Search results for: classification model

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: classification, singing, spectral analysis, vocal emission, vocal register

Procedia PDF Downloads 282

Authors: Massimo Miccoli, Luca Marangoni, Alberto Aniello Scaringi, Alessandro Marceddu, Alessandro Amicone

Abstract:

The susceptibility of deep neural networks (DNNs) to adversarial manipulations is a recognized challenge within the computer vision domain. Adversarial examples, crafted by adding subtle yet malicious alterations to benign images, exploit this vulnerability. Various defense strategies have been proposed to safeguard DNNs against such attacks, stemming from diverse research hypotheses. Building upon prior work, our approach involves the utilization of autoencoder models. Autoencoders, a type of neural network, are trained to learn representations of training data and reconstruct inputs from these representations, typically minimizing reconstruction errors like mean squared error (MSE). Our autoencoder was trained on a dataset of benign examples; learning features specific to them. Consequently, when presented with significantly perturbed adversarial examples, the autoencoder exhibited high reconstruction errors. The architecture of the autoencoder was tailored to the dimensions of the images under evaluation. We considered various image sizes, constructing models differently for 256x256 and 512x512 images. Moreover, the choice of the computer vision model is crucial, as most adversarial attacks are designed with specific AI structures in mind. To mitigate this, we proposed a method to replace image-specific dimensions with a structure independent of both dimensions and neural network models, thereby enhancing robustness. Our multi-modal autoencoder reconstructs the spectral representation of images across the red-green-blue (RGB) color channels. To validate our approach, we conducted experiments using diverse datasets and subjected them to adversarial attacks using models such as ResNet50 and ViT_L_16 from the torch vision library. The autoencoder extracted features used in a classification model, resulting in an MSE (RGB) of 0.014, a classification accuracy of 97.33%, and a precision of 99%.

Keywords: adversarial attacks, malicious images detector, binary classifier, multimodal transformer autoencoder

Procedia PDF Downloads 47

Authors: Ali Asheibi

Abstract:

The rapid increase in the size of databases required to store power quality monitoring data has demanded new techniques for analysing and understanding the data. One suggested technique to assist in analysis is data mining. Preparing raw data to be ready for data mining exploration take up most of the effort and time spent in the whole data mining process. Clustering is an important technique in data mining and machine learning in which underlying and meaningful groups of data are discovered. Large amounts of harmonic data have been collected from an actual harmonic monitoring system in a distribution system in Australia for three years. This amount of acquired data makes it difficult to identify operational events that significantly impact the harmonics generated on the system. In this paper, harmonic data preparation processes to better understanding of the data have been presented. Underlying classes in this data has then been identified using clustering technique based on the Minimum Message Length (MML) method. The underlying operational information contained within the clusters can be rapidly visualised by the engineers. The C5.0 algorithm was used for classification and interpretation of the generated clusters.

Keywords: data mining, harmonic data, clustering, classification

Procedia PDF Downloads 223

Authors: Marta D'Onofrio

Abstract:

The debate on the digitalization of the economy has raised questions about how both labor and the regulation of work processes are changing due to the introduction of digital technologies in the productive system. Within the literature, the term ‘digital labor’ is commonly used to identify the impact of digitalization on labor. Despite the wide use of this term, it is still not available an unambiguous definition of it, and this could create confusion in the use of terminology and in the attempts of classification. As a consequence, the purpose of this paper is to provide for a definition and to propose a classification of ‘digital labor’, resorting to the theoretical approach of organizational studies.

Keywords: digital labor, digitalization, data-driven algorithms, big data, organizational studies

Procedia PDF Downloads 127

Authors: Manaranjan Pradhan, Shailaja Grover, U. Dinesh Kumar

Abstract:

Farming community in India, as well as other parts of the world, is one of the highly stressed communities due to reasons such as increasing input costs (cost of seeds, fertilizers, pesticide), droughts, reduced revenue leading to farmer suicides. Lack of integrated farm advisory system in India adds to the farmers problems. Farmers need right information during the early stages of crop’s lifecycle to prevent damage and loss in revenue. In this paper, we use deep learning techniques to develop an early warning system for detection of crop diseases using images taken by farmers using their smart phone. The research work leads to building a smart assistant using analytics and big data which could help the farmers with early diagnosis of the crop diseases and corrective actions. The classical approach for crop disease management has been to identify diseases at crop level. Recently, ImageNet Classification using the convolutional neural network (CNN) has been successfully used to identify diseases at individual plant level. Our model uses convolution filters, max pooling, dense layers and dropouts (to avoid overfitting). The models are built for binary classification (healthy or not healthy) and multi class classification (identifying which disease). Transfer learning is used to modify the weights of parameters learnt through ImageNet dataset and apply them on crop diseases, which reduces number of epochs to learn. One shot learning is used to learn from very few images, while data augmentation techniques are used to improve accuracy with images taken from farms by using techniques such as rotation, zoom, shift and blurred images. Models built using combination of these techniques are more robust for deploying in the real world. Our model is validated using tomato crop. In India, tomato is affected by 10 different diseases. Our model achieves an accuracy of more than 95% in correctly classifying the diseases. The main contribution of our research is to create a personal assistant for farmers for managing plant disease, although the model was validated using tomato crop, it can be easily extended to other crops. The advancement of technology in computing and availability of large data has made possible the success of deep learning applications in computer vision, natural language processing, image recognition, etc. With these robust models and huge smartphone penetration, feasibility of implementation of these models is high resulting in timely advise to the farmers and thus increasing the farmers' income and reducing the input costs.

