Accuracy Of Classification Algorithms Research Articles

Multi Graded Brain Tumor Classification using YOLOv7

In recent years, significant progress has been made in the field of diagnosis and classification of brain tumors, mainly attributed to advancements in artificial intelligence and medical imaging. The main objective of this study is to improve the detection and classification of brain tumors by applying and utilizing of artificial intelligence (AI) and recent advancements in medical imaging techniques. Automation of the process of tumor identification and then classification, in addition to tumor grading, will definitely improve all procedures of brain tumor treatment and enhance patient care. The proposed system combines convolutional neural networks (CNNs), which act as extract features, and the You Only Look Once Algorithm (YOLOv7) for effective object identification and accurate classification. The methodology described in this study involves employing a technique of multilayer classification, which integrates three distinct datasets. This comprehensive approach shows an exceptional levels of accuracy and precision. At the initial level, the model attains a 99.78% accuracy in distinguishing between tumor and nontumor cases. At the next level the system accurately sorts types of brain tumors (such, as glioma, meningioma and pituitary tumors) with an average accuracy of 99.35%. Moving on to the final stage it successfully distinguishes between low grade and high grade glioma tumors with a precision of 93.07%. Moreover the model shows accuracies ranging from 99.41%, to 99.61% when classifying types of brain tumors and nontumor cases. The proposed system has the ability to determine the boundaries of the tumor, and thus this has helped in calculating the sizes of tumors with high accuracy. Index Terms- Brain tumor, MRI, Convolutional Neural Network, YOLO, Tumor grading.

Evaluation of Different Classification Algorithms for Land Use Land Cover Mapping

For efficient sustainable management and monitoring landscape changes over times, reliable land use land cover (LULC) mapping using the most accurate classification algorithms is required. Increasing innovative classification algorithms and satellite data demands finding the most suitable classifier to create accurate maps of different features efficiently. The challenge addressed in this study is to identify the most accurate algorithm for classifying and generating reliable LULC. The objective of this research was to identify the best classification among several algorithms both overall and in each individual class by using ArcGIS Pro and Google Earth Engine with Landsat 8 and Sentinel-2 datasets for Ranya city as the study area. Support vector machine (SVM), maximum likelihood, random tree, classification and regression tree, K-Nearest Neighbor and iterative self organizing cluster algorithms were used to classify the satellite image of the study area. The kappa coefficient matrix was used to assess the performance of each classifier and method. The study showed that the random tree algorithm achieved highest overall accuracy using Sentinel-2 with 83%. Meanwhile, when the specific class accuracy is priority, the result suggests the use of SVM algorithm using Sentinel-2 for building footprint extraction with 92% accuracy. The result also showed that the outcomes of most algorithms were better using Sentinel-2 rather than Landsat 8, making Sentinel-2 more suitable for accurate LULC mapping. The outcomes of the research assessed different classification algorisms to find the best algorithms and methods that can be used to generate accurate and efficient LULC maps.

A comparative experimental research on the diagnosis of tooth root cracks in asymmetric spur gear pairs with a one-dimensional convolutional neural network

Gearboxes transfer rotational motion and handle precision functionalities in many fields, including aviation, wind turbines, and industrial services. Their health management is essential to minimize workforce risks, increase the level of safety, and avoid machine breakdowns. From this standpoint, the present experimental research work developed a convolutional neural network-based method for diagnosing different levels of tooth root cracks (25 %-50 %-75 %-100 %) for symmetric (20°/20°) and asymmetric (20°/30°) profiled gear pairs. A series of vibration experiments were performed on a one-stage spur gearbox to achieve this by using a tri-axial accelerometer under variable working loads. The main purpose of this experimental research study is to explore the influence of the tooth profile on spur gears’ vibration responses and whether utilizing an asymmetric tooth profile would positively impact a deep learning algorithm's classification accuracy to add to the enhancements it provides in terms of fatigue life, mesh stiffness, and impact strength. Experimental results revealed that the overall classification accuracy could be increased by 7.712 % by feeding the proposed deep learning model with vibration data measured using test samples with asymmetric teeth.

