100, shape 0.7, compactness 0.7) and 86% for the 2021 image (scale 100, shape 0.9, compactness 0.2). The most significant change was a 537-hectare reduction in paddy field.

Abstract: Transportation is one of the crucial factors in the development of a country. This can be observed from the increasing needs of transportation in supporting human activities in residential and urban areas. Therefore, it is essential to maintain the infrastructure that supports the needs of transportation. One of the infrastructures that need to be considered as the main factor of transportation is road condition. Damaged road conditions can cause obstacles to the transportation system. One way to detect road damage is by measuring the vibration values that occur under different road conditions using an accelerometer as a vibration recorder. The vibration data is classified into three groups based on the road conditions where the recordings took place, namely good road condition, speed bumps (bump), and potholes. A total of 52 data samples were collected for each road condition in Yogyakarta using a motorcycle, which were then processed into vibration data in the frequency domain. The vibration data processing was carried out using Jupyter Notebook software with Python programming language and the algorithms used in this research were Fast Fourier Transform (FFT), SG Filtering, and Power Spectral Density (PSD) to determine the strength of the vibration signal. After that classification was performed by applying supervised machine learning using the multiclass classification algorithm on Support Vector Machine (SVM) other than that, cross-validation process was implemented to know the performance of the machine learning model. The classification results show an accuracy value of 92.31% for predicting road condition labels in the training model and 97.44% for the testing model. Both models are calculated using 75% of the total data for the training model and 25% of the total data for the testing model.

Abstract: The frequent use of railway tracks in railway operations can cause damage or wear that can disrupt comfort and resulted vibrations on the trains. There are various types of damage that can occur to railway tracks, one of which is longitudinal level damage. Machine learning can be employed to predict the damage. However, it is quite difficult to predict based on real data with a high amount of data. Therefore, a railway miniature is fabricated with a controlled damage. Therefore, this study has purpose to predict the damage using the produced data from railway miniature. The vibrations was measured using an accelerometer device that available on smartphones with the Phypox application, and it will be mounted on a miniature railway track with three different track conditions: one normal and two abnormal, with each track condition has 50 data points. With the assistance of machine learning as the main brain behind the vibration detection program, vibration data can be classified based on the track conditions experienced. The data was processed into frequency domain using Fast Fourier Transform (FFT) algorithm, filtered using SG-Filter, and Power Spectral Density (PSD) will be used to assess the strength of the vibration signal. The vibration data processing was carried out using Jupyter Notebook software with Python programming language. Classification was performed by applying supervised machine learning using the classification method of Support Vector Machine (SVM). In classification process, results obtained show an accuracy of 88.19% for training model and an accuracy of 82.61% for testing model, computed using 85% of total data for training model and 15% of total data for testing model. The produced data and built machine learning can be further applied for checking the rail damage at uncontrollable environment.

Abstract: Intelligent neural networks are used efficiently for image classification and recognition in various scientific areas. One of the most important of these areas is nanoscience. Researchers are currently seeking to apply various deep learning neural networks models for fast and intelligent prediction and recognition of nanostructures based on scanning electron microscopy images. Models of Deep Convolutional Neural Networks (DCNN) have reached a high accuracy rate in nanoparticles classification and recognition. In fact, the improvement of the classification accuracy strongly relies on the perfect fine-tuning of image data and model parameters and that is what this research has worked for. The aim of this paper is to present a model, specifically the VGG16 convolutional neural network model, for high accurate nanoparticles ordering classification. The model has been used to classify the nanoparticles ordering using a typical dataset of electron microscopy images. In this research, an experiment has been carried out to achieve better accuracy rate in comparison to previously recorded accuracy rates. Data augmentation, modification techniques, and model tuning parameters are applied to excess the ability of the model for classifying the input image to ordered or non-ordered nanoparticles. Compared to the related works, the presented model has outperformed the pervious by achieving an accuracy rate of 97%. In this work, it has been observed that training iterations and balanced training data significantly improve the model performance and enhance the accuracy rate.

Abstract: The article provides an analytical review of the main problems and prospects for the use and introduction of polymer concrete in modern construction industries. It was found that due to high plasticity, low porosity and the ability to quickly gain strength, polymer concretes are used for the manufacture of decorative products of small architecture, structural load-bearing and decorative overhead parts, decorative paving tiles and paving stones, products for hydrotechnical purposes, etc. by methods of vibration molding and casting. The classification of polymer concretes used in modern construction industries is provided, as well as an idea of the properties of the most popular polymer concretes based on thermosetting polymers – furan, epoxy and polyester. The advantages and disadvantages of known polymer concretes and the main promising directions of implementation for the manufacture of building products and structures are given. Attention is focused on the influence of the qualitative and quantitative composition of polymer concrete, the nature of the thermosetting polymer binder, the type of fillers and aggregates, the terms of hardening, the degree of polymerization on the most important physical, mechanical and technological properties of the finished materials.