Keywords: analytics in agriculture, CNN, crop disease detection, data augmentation, image recognition, one shot learning, transfer learning

Procedia PDF Downloads 98

Authors: Wagneur Edouard

Abstract:

Tropical algebra is the algebra constructed over an idempotent semifield S. We show here that every m-dimensional tropical module M over S with strongly independent basis can be embedded into Sm, and provide an algebraic invariant -the Γ-matrix of M- which characterises the isomorphy class of M. The strong independence condition also yields a significant improvement to the Whitney embedding for tropical torsion modules published earlier We also show that the strong independence of the basis of M is equivalent to the unique representation of elements of M. Numerous examples illustrate our results.

Keywords: classification, idempotent semi-modules, strong independence, tropical algebra

Procedia PDF Downloads 351

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 105

Authors: O. J. Akinsola, Yinan Zheng, Rose Anorlu, F. T. Ogunsola, Lifang Hou, Robert Leo-Murphy

Abstract:

Cervical Cancer (CC) is the 2nd most common cancer among women living in low and middle-income countries, with no associated symptoms during formative periods. With the advancement and innovative medical research, there are numerous preventive measures being utilized, but the incidence of cervical cancer cannot be truncated with the application of only screening tests. The mortality associated with this invasive cervical cancer can be nipped in the bud through the important role of early-stage detection. This study research selected an array of different top features selection techniques which was aimed at developing a model that could validly diagnose the risk factors of cervical cancer. A retrospective clinic-based cohort study was conducted on 178 HIV-associated cervical cancer patients in Lagos University teaching Hospital, Nigeria (U54 data repository) in April 2022. The outcome measure was the automated prediction of the HIV-associated cervical cancer cases, while the predictor variables include: demographic information, reproductive history, birth control, sexual history, cervical cancer screening history for invasive cervical cancer. The proposed technique was assessed with R and Python programming software to produce the model by utilizing the classification algorithms for the detection and diagnosis of cervical cancer disease. Four machine learning classification algorithms used are: the machine learning model was split into training and testing dataset into ratio 80:20. The numerical features were also standardized while hyperparameter tuning was carried out on the machine learning to train and test the data. Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbor (KNN). Some fitting features were selected for the detection and diagnosis of cervical cancer diseases from selected characteristics in the dataset using the contribution of various selection methods for the classification cervical cancer into healthy or diseased status. The mean age of patients was 49.7±12.1 years, mean age at pregnancy was 23.3±5.5 years, mean age at first sexual experience was 19.4±3.2 years, while the mean BMI was 27.1±5.6 kg/m2. A larger percentage of the patients are Married (62.9%), while most of them have at least two sexual partners (72.5%). Age of patients (OR=1.065, p<0.001**), marital status (OR=0.375, p=0.011**), number of pregnancy live-births (OR=1.317, p=0.007**), and use of birth control pills (OR=0.291, p=0.015**) were found to be significantly associated with HIV-associated cervical cancer. On top ten 10 features (variables) considered in the analysis, RF claims the overall model performance, which include: accuracy of (72.0%), the precision of (84.6%), a recall of (84.6%) and F1-score of (74.0%) while LR has: an accuracy of (74.0%), precision of (70.0%), recall of (70.0%) and F1-score of (70.0%). The RF model identified 10 features predictive of developing cervical cancer. The age of patients was considered as the most important risk factor, followed by the number of pregnancy livebirths, marital status, and use of birth control pills, The study shows that data mining techniques could be used to identify women living with HIV at high risk of developing cervical cancer in Nigeria and other sub-Saharan African countries.

Keywords: associated cervical cancer, data mining, random forest, logistic regression

Procedia PDF Downloads 58

Authors: Amirali Mahouti, Hooshang Katebi

Abstract:

Enlargement of Tabriz metropolis to the east and north-east caused urban construction to be built on Marl layers and because of increase in excavations depth, further information of this layer is inescapable. Looking at geotechnical investigation shows there is not enough information about Tabriz Marl and this soil has been classified only by color. Tabriz Marl is lacustrine carbonate sediment outcrops, surrounds eastern, northern and southern region of city in the East Azerbaijan Province of Iran and is known as bed rock of city under alluvium sediments. This investigation aims to characterize geotechnical parameters of this soil to identify and set it in classification system of carbonated soils. For this purpose, specimens obtained from 80 locations over the city and subjected to physical and mechanical tests, such as Atterberg limits, density, moisture content, unconfined compression, direct shear and consolidation. CaCO3 content, organic content, PH, XRD, XRF, TGA and geophysical downhole tests also have been done on some of them.

