Accurate Training Data Research Articles

Modeling the impact of resource allocation decisions on genomic prediction using maize multi‐environment data

AbstractIn a hybrid maize (Zea mays L.) breeding program that utilizes genomic selection, resource allocation used in phenotypic data acquisition must be balanced between population size, number of environments, and the number of testers used for generating hybrids. Plant breeders evaluate newly developed inbred lines using multi‐environment trials to account for genotype‐by‐environment interaction effects. The replication of hybrids across environments in these trials impacts the training data accuracy for developing genomic prediction models. This study examined the impact of resource allocation scenarios on genomic prediction accuracy using a multi‐environment trial dataset generated using inbred lines crossed to multiple testers. A total of 369 Stiff Stalk double haploid lines from a synthetic mapping population were testcrossed to three non‐Stiff Stalk inbred lines as testers, PHZ51, PHK76, and PHP02, and evaluated across 34 environments by the Genomes to Fields Initiative in 2020 and 2021. Resource allocation scenarios significantly impacted site‐specific genomic prediction accuracy for unobserved hybrids in unobserved environments. A training set with three to five environments that had the highest quality data produced similar prediction accuracy as data from 10 random environments for both observed and unobserved hybrids, indicating that strong prediction models can be built with a limited set of environments for both grain yield and plant height. We found that resource‐efficient prediction models that use data from one tester and three to five environments can effectively conduct selection of untested hybrids and in untested environments. Public research programs are often limited in testing capacity, and this study provides support for genomic selection in resource‐limited breeding programs.

A feature selection method for overlapping peaks in vibrational spectroscopy using nonnegatively constrained classical least squares

Chemometric models for multicomponent mixture analysis are reliant upon representative and accurate training data. However, the required amount of training data can increase exponentially with the number of constituents. Shifting spectral baselines and changing process objectives may necessitate recurring calibration data collection. Furthermore, all possible constituents may not be known prior to analysis. Here, we introduce a preprocessing procedure that reduces the burden of collecting extensive calibration datasets by filtering out non-target species (species that are not part of the calibration data) in real-time. The method, nonnegatively constrained classical least squares (NCCLS), utilizes a spectral nonnegativity constraint on non-target species to remove them from mixture spectra. The preprocessing method is physically motivated, does not rely on time-series data, and can operate in real-time. NCCLS is compared to established methods using in silico data and an experimental dataset comprised of Raman spectra and attenuated total reflectance - Fourier transform infrared spectra.

ANALISIS SENTIMEN SOSIAL MEDIA TWITTER TERKAIT TABUNGAN PERUMAHAN RAKYAT (TAPERA) DENGAN NAÏVE BAYES

The advancement of technology has brought significant changes in various aspects of life, including how people interact and express their opinions on social media. This study aims to analyze the sentiment of conversations on Twitter regarding the government-initiated Housing Savings Program (TAPERA). Using the Naïve Bayes classification method, data was collected through the Google Collab platform and processed using the tweet-harvest library, successfully gathering 1,800 tweets that met the search criteria. The data preprocessing stage included cleaning and manual sentiment labeling to obtain accurate training data. The analysis results show that out of 720 tested tweets, 473 tweets had negative sentiment (65.69%) and 247 tweets had positive sentiment (34.31%). The Naïve Bayes model used in this study demonstrated good performance with an accuracy of 84.17%, precision for the negative class at 88.71%, recall for the negative class at 88.60%, precision for the positive class at 78.54%, and recall for the positive class at 76.08%. The conclusion of this study is that the Naïve Bayes method is effective in classifying public sentiment towards the TAPERA program, providing important insights for relevant parties in evaluating and improving the program's effectiveness.

