Search results for: classifiers accuracy

Authors: Ratun Rahman, Rafid Islam, Akin Ahmed, Kamrul Hasan, Hasan Mahmud

Abstract:

Malware is becoming more prevalent, and several threat categories have risen dramatically in recent years. This paper provides a bird's-eye view of the world of malware analysis. The efficiency of five different machine learning methods (Naive Bayes, K-Nearest Neighbor, Decision Tree, Random Forest, and TensorFlow Decision Forest) combined with features picked from the retrieval of Android permissions to categorize applications as harmful or benign is investigated in this study. The test set consists of 1,168 samples (among these android applications, 602 are malware and 566 are benign applications), each consisting of 948 features (permissions). Using the permission-based dataset, the machine learning algorithms then produce accuracy rates above 80%, except the Naive Bayes Algorithm with 65% accuracy. Of the considered algorithms TensorFlow Decision Forest performed the best with an accuracy of 90%.

Keywords: android malware detection, machine learning, malware, malware analysis

Procedia PDF Downloads 170

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 122

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 95

Authors: Yan Cheng, Yijun Shao, James Rudolph, Charlene R. Weir, Beth Sahlmann, Qing Zeng-Treitler

Abstract:

Supervised predictive models require labeled data for training purposes. Complete and accurate labeled data, i.e., a ‘gold standard’, is not always available, and imperfectly labeled data may need to serve as an alternative. An important question is if the accuracy of the labeled data creates a performance ceiling for the trained model. In this study, we trained several models to recognize the presence of delirium in clinical documents using data with annotations that are not completely accurate (i.e., weakly-supervised learning). In the external evaluation, the support vector machine model with a linear kernel performed best, achieving an area under the curve of 89.3% and accuracy of 88%, surpassing the 80% accuracy of the training sample. We then generated a set of simulated data and carried out a series of experiments which demonstrated that models trained on imperfect data can (but do not always) outperform the accuracy of the training data, e.g., the area under the curve for some models is higher than 80% when trained on the data with an error rate of 40%. Our experiments also showed that the error resistance of linear modeling is associated with larger sample size, error type, and linearity of the data (all p-values < 0.001). In conclusion, this study sheds light on the usefulness of imperfect data in clinical research via weakly-supervised learning.

Keywords: weakly-supervised learning, support vector machine, prediction, delirium, simulation

Procedia PDF Downloads 200

Authors: Meenal Badki

Abstract:

We address the issue of active feature determination, where the objective is to determine the set of examples on which additional data (such as lab tests) needs to be gathered, given a large number of examples with some features (such as demographics) and some examples with all the features (such as the complete Electronic Health Record). We note that certain features may be more costly, unique, or laborious to gather. Our proposal is a general active learning approach that is independent of classifiers and similarity metrics. It allows us to identify examples that differ from the full data set and obtain all the features for the examples that match. Our comprehensive evaluation shows the efficacy of this approach, which is driven by four authentic clinical tasks.

Keywords: feature determination, classification, active learning, sample-efficiency

Procedia PDF Downloads 77

Authors: Hooriya Sadr Dadras, Shiva Seyed Erfani

Abstract:

Speaking skills merit meticulous attention both on the side of the learners and the teachers. In particular, accuracy is a critical component to guarantee the messages to be conveyed through conversation because a wrongful change may adversely alter the content and purpose of the talk. Different types of tasks have served teachers to meet numerous educational objectives. Besides, negotiation of meaning and the use of different strategies have been areas of concern in socio-cultural theories of SLA. Negotiation of meaning is among the conversational processes which have a crucial role in facilitating the understanding and expression of meaning in a given second language. Conversational strategies are used during interaction when there is a breakdown in communication that leads to the interlocutor attempting to remedy the gap through talk. Therefore, this study was an attempt to investigate if there was any significant difference between the effect of reasoning gap tasks and information gap tasks on the frequency of conversational strategies used in negotiation of meaning in classrooms on one hand, and on the accuracy in speaking of Iranian intermediate EFL learners on the other. After a pilot study to check the practicality of the treatments, at the outset of the main study, the Preliminary English Test was administered to ensure the homogeneity of 87 out of 107 participants who attended the intact classes of a 15 session term in one control and two experimental groups. Also, speaking sections of PET were used as pretest and posttest to examine their speaking accuracy. The tests were recorded and transcribed to estimate the percentage of the number of the clauses with no grammatical errors in the total produced clauses to measure the speaking accuracy. In all groups, the grammatical points of accuracy were instructed and the use of conversational strategies was practiced. Then, different kinds of reasoning gap tasks (matchmaking, deciding on the course of action, and working out a time table) and information gap tasks (restoring an incomplete chart, spot the differences, arranging sentences into stories, and guessing game) were manipulated in experimental groups during treatment sessions, and the students were required to practice conversational strategies when doing speaking tasks. The conversations throughout the terms were recorded and transcribed to count the frequency of the conversational strategies used in all groups. The results of statistical analysis demonstrated that applying both the reasoning gap tasks and information gap tasks significantly affected the frequency of conversational strategies through negotiation. In the face of the improvements, the reasoning gap tasks had a more significant impact on encouraging the negotiation of meaning and increasing the number of conversational frequencies every session. The findings also indicated both task types could help learners significantly improve their speaking accuracy. Here, applying the reasoning gap tasks was more effective than the information gap tasks in improving the level of learners’ speaking accuracy.

Keywords: accuracy in speaking, conversational strategies, information gap tasks, reasoning gap tasks

Procedia PDF Downloads 309

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: classification, CNN, deep learning, prediction, SNR

Procedia PDF Downloads 134

Authors: Matthew Buns

Abstract:

Training specificity is imperative for successful performance of the elite athlete. Virtual reality (VR) has been successfully applied to a broad range of training domains. However, to date there is little research investigating the use of VR for sport training. The purpose of this study was to address the question of whether virtual reality (VR) training can improve real world hockey shooting performance. Twenty four volunteers were recruited and randomly selected to complete the virtual training intervention or enter a control group with no training. Four primary types of data were collected: 1) participant’s experience with video games and hockey, 2) participant’s motivation toward video game use, 3) participants technical performance on real-world hockey, and 4) participant’s technical performance in virtual hockey. One-way multivariate analysis of variance (ANOVA) indicated that that the intervention group demonstrated significantly more real-world hockey accuracy [F(1,24) =15.43, p <.01, E.S. = 0.56] while shooting on goal than their control group counterparts [intervention M accuracy = 54.17%, SD=12.38, control M accuracy = 46.76%, SD=13.45]. One-way multivariate analysis of variance (MANOVA) repeated measures indicated significantly higher outcome scores on real-world accuracy (35.42% versus 54.17%; ES = 1.52) and velocity (51.10 mph versus 65.50 mph; ES=0.86) of hockey shooting on goal. This research supports the idea that virtual training is an effective tool for increasing real-world hockey skill.

Keywords: virtual training, hockey skills, video game, esports

Procedia PDF Downloads 147

Authors: Shahabeddin Sotudian, M. H. Fazel Zarandi, I. B. Turksen

Abstract:

Hepatitis is one of the most common and dangerous diseases that affects humankind, and exposes millions of people to serious health risks every year. Diagnosis of Hepatitis has always been a challenge for physicians. This paper presents an effective method for diagnosis of hepatitis based on interval Type-II fuzzy. This proposed system includes three steps: pre-processing (feature selection), Type-I and Type-II fuzzy classification, and system evaluation. KNN-FD feature selection is used as the preprocessing step in order to exclude irrelevant features and to improve classification performance and efficiency in generating the classification model. In the fuzzy classification step, an “indirect approach” is used for fuzzy system modeling by implementing the exponential compactness and separation index for determining the number of rules in the fuzzy clustering approach. Therefore, we first proposed a Type-I fuzzy system that had an accuracy of approximately 90.9%. In the proposed system, the process of diagnosis faces vagueness and uncertainty in the final decision. Thus, the imprecise knowledge was managed by using interval Type-II fuzzy logic. The results that were obtained show that interval Type-II fuzzy has the ability to diagnose hepatitis with an average accuracy of 93.94%. The classification accuracy obtained is the highest one reached thus far. The aforementioned rate of accuracy demonstrates that the Type-II fuzzy system has a better performance in comparison to Type-I and indicates a higher capability of Type-II fuzzy system for modeling uncertainty.