Heart Sound Processing for Early Diagnostic of Heart Abnormalities using Support Vector Machine

This paper addresses the critical issue of cardiovascular disease (CVD), the leading cause of global mortality, emphasizing the imperative for effective and early detection to mitigate CVD-related deaths. The research problem underscores the urgency of developing advanced diagnostic tools to identify heart abnormalities promptly. The primary objective is to create a Support Vector Machine (SVM) algorithm for accurate classification of different heart conditions, namely Normal heart, Mitral Stenosis, and Mitral Regurgitation. To achieve this objective, the study utilizes a dataset of heart sounds available online using a 10-fold cross-validation method. The focus is on evaluating the efficacy of various kernel functions within the SVM framework for heart sound classification. The findings demonstrate that the linear kernel exhibits superior accuracy and robustness in effectively classifying heart conditions. Notably, the proposed classification method attains an impressive 96% accuracy, highlighting its potential as a reliable tool for early detection of cardiovascular diseases. This research contributes to the ongoing efforts to enhance diagnostic capabilities and ultimately reduce the global burden of CVD-related fatalities.

Computer model for detecting tsunami wave hazard on built-up land using machine learning and sentinel 2A satellite imagery

<p>The aim of this research is to compile a tsunami wave hazard scale based on built-up land density extracted and classified by machine learning from Sentinel 2A satellite and digital elevation model (DEM) imageries. This research was carried out in 5 stages, namely: (i) pre-processing of Sentinel 2A and DEM images, (ii) Classification of VI data using the machine learning algorithms, (iii) Spatial prediction using the ordinary kriging method, (iv) Field testing using the confusion matrix method, (v) Preparation of decision matrix for tsunami wave hazard. The results of the study show that the most accurate classification algorithm for classifying built-up indices data is the k-nearest neighbor (k-NN) algorithm. The results of the statistical accuracy test show that the most accurate is normalized difference built-up index (NDBI) with a mean of square error (MSE) value of 0.073 and a mean of absolute error (MAE) of 0.003. DEM analysis shows that the research area is at an altitude of 0–15 meters above sea level so it is in the high vulnerability to medium vulnerability category. Field testing showed user accuracy of 91.11%, manufacturer accuracy of 92.16%, and overall average accuracy of 91%.</p>

Corrosion inhibition by Myristica fragrans extract in neem biodiesel: Evaluation by machine learning and traditional methods

Ethyl acetate extract of Myristica fragrans mace flowers was investigated as an effective inhibitor for copper in neem biodiesel. Employing the ASTM D130 method to assess copper corrosion in biodiesel, a remarkable inhibition efficiency of 98.04% was achieved. Inhibitor adsorption on the surface of copper metal was substantiated by FTIR spectral evaluation. Surface morphology studies by SEM confirmed the protective nature of the inhibitor for copper metal corrosion prevention. Further, several support vector machine (SVM) learning algorithms were employed with three different classes of corrosion to study the corrosion inhibition of which, the medium Gaussian procedure gave a maximum accuracy of 92.4%. The work reveals the applicability of the SVM algorithm for accurate corrosion estimation and classification not only in biodiesel medium but also in various environments.

Analysis and Benchmarking of feature reduction for classification under computational constraints

Machine learning is most often expensive in terms of computational and memory costs due to training with large volumes of data. Current computational limitations of many computing systems motivate us to investigate practical approaches, such as feature selection and reduction, to reduce the time and memory costs while not sacrificing the accuracy of classification algorithms. In this work, we carefully review, analyze, and identify the feature reduction methods that have low costs/overheads in terms of time and memory. Then, we evaluate the identified reduction methods in terms of their impact on the accuracy, precision, time, and memory costs of traditional classification algorithms. Specifically, we focus on the least resource intensive feature reduction methods that are available in Scikit-Learn library. Since our goal is to identify the best performing low-cost reduction methods, we do not consider complex expensive reduction algorithms in this study. In our evaluation, we find that at quadratic-scale feature reduction, the classification algorithms achieve the best trade-off among competitive performance metrics. Results show that the overall training times are reduced 61%, the model sizes are reduced 6×, and accuracy scores increase 25% compared to the baselines on average with quadratic scale reduction.