Keywords: carbonated soils, classification of soils, mineralogy, physical and mechanical tests for Marls, Tabriz Marl

Procedia PDF Downloads 298

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 114

Authors: Ronak Khosravi, Mahmood Abbasi Layegh, Siamak Haghipour, Avin Esmaili

Abstract:

In this paper, a study on classification of musical woodwind instruments using a small set of features selected from a broad range of extracted ones by the sequential forward selection method was carried out. Firstly, we extract 42 features for each record in the music database of 402 sound files belonging to five different groups of Flutes (end blown and internal duct), Single –reed, Double –reed (exposed and capped), Triple reed and Quadruple reed. Then, the sequential forward selection method is adopted to choose the best feature set in order to achieve very high classification accuracy. Two different classification techniques of support vector machines and relevance vector machines have been tested out and an accuracy of up to 96% can be achieved by using 21 time, frequency and coefficient features and relevance vector machine with the Gaussian kernel function.

Keywords: coefficient features, relevance vector machines, spectral features, support vector machines, temporal features

Procedia PDF Downloads 293

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 120

Authors: Mohammed Mustapha Alhaji, Sadiku Salawu

Abstract:

A clay soil which classified under A-7-6 soil according to AASHTO soil classification system and CH according to the unified soil classification system was stabilized using A-3 soil (AASHTO soil classification system). The clay soil was replaced with 0%, 10%, 20% to 100% A-3 soil, compacted at both the BSL and BSH compaction energy level and using unconfined compressive strength as evaluation criteria. The MDD of the compactions at both the BSL and BSH compaction energy levels showed increase in MDD from 0% A-3 soil replacement to 40% A-3 soil replacement after which the values reduced to 100% A-3 soil replacement. The trend of the OMC with varied A-3 soil replacement is similar to that of MDD but in a reversed order. The OMC reduced from 0% A-3 soil replacement to 40% A-3 soil replacement after which the values increased to 100% A-3 soil replacement. This trend was attributed to the observed reduction in the void ratio from 0% A-3 soil replacement to 40% A-3 soil replacement after which the void ratio increased to 100% A-3 soil replacement. The maximum UCS for clay at varied A-3 soil replacement increased from 272 and 770kN/m2 for BSL and BSH compaction energy level at 0% A-3 soil replacement to 295 and 795kN/m2 for BSL and BSH compaction energy level respectively at 10% A-3 soil replacement after which the values reduced to 22 and 60kN/m2 for BSL and BSH compaction energy level respectively at 70% A-3 soil replacement. Beyond 70% A-3 soil replacement, the mixture cannot be moulded for UCS test.

Keywords: A-3 soil, clay minerals, pozzolanic action, stabilization

Procedia PDF Downloads 405

Authors: Anoop T. R., Otman Basir, Robert F. Hess, Eileen E. Birch, Brooke A. Koritala, Reed M. Jost, Becky Luu, David Stager, Ben Thompson

Abstract:

Strabismus refers to a misalignment of the eyes. Early detection and treatment of strabismus in childhood can prevent the development of permanent vision loss due to abnormal development of visual brain areas. We developed a two-stage method for strabismus detection and classification based on photographs of the face. The first stage detects the presence or absence of strabismus, and the second stage classifies the type of strabismus. The first stage comprises face detection using Haar cascade, facial landmark estimation, face alignment, aligned face landmark detection, segmentation of the eye region, and detection of strabismus using VGG 16 convolution neural networks. Face alignment transforms the face to a canonical pose to ensure consistency in subsequent analysis. Using facial landmarks, the eye region is segmented from the aligned face and fed into a VGG 16 CNN model, which has been trained to classify strabismus. The CNN determines whether strabismus is present and classifies the type of strabismus (exotropia, esotropia, and vertical deviation). If stage 1 detects strabismus, the eye region image is fed into stage 2, which starts with the estimation of pupil center coordinates using mask R-CNN deep neural networks. Then, the distance between the pupil coordinates and eye landmarks is calculated along with the angle that the pupil coordinates make with the horizontal and vertical axis. The distance and angle information is used to characterize the degree and direction of the strabismic eye misalignment. This model was tested on 100 clinically labeled images of children with (n = 50) and without (n = 50) strabismus. The True Positive Rate (TPR) and False Positive Rate (FPR) of the first stage were 94% and 6% respectively. The classification stage has produced a TPR of 94.73%, 94.44%, and 100% for esotropia, exotropia, and vertical deviations, respectively. This method also had an FPR of 5.26%, 5.55%, and 0% for esotropia, exotropia, and vertical deviation, respectively. The addition of one more feature related to the location of corneal light reflections may reduce the FPR, which was primarily due to children with pseudo-strabismus (the appearance of strabismus due to a wide nasal bridge or skin folds on the nasal side of the eyes).