Keywords: hepatitis disease, medical diagnosis, type-I fuzzy logic, type-II fuzzy logic, feature selection

Procedia PDF Downloads 307

Authors: V. Rashtchi, H. Bizhani, F. R. Tatari

Abstract:

This paper presents a new online loss minimization for an induction motor drive. Among the many loss minimization algorithms (LMAs) for an induction motor, a particle swarm optimization (PSO) has the advantages of fast response and high accuracy. However, the performance of the PSO and other optimization algorithms depend on the accuracy of the modeling of the motor drive and losses. In the development of the loss model, there is always a trade off between accuracy and complexity. This paper presents a new online optimization to determine an optimum flux level for the efficiency optimization of the vector-controlled induction motor drive. An induction motor (IM) model in d-q coordinates is referenced to the rotor magnetizing current. This transformation results in no leakage inductance on the rotor side, thus the decomposition into d-q components in the steady-state motor model can be utilized in deriving the motor loss model. The suggested algorithm is simple for implementation.

Keywords: induction machine, loss minimization, magnetizing current, particle swarm optimization

Procedia PDF Downloads 634

Authors: Kumar Kanudkuri, A. Sandhya

Abstract:

Typically, in a MRI clinical setting, there are several protocols run, each indicated for a specific anatomy and disease condition. However, these protocols or parameters within them can change over time due to changes to the recommendations by the physician groups or updates in the software or by the availability of new technologies. Most of the time, the changes are performed by the MRI technologist to account for either time, coverage, physiological, or Specific Absorbtion Rate (SAR ) reasons. However, giving properly guidelines to MRI technologist is important so that they do not change the parameters that negatively impact the image quality. Typically a standard American College of Radiology (ACR) MRI phantom is used for Quality Control (QC) in order to guarantee that the primary objectives of MRI are met. The visual evaluation of quality depends on the operator/reviewer and might change amongst operators as well as for the same operator at various times. Therefore, overcoming these constraints is essential for a more impartial evaluation of quality. This makes quantitative estimation of image quality (IQ) metrics for MRI quality control is very important. So in order to solve this problem, we proposed that there is a need for a robust, open-source, and automated MRI image control tool. The Designed and developed an automatic analysis tool for measuring MRI image quality (IQ) metrics like Signal to Noise Ratio (SNR), Signal to Noise Ratio Uniformity (SNRU), Visual Information Fidelity (VIF), Feature Similarity (FSIM), Gray level co-occurrence matrix (GLCM), slice thickness accuracy, slice position accuracy, High contrast spatial resolution) provided good accuracy assessment. A standardized quality report has generated that incorporates metrics that impact diagnostic quality.

Keywords: ACR MRI phantom, MRI image quality metrics, SNRU, VIF, FSIM, GLCM, slice thickness accuracy, slice position accuracy

Procedia PDF Downloads 173

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 118

Authors: Gurukiran Veerapur, Nytik Birudavolu, Seetharam U. N., Chandravva Hebbi, R. Praneeth Reddy

Abstract:

This work presents a robust approach for the recognition of characters in Telugu and Kannada, two South Indian scripts with structural similarities in characters. To recognize the characters exhaustive datasets are required, but there are only a few publicly available datasets. As a result, we decided to create a dataset for one language (source language),train the model with it, and then test it with the target language.Telugu is the target language in this work, whereas Kannada is the source language. The suggested method makes use of Canny edge features to increase character identification accuracy on pictures with noise and different lighting. A dataset of 45,150 images containing printed Kannada characters was created. The Nudi software was used to automatically generate printed Kannada characters with different writing styles and variations. Manual labelling was employed to ensure the accuracy of the character labels. The deep learning models like CNN (Convolutional Neural Network) and Visual Attention neural network (VAN) are used to experiment with the dataset. A Visual Attention neural network (VAN) architecture was adopted, incorporating additional channels for Canny edge features as the results obtained were good with this approach. The model's accuracy on the combined Telugu and Kannada test dataset was an outstanding 97.3%. Performance was better with Canny edge characteristics applied than with a model that solely used the original grayscale images. The accuracy of the model was found to be 80.11% for Telugu characters and 98.01% for Kannada words when it was tested with these languages. This model, which makes use of cutting-edge machine learning techniques, shows excellent accuracy when identifying and categorizing characters from these scripts.