Using Genetic Algorithm Feature Selection to Optimize XGBoost Performance in Australian Credit

To reduce credit risk in credit institutions, credit risk management practices need to be implemented so that lending institutions can survive in the long term. Data mining is one of the techniques used for credit risk management. Where data mining can find information patterns from big data using classification techniques with the resulting level of accuracy. This research aims to increase the accuracy of classification algorithms in predicting credit risk by applying genetic algorithms as the best feature selection method. Thus, the most important feature will be used to search for credit risk information. This research applies a classification method using the XGBoost classifier on the Australian credit dataset, then carries out an evaluation by measuring the level of accuracy and AUC. The results show an increase in accuracy of 2.24%, with an accuracy value of 89.93% after optimization using a genetic algorithm. So, through research on genetic algorithm feature selection, we can improve the accuracy performance of the XGBoost algorithm on the Australian credit dataset.

An Investigation on the Use of Clustering Algorithms for Data Preprocessing in Breast Cancer Diagnosis

Classification algorithms are commonly used as a decision support system for diagnosing many diseases, such as breast cancer. The accuracy of classification algorithms can be affected negatively if the data contains outliers and/or noisy data. For this reason, outlier detection methods are frequently used in this field. In this study, we propose and compare various models that use clustering algorithms to detect outliers in the data preprocessing stage of classification to investigate their effects on classification accuracy. Clustering algorithms such as DBSCAN, HDBSCAN, OPTICS, FuzzyCMeans, and MCMSTClustering (MCMST) were used separately in the data preprocessing stage of the k Nearest Neighbor (kNN) classification algorithm for outlier elimination, and then the results were compared. According to the obtained results, MCMST algorithm was more successful in outlier elimination. The classification accuracy of the kNN + MCMST model was 0.9834, which was the best one, while the accuracy of kNN algorithm without using any data preprocessing was 0.9719.

A subspace aggregating algorithm for accurate classification

A subspace aggregating algorithm for accurate classification

Technical and functional design considerations for a real-world interpretable AI solution for NIR perfusion analysis (including cancer)

Near infrared (NIR) analysis of tissue perfusion via indocyanine green fluorescence assessment is performed clinically during surgery for a range of indications. Its usefulness can potentially be further enhanced through the application of interpretable artificial intelligence (AI) methods to improve dynamic interpretation accuracy in these and also open new applications. While its main use currently is for perfusion assessment as a tissue health check prior to performing an anastomosis, there is increasing interest in using fluorophores for cancer detection during surgical interventions with most research being based on the paradigm of static imaging for fluorophore uptake hours after preoperative dosing. Although some image boosting and relative estimation of fluorescence signals is already inbuilt into commercial NIR systems, fuller implementation of AI methods can enable actionable predictions especially when applied during the dynamic, early inflow-outflow phase that occurs seconds to minutes after ICG (or indeed other fluorophore) administration. Already research has shown that such methods can accurately differentiate cancer from benign tissue in the operating theatre in real time in principle based on their differential signalling and could be useful for tissue perfusion classification more generally. This can be achieved through the generation of fluorescence intensity curves from an intra-operative NIR video stream. These curves are processed to adjust for image disturbances and curve features known to be influential in tissue characterisation are extracted. Existing machine learning based classifiers can then use these features to classify the tissue in question according to prior training sets. The use of this interpretable methodology enables accurate classification algorithms to be built with modest training sets in comparison to those required for deep learning modelling in addition to achieving compliance with medical device regulations. Integration of the multiple algorithms required to achieve this classification into a desktop application or medical device could make the use of this method accessible and useful to (as well as useable by) surgeons without prior training in computer technology. This document details some technical and functional design considerations underlying such a novel recommender system to advance the foundational concept and methodology as software as medical device for in situ cancer characterisation with relevance more broadly also to other tissue perfusion applications.