Keywords: strabismus, deep neural networks, face detection, facial landmarks, face alignment, segmentation, VGG 16, mask R-CNN, pupil coordinates, angle deviation, horizontal and vertical deviation

Procedia PDF Downloads 59

Authors: Chimey Lhamo, Ngawang Tsering

Abstract:

Traditional Tibetan medicine, known as Sowa Rigpa (Science of healing), originated more than 2500 years ago with an insightful background, and it has been growing significant attention in many Asian countries like China, India, Bhutan, and Nepal. Particularly, the Indian government has targeted Traditional Tibetan medicine as its major Indian medical system, including Ayurveda. Although Traditional Tibetan medicine has been growing interest and has a long history, it is not easily recognized worldwide because it exists only in the Tibetan language and it is neither accessible nor understood by patent examiners at the international patent office, data about Traditional Tibetan medicine is not yet broadly exist in the Internet. There has also been the exploitation of traditional Tibetan medicine increasing. The Traditional Knowledge Digital Library is a database aiming to prevent the patenting and misappropriation of India’s traditional medicine knowledge by using India’s Traditional knowledge Digital Library on Sowa Rigpa in order to prevent its exploitation at international patent with the help of information technology tools and an innovative classification systems-traditional knowledge resource classification (TKRC). As of date, more than 3000 Sowa Rigpa formulations have been transcribed into a Traditional Knowledge Digital Library database. In this paper, we are presenting India's Traditional Knowledge Digital Library for Traditional Tibetan medicine, and this database system helps to preserve and prevent the exploitation of Sowa Rigpa. Gradually it will be approved and accepted globally.

Keywords: traditional Tibetan medicine, India's traditional knowledge digital library, traditional knowledge resources classification, international patent classification

Procedia PDF Downloads 108

Authors: Kuei-Ling Sun, Emily Chia-Yu Su

Abstract:

Allergy is a hypersensitive overreaction of the immune system to environmental stimuli, and a major health problem. These overreactions include rashes, sneezing, fever, food allergies, anaphylaxis, asthmatic, shock, or other abnormal conditions. Allergies can be caused by food, insect stings, pollen, animal wool, and other allergens. Their development of allergies is due to both genetic and environmental factors. Allergies involve immunoglobulin E antibodies, a part of the body’s immune system. Immunoglobulin E antibodies will bind to an allergen and then transfer to a receptor on mast cells or basophils triggering the release of inflammatory chemicals such as histamine. Based on the increasingly serious problem of environmental change, changes in lifestyle, air pollution problem, and other factors, in this study, we both collect allergens and non-allergens from several databases and use several machine learning methods for classification, including logistic regression (LR), stepwise regression, decision tree (DT) and neural networks (NN) to do the model comparison and determine the permutations of allergen amino acid’s sequence.

Keywords: allergy, classification, decision tree, logistic regression, machine learning

Procedia PDF Downloads 278

Authors: Zahow Muoftah

Abstract:

Traditional manual visual grading of fruits has been one of the agricultural industry’s major challenges due to its laborious nature as well as inconsistency in the inspection and classification process. The main requirements for computer vision and visual processing are some effective techniques for identifying defects and estimating defect areas. Automated defect detection using computer vision and machine learning has emerged as a promising area of research with a high and direct impact on the visual inspection domain. Grading, sorting, and disease detection are important factors in determining the quality of fruits after harvest. Many studies have used computer vision to evaluate the quality level of fruits during post-harvest. Many studies have used computer vision to evaluate the quality level of fruits during post-harvest. Many studies have been conducted to identify diseases and pests that affect the fruits of agricultural crops. However, most previous studies concentrated solely on the diagnosis of a lesion or disease. This study focused on a comprehensive study to identify pests and diseases of apple and banana fruits using detection and classification defects on Banana and Apples by Computer Vision. As a result, the current article includes research from these domains as well. Finally, various pattern recognition techniques for detecting apple and banana defects are discussed.

Keywords: computer vision, banana, apple, detection, classification

Procedia PDF Downloads 77

Authors: Nassima Noufail, Sara Bouhali

Abstract:

In this work, we develop a semi-supervised solution for the purpose of action detection in videos and propose an efficient algorithm for video segmentation. The approach is divided into video segmentation, feature extraction, and classification. In the first part, a video is segmented into clips, and we used the K-means algorithm for this segmentation; our goal is to find groups based on similarity in the video. The application of k-means clustering into all the frames is time-consuming; therefore, we started by the identification of transition frames where the scene in the video changes significantly, and then we applied K-means clustering into these transition frames. We used two image filters, the gaussian filter and the Laplacian of Gaussian. Each filter extracts a set of features from the frames. The Gaussian filter blurs the image and omits the higher frequencies, and the Laplacian of gaussian detects regions of rapid intensity changes; we then used this vector of filter responses as an input to our k-means algorithm. The output is a set of cluster centers. Each video frame pixel is then mapped to the nearest cluster center and painted with a corresponding color to form a visual map. The resulting visual map had similar pixels grouped. We then computed a cluster score indicating how clusters are near each other and plotted a signal representing frame number vs. clustering score. Our hypothesis was that the evolution of the signal would not change if semantically related events were happening in the scene. We marked the breakpoints at which the root mean square level of the signal changes significantly, and each breakpoint is an indication of the beginning of a new video segment. In the second part, for each segment from part 1, we randomly selected a 16-frame clip, then we extracted spatiotemporal features using convolutional 3D network C3D for every 16 frames using a pre-trained model. The C3D final output is a 512-feature vector dimension; hence we used principal component analysis (PCA) for dimensionality reduction. The final part is the classification. The C3D feature vectors are used as input to a multi-class linear support vector machine (SVM) for the training model, and we used a multi-classifier to detect the action. We evaluated our experiment on the UCF101 dataset, which consists of 101 human action categories, and we achieved an accuracy that outperforms the state of art by 1.2%.

Keywords: video segmentation, action detection, classification, Kmeans, C3D

Procedia PDF Downloads 51

Authors: Amine Ben Slama, Aymen Mouelhi, Sondes Manoubi, Chiraz Mbarek, Hedi Trabelsi, Mounir Sayadi, Farhat Fnaiech

Abstract:

Vertigo is a sensation of feeling off balance; the cause of this symptom is very difficult to interpret and needs a complementary exam. Generally, vertigo is caused by an ear problem. Some of the most common causes include: benign paroxysmal positional vertigo (BPPV), Meniere's disease and vestibular neuritis (VN). In clinical practice, different tests of videonystagmographic (VNG) technique are used to detect the presence of vestibular neuritis (VN). The topographical diagnosis of this disease presents a large diversity in its characteristics that confirm a mixture of problems for usual etiological analysis methods. In this study, a vestibular neuritis analysis method is proposed with videonystagmography (VNG) applications using an estimation of pupil movements in the case of an uncontrolled motion to obtain an efficient and reliable diagnosis results. First, an estimation of the pupil displacement vectors using with Hough Transform (HT) is performed to approximate the location of pupil region. Then, temporal and frequency features are computed from the rotation angle variation of the pupil motion. Finally, optimized features are selected using Fisher criterion evaluation for discrimination and classification of the VN disease.Experimental results are analyzed using two categories: normal and pathologic. By classifying the reduced features using the Support Vector Machine (SVM), 94% is achieved as classification accuracy. Compared to recent studies, the proposed expert system is extremely helpful and highly effective to resolve the problem of VNG analysis and provide an accurate diagnostic for medical devices.

Keywords: nystagmus, vestibular neuritis, videonystagmographic system, VNG, Fisher criterion, support vector machine, SVM

Procedia PDF Downloads 121

Authors: Shahrzad Zolfagharnassab, Abdul Rashid Mohamed Shariff, Reza Ehsani, Hawa Ze Jaffar, Ishak Aris

Abstract:

Ripeness estimation of oil palm fresh fruit is important processes that affect the profitableness and salability of oil palm fruits. The adulthood or ripeness of the oil palm fruits influences the quality of oil palm. Conventional procedure includes physical grading of Fresh Fruit Bunches (FFB) maturity by calculating the number of loose fruits per bunch. This physical classification of oil palm FFB is costly, time consuming and the results may have human error. Hence, many researchers try to develop the methods for ascertaining the maturity of oil palm fruits and thereby, deviously the oil content of distinct palm fruits without the need for exhausting oil extraction and analysis. This research investigates the potential of infrared images (Thermal Images) as a predictor to classify the oil palm FFB ripeness. A total of 270 oil palm fresh fruit bunches from most common cultivar of oil palm bunches Nigresens according to three maturity categories: under ripe, ripe and over ripe were collected. Each sample was scanned by the thermal imaging cameras FLIR E60 and FLIR T440. The average temperature of each bunches were calculated by using image processing in FLIR Tools and FLIR ThermaCAM researcher pro 2.10 environment software. The results show that temperature content decreased from immature to over mature oil palm FFBs. An overall analysis-of-variance (ANOVA) test was proved that this predictor gave significant difference between underripe, ripe and overripe maturity categories. This shows that the temperature as predictors can be good indicators to classify oil palm FFB. Classification analysis was performed by using the temperature of the FFB as predictors through Linear Discriminant Analysis (LDA), Mahalanobis Discriminant Analysis (MDA), Artificial Neural Network (ANN) and K- Nearest Neighbor (KNN) methods. The highest overall classification accuracy was 88.2% by using Artificial Neural Network. This research proves that thermal imaging and neural network method can be used as predictors of oil palm maturity classification.

