Search results for: classifiers accuracy

Authors: Javad Rahimipour Anaraki, Saeed Samet, Mahdi Eftekhari, Chang Wook Ahn

Abstract:

Feature selection and attribute reduction are crucial problems, and widely used techniques in the field of machine learning, data mining and pattern recognition to overcome the well-known phenomenon of the Curse of Dimensionality. This paper presents a feature selection method that efficiently carries out attribute reduction, thereby selecting the most informative features of a dataset. It consists of two components: 1) a measure for feature subset evaluation, and 2) a search strategy. For the evaluation measure, we have employed the fuzzy-rough dependency degree (FRFDD) of the lower approximation-based fuzzy-rough feature selection (L-FRFS) due to its effectiveness in feature selection. As for the search strategy, a modified version of a binary shuffled frog leaping algorithm is proposed (B-SFLA). The proposed feature selection method is obtained by hybridizing the B-SFLA with the FRDD. Nine classifiers have been employed to compare the proposed approach with several existing methods over twenty two datasets, including nine high dimensional and large ones, from the UCI repository. The experimental results demonstrate that the B-SFLA approach significantly outperforms other metaheuristic methods in terms of the number of selected features and the classification accuracy.

Keywords: binary shuffled frog leaping algorithm, feature selection, fuzzy-rough set, minimal reduct

Procedia PDF Downloads 227

Authors: Kemal Polat

Abstract:

In this paper, an attribute weighting method called fuzzy C-means clustering based attribute weighting (FCMAW) for classification of Diabetes disease dataset has been used. The aims of this study are to reduce the variance within attributes of diabetes dataset and to improve the classification accuracy of classifier algorithm transforming from non-linear separable datasets to linearly separable datasets. Pima Indians Diabetes dataset has two classes including normal subjects (500 instances) and diabetes subjects (268 instances). Fuzzy C-means clustering is an improved version of K-means clustering method and is one of most used clustering methods in data mining and machine learning applications. In this study, as the first stage, fuzzy C-means clustering process has been used for finding the centers of attributes in Pima Indians diabetes dataset and then weighted the dataset according to the ratios of the means of attributes to centers of theirs. Secondly, after weighting process, the classifier algorithms including support vector machine (SVM) and k-NN (k- nearest neighbor) classifiers have been used for classifying weighted Pima Indians diabetes dataset. Experimental results show that the proposed attribute weighting method (FCMAW) has obtained very promising results in the classification of Pima Indians diabetes dataset.

Keywords: fuzzy C-means clustering, fuzzy C-means clustering based attribute weighting, Pima Indians diabetes, SVM

Procedia PDF Downloads 416

Authors: Chayanika Hazarika Bordoloi

Abstract:

This paper is an attempt to work on a highly inflectional language called Assamese. This is also one of the national languages of India and very little has been achieved in terms of computational research. Building a language processing tool for a natural language is not very smooth as the standard and language representation change at various levels. This paper presents inflectional suffixes of Assamese verbs and how the statistical tools, along with linguistic features, can improve the tagging accuracy. Conditional random fields (CRF tool) was used to automatically tag and train the text data; however, accuracy was improved after linguistic featured were fed into the training data. Assamese is a highly inflectional language; hence, it is challenging to standardizing its morphology. Inflectional suffixes are used as a feature of the text data. In order to analyze the inflections of Assamese word forms, a list of suffixes is prepared. This list comprises suffixes, comprising of all possible suffixes that various categories can take is prepared. Assamese words can be classified into inflected classes (noun, pronoun, adjective and verb) and un-inflected classes (adverb and particle). The corpus used for this morphological analysis has huge tokens. The corpus is a mixed corpus and it has given satisfactory accuracy. The accuracy rate of the tagger has gradually improved with the modified training data.