Klasifikasi Sel Tumor Payudara Menggunakan Algoritma Support Vector Machine (SVM)

Cancer is a large group of diseases that can begin in almost any organ or tissue of the body when abnormal cells grow uncontrollably, beyond their normal limits to invade adjacent parts of the body and/or spread to other organs. There is a lot of information about breast cancer that can be accessed easily. Information about breast cancer can be processed with machine learning. Machine learning can discover new meaningful correlations, patterns and trends by sifting through large amounts of data stored in repositories, using pattern recognition technology and statistical and mathematical techniques. The purpose of this research is to determine the value of the accuracy of the SVM model on training data and testing data; and to determine the precision value of the SVM model on training data and testing data. Wisconsin Breast Cancer (WBC) data available in the UCI Machine Learning Repository. The data have been processed using the Python programming language with a support vector machine (SVM) modeling algorithm. The results of this research indicate that the value of accuracy in training data was equal to , the value of accuracy in testing data was equal to , and the value of precision in the SVM model algorithm was obtained as large as for training data and as large as for data testing.

Classification of Marine Fish Based on Image Using Convolutional Neural Network Algorithm and VGG16

Marine fish are one of the many natural resources that frequently consumed by people. However, several types of marine fish are prohibited from consumption due to being nearly extinct. Additionally, some fish species contain high levels of mercury that can be harmful to human if consumed. Because of the large number of marine fish species, it becomes challenging to identify them without knowledge of fisheries. Moreover, computers have become highly advanced devices that facilitate various human activities. This advancement allows for the creation of systems capable of processing information from images, known as image classification. There are numerous methods that can be employed in designing an image classification system, one of which is transfer learning. This study was aimed to design an image classification system using the transfer learning method with a pre-trained VGG16 model and Convolutional Neural Network algorithm. The research results showed a training data accuracy of 100% and a validation data accuracy of 99.3%, with an overall accuracy of 84% and a loss value of 0.6591.

Enhancing coastal water body segmentation with Landsat Irish Coastal Segmentation (LICS) dataset

Ireland’s coastline, a critical and dynamic resource, is facing challenges such as erosion, sedimentation, and human activities. Monitoring these changes is a complex task we approach using a combination of satellite imagery and deep learning methods. However, limited research exists in this area, particularly for Ireland. This paper presents the Landsat Irish Coastal Segmentation (LICS) dataset, which aims to facilitate the development of deep learning methods for coastal water body segmentation while addressing modelling challenges specific to Irish meteorology and coastal types. The dataset is used to evaluate various automated approaches for segmentation, with U-NET achieving the highest accuracy of 95.0% among deep learning methods. Nevertheless, the Normalised Difference Water Index (NDWI) benchmark outperformed U-NET with an average accuracy of 97.2%. The study suggests that deep learning approaches can be further improved with more accurate training data and by considering alternative measurements of erosion. The LICS dataset and code are freely available to support reproducible research and further advancements in coastal monitoring efforts.

Towards consistency in pediatric brain tumor measurements: Challenges, solutions, and the role of artificial intelligence-based segmentation.

MR imaging is central to the assessment of tumor burden and changes over time in neuro-oncology. Several response assessment guidelines have been set forth by the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working groups in different tumor histologies; however, the visual delineation of tumor components using MRIs is not always straightforward, and complexities not currently addressed by these criteria can introduce inter- and intra-observer variability in manual assessments. Differentiation of non-enhancing tumors from peritumoral edema, mild enhancement from absence of enhancement, and various cystic components can be challenging; particularly given a lack of sufficient and uniform imaging protocols in clinical practice. Automated tumor segmentation with artificial intelligence (AI) may be able to provide more objective delineations, but rely on accurate and consistent training data created manually (ground truth). Herein, this paper reviews existing challenges and potential solutions to identifying and defining subregions of pediatric brain tumors (PBTs) that are not explicitly addressed by current guidelines. The goal is to assert the importance of defining and adopting criteria for addressing these challenges, as it will be critical to achieving standardized tumor measurements and reproducible response assessment in PBTs, ultimately leading to more precise outcome metrics and accurate comparisons among clinical studies.

Critical Risk Assessment, Diagnosis, and Survival Analysis of Breast Cancer.