Keywords: base characters, modifiers, guninthalu, aksharas, vattakshara, VAN

Procedia PDF Downloads 53

Authors: Sophie Mills, Leila L. Touil, Richard Sisson

Abstract:

Introduction: The TNM classification is the global standard for the staging of head and neck cancers. Accurate clinical-radiological staging of tumours (cTNM) is essential to predict prognosis, facilitate surgical planning and determine the need for other therapeutic modalities. This study aims to determine the accuracy of pre-operative cTNM staging using pathological TNM (pTNM) and consider possible causes of TNM stage migration, noting any variation throughout the COVID-19 pandemic. Materials and Methods: A retrospective cohort study examined records of patients with surgical management of head and neck cancer at a tertiary head and neck centre from November 2019 to November 2020. Data was extracted from Somerset Cancer Registry and histopathology reports. cTNM and pTNM were compared before and during the first wave of COVID-19, as well as with other potential prognostic factors such as tumour site and tumour stage. Results: 119 cases were identified, of which 52.1% (n=62) were male, and 47.9% (n=57) were female with a mean age of 67 years. Clinical and pathological staging differed in 54.6% (n=65) of cases. Of the patients with stage migration, 40.4% (n=23) were up-staged and 59.6% (n=34) were down-staged compared with pTNM. There was no significant difference in the accuracy of cTNM staging compared with age, sex, or tumour site. There was a statistically highly significant (p < 0.001) correlation between cTNM accuracy and tumour stage, with the accuracy of cTNM staging decreasing with the advancement of pTNM staging. No statistically significant variation was noted between patients staged prior to and during COVID-19. Conclusions: Discrepancies in staging can impact management and outcomes for patients. This study found that the higher the pTNM, the more likely stage migration will occur. These findings are concordant with the oncology literature, which highlights the need to improve the accuracy of cTNM staging for more advanced tumours.

Keywords: COVID-19, head and neck cancer, stage migration, TNM staging

Procedia PDF Downloads 109

Authors: Adel Edwar Waheeb Louka

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 74

Authors: Zuhal Kurt, Meral Kurt, Bilge T. Bal, Kemal Ozkan

Abstract:

Shade matching and reproduction is the most important element of success in prosthetic dentistry. Until recently, shade matching procedure was implemented by dentists visual perception with the help of shade guides. Since many factors influence visual perception; tooth shade matching using visual devices (shade guides) is highly subjective and inconsistent. Subjective nature of this process has lead to the development of instrumental devices. Nowadays, colorimeters, spectrophotometers, spectroradiometers and digital image analysing systems are used for instrumental shade selection. Instrumental devices have advantages that readings are quantifiable, can obtain more rapidly and simply, objectively and precisely. However, these devices have noticeable drawbacks. For example, translucent structure and irregular surfaces of teeth lead to defects on measurement with these devices. Also between the results acquired by devices with different measurement principles may make inconsistencies. So, its obligatory to search for new methods for dental shade matching process. A computer-aided system device; digital camera has developed rapidly upon today. Currently, advances in image processing and computing have resulted in the extensive use of digital cameras for color imaging. This procedure has a much cheaper process than the use of traditional contact-type color measurement devices. Digital cameras can be taken by the place of contact-type instruments for shade selection and overcome their disadvantages. Images taken from teeth show morphology and color texture of teeth. In last decades, a new method was recommended to compare the color of shade tabs taken by a digital camera using color features. This method showed that visual and computer-aided shade matching systems should be used as concatenated. Recently using methods of feature extraction techniques are based on shape description and not used color information. However, color is mostly experienced as an essential property in depicting and extracting features from objects in the world around us. When local feature descriptors with color information are extended by concatenating color descriptor with the shape descriptor, that descriptor will be effective on visual object recognition and classification task. Therefore, the color descriptor is to be used in combination with a shape descriptor it does not need to contain any spatial information, which leads us to use local histograms. This local color histogram method is remain reliable under variation of photometric changes, geometrical changes and variation of image quality. So, coloring local feature extraction methods are used to extract features, and also the Scale Invariant Feature Transform (SIFT) descriptor used to for shape description in the proposed method. After the combination of these descriptors, the state-of-art descriptor named by Color-SIFT will be used in this study. Finally, the image feature vectors obtained from quantization algorithm are fed to classifiers such as Nearest Neighbor (KNN), Naive Bayes or Support Vector Machines (SVM) to determine label(s) of the visual object category or matching. In this study, SVM are used as classifiers for color determination and shade matching. Finally, experimental results of this method will be compared with other recent studies. It is concluded from the study that the proposed method is remarkable development on computer aided tooth shade determination system.