Keywords: CRF, morphology, tagging, tagset

Procedia PDF Downloads 195

Authors: Emmanuel Osaze Oshoiribhor, Adetokunbo MacGregor John-Otumu

Abstract:

There has been a need in recent years to predict student academic achievement prior to graduation. This is to assist them in improving their grades, especially for those who have struggled in the past. The purpose of this research is to use supervised learning techniques to create a model that predicts student academic progress. Many scholars have developed models that predict student academic achievement based on characteristics including smoking, demography, culture, social media, parent educational background, parent finances, and family background, to mention a few. This element, as well as the model used, could have misclassified the kids in terms of their academic achievement. As a prerequisite to predicting if the student will perform well in the future on related courses, this model is built using a logistic regression classifier with basic features such as the previous semester's course score, attendance to class, class participation, and the total number of course materials or resources the student is able to cover per semester. With a 96.7 percent accuracy, the model outperformed other classifiers such as Naive bayes, Support vector machine (SVM), Decision Tree, Random forest, and Adaboost. This model is offered as a desktop application with user-friendly interfaces for forecasting student academic progress for both teachers and students. As a result, both students and professors are encouraged to use this technique to predict outcomes better.

Keywords: artificial intelligence, ML, logistic regression, performance, prediction

Procedia PDF Downloads 110

Authors: M. D. D. Chathurangi, M. G. K. Nayanathara, K. M. H. M. M. Gunapala, G. M. R. G. Dayananda, Kavinga Yapa Abeywardena, Deemantha Siriwardana

Abstract:

Due to the growing popularity of social media platforms at present, there are various concerns, mostly cyberbullying, spam, bot accounts, and the spread of incorrect information. To develop a risk score calculation system as a thorough method for deciphering and exposing unethical social media profiles, this research explores the most suitable algorithms to our best knowledge in detecting the mentioned concerns. Various multiple models, such as Naïve Bayes, CNN, KNN, Stochastic Gradient Descent, Gradient Boosting Classifier, etc., were examined, and the best results were taken into the development of the risk score system. For cyberbullying, the Logistic Regression algorithm achieved an accuracy of 84.9%, while the spam-detecting MLP model gained 98.02% accuracy. The bot accounts identifying the Random Forest algorithm obtained 91.06% accuracy, and 84% accuracy was acquired for fake news detection using SVM.

Keywords: cyberbullying, spam behavior, bot accounts, fake news, machine learning

Procedia PDF Downloads 40

Authors: Naser Safdarian, Nader Jafarnia Dabanloo

Abstract:

In this paper we used four features i.e. Q-wave integral, QRS complex integral, T-wave integral and total integral as extracted feature from normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our research we focused on detection and localization of MI in standard ECG. We use the Q-wave integral and T-wave integral because this feature is important impression in detection of MI. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI. Because these methods have good accuracy for classification of normal and abnormal signals. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 80% for accuracy in test data for localization and over 95% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve accuracy of classification by adding more features in this method. A simple method based on using only four features which extracted from standard ECG is presented which has good accuracy in MI localization.

Keywords: ECG signal processing, myocardial infarction, features extraction, pattern recognition

Procedia PDF Downloads 456

Authors: Daniel Hyun

Abstract:

Dental implants are one of the top 3 reasons to sue a dentist for malpractice. It involves dental implant complications, usually because of the angle of the implant from the surgery. At present, surgeons usually use a 3D-printed navigator that is customized for the patient’s teeth. However, those can’t be reused for other patients as they require time. Therefore, I made a guiding device to assist the surgeon in implant operations. The surgeon can input the objective of the operation, and the device constantly checks if the surgery is heading towards the objective within the set range, telling the surgeon by manipulating the LED. We tested the prototypes’ consistency and accuracy by checking the graph, average standard deviation, and the average change of the calculated angles. The accuracy of performance was also acquired by running the device and checking the outputs. My first prototype used accelerometer and gyroscope sensors from the Arduino MPU6050 sensor, getting a changeable graph, achieving 0.0295 of standard deviations, 0.25 of average change, and 66.6% accuracy of performance. The second prototype used only the gyroscope, and it got a constant graph, achieved 0.0062 of standard deviation, 0.075 of average change, and 100% accuracy of performance, indicating that the accelerometer sensor aggravated the functionality of the device. Using the gyroscope sensor allowed it to measure the orientations of separate axes without affecting each other and also increased the stability and accuracy of the measurements.