Breast cancer is the most prevalent type of cancer in women. Risk factor assessment can aid in directing counseling regarding risk reduction and breast cancer surveillance. This research aims to (1) investigate the relationship between various risk factors and breast cancer incidence using the BCSC (Breast Cancer Surveillance Consortium) Risk Factor Dataset and create a prediction model for assessing the risk of developing breast cancer; (2) diagnose breast cancer using the Breast Cancer Wisconsin diagnostic dataset; and (3) analyze breast cancer survivability using the SEER (Surveillance, Epidemiology, and End Results) Breast Cancer Dataset. Applying resampling techniques on the training dataset before using various machine learning techniques can affect the performance of the classifiers. The three breast cancer datasets were examined using a variety of pre-processing approaches and classification models to assess their performance in terms of accuracy, precision, F-1 scores, etc. The PCA (principal component analysis) and resampling strategies produced remarkable results. For the BCSC Dataset, the Random Forest algorithm exhibited the best performance out of the applied classifiers, with an accuracy of 87.53%. Out of the different resampling techniques applied to the training dataset for training the Random Forest classifier, the Tomek Link exhibited the best test accuracy, at 87.47%. We compared all the models used with previously used techniques. After applying the resampling techniques, the accuracy scores of the test data decreased even if the training data accuracy increased. For the Breast Cancer Wisconsin diagnostic dataset, the K-Nearest Neighbor algorithm had the best accuracy with the original dataset test set, at 94.71%, and the PCA dataset test set exhibited 95.29% accuracy for detecting breast cancer. Using the SEER Dataset, this study also explores survival analysis, employing supervised and unsupervised learning approaches to offer insights into the variables affecting breast cancer survivability. This study emphasizes the significance of individualized approaches in the management and treatment of breast cancer by incorporating phenotypic variations and recognizing the heterogeneity of the disease. Through data-driven insights and advanced machine learning, this study contributes significantly to the ongoing efforts in breast cancer research, diagnostics, and personalized medicine.

Machine Learning-Based Prediction of Elastic Properties Using Reduced Datasets of Accurate Calculations Results

In this paper, the applicability of machine learning for predicting the elastic properties of binary and ternary bcc Ti and Zr disordered alloys with 34 different doping elements is explored. The original dataset contained 3 independent elastic constants, bulk moduli, shear moduli, and Young’s moduli of 1642 compositions calculated using the EMTO-CPA method and PAW-SQS calculation results for 62 compositions. The architecture of the system is made as a pipeline of a pair of predicting blocks. The first one took as the input a set of descriptors of the qualitative and quantitative compositions of alloys and approximated the EMTO-CPA data, and the second one took predictions of the first model and trained on the results of the PAW-SQS calculations. The main idea of such architecture is to achieve prediction accuracy at the PAW-SQS level, while reducing the resource intensity for obtaining the training set by a multiple of the ratio of the training subsets sizes corresponding to the two used calculation methods (EMTO-CPA/PAW-SQS). As a result, model building and testing methods accounting for the lack of accurate training data on the mechanical properties of alloys (PAW-SQS), balanced out by using predictions of inaccurate resource-effective first-principle calculations (EMTO-CPA), are demonstrated.

Optimising Cataract Detection in Fundus Images through EfficientNet-Based Classification

Turbidity of the lens of the eyeball that causes blindness or loss of vision is known as a cataract. By diagnosing the causes and symptoms of cataracts, early detection helps patients in prevention and treatment. The purpose of the research was to classify the image of the fundus into two classes: normal and cataract. The study also looked at how the optimizers for stochastic gradient descent, adaptive moment estimation, root mean square propagation, adaptive gradient algorithm, adaptive delta, and Nesterov-accelerated adaptive moment estimation stacked up against each other. We used the EfficientNet architecture in CNN and preprocessed the normal fundus and cataract fundus images by dividing each into training data (N = 80) and validation data (N = 20) from the Kaggle repository. We added test data from the normal fondus image (N =20) to see the accuracy of the results. We get 100% accuracy of training data, 87% and 77% validation data, and 100% and 95% test data.