Keywords: classifiers, color determination, computer-aided system, tooth shade matching, feature extraction

Procedia PDF Downloads 448

Authors: Navab Karimi, Tohid Alizadeh

Abstract:

An intelligent vision-based system was designed to measure the quality and purity of raisins. A machine vision setup was utilized to capture the images of bulk raisins in ranges of 5-50% mixed pure-impure berries. The textural features of bulk raisins were extracted using Grey-level Histograms, Co-occurrence Matrix, and Local Binary Pattern (a total of 108 features). Genetic Algorithm and neural network regression were used for selecting and ranking the best features (21 features). As a result, the GLCM features set was found to have the highest accuracy (92.4%) among the other sets. Followingly, multiple feature combinations of the previous stage were fed into the second regression (linear regression) to increase accuracy, wherein a combination of 16 features was found to be the optimum. Finally, a Support Vector Machine (SVM) classifier was used to differentiate the mixtures, producing the best efficiency and accuracy of 96.2% and 97.35%, respectively.

Keywords: sun-dried organic raisin, genetic algorithm, feature extraction, ann regression, linear regression, support vector machine, south azerbaijan.

Procedia PDF Downloads 73

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 126

Authors: Altilio Rosa, Chirico Francesco, Foglia Goffredo

Abstract:

In recent years, the number of Unmanned Aerial Vehicles (UAVs) has significantly increased. The rapid development of commercial and recreational drones makes them an important part of our society. Despite the growing list of their applications, these vehicles pose a huge threat to civil and military installations: detection, classification and neutralization of such flying objects become an urgent need. Radar is an effective remote sensing tool for detecting and tracking flying objects, but scenarios characterized by the presence of a high number of tracks related to flying birds make especially challenging the drone detection task: operator PPI is cluttered with a huge number of potential threats and his reaction time can be severely affected. Flying birds compared to UAVs show similar velocity, RADAR cross-section and, in general, similar characteristics. Building from the absence of a single feature that is able to distinguish UAVs and birds, this paper uses a multiple features approach where an original feature selection technique is developed to feed binary classifiers trained to distinguish birds and UAVs. RADAR tracks acquired on the field and related to different UAVs and birds performing various trajectories were used to extract specifically designed target movement-related features based on velocity, trajectory and signal strength. An optimization strategy based on a genetic algorithm is also introduced to select the optimal subset of features and to estimate the performance of several classification algorithms (Neural network, SVM, Logistic regression…) both in terms of the number of selected features and misclassification error. Results show that the proposed methods are able to reduce the dimension of the data space and to remove almost all non-drone false targets with a suitable classification accuracy (higher than 95%).

Keywords: birds, classification, machine learning, UAVs

Procedia PDF Downloads 224

Authors: Zhihao Zheng, Zhilin Wang, Linxin Liu

Abstract:

In the research of automated knowledge question-answering systems, accuracy and efficiency are critical challenges. This paper proposes a knowledge graph-enhanced Retrieval-Augmented Generation (RAG) method, combined with a Graph Neural Network (GNN) structure, to automatically determine the correctness of knowledge competition questions. First, a domain-specific knowledge graph was constructed from a large corpus of academic journal literature, with key entities and relationships extracted using Natural Language Processing (NLP) techniques. Then, the RAG method's retrieval module was expanded to simultaneously query both text databases and the knowledge graph, leveraging the GNN to further extract structured information from the knowledge graph. During answer generation, contextual information provided by the knowledge graph and GNN is incorporated to improve the accuracy and consistency of the answers. Experimental results demonstrate that the knowledge graph and GNN-enhanced RAG method perform excellently in determining the correctness of questions, achieving an accuracy rate of 95%. Particularly in cases involving ambiguity or requiring contextual information, the structured knowledge provided by the knowledge graph and GNN significantly enhances the RAG method's performance. This approach not only demonstrates significant advantages in improving the accuracy and efficiency of automated knowledge question-answering systems but also offers new directions and ideas for future research and practical applications.