Keywords: implant, guide, accelerometer, gyroscope, handpiece

Procedia PDF Downloads 44

Authors: Emmanuel Osaze Oshoiribhor, Adetokunbo MacGregor John-Otumu

Abstract:

In recent years, there has been a desire to forecast student academic achievement prior to graduation. This is to help them improve their grades, particularly for individuals with poor performance. The goal of this study is to employ supervised learning techniques to construct a predictive model for student academic achievement. Many academics have already constructed models that predict student academic achievement based on factors such as smoking, demography, culture, social media, parent educational background, parent finances, and family background, to name a few. This feature and the model employed may not have correctly classified the students in terms of their academic performance. This model is built using a logistic regression classifier with basic features such as the previous semester's course score, attendance to class, class participation, and the total number of course materials or resources the student is able to cover per semester as a prerequisite to predict if the student will perform well in future on related courses. The model outperformed other classifiers such as Naive bayes, Support vector machine (SVM), Decision Tree, Random forest, and Adaboost, returning a 96.7% accuracy. This model is available as a desktop application, allowing both instructors and students to benefit from user-friendly interfaces for predicting student academic achievement. As a result, it is recommended that both students and professors use this tool to better forecast outcomes.

Keywords: artificial intelligence, ML, logistic regression, performance, prediction

Procedia PDF Downloads 98

Authors: Jaypalsinh B. Parmar, Pintu Nakrani, Ashish Chaurasia

Abstract:

Digital Elevation Model (DEM) is considered as an important data in GIS-based terrain analysis for many applications and assessment of processes such as environmental and climate change studies, hydrologic modelling, etc. Vertical accuracy of DEM having geographically dynamic nature depends on different parameters which affect the model simulation outcomes. Vertical accuracy assessment in Indian landscape especially in low-lying coastal urban terrain such as lower Tapi Basin is very limited. In the present study, attempt has been made to evaluate the vertical accuracy of 30m resolution open source Indian National Cartosat-1 DEM v3 for Lower Tapi Basin (LTB) from western India. The extensive field investigation is carried out using stratified random fast static DGPS survey in the entire study region, and 117 high accuracy ground control points (GCPs) have been obtained. The above open source DEM was compared with obtained GCPs, and different statistical attributes were envisaged, and vertical error histograms were also evaluated.

Keywords: CartoDEM, Digital Elevation Model, GPS, lower Tapi basin

Procedia PDF Downloads 359

Authors: Christina Adly, Meena Abdelmeseeh, Tamer Basha

Abstract:

This paper proposes a system for hand movement recognition using multichannel surface EMG(sEMG) signals obtained from 40 subjects using 40 different exercises, which are available on the Ninapro(Non-Invasive Adaptive Prosthetics) database. First, we applied processing methods to the raw sEMG signals to convert them to their amplitudes. Second, we used deep learning methods to solve our problem by passing the preprocessed signals to Fully connected neural networks(FCNN) and recurrent neural networks(RNN) with Long Short Term Memory(LSTM). Using intrasubject evaluation, The accuracy using the FCNN is 72%, with a processing time for training around 76 minutes, and for RNN's accuracy is 79.9%, with 8 minutes and 22 seconds processing time. Third, we applied some postprocessing methods to improve the accuracy, like majority voting(MV) and Movement Error Rate(MER). The accuracy after applying MV is 75% and 86% for FCNN and RNN, respectively. The MER value has an inverse relationship with the prediction delay while varying the window length for measuring the MV. The different part uses the RNN with the intersubject evaluation. The experimental results showed that to get a good accuracy for testing with reasonable processing time, we should use around 20 subjects.