Improved power quality based PVDG system using different optimised MPPT controllers

The characteristic curve of photovoltaic (PV) modules is nonlinear due to environmental influences. The maximum quantity of energy can only be taken from the nonlinear angle of the solar system at one exact moment. The primary function of an MPPT (maximum power point tracking) controller in a PV system is to extract maximum power point (MPP) from solar panels. In this paper, an enhanced MPPT approach using different optimization techniques is suggested for PV systems. The Fuzzy logic controller (FLC), Whale Optimization Algorithm(WOA), and Modified Grey Wolf Optimization algorithm (MGWO) are presented for the MPPT controller. Among all methods, the MGWO technique is one of the best at determining the MPP in solar systems because of its quick response and low fluctuations. Accurate training data is one of the biggest challenges in developing an effective MGWO. The irradiance and temperature are taken into consideration as input variables, and the optimal voltages are optimized as an output variable using the MGWO algorithm. Matlab/Simulink simulations are run to verify the suggested model’s suggested tracking effectiveness. To ensure accurate results, simulations are run under various climatic conditions. The simulation result shows that the proposed method operates correctly in a variety of climatic conditions efficiently.

Fibre orientation atlas guided rapid segmentation of white matter tracts.

Fibre tract delineation from diffusion magnetic resonance imaging (MRI) is a valuable clinical tool for neurosurgical planning and navigation, as well as in research neuroimaging pipelines. Several popular methods are used for this task, each with different strengths and weaknesses making them more or less suited to different contexts. For neurosurgical imaging, priorities include ease of use, computational efficiency, robustness to pathology and ability to generalise to new tracts of interest. Many existing methods use streamline tractography, which may require expert neuroimaging operators for setting parameters and delineating anatomical regions of interest, or suffer from as a lack of generalisability to clinical scans involving deforming tumours and other pathologies. More recently, data-driven approaches including deep-learning segmentation models and streamline clustering methods have improved reproducibility and automation, although they can require large amounts of training data and/or computationally intensive image processing at the point of application. We describe an atlas-based direct tract mapping technique called 'tractfinder', utilising tract-specific location and orientation priors. Our aim was to develop a clinically practical method avoiding streamline tractography at the point of application while utilising prior anatomical knowledge derived from only 10-20 training samples. Requiring few training samples allows emphasis to be placed on producing high quality, neuro-anatomically accurate training data, and enables rapid adaptation to new tracts of interest. Avoiding streamline tractography at the point of application reduces computational time, false positives and vulnerabilities to pathology such as tumour deformations or oedema. Carefully filtered training streamlines and track orientation distribution mapping are used to construct tract specific orientation and spatial probability atlases in standard space. Atlases are then transformed to target subject space using affine registration and compared with the subject's voxel-wise fibre orientation distribution data using a mathematical measure of distribution overlap, resulting in a map of the tract's likely spatial distribution. This work includes extensive performance evaluation and comparison with benchmark techniques, including streamline tractography and the deep-learning method TractSeg, in two publicly available healthy diffusion MRI datasets (from TractoInferno and the Human Connectome Project) in addition to a clinical dataset comprising paediatric and adult brain tumour scans. Tract segmentation results display high agreement with established techniques while requiring less than 3 min on average when applied to a new subject. Results also display higher robustness than compared methods when faced with clinical scans featuring brain tumours and resections. As well as describing and evaluating a novel proposed tract delineation technique, this work continues the discussion on the challenges surrounding the white matter segmentation task, including issues of anatomical definitions and the use of quantitative segmentation comparison metrics.