Abstract: Several defects were analyzed through the manufacturing chain along with their impact on devices. High kill rate of micropipes were seen on both Diodes and MOSFETs as expected. The purity of micropipe detection was found to be affected by the presence of inclusions. Inclusions were successfully sub-classified and separated out from micropipes, based on their location depth from the wafer surface. The effect on devices was found to relate to how deep the inclusion was located, with the ones at the surface having the biggest impact. Various sources of Stacking Faults (SFs) were reported, with Basal Plane Dislocations (BPDs) in the crystal being a major contributor. Higher local densities of BPDs were found to have a more detrimental effect. SFs were sub-classified using the wavelength of each peak. The effect of both overall SFs and each SF sub-type on devices was determined, each sub-type having different effect on the device. Various ways of mitigating the effects of defects and dislocations are demonstrated. Reducing killer defects, SF nucleation probability, and BPDs propagation by epitaxial process optimizations are shown. Resilience up to 3500A/cm² against bipolar degradation is demonstrated by using an engineered buffer layer. Process and device design optimizations show high resiliency against crystal and epi defects and dislocations, with improved yield and lower leakage.

Abstract: Social media analytics is a form of information analytics that is quite important in today's cyber situation. Cybercrime is criminal behaviour based on computers and internet networks. Cybercriminals usually hack systems to obtain the personal information of victims. There are many types of cybercrimes. There are four types of cybercrimes: Phishing scams, Hacking, Cyber Stalking and Cyber Bullying. This research aims to help the process analysis by the Police or investigative institutions of the private sector in knowing the results of public sentiment on social media related to current cyber crimes. Ciber Crime identifying using machine learning techniques, based sentiment analysis. Method used for sentiment analysis related to cybercrime is Random Forest, Naïve Bayes, and KNN. The highest accuracy value of the three methods tried is the Naive Bayes algorithm of 99.45%. The highest precision value uses the Naive Bayes algorithm of 99.80%, and the highest recall value uses the random forest algorithm of 100%.

Abstract: Cancer is the second most common cause of death in the world. WHO notes, deaths caused by cancer will reach 10 million cases in 2021. Of many cancers, breast cancer is a cancer with the most cases. Early diagnosis of breast cancer plays an important role in the treatment process. Various imaging methods, including magnetic mammography, are used to diagnose breast cancer. With the help of machine learning, the process of diagnosing breast cancer with mammography images is more precise and accurate. Various machine-learning methods have been developed by researchers to diagnose breast cancer. Among them is a deep learning method that can achieve good feature representation and can solve the problem of image classification and object localization. Through a systematic literature review, this research collects and analyzes related studies regarding the classification of breast cancer that have been done previously. Several aspects that will be evaluated include the methods used, data sources used, and accuracy of the method used. This research is expected to provide clear knowledge about the advantages and disadvantages of using artificial intelligence techniques for breast cancer classification. The results of this study can provide insight for researchers and medical practitioners in the further development and application of deep learning methods in the diagnosis and classification of breast cancer.

Abstract: There is a great deal of uncertainty regarding the factors that influence their final year grade, which includes their entry qualification. This paper investigates the impact of entry qualification and pre-university CGPA on student performance at the university level. Entry qualifications are critical for educational institutions or educational providers to ensure the quality of the graduates. The goal of this study is to analyze and compare performance of Bachelor of Science (Industrial Statistics) with Honours (BWQ) students. Total of 54 students were selected form the Faculty of Applied Sciences and Technology (FAST), Universiti Tun Hussein Onn Malaysia (UTHM). The students are coming from Malaysian Higher School Certificate (STPM) and Malaysian Matriculation Programme. Paired t test and Z test were carried out to analyze the impact of pre-university’s CGPA and each semester’s GPA as well as impact of entry qualification towards their final year grade. Classification and Regression Tree (CART), K-Nearest Neighbors and Naïve Bayes were used to develop and predict the students’ performance. The findings show that there is no relation between the result obtained from previous semester towards the next semester. Meanwhile, students from STPM outperform Matriculation in terms of their GPA per semester, pre-university CGPA as well as their final CGPA. The K-Nearest Neighbors and Naïve Bayes models have been documented as the most efficient data mining techniques in predicting student performance with the highest percentage of accuracy of 100%.

Abstract: Lung sound analysis plays an important role in the assessment and diagnosis of respiratory conditions and diseases. It can provide valuable information about the functioning of the respiratory system, including the airways, lungs, and associated structures. By analyzing the characteristics of lung sounds, healthcare professionals can gain insights into the presence of abnormalities, such as airway obstructions, lung diseases, and respiratory infections. In this paper, a multiple channel model for processing and classifying abnormalities in lung sound is proposed, which utilize the characteristics of Mel spectrogram and the Empirical Mode Decomposition (EMD). Unlike previous research which directly convert the lung sound into scalogram or spectrogram, the pre-processing of the original audio signal is considered and focused in this paper. This pre-processing step includes denoising, resampling, padding and augmentation, which incredibly increase the quality of the input signal. Finally, the multiple channel is put into the VGG16 deep learning model to classify the abnormalities in lung sound, including wheezes, crackles, and both. The model is trained and tested on the benchmark ICBHI dataset. The proposed model has shown better performance when compared with the state-of-the-art researches.