Keywords: hand movement recognition, recurrent neural network, movement error rate, intrasubject evaluation, intersubject evaluation

Procedia PDF Downloads 145

Authors: Mehrnaz Mostafavi

Abstract:

The assessment and categorization of incidental lung nodules present a considerable challenge in healthcare, often necessitating resource-intensive multiple computed tomography (CT) scans for growth confirmation. This research addresses this issue by introducing a distinct computational approach leveraging radiomics and deep-learning methods. However, understanding local services is essential before implementing these advancements. With diverse tracking methods in place, there is a need for efficient and accurate identification approaches, especially in the context of managing lung nodules alongside pre-existing cancer scenarios. This study explores the integration of text-based algorithms in medical data curation, indicating their efficacy in conjunction with machine learning and deep-learning models for identifying lung nodules. Combining medical images with text data has demonstrated superior data retrieval compared to using each modality independently. While deep learning and text analysis show potential in detecting previously missed nodules, challenges persist, such as increased false positives. The presented research introduces a Structured-Query-Language (SQL) algorithm designed for identifying pulmonary nodules in a tertiary cancer center, externally validated at another hospital. Leveraging natural language processing (NLP) and machine learning, the algorithm categorizes lung nodule reports based on sentence features, aiming to facilitate research and assess clinical pathways. The hypothesis posits that the algorithm can accurately identify lung nodule CT scans and predict concerning nodule features using machine-learning classifiers. Through a retrospective observational study spanning a decade, CT scan reports were collected, and an algorithm was developed to extract and classify data. Results underscore the complexity of lung nodule cohorts in cancer centers, emphasizing the importance of careful evaluation before assuming a metastatic origin. The SQL and NLP algorithms demonstrated high accuracy in identifying lung nodule sentences, indicating potential for local service evaluation and research dataset creation. Machine-learning models exhibited strong accuracy in predicting concerning changes in lung nodule scan reports. While limitations include variability in disease group attribution, the potential for correlation rather than causality in clinical findings, and the need for further external validation, the algorithm's accuracy and potential to support clinical decision-making and healthcare automation represent a significant stride in lung nodule management and research.

Keywords: lung cancer diagnosis, structured-query-language (SQL), natural language processing (NLP), machine learning, CT scans

Procedia PDF Downloads 103

Authors: Md. Khayrul Bashar, Md. Saiful Islam, Kimiko Yamashita, Yano Midori

Abstract:

Despite having some progress in human authentication, conventional biometrics (e.g., facial features, fingerprints, retinal scans, gait, voice patterns) are not robust against falsification because they are neither confidential nor secret to an individual. As a non-invasive tool, electrocardiogram (ECG) has recently shown a great potential in human recognition due to its unique rhythms characterizing the variability of human heart structures (chest geometry, sizes, and positions). Moreover, ECG has a real-time vitality characteristic that signifies the live signs, which ensure legitimate individual to be identified. However, the detection accuracy of the current ECG-based methods is not sufficient due to a high variability of the individual’s heartbeats at a different instance of time. These variations may occur due to muscle flexure, the change of mental or emotional states, and the change of sensor positions or long-term baseline shift during the recording of ECG signal. In this study, a new method is proposed for human identification, which is based on the extraction of the local roughness of ECG heartbeat signals. First ECG signal is preprocessed using a second order band-pass Butterworth filter having cut-off frequencies of 0.00025 and 0.04. A number of local binary patterns are then extracted by applying a moving neighborhood window along the ECG signal. At each instant of the ECG signal, the pattern is formed by comparing the ECG intensities at neighboring time points with the central intensity in the moving window. Then, binary weights are multiplied with the pattern to come up with the local roughness description of the signal. Finally, histograms are constructed that describe the heartbeat signals of individual subjects in the database. One advantage of the proposed feature is that it does not depend on the accuracy of detecting QRS complex, unlike the conventional methods. Supervised recognition methods are then designed using minimum distance to mean and Bayesian classifiers to identify authentic human subjects. An experiment with sixty (60) ECG signals from sixty adult subjects from National Metrology Institute of Germany (NMIG) - PTB database, showed that the proposed new method is promising compared to a conventional interval and amplitude feature-based method.