Supervised Classification Accuracy Assessment Using Remote Sensing and Geographic Information System

Assessing the accuracy of classification algorithms is paramount as it provides insights into reliability and effectiveness in solving real-world problems. Accuracy examination is essential in any remote sensing-based classification practice, given that classification maps consistently include misclassified pixels and classification misconceptions. In this study, two imaginary satellites for Duhok province, Iraq, were captured at regular intervals, and the photos were analyzed using spatial analysis tools to provide supervised classifications. Some processes were conducted to enhance the categorization, like smoothing. The classification results indicate that Duhok province is divided into four classes: vegetation cover, buildings, water bodies, and bare lands. During 2013-2022, vegetation cover increased from 63% in 2013 to 66% in 2022; buildings roughly increased by 1% to 3% yearly; water bodies showed a decrease of 2% to 1%; the amount of unoccupied land showed a decrease from 34% to 30%. Therefore, the classification accuracy was assessed using the approach of comparison with field data; the classification accuracy was about 85%.

Expeditious Dynamic Clustering in Preprocessing for High‐Performance Classification

The accuracy of classification algorithms across different applications is significantly influenced by data preprocessing. A well‐executed data preprocessing phase can notably enhance the outcomes of classification. This research introduces a swift data preprocessing technique characterized by its simplicity, ease of comprehension, and remarkable efficacy in data classification tasks. The algorithm proposed herein streamlines the process of data comprehension, simultaneously ensuring high efficiency in classification outcomes. Moreover, it demonstrates versatility across diverse large datasets. Termed as expeditious dynamic clustering (EDC), this innovative data preprocessing algorithm amalgamates several conceptual algorithms into a cohesive framework. The approach employs a top‐down data clustering technique, focusing on clusters with ascending values (initial clustering phase of EDC) to determine the optimal number of clusters for each feature. This involves comparing member dissimilarity within the feature set. Subsequently, it integrates low‐frequency clusters into the clustering process dynamically to refine the cluster count. This integration selectively combines clusters based on a low‐frequency criterion value, optimizing the clustering of the dataset. The EDC execution method operates without the need for a computational distance function, thereby revolutionizing the clustering paradigm for high‐performance data classification. To assess the effectiveness of data preprocessing methods employing the novel EDC concept, its performance was evaluated with various data classification algorithms, including neural networks and decision trees. The experiments encompassed large datasets featuring diverse data types and classes, totalling 13 datasets. The results showcased strong classification performance and high accuracy. Furthermore, in addition to EDC data preprocessing, appending it to the classification model alongside the aforementioned two models can facilitate feature selection without compromising classification accuracy.

Machine Learning Based Analysis and Prediction of Emotional Expressions in Dance Movements

Abstract Dance movement is a powerful way to convey human emotions, and analyzing and predicting the emotional expression of dance movement through machine learning has become a hotspot in the field of artificial intelligence research nowadays. This paper employs the Seagull optimization algorithm to enhance the SVM classification model, laying the algorithmic groundwork for the research, and refines it to align with the research requirements. The classification of dance movements is accomplished by the nonlinear regression algorithm in the support vector machine regression algorithm, while the task of capturing dance movements is realized by means of Euler angles to describe the orientation, rotation matrices to transform vectors between different coordinate systems, and quaternions to optimize the Euler angles. Finally, this paper analyses and predicts the emotional expression of dance movements using a classification loss model (LSTMBO) and a W-RNN model that incorporates the weights of emotion words. In this paper, tests on the classification algorithm revealed that the algorithm's classification accuracy is above 90% for all datasets used in the research. Moreover, the performance and effectiveness of dance action capture are significantly better than other comparative algorithms. Simultaneously, this paper's algorithm achieves an accuracy of over 80% in predicting emotions expressed through dance movements. Numerous experiments have proven the effectiveness and superiority of the algorithm model in this paper, thereby promoting the research and development of the field.