Keywords: knowledge graph, graph neural network, retrieval-augmented generation, NLP

Procedia PDF Downloads 42

Authors: A. Sathiya Susuman, Hamisi F. Hamisi

Abstract:

Background: Many socio-economic and demographic data are age-sex attributed. However, a variety of irregularities and misstatement are noted with respect to age-related data and less to sex data because of its biological differences between the genders. Noting the misstatement/misreporting of age data regardless of its significance importance in demographics and epidemiological studies, this study aims at assessing the quality of 2012 Tanzania Population and Housing Census Results. Methods: Data for the analysis are downloaded from Tanzania National Bureau of Statistics. Age heaping and digit preference were measured using summary indices viz., Whipple’s index, Myers’ blended index, and Age-Sex Accuracy index. Results: The recorded Whipple’s index for both sexes was 154.43; male has the lowest index of about 152.65 while female has the highest index of about 156.07. For Myers’ blended index, the preferences were at digits ‘0’ and ‘5’ while avoidance were at digits ‘1’ and ‘3’ for both sexes. Finally, Age-sex index stood at 59.8 where sex ratio score was 5.82 and age ratio scores were 20.89 and 21.4 for males and female respectively. Conclusion: The evaluation of the 2012 PHC data using the demographic techniques has qualified the data inaccurate as the results of systematic heaping and digit preferences/avoidances. Thus, innovative methods in data collection along with measuring and minimizing errors using statistical techniques should be used to ensure accuracy of age data.

Keywords: age heaping, digit preference/avoidance, summary indices, Whipple’s index, Myer’s index, age-sex accuracy index

Procedia PDF Downloads 477

Authors: Amin AminiKhafri, James M. Dawson-Edwards, Ryan M. Simpson, Simaan M. AbouRizk

Abstract:

Earned value management (EVM) has been introduced as an integrated method to combine schedule, budget, and work breakdown structure (WBS). EVM provides various indices to demonstrate project performance including the cost performance index (CPI). CPI is also used to forecast final project cost at completion based on the cost performance during the project execution. Knowing the final project cost during execution can initiate corrective actions, which can enhance project outputs. CPI, however, is not constant during the project, and calculating the final project cost using a variable index is an inaccurate and challenging task for practitioners. Since CPI is based on the cumulative progress values and because of the learning curve effect, CPI variation dampens and stabilizes as project progress. Although various definitions for the CPI stability have been proposed in literature, many scholars have agreed upon the definition that considers a project as stable if the CPI at 20% completion varies less than 0.1 from the final CPI. While 20% completion point is recognized as the stability point for military development projects, construction projects stability have not been studied. In the current study, an empirical study was first conducted using construction project data to determine the stability point for construction projects. Early findings have demonstrated that a majority of construction projects stabilize towards completion (i.e., after 70% completion point). To investigate the effect of CPI stability on cost forecast accuracy, the correlation between CPI stability and project cost at completion forecast accuracy was also investigated. It was determined that as projects progress closer towards completion, variation of the CPI decreases and final project cost forecast accuracy increases. Most projects were found to have 90% accuracy in the final cost forecast at 70% completion point, which is inlined with findings from the CPI stability findings. It can be concluded that early stabilization of the project CPI results in more accurate cost at completion forecasts.

Keywords: cost performance index, earned value management, empirical study, final project cost

Procedia PDF Downloads 156

Authors: Riznaldi Akbar

Abstract:

In this study, we compared the performance of the Artificial Neural Network (ANN) model with back-propagation algorithm in correctly predicting in-sample and out-of-sample external debt crisis in Indonesia. We found that exchange rate, foreign reserves, and exports are the major determinants to experiencing external debt crisis. The ANN in-sample performance provides relatively superior results. The ANN model is able to classify correctly crisis of 89.12 per cent with reasonably low false alarms of 7.01 per cent. In out-of-sample, the prediction performance fairly deteriorates compared to their in-sample performances. It could be explained as the ANN model tends to over-fit the data in the in-sample, but it could not fit the out-of-sample very well. The 10-fold cross-validation has been used to improve the out-of-sample prediction accuracy. The results also offer policy implications. The out-of-sample performance could be very sensitive to the size of the samples, as it could yield a higher total misclassification error and lower prediction accuracy. The ANN model could be used to identify past crisis episodes with some accuracy, but predicting crisis outside the estimation sample is much more challenging because of the presence of uncertainty.