Keywords: human identification, ECG biometrics, local roughness patterns, supervised classification

Procedia PDF Downloads 405

Authors: Danni Cong, Meiping Wu, Hua Mu, Xiaofeng He, Junxiang Lian, Juliang Cao, Shaokun Cai, Hao Qin

Abstract:

Gravity field is of great significance in geoscience, national economy and national security, and gravitational gradient measurement has been extensively studied due to its higher accuracy than gravity measurement. Gravity gradient sensor, being one of core devices of the gravity gradient instrument, plays a key role in measuring accuracy. Therefore, this paper starts from analyzing the working principle of the gravity gradient sensor by Newton’s law, and then considers the relative motion between inertial and non-inertial systems to build a relatively adequate mathematical model, laying a foundation for the measurement error calibration, measurement accuracy improvement.

Keywords: gravity gradient, gravity gradient sensor, accelerometer, single-axis rotation modulation

Procedia PDF Downloads 328

Authors: Dmytro Zubov, Francesco Volponi

Abstract:

In this paper, D-Wave quantum computing Ising model is used for the forecasting of positive extremes of daily mean air temperature. Forecast models are designed with two to five qubits, which represent 2-, 3-, 4-, and 5-day historical data respectively. Ising model’s real-valued weights and dimensionless coefficients are calculated using daily mean air temperatures from 119 places around the world, as well as sea level (Aburatsu, Japan). In comparison with current methods, this approach is better suited to predict heat wave values because it does not require the estimation of a probability distribution from scarce observations. Proposed forecast quantum computing algorithm is simulated based on traditional computer architecture and combinatorial optimization of Ising model parameters for the Ronald Reagan Washington National Airport dataset with 1-day lead-time on learning sample (1975-2010 yr). Analysis of the forecast accuracy (ratio of successful predictions to total number of predictions) on the validation sample (2011-2014 yr) shows that Ising model with three qubits has 100 % accuracy, which is quite significant as compared to other methods. However, number of identified heat waves is small (only one out of nineteen in this case). Other models with 2, 4, and 5 qubits have 20 %, 3.8 %, and 3.8 % accuracy respectively. Presented three-qubit forecast model is applied for prediction of heat waves at other five locations: Aurel Vlaicu, Romania – accuracy is 28.6 %; Bratislava, Slovakia – accuracy is 21.7 %; Brussels, Belgium – accuracy is 33.3 %; Sofia, Bulgaria – accuracy is 50 %; Akhisar, Turkey – accuracy is 21.4 %. These predictions are not ideal, but not zeros. They can be used independently or together with other predictions generated by different method(s). The loss of human life, as well as environmental, economic, and material damage, from extreme air temperatures could be reduced if some of heat waves are predicted. Even a small success rate implies a large socio-economic benefit.

Keywords: heat wave, D-wave, forecast, Ising model, quantum computing

Procedia PDF Downloads 500

Authors: Mostafa ‘Neo’ Mohsenvand, Mohammad Rasool Izadi, Pattie Maes

Abstract:

EEG-based biometrics (user identification) has been explored on small datasets of no more than 157 subjects. Here we show that the accuracy of modern supervised methods falls rapidly as the number of users increases to a few thousand. Moreover, supervised methods require a large amount of labeled data for training which limits their applications in real-world scenarios where acquiring data for training should not take more than a few minutes. We show that using contrastive learning for pre-training, it is possible to maintain high accuracy on a dataset of 2130 subjects while only using a fraction of labels. We compare 5 different self-supervised tasks for pre-training of the encoder where our proposed method achieves the accuracy of 96.4%, improving the baseline supervised models by 22.75% and the competing self-supervised model by 3.93%. We also study the effects of the length of the signal and the number of channels on the accuracy of the user-identification models. Our results reveal that signals from temporal and frontal channels contain more identifying features compared to other channels.