Evaluating the Accuracy of Classification Algorithms for Detecting Heart Disease Risk

The healthcare industry generates enormous amounts of complex clinical data that make the prediction of disease detection a complicated process. In medical informatics, making effective and efficient decisions is very important. Data Mining (DM) techniques are mainly used to identify and extract hidden patterns and interesting knowledge to diagnose and predict diseases in medical datasets. Nowadays, heart disease is considered one of the most important problems in the healthcare field. Therefore, early diagnosis leads to a reduction in deaths. DM techniques have proven highly effective for predicting and diagnosing heart diseases. This work utilizes the classification algorithms with a medical dataset of heart disease; namely, J48, Random Forest, and Naïve Bayes to discover the accuracy of their performance. We also examine the impact of the feature selection method. A comparative and analysis study was performed to determine the best technique using Waikato Environment for Knowledge Analysis (Weka) software, version 3.8.6. The performance of the utilized algorithms was evaluated using standard metrics such as accuracy, sensitivity and specificity. The importance of using classification techniques for heart disease diagnosis has been highlighted. We also reduced the number of attributes in the dataset, which showed a significant improvement in prediction accuracy. The results indicate that the best algorithm for predicting heart disease was Random Forest with an accuracy of 99.24%.

Development and Validation of a Cyber-Physical System Leveraging EFDPN for Enhanced WSN-IoT Network Security.

In the current digital era, Wireless Sensor Networks (WSNs) and the Internet of Things (IoT) are evolving, transforming human experiences by creating an interconnected environment. However, ensuring the security of WSN-IoT networks remains a significant hurdle, as existing security models are plagued with issues like prolonged training durations and complex classification processes. In this study, a robust cyber-physical system based on the Emphatic Farmland Fertility Integrated Deep Perceptron Network (EFDPN) is proposed to enhance the security of WSN-IoT. This initiative introduces the Farmland Fertility Feature Selection (F3S) technique to alleviate the computational complexity of identifying and classifying attacks. Additionally, this research leverages the Deep Perceptron Network (DPN) classification algorithm for accurate intrusion classification, achieving impressive performance metrics. In the classification phase, the Tunicate Swarm Optimization (TSO) model is employed to improve the sigmoid transformation function, thereby enhancing prediction accuracy. This study demonstrates the development of an EFDPN-based system designed to safeguard WSN-IoT networks. It showcases how the DPN classification technique, in conjunction with the TSO model, significantly improves classification performance. In this research, we employed well-known cyber-attack datasets to validate its effectiveness, revealing its superiority over traditional intrusion detection methods, particularly in achieving higher F1-score values. The incorporation of the F3S algorithm plays a pivotal role in this framework by eliminating irrelevant features, leading to enhanced prediction accuracy for the classifier, marking a substantial stride in fortifying WSN-IoT network security. This research presents a promising approach to enhancing the security and resilience of interconnected cyber-physical systems in the evolving landscape of WSN-IoT networks.

Air Quality Classification Using Extreme Gradient Boosting (XGBOOST) Algorithm

Air pollution is a serious issue caused by vehicle exhaust, industrial factories, and piles of garbage. The impact is detrimental to human health and the environment. To quickly and accurately monitor classification, techniques are used. One efficient and accurate classification algorithm is XGBoost, a development of the Gradient Decision Tree (GDBT) with several advantages, such as high scalability and prevention of overfitting. The parameters used in the classification include (PM10), (PM2,5),(SO2),(CO),(O3) and (NO2). This study aims to classify air quality into three labels or categories: good, moderate, and unhealthy. In the dataset used to experience an imbalance class, to overcome the imbalance class, techniques will be carried out, namely SMOTE, Random UnderSampling, and Random OverSampling, by producing an accuracy of up to 98,61% with the SMOTE technique for class imbalance. Testing the level of accuracy is done by using the Confusion Matrix.TRANSLATE with x EnglishArabicHebrewPolishBulgarianHindiPortugueseCatalanHmong DawRomanianChinese SimplifiedHungarianRussianChinese TraditionalIndonesianSlovakCzechItalianSlovenianDanishJapaneseSpanishDutchKlingonSwedishEnglishKoreanThaiEstonianLatvianTurkishFinnishLithuanianUkrainianFrenchMalayUrduGermanMalteseVietnameseGreekNorwegianWelshHaitian CreolePersian //  TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster PortalBack//