Simulation and forecasting of power by energy harvesting method in photovoltaic panels using artificial neural network

Heat is an important efficiency reducing factor in photovoltaic systems. Although many studies in the literature are related to the removal of waste heat from photovoltaic panels, the disadvantages such as installation and maintenance of cooling systems should not be forgotten. A study has shown that with a new approach, energy can be produced with the method of energy harvesting from waste heat. The results of the study were limited to a geographical region and climatic conditions in Aksaray, Turkey. In this article, the results of the study, which was limited to a region, were extended using the finite element method analysis and the artificial neural network model. Ten different cases were determined and temperature gradient was found by finite element analysis. The forecasting algorithm was developed with artificial neural network and estimates the harvestable power based on the temperature gradient. The accuracy of the algorithm was tested with the MSE and nRMSE statistical metrics which were calculated as 59.1423 mW and 13.6189 %, respectively. The training data accuracy of the network was 0.93987 and the combined accuracy was 0.94364. The results of this study are important to be a reference for researchers who want to establish a photovoltaic panel energy harvesting system.

Beyond 10log10M array gain: A beamforming method under non-Gaussian noise and multi-sources

Recently, deep learning techniques have been applied in the field of direction of arrival (DOA) to enhance beamforming in various practical applications, such as traffic positioning and hydro-acoustic detection. However, the effectiveness of these algorithms relies heavily on the availability of accurate training data that closely resembles real-world data, which can be challenging to obtain, particularly in hydro-acoustic environments. This is primarily due to the limited array gain (AG) and the constant fluctuations in ambient noise. Additionally, the presence of non-Gaussian noise in the background further complicates the process of identifying the desired signal, and it is worth noting that state-of-the-art deep learning methods have a limitation in detecting up to four sources. To address these challenges, we propose a novel method that employs a diagonal beam spectrum (DBS) feature to suppress non-Gaussian noise and enhance array gain. By incorporating DBS, our method surpasses the theoretical 10logM array gain and achieves an impressive 25logM array gain, while effectively detecting signals as low as -38dB (where M denotes the number of sensors). We also employ SA-U-NET, an image edge detection network based on DBS, to detect more than four sound sources and optimize angular positioning. The experiments focus on accuracy and array gain improvements of algorithms. Our proposed method achieves up to 91.67% correctness and 35dB array gain (i.e., 4 times better than the next best baseline) in experiments compared to other methods, demonstrating the potential of DBS and SA-U-NET.

Posture Estimation of Curve Running Motion Using Nano-Biosensor and Machine Learning

Curve running is a common form of training and competition. Conducting research on posture estimation during curve running can provide more accurate training and competition data for athletes. However, due to the unique nature of curve running, traditional posture estimation methods neglect the temporal changes in athlete posture, resulting in a decrease in estimation accuracy. Therefore, a posture estimation method for curve running motion using nano-biosensor and machine learning is proposed. First, the motion parameters of humans are collected by nano-biosensor, and the posture coordinates are obtained preliminarily. Second, the posture coordinates are established according to the human motion parameters, and the curve running posture data is obtained and filtered to obtain more accurate data. Finally, the Bayesian network in machine learning is used to continuously track the posture, and a nonlinear equation is established to fuse the posture angle obtained by the sensor and the posture tracked by the Bayesian network, to realize the posture estimation of curve running motion. The results show that the proposed estimation method has a good motion posture estimation effect, and the hip joint estimation error, knee joint estimation error and ankle joint estimation error are all less than 5°, and the endpoint displacement estimation offset rate is less than 2%. It can realize accurate motion posture estimation of curve running motion, and has important application value in the field of track training.

Objective satellite methods including AI algorithms reviewed for the tenth International workshop on tropical cyclones (IWTC-10)

Here we explore the latest four years (2019–2022) of using satellite data to objectively analyze tropical cyclones (TC) and issue recommendations for improved analysis. We first discuss new methods of direct retrieval from SAR and geostationary imagers. Next, we survey some of the most prominent new techniques in AI and discuss their major capabilities (especially accuracy in nonlinear TC behavior, characterization of model uncertainty and creation of synthetic satellite imagery) and limitations (especially lack of transparency and limited amount of training data). We also identify concerns with biases and unlabeled uncertainties in the Best Track records as being a first-order limitation for further progress in objective methods. The article concludes with recommendations to improve future objective methods, especially in the area of more accurate and reliable training data sets.