Keywords: artificial neural network, maturity classification, oil palm FFB, thermal imaging

Procedia PDF Downloads 326

Authors: S. M. Azad, H. Ghodsi Pour, F. Roshannafasa

Abstract:

In recent years ‘technology management and policymaking’ is one of the most important problems in management science. In this field, different generations of innovation and technology management are presented which the earliest one is Innovation System (IS) approach. In a general classification, innovation systems are divided in to 4 approaches: Technical, sectoral, regional, and national. There are many researches in relation to each of these approaches in different academic fields. Every approach has some benefits. If two or more approaches hybrid, their benefits would be combined. In addition, according to the sectoral structure of the governance model in Iran, in many sectors such as information technology, the combination of three other approaches with sectoral approach is essential. Hence, in this paper, combining two IS approaches (technical and sectoral) and using system dynamics, a generic model is presented for a sample of software industry. As a complimentary point, this article is introducing a new hybrid approach called Techno-Sectoral Innovation System. This TSIS model is accomplished by Changing concepts of the ‘functions’ which came from Technological IS literature and using them into sectoral system as measurable indicators.

Keywords: innovation system, technology, techno-sectoral system, functional indicators, system dynamics

Procedia PDF Downloads 415

Authors: Misrak Assefa

Abstract:

The Amharic language is the second most widely spoken Semitic language in the world. There are several new overloaded on the web. Searching some useful documents from the web on a specific topic, which is written in the Amharic language, is a challenging task. Hence, document categorization is required for managing and filtering important information. In the classification of Amharic text news, there is still a gap in the domain of information that needs to be launch. This study attempts to design an automatic Amharic news classification using a supervised learning mechanism on four un-touch classes. To achieve this research, 4,182 news articles were used. Naive Bayes (NB) and Decision tree (j48) algorithms were used to classify the given Amharic dataset. In this paper, k-fold cross-validation is used to estimate the accuracy of the classifier. As a result, it shows those algorithms can be applicable in Amharic news categorization. The best average accuracy result is achieved by j48 decision tree and naïve Bayes is 95.2345 %, and 94.6245 % respectively using three categories. This research indicated that a typical decision tree algorithm is more applicable to Amharic news categorization.

Keywords: text categorization, supervised machine learning, naive Bayes, decision tree

Procedia PDF Downloads 166

Authors: Syed Romat Ali Shah, Bilal Shoaib, Saleem Akhtar, Munib Ahmad, Shahan Sadiqui

Abstract:

Classification is a data mining technique, which is recognizedon Machine Learning (ML) algorithm. It is used to classifythe individual articlein a knownofinformation into a set of predefinemodules or group. Web mining is also a portion of that sympathetic of data mining methods. The main purpose of this paper to analysis and compare the performance of Naïve Bayse Algorithm, Decision Tree, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN)and Support Vector Machine (SVM). This paper consists of different ML algorithm and their advantages and disadvantages and also define research issues.

Keywords: Data Mining, Web Mining, classification, ML Algorithms

Procedia PDF Downloads 262

Authors: Tsega Asresa Mengistu, Getahun Tigistu

Abstract:

Computer vision is an artificial intelligence subfield that allows computers and systems to retrieve meaning from digital images. It is applied in various fields of study self-driving cars, video surveillance, agriculture, Quality control, Health care, construction, military, and everyday life. Aromatic and medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, and other natural health products for therapeutic and Aromatic culinary purposes. Herbal industries depend on these special plants. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs, and going to export not only industrial raw materials but also valuable foreign exchange. There is a lack of technologies for the classification and identification of Aromatic and medicinal plants in Ethiopia. The manual identification system of plants is a tedious, time-consuming, labor, and lengthy process. For farmers, industry personnel, academics, and pharmacists, it is still difficult to identify parts and usage of plants before ingredient extraction. In order to solve this problem, the researcher uses a deep learning approach for the efficient identification of aromatic and medicinal plants by using a convolutional neural network. The objective of the proposed study is to identify the aromatic and medicinal plant Parts and usages using computer vision technology. Therefore, this research initiated a model for the automatic classification of aromatic and medicinal plants by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides the root, flower and fruit, latex, and barks. The study was conducted on aromatic and medicinal plants available in the Ethiopian Institute of Agricultural Research center. An experimental research design is proposed for this study. This is conducted in Convolutional neural networks and Transfer learning. The Researcher employs sigmoid Activation as the last layer and Rectifier liner unit in the hidden layers. Finally, the researcher got a classification accuracy of 66.4 in convolutional neural networks and 67.3 in mobile networks, and 64 in the Visual Geometry Group.

Keywords: aromatic and medicinal plants, computer vision, deep convolutional neural network

Procedia PDF Downloads 394

Authors: Andrey V. Timofeev, Dmitry V. Egorov

Abstract:

This paper introduces an original method of parametric optimization of the structure for multimodal decision-level fusion scheme which combines the results of the partial solution of the classification task obtained from assembly of the mono-modal classifiers. As a result, a multimodal fusion classifier which has the minimum value of the total error rate has been obtained.