Keywords: debt crisis, external debt, artificial neural network, ANN

Procedia PDF Downloads 445

Authors: Fernando Maass, Pablo Martin, Jorge Olivares

Abstract:

The Bessel function J₀(x) is very important in Electrodynamics and Physics, as well as its zeros. In this work, a method to obtain high accuracy approximation is presented through an application to that function. In most of the applications of this function, the values of the zeros are very important. In this work, analytic approximations for this function have been obtained valid for all positive values of the variable x, which have high accuracy for the function as well as for the zeros. The approximation is determined by the simultaneous used of the power series and asymptotic expansion. The structure of the approximation is a combination of two rational functions with elementary functions as trigonometric and fractional powers. Here us in Pade method, rational functions are used, but now there combined with elementary functions us fractional powers hyperbolic or trigonometric functions, and others. The reason of this is that now power series of the exact function are used, but together with the asymptotic expansion, which usually includes fractional powers trigonometric functions and other type of elementary functions. The approximation must be a bridge between both expansions, and this can not be accomplished using only with rational functions. In the simplest approximation using 4 parameters the maximum absolute error is less than 0.006 at x ∼ 4.9. In this case also the maximum relative error for the zeros is less than 0.003 which is for the second zero, but that value decreases rapidly for the other zeros. The same kind of behaviour happens for the relative error of the maximum and minimum of the functions. Approximations with higher accuracy and more parameters will be also shown. All the approximations are valid for any positive value of x, and they can be calculated easily.

Keywords: analytic approximations, asymptotic approximations, Bessel functions, quasirational approximations

Procedia PDF Downloads 253

Authors: Cristian Chacha, David Asiain, Jesús Ponce de León, José Ramón Beltrán

Abstract:

This work explores and characterizes the behavior of the AFE AD5941 in impedance measurement using an embedded algorithm with a constant current AC source. The main aim of this research is to improve the exact measurement of impedance values for their application in EDA-focused wearable devices. Through comprehensive study and characterization, it has been observed that employing a measurement sequence with a constant current source produces results with increased dispersion but higher accuracy. As a result, this approach leads to a more accurate system for impedance measurement.

Keywords: EDA, constant current AC source, wearable, precision, accuracy, impedance

Procedia PDF Downloads 108

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 143

Authors: Ella Sèdé Maforikan

Abstract:

Accurate land cover mapping is essential for effective environmental monitoring and natural resources management. This study focuses on assessing the classification performance of two satellite datasets and evaluating the impact of different input feature combinations on classification accuracy in the Beterou catchment, situated in the northern part of Benin. Landsat-8 and Sentinel-2 images from June 1, 2020, to March 31, 2021, were utilized. Employing the Random Forest (RF) algorithm on Google Earth Engine (GEE), a supervised classification categorized the land into five classes: forest, savannas, cropland, settlement, and water bodies. GEE was chosen due to its high-performance computing capabilities, mitigating computational burdens associated with traditional land cover classification methods. By eliminating the need for individual satellite image downloads and providing access to an extensive archive of remote sensing data, GEE facilitated efficient model training on remote sensing data. The study achieved commendable overall accuracy (OA), ranging from 84% to 85%, even without incorporating spectral indices and terrain metrics into the model. Notably, the inclusion of additional input sources, specifically terrain features like slope and elevation, enhanced classification accuracy. The highest accuracy was achieved with Sentinel-2 (OA = 91%, Kappa = 0.88), slightly surpassing Landsat-8 (OA = 90%, Kappa = 0.87). This underscores the significance of combining diverse input sources for optimal accuracy in land cover mapping. The methodology presented herein not only enables the creation of precise, expeditious land cover maps but also demonstrates the prowess of cloud computing through GEE for large-scale land cover mapping with remarkable accuracy. The study emphasizes the synergy of different input sources to achieve superior accuracy. As a future recommendation, the application of Light Detection and Ranging (LiDAR) technology is proposed to enhance vegetation type differentiation in the Beterou catchment. Additionally, a cross-comparison between Sentinel-2 and Landsat-8 for assessing long-term land cover changes is suggested.