Predict2Protect: Machine Learning Web Application in Early Detection of Heart Disease.

Across the world, there are few universal scenarios, but the pain of losing a loved one to heart disease is an exception and a reality shared by millions every year. Heart disease is the greatest killer in society today, and one prevalent root of this issue is untimely diagnosis, often caused by unsustainable costs and lack of accessible healthcare for underserved populations. Recognizing these disparities, the goal of this project was to create an easily available application and interface for all that accurately indicates one's risk of heart disease. To address this, a machine learning model, Predict2Protect, was built in Python. An open-source dataset compiled of 1025 patients of diverse backgrounds was scaled, adjusted to include inquiries answerable by patients, and split into 75% for training, 15% for validation, and 25% for testing. Four models were tested with the hypothesis that if the RandomForestClassifier was used, it would have the highest validity. This was not supported, as the DecisionTree model had a 100% accuracy for training data and 95% for test data. Through the application software Streamlit, this program was processed into a web application that is now found in browser extensions. The application reports the risk of one having heart disease with a 95% accuracy and describes the risk percentage of developing heart disease within the next year. With a simple interface and high accuracy, Predict2Protect aims to provide a view into one's health with the goals of accessible heart disease prediction and early treatment for patients around the world.

Inter-rater Reliability and Cost in Pricing for Creating Dataset Focused on Mediolateral Oblique View in Mammography

The purpose of this study was to assess inter-rater reliability and workload for creating accurate training data in the clinical evaluation of mammographic positioning for deep learning. A total of 107 mammographic images without lesions were labeled by two certified radiologic technologists in seven items: six clinical image evaluation criteria in positioning and breast tissue density. The kappa coefficient was calculated as an indicator of interrater reliability. Furthermore, the labeling cost per image was calculated based on labeling time and salary for the technologists. The kappa coefficients were 0.71 for inframammary fold, 0.43 for nipple in profile, 0.45 for great pectoral muscle, 0.10 for symmetrical images, and 0.61 for retromammary fat. No significant difference was found in the coefficients of spread of breast tissue. The cost per image was calculated at 11.0 yen. The inter-rater reliability for the inframammary fold, nipple in profile, great pectoral muscle, and retromammary fat ranged from "moderate" to "substantial." The reliability for symmetrical images was "slight," indicating the need for a consensus among evaluators during labeling. The labeling cost was equivalent to or higher than that of existing services.

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications.

This study examined if occluded joint locations, obtained from 2D markerless motion capture (single camera view), produced 2D joint angles with reduced agreement compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias and limits of agreement for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane limits of agreement accounted for 35-46% of total range of motion at the hip and knee, Bland-Altman bias and limits of agreement (-4.6-1.6 ± 3.7-4.2˚) were actually similar to previously reported marker-based error values. This was not true for the ankle, where the limits of agreement (± 12˚) were still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing methods for creating anatomically accurate markerless training data using marker-based motion capture data.

Pneumonia Classification Based on GLCM Features Extraction using K-Nearest Neighbor

<p class="Abstract">Pneumonia has been detected using Machine learning. The stages in this study began with preprocessing in 4 stages: resizing, cropping, filtering using a high pass filter, and Adaptive Histogram Equalization. The feature extraction process continued with 22 Gray Level Co-occurrence Matrix (GLCM) features and classification using K-Nearest Neighbor (KNN). The image used was 150 data sets for training on the classification of 3 classes with a ratio of 50:50:50 while training on two classes was 50 bacterial pneumonia and 50 viral pneumonia. The most optimal training data accuracy results were obtained using the angle direction on the GLCM, namely 135o with the KNN classification (k = 3). For the classification of two classes Using 40 data sets, an accuracy of 91% was obtained, while testing for three classes with 60 data sets was 83.3%.</p>