Keywords: brainprint, contrastive learning, electroencephalo-gram, self-supervised learning, user identification

Procedia PDF Downloads 157

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 165

Authors: Rashi Bhalla, Russel Pears, M. Asif Naeem

Abstract:

In this 'Information Explosion Era' analyzing data 'a critical commodity' and mining knowledge from vertically distributed data stream incurs huge communication cost. However, an effort to decrease the communication in the distributed environment has an adverse influence on the classification accuracy; therefore, a research challenge lies in maintaining a balance between transmission cost and accuracy. This paper proposes a method based on Bayesian inference to reduce the communication volume in a heterogeneous distributed environment while retaining prediction accuracy. Our experimental evaluation reveals that a significant reduction in communication can be achieved across a diverse range of dataset types.

Keywords: big data, bayesian inference, distributed data stream mining, heterogeneous-distributed data

Procedia PDF Downloads 161

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model 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 66

Authors: Jyotismita Talukdar

Abstract:

In this paper, a study has been made on the possibility and accuracy of early prediction of several Heart Disease using Artificial Neural Network. (ANN). The study has been made in both noise free environment and noisy environment. The data collected for this analysis are from five Hospitals. Around 1500 heart patient’s data has been collected and studied. The data is analysed and the results have been compared with the Doctor’s diagnosis. It is found that, in noise free environment, the accuracy varies from 74% to 92%and in noisy environment (2dB), the results of accuracy varies from 62% to 82%. In the present study, four basic attributes considered are Blood Pressure (BP), Fasting Blood Sugar (FBS), Thalach (THAL) and Cholesterol (CHOL.). It has been found that highest accuracy(93%), has been achieved in case of PPI( Post-Permanent-Pacemaker Implementation ), around 79% in case of CAD(Coronary Artery disease), 87% in DCM (Dilated Cardiomyopathy), 89% in case of RHD&MS(Rheumatic heart disease with Mitral Stenosis), 75 % in case of RBBB +LAFB (Right Bundle Branch Block + Left Anterior Fascicular Block), 72% for CHB(Complete Heart Block) etc. The lowest accuracy has been obtained in case of ICMP (Ischemic Cardiomyopathy), about 38% and AF( Atrial Fibrillation), about 60 to 62%.

Keywords: coronary heart disease, chronic stable angina, sick sinus syndrome, cardiovascular disease, cholesterol, Thalach

Procedia PDF Downloads 176

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation

Procedia PDF Downloads 193

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 215

Authors: C. V. Aravinda, H. N. Prakash

Abstract:

In this paper, we tried to convey fusion and state of art pertaining to SIL character recognition systems. In the first step, the text is preprocessed and normalized to perform the text identification correctly. The second step involves extracting relevant and informative features. The third step implements the classification decision. The three stages which involved are Data acquisition and preprocessing, Feature extraction, and Classification. Here we concentrated on two techniques to obtain features, Feature Extraction & Feature Selection. Edge-hinge distribution is a feature that characterizes the changes in direction of a script stroke in handwritten text. The edge-hinge distribution is extracted by means of a windowpane that is slid over an edge-detected binary handwriting image. Whenever the mid pixel of the window is on, the two edge fragments (i.e. connected sequences of pixels) emerging from this mid pixel are measured. Their directions are measured and stored as pairs. A joint probability distribution is obtained from a large sample of such pairs. Despite continuous effort, handwriting identification remains a challenging issue, due to different approaches use different varieties of features, having different. Therefore, our study will focus on handwriting recognition based on feature selection to simplify features extracting task, optimize classification system complexity, reduce running time and improve the classification accuracy.

Keywords: word segmentation and recognition, character recognition, optical character recognition, hand written character recognition, South Indian languages

Procedia PDF Downloads 497

Authors: Suzan Anwar, Utkarsh Goyal

Abstract:

Heart rate (HR) is a predictor of cardiovascular, cerebrovascular, and all-cause mortality in the general population, as well as in patients with cardio and cerebrovascular diseases. Machine learning (ML) significantly improves the accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment while avoiding unnecessary treatment of others. This research examines relationship between the individual's various heart health inputs like age, sex, cp, trestbps, thalach, oldpeaketc, and the likelihood of developing heart disease. Machine learning techniques like logistic regression and decision tree, and Python are used. The results of testing and evaluating the model using the Heart Failure Prediction Dataset show the chance of a person having a heart disease with variable accuracy. Logistic regression has yielded an accuracy of 80.48% without data handling. With data handling (normalization, standardscaler), the logistic regression resulted in improved accuracy of 87.80%, decision tree 100%, random forest 100%, and SVM 100%.