Keywords: classification accuracy, fusion solution, total error rate, multimodal fusion classifier

Procedia PDF Downloads 440

Authors: Hammad T. Janjuhah, Josep Sanjuan, Mohamed K. Salah

Abstract:

Biological and chemical activities in carbonates are responsible for the complexity of the pore system. Primary porosity is generally of natural origin while secondary porosity is subject to chemical reactivity through diagenetic processes. To understand the integrated part of hydrocarbon exploration, it is necessary to understand the carbonate pore system. However, the current porosity classification scheme is limited to adequately predict the petrophysical properties of different reservoirs having various origins and depositional environments. Rock classification provides a descriptive method for explaining the lithofacies but makes no significant contribution to the application of porosity and permeability (poro-perm) correlation. The Central Luconia carbonate system (Malaysia) represents a good example of pore complexity (in terms of nature and origin) mainly related to diagenetic processes which have altered the original reservoir. For quantitative analysis, 32 high-resolution images of each thin section were taken using transmitted light microscopy. The quantification of grains, matrix, cement, and macroporosity (pore types) was achieved using a petrographic analysis of thin sections and FESEM images. The point counting technique was used to estimate the amount of macroporosity from thin section, which was then subtracted from the total porosity to derive the microporosity. The quantitative observation of thin sections revealed that the mouldic porosity (macroporosity) is the dominant porosity type present, whereas the microporosity seems to correspond to a sum of 40 to 50% of the total porosity. It has been proven that these Miocene carbonates contain a significant amount of microporosity, which significantly complicates the estimation and production of hydrocarbons. Neglecting its impact can increase uncertainty about estimating hydrocarbon reserves. Due to the diversity of geological parameters, the application of existing porosity classifications does not allow a better understanding of the poro-perm relationship. However, the classification can be improved by including the pore types and pore structures where they can be divided into macro- and microporosity. Such studies of microporosity identification/classification represent now a major concern in limestone reservoirs around the world.

Keywords: overview of porosity classification, reservoir characterization, microporosity, carbonate reservoir

Procedia PDF Downloads 125

Authors: Mohamed Alimoussa, Alice Porebski, Nicolas Vandenbroucke, Rachid Oulad Haj Thami, Sana El Fkihi

Abstract:

Color and texture are highly discriminant visual cues that provide an essential information in many types of images. Color texture representation and classification is therefore one of the most challenging problems in computer vision and image processing applications. Color textures can be represented in different color spaces by using multiple image descriptors which generate a high dimensional set of texture features. In order to reduce the dimensionality of the feature set, feature selection techniques can be used. The goal of feature selection is to find a relevant subset from an original feature space that can improve the accuracy and efficiency of a classification algorithm. Traditionally, feature selection is focused on removing irrelevant features, neglecting the possible redundancy between relevant ones. This is why some feature selection approaches prefer to use feature clustering analysis to aid and guide the search. These techniques can be divided into two categories. i) Feature clustering-based ranking algorithm uses feature clustering as an analysis that comes before feature ranking. Indeed, after dividing the feature set into groups, these approaches perform a feature ranking in order to select the most discriminant feature of each group. ii) Feature clustering-based subset search algorithms can use feature clustering following one of three strategies; as an initial step that comes before the search, binded and combined with the search or as the search alternative and replacement. In this paper, we propose a new feature clustering-based sequential selection approach for the purpose of color texture representation and classification. Our approach is a three step algorithm. First, irrelevant features are removed from the feature set thanks to a class-correlation measure. Then, introducing a new automatic feature clustering algorithm, the feature set is divided into several feature clusters. Finally, a sequential search algorithm, based on a filter model and a separability measure, builds a relevant and non redundant feature subset: at each step, a feature is selected and features of the same cluster are removed and thus not considered thereafter. This allows to significantly speed up the selection process since large number of redundant features are eliminated at each step. The proposed algorithm uses the clustering algorithm binded and combined with the search. Experiments using a combination of two well known texture descriptors, namely Haralick features extracted from Reduced Size Chromatic Co-occurence Matrices (RSCCMs) and features extracted from Local Binary patterns (LBP) image histograms, on five color texture data sets, Outex, NewBarktex, Parquet, Stex and USPtex demonstrate the efficiency of our method compared to seven of the state of the art methods in terms of accuracy and computation time.

Keywords: feature selection, color texture classification, feature clustering, color LBP, chromatic cooccurrence matrix

Procedia PDF Downloads 105

Authors: Hao-Hsiang Ku, Ching-Ho Chi

Abstract:

Big data applications have become an imperative for many fields. Many researchers have been devoted into increasing correct rates and reducing time complexities. Hence, the study designs and proposes an Ontology-based backpropagation neural network classification and reasoning strategy for NoSQL big data applications, which is called ON4NoSQL. ON4NoSQL is responsible for enhancing the performances of classifications in NoSQL and SQL databases to build up mass behavior models. Mass behavior models are made by MapReduce techniques and Hadoop distributed file system based on Hadoop service platform. The reference engine of ON4NoSQL is the ontology-based backpropagation neural network classification and reasoning strategy. Simulation results indicate that ON4NoSQL can efficiently achieve to construct a high performance environment for data storing, searching, and retrieving.