Anatomization of Respiratory Diseases Using Machine Learning

The respiratory system is frequently susceptible to various diseases, with chronic obstructive pulmonary disease (COPD) serving as a notable illustration. COPD is distinguished by an enduring lung ailment characterized by a gradual reduction in lung function over time. Precise prediction of respiratory diseases is of utmost importance, as a failure to do so can lead to fatal consequences. Timely diagnosis plays a pivotal role in reducing mortality rates. In this research, raw spirometry data undergoes a process of feature selection to identify relevant attributes. These selected characteristics are subsequently input into a classification system to distinguish between normal, obstructive, and restrictive cases. The study illustrates how the accuracy of classification algorithms, particularly in the field of machine learning, can be significantly improved through feature selection methods. The suggested study has significantly enhanced the accuracy of categorization using a variety of algorithms, such as Naïve Bayes, Support Vector Machine, Logistic Regression, and K-Nearest Neighbor. Among these algorithms, Logistic Regression emerges as the most accurate classifier in this specific context. This investigation underscores the critical importance of early detection and emphasizes the potential of machine learning techniques in enhancing the accuracy of diagnosing respiratory diseases, particularly COPD, which can have a profound impact on patient outcomes.

Fine-scale characterization of irrigated and rainfed croplands at national scale using multi-source data, random forest, and deep learning algorithms

Knowledge of the extent and distribution of irrigated and rainfed croplands is critical in providing the necessary baseline data for enhancing agricultural efficiency and making informed policy decisions. Accurately identifying and mapping irrigated and rainfed croplands can hasten the attainment of Sustainable Development Goals (SDGs) 1 and 2, aimed at reducing poverty and hunger, respectively. However, traditional methods employed to identify and map cropland areas are expensive and require substantial labour, particularly in extensive environments. As a result, this study presents a comprehensive and spatially explicit methodological framework for identifying and mapping national-scale irrigated and rainfed croplands in South Africa. This framework leverages low-cost earth observation technologies (Sentinel-2 MSI) and employs highly accurate classification algorithms, namely Deep Learning Neural Network (DNN) and Random Forest (RF). The proposed methodology strategically integrates data from multiple sources, including public repositories (e.g., cropland data, evapotranspiration), ongoing research (e.g., land cover maps), and field data, to enhance the accuracy and reliability of the results. The methodology begins by employing a robust random forest model to classify the study area into distinct land cover types. Leveraging the power of a deep learning neural network (DNN), the method accurately distinguishes between irrigated and rainfed croplands in South Africa. The random forest model achieved a notable classification accuracy of 0.77 when identifying the main land-use and land cover types. Meanwhile, the deep learning neural network (DNN) model achieved an accuracy of 0.71 in differentiating rainfed and irrigated croplands at a national scale. These results highlight the effectiveness of the proposed methodology in providing baseline information relevant to crop monitoring, yield forecasting, and understanding agricultural food supply systems. Furthermore, the proposed methodology has the potential to offer timely and accurate information on cropland areas and their extent which could assist in implementing targeted interventions for optimising agricultural productivity. With its potential to be upscaled to other sub-Saharan countries, this methodology enriches agricultural decision-making and plays a vital role in bolstering food security and advancing the attainment of SDGs.

An adaptive selective ensemble algorithm for fault classification

With the aim of improving the classification performance of a single extreme learning machine (ELM) for fault diagnosis, an adaptive selective ensemble classification algorithm is proposed based on the idea of ensemble learning. The proposed algorithm achieves better classification performance than a single model and the selected ELM subnetworks are selected adaptively and the ensemble weights of selected ELM subnetworks are calculated adaptively, which avoids the complex process of manually selecting subnetworks and calculating ensemble weights. First, a regularized error weight adjustment ELM is constructed by introducing regularization parameters and error weight adjustment matrix to a standard ELM, where the error weight adjustment matrix is obtained by the method of adaptive Gaussian kernel density estimation. Then, discrepancy subnetworks are constructed using six different activation functionsand the ensemble weights of subnetworks are obtained adaptively according to the normalized ratio of mean and variance of subnetwork F-scores to achieve the ensemble of subnetworks. Finally, the adaptive selective ensemble classification algorithm is validated using the UCI dataset and experimental acoustic emission signals of gearbox faults. The results show that the adaptive selective ensemble method can improve the stability and accuracy of classification algorithms and the achieved classification accuracy for experimental acoustic emission was 0.9773.