Keywords: heart rate, machine learning, SVM, decision tree, logistic regression, random forest

Procedia PDF Downloads 138

Authors: Laiba Amin, Rashna H. Sukhia, Mubassar Fida

Abstract:

Introduction: This study evaluates the accuracy of responses from ChatGPT, Google Bard, and Microsoft Copilot regarding dentofacial orthopedic appliances. As artificial intelligence (AI) increasingly enhances various fields, including healthcare, understanding its reliability in specialized domains like orthodontics becomes crucial. By comparing the accuracy of different AI models, this study aims to shed light on their effectiveness and potential limitations in providing technical insights. Materials and Methods: A total of 110 questions focused on dentofacial orthopedic appliances were posed to each AI model. The responses were then evaluated by five experienced orthodontists using a modified 5-point Likert scale to ensure a thorough assessment of accuracy. This structured approach allowed for consistent and objective rating, facilitating a meaningful comparison between the AI systems. Results: The results revealed that Google Bard demonstrated the highest accuracy at 74%, followed by Microsoft Copilot, with an accuracy of 72.2%. In contrast, ChatGPT was found to be the least accurate, achieving only 52.2%. These results highlight significant differences in the performance of the AI models when addressing orthodontic queries. Conclusions: Our study highlights the need for caution in relying on AI for orthodontic insights. The overall accuracy of the three chatbots was 66%, with Google Bard performing best for removable Class II appliances. Microsoft Copilot was more accurate than ChatGPT, which, despite its popularity, was the least accurate. This variability emphasizes the importance of human expertise in interpreting AI-generated information. Further research is necessary to improve the reliability of AI models in specialized healthcare settings.

Keywords: artificial intelligence, large language models, orthodontics, dentofacial orthopaedic appliances, accuracy assessment.

Procedia PDF Downloads 14

Authors: Palwinder Singh, Munish Sandhir, Tejinder Singh

Abstract:

The ordinary differential equations (ODE) represent a natural framework for mathematical modeling of many real-life situations in the field of engineering, control systems, physics, chemistry and astronomy etc. Such type of differential equations can be solved by analytical methods or by numerical methods. If the solution is calculated using analytical methods, it is done through calculus theories, and thus requires a longer time to solve. In this paper, we compare the numerical accuracy of the solutions given by the three main types of one-step initial value solvers: Taylor’s Series Method, Euler’s Method and Runge-Kutta Fourth Order Method (RK4). The comparison of accuracy is obtained through comparing the solutions of ordinary differential equation given by these three methods. Furthermore, to verify the accuracy; we compare these numerical solutions with the exact solutions.

Keywords: Ordinary differential equations (ODE), Taylor’s Series Method, Euler’s Method, Runge-Kutta Fourth Order Method

Procedia PDF Downloads 359

Authors: Mohammad Hadi Mahmoodi, Elahe Saedpanah

Abstract:

Since pronunciation is among those factors that can have strong effects on EFL learners’ successful communication, instructional programs with accurate pronunciation purposes seem to be a necessity in any L2 teaching context. The widespread use of smart mobile phones brings with itself various educational applications, which can assist foreign language learners in learning and speaking another language other than their L1. In line with this supportive innovation, the present study investigated the role of LDOCE (Longman Dictionary of Contemporary English), a mobile application, on improving Iranian EFL learners’ pronunciation accuracy. To this aim, 40 EFL learners studying English at the intermediate level participated in the current study. This was an experimental research with two groups of 20 students in an experimental and a control group. The data were collected through the administration of a pronunciation pretest before the instruction and a post-test after the treatment. In addition, the assessment was based on the pupils’ recorded voices while reading the selected words. The results of the independent samples t-test indicated that using LDOCE significantly affected Iranian EFL learners' pronunciation accuracy with those in the experimental group outperforming their control group counterparts.