Keywords: land cover mapping, Google Earth Engine, random forest, Beterou catchment

Procedia PDF Downloads 63

Authors: Sebastian Oportus, Fabrizio Alvarez

Abstract:

3D digitalization of heritage objects is widely used nowadays. However, the most advanced 3D scanners in the market that capture topology and texture at the same time, and are specifically made for this purpose, don’t deliver the accuracy that is needed for scientific research. In the last three years, we have developed a method that combines the use of Metrologic grade laser scans, that allows us to work with a high accuracy topology up to 15 times more precise and combine this mesh with a texture obtained from high definition photogrammetry with up to 100 times more pixel concentrations. The result is an accurate digitalization that promotes heritage preservation, scientific study, high detail reproduction, and digital restoration, among others. In Chile, we have already performed 478 digitalizations of high-value heritage pieces and compared the results with up to five different digitalization methods; the results obtained show a considerable better dimensional accuracy and texture resolution. We know the importance of high precision and resolution for academics and museology; that’s why our proposal is to set a worldwide standard using this open source methodology.

Keywords: 3D digitalization, digital heritage, heritage preservation, digital restauration, heritage reproduction

Procedia PDF Downloads 189

Authors: Aisulu Tileukulova, Zhexebay Dauren

Abstract:

Radar plays an important role because it is widely used in civil and military fields. Target detection is one of the most important radar applications. The accuracy of detecting inconspicuous aerial objects in radar facilities is lower against the background of noise. Convolutional neural networks can be used to improve the recognition of this type of aerial object. The purpose of this work is to develop an algorithm for recognizing aerial objects using convolutional neural networks, as well as training a neural network. In this paper, the structure of a convolutional neural network (CNN) consists of different types of layers: 8 convolutional layers and 3 layers of a fully connected perceptron. ReLU is used as an activation function in convolutional layers, while the last layer uses softmax. It is necessary to form a data set for training a neural network in order to detect a target. We built a Confusion Matrix of the CNN model to measure the effectiveness of our model. The results showed that the accuracy when testing the model was 95.7%. Classification of echo signals using CNN shows high accuracy and significantly speeds up the process of predicting the target.

Keywords: radar, neural network, convolutional neural network, echo signals

Procedia PDF Downloads 354

Authors: Pablo Martin, Jorge Olivares, Fernando Maass

Abstract:

A method to obtain analytic approximations for special function of interest in engineering and physics is described here. Each approximate function will be valid for every positive value of the variable and accuracy will be high and increasing with the number of parameters to determine. The general technique will be shown through an application to the modified Bessel function of order zero, I₀(x). The form and the calculation of the parameters are performed with the simultaneous use of the power series and asymptotic expansion. As in Padé method rational functions are used, but now they are combined with other elementary functions as; fractional powers, hyperbolic, trigonometric and exponential functions, and others. The elementary function is determined, considering that the approximate function should be a bridge between the power series and the asymptotic expansion. In the case of the I₀(x) function two analytic approximations have been already determined. The simplest one is (1+x²/4)⁻¹/⁴(1+0.24273x²) cosh(x)/(1+0.43023x²). The parameters of I₀(x) were determined using the leading term of the asymptotic expansion and two coefficients of the power series, and the maximum relative error is 0.05. In a second case, two terms of the asymptotic expansion were used and 4 of the power series and the maximum relative error is 0.001 at x≈9.5. Approximations with much higher accuracy will be also shown. In conclusion a new technique is described to obtain analytic approximations to some functions of interest in sciences, such that they have a high accuracy, they are valid for every positive value of the variable, they can be integrated and differentiated as the usual, functions, and furthermore they can be calculated easily even with a regular pocket calculator.

Keywords: analytic approximations, mathematical-physics applications, quasi-rational functions, special functions

Procedia PDF Downloads 252