Keywords: Hadoop, NoSQL, ontology, back propagation neural network, high distributed file system

Procedia PDF Downloads 238

Authors: Nguyen J. M., Lucas G., Ruan S., Digonnet H., Antonioli D.

Abstract:

Introduction: Deep Learning (DL) is a very powerful tool for analyzing image data. But for tabular data, it cannot compete with machine learning methods like XGBoost. The research question becomes: can tabular data be transformed into images that can be analyzed by simple CNNs (Convolutional Neuron Networks)? Will DL be the absolute tool for data classification? All current solutions consist in repositioning the variables in a 2x2 matrix using their correlation proximity. In doing so, it obtains an image whose pixels are the variables. We implement a technology, DeepNIC, that offers the possibility of obtaining an image for each variable, which can be analyzed by simple CNNs. Material and method: The 'ROP' (Regression OPtimized) model is a binary and atypical decision tree whose nodes are managed by a new artificial neuron, the Neurop. By positioning an artificial neuron in each node of the decision trees, it is possible to make an adjustment on a theoretically infinite number of variables at each node. From this new decision tree whose nodes are artificial neurons, we created the concept of a 'Random Forest of Perfect Trees' (RFPT), which disobeys Breiman's concepts by assembling very large numbers of small trees with no classification errors. From the results of the RFPT, we developed a family of 10 statistical information criteria, Nguyen Information Criterion (NICs), which evaluates in 3 dimensions the predictive quality of a variable: Performance, Complexity and Multiplicity of solution. A NIC is a probability that can be transformed into a grey level. The value of a NIC depends essentially on 2 super parameters used in Neurops. By varying these 2 super parameters, we obtain a 2x2 matrix of probabilities for each NIC. We can combine these 10 NICs with the functions AND, OR, and XOR. The total number of combinations is greater than 100,000. In total, we obtain for each variable an image of at least 1166x1167 pixels. The intensity of the pixels is proportional to the probability of the associated NIC. The color depends on the associated NIC. This image actually contains considerable information about the ability of the variable to make the prediction of Y, depending on the presence or absence of other variables. A basic CNNs model was trained for supervised classification. Results: The first results are impressive. Using the GSE22513 public data (Omic data set of markers of Taxane Sensitivity in Breast Cancer), DEEPNic outperformed other statistical methods, including XGBoost. We still need to generalize the comparison on several databases. Conclusion: The ability to transform any tabular variable into an image offers the possibility of merging image and tabular information in the same format. This opens up great perspectives in the analysis of metadata.

Keywords: tabular data, CNNs, NICs, DeepNICs, random forest of perfect trees, classification

Procedia PDF Downloads 84

Authors: Farina Riaz, Shahab Abdulla, Srinjoy Ganguly, Hajime Suzuki, Ravinesh C. Deo, Susan Hopkins

Abstract:

Recently, quantum machine learning has received significant attention. For various types of data, including text and images, numerous quantum machine learning (QML) models have been created and are being tested. Images are exceedingly complex data components that demand more processing power. Despite being mature, classical machine learning still has difficulties with big data applications. Furthermore, quantum technology has revolutionized how machine learning is thought of, by employing quantum features to address optimization issues. Since quantum hardware is currently extremely noisy, it is not practicable to run machine learning algorithms on it without risking the production of inaccurate results. To discover the advantages of quantum versus classical approaches, this research has concentrated on colored image data. Deep learning classification models are currently being created on Quantum platforms, but they are still in a very early stage. Black and white benchmark image datasets like MNIST and Fashion MINIST have been used in recent research. MNIST and CIFAR-10 were compared for binary classification, but the comparison showed that MNIST performed more accurately than colored CIFAR-10. This research will evaluate the performance of the QML algorithm on the colored benchmark dataset CIFAR-10 to advance QML's real-time applicability. However, deep learning classification models have not been developed to compare colored images like Quantum Convolutional Neural Network (QCNN) to determine how much it is better to classical. Only a few models, such as quantum variational circuits, take colored images. The methodology adopted in this research is a hybrid approach by using penny lane as a simulator. To process the 10 classes of CIFAR-10, the image data has been translated into grey scale and the 28 × 28-pixel image containing 10,000 test and 50,000 training images were used. The objective of this work is to determine how much the quantum approach can outperform a classical approach for a comprehensive dataset of color images. After pre-processing 50,000 images from a classical computer, the QCNN model adopted a hybrid method and encoded the images into a quantum simulator for feature extraction using quantum gate rotations. The measurements were carried out on the classical computer after the rotations were applied. According to the results, we note that the QCNN approach is ~12% more effective than the traditional classical CNN approaches and it is possible that applying data augmentation may increase the accuracy. This study has demonstrated that quantum machine and deep learning models can be relatively superior to the classical machine learning approaches in terms of their processing speed and accuracy when used to perform classification on colored classes.

Keywords: CIFAR-10, quantum convolutional neural networks, quantum deep learning, quantum machine learning

Procedia PDF Downloads 97