Keywords: LDOCE, EFL learners, pronunciation accuracy, CALL, MALL

Procedia PDF Downloads 549

Authors: Shuo Liu

Abstract:

In Chinese text classification tasks, redundant words and phrases can interfere with the formation of extracted and analyzed text information, leading to a decrease in the accuracy of the classification model. To reduce irrelevant elements, extract and utilize text content information more efficiently and improve the accuracy of text classification models. In this paper, the text in the corpus is first extracted using the TextRank algorithm for abstraction, the words in the abstract are used as nodes to construct a text graph, and then the graph attention network (GAT) is used to complete the task of classifying the text. Testing on a Chinese dataset from the network, the classification accuracy was improved over the direct method of generating graph structures using text.

Keywords: Chinese natural language processing, text classification, abstract extraction, graph attention network

Procedia PDF Downloads 102

Authors: Kemka C. Ihemelandu, Chukwuemeka U. Ihemelandu

Abstract:

The incidence of melanoma has been increasing rapidly over the past two decades, making melanoma a current public health crisis. Unfortunately, even as screening efforts continue to expand in an effort to ameliorate the death rate from melanoma, there is a need to improve diagnostic accuracy to decrease misdiagnosis. Artificial intelligence (AI) a new frontier in patient care has the ability to improve the accuracy of melanoma diagnosis. Convolutional neural network (CNN) a form of deep neural network, most commonly applied to analyze visual imagery, has been shown to outperform the human brain in pattern recognition. However, there are noted limitations with the accuracy of the CNN models. Our aim in this study was the optimization of convolutional neural network algorithms for the automated diagnosis of melanoma. We hypothesized that Optimal selection of the momentum and batch hyperparameter increases model accuracy. Our most successful model developed during this study, showed that optimal selection of momentum of 0.25, batch size of 2, led to a superior performance and a faster model training time, with an accuracy of ~ 83% after nine hours of training. We did notice a lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone. Training set image transformations did not result in a superior model performance in our study.

Keywords: melanoma, convolutional neural network, momentum, batch hyperparameter

Procedia PDF Downloads 101

Authors: Vo Ngoc Phu, Phan Thi Tuoi

Abstract:

We have explored different methods of improving the accuracy of sentiment classification. The sentiment orientation of a document can be positive (+), negative (-), or neutral (0). We combine five dictionaries from [2, 3, 4, 5, 6] into the new one with 21137 entries. The new dictionary has many verbs, adverbs, phrases and idioms, that are not in five ones before. The paper shows that our proposed method based on the combination of Term-Counting method and Enhanced Contextual Valence Shifters method has improved the accuracy of sentiment classification. The combined method has accuracy 68.984% on the testing dataset, and 69.224% on the training dataset. All of these methods are implemented to classify the reviews based on our new dictionary and the Internet Movie data set.

Keywords: sentiment classification, sentiment orientation, valence shifters, contextual, valence shifters, term counting

Procedia PDF Downloads 505

Authors: Jeff Colwell, Benjamin Knox

Abstract:

While fire and explosion incidents are often observed by eyewitnesses, the weight that fire investigators should place on those observations in their investigations is a complex issue. There is no doubt that eyewitness statements can be an important component to an investigation, particularly when other evidence is sparse, as is often the case when damage to the scene is severe. However, it is well known that eyewitness statements can be incorrect for a variety of reasons, including deception. In this paper, we reviewed factors that can have an effect on the complex processes associated with the perception, retention, and retrieval of an event. We then review the accuracy of eyewitness statements from unique criminal and civil incidents, including fire and explosion incidents, in which the accuracy of the statements could be independently evaluated. Finally, the motives for deceptive eyewitness statements are described, along with techniques that fire and explosion investigators can employ, to increase the accuracy of the eyewitness statements that they solicit.

Keywords: fire, explosion, eyewitness, reliability

Procedia PDF Downloads 383