Smith, Joe · Zenodo (CERN European Organization for Nuclear Research) · 2024
<p>The following datasets and code accompany the paper "Astrometric Binary Classification Via Artificial Neural Networks" by Joe Smith, submitted to the ApJ in April 2024.</p>\n<p>The data to train the artificial neural network can be found here: https://zenodo.org/records/4435257. This catalog was derived from <em>Gaia</em> DR3 in El-Badry, K., Rix, H.-W., & Heintz, T. M. 2021, MNRAS, 506, 2269, doi: <a href="https://doi.org/10.1093/mnras/stab323">10.1093/mnras/staab323</a>. <br><br>If one wishes to evaluate or test the general architecture of the model, should one choose to do so, there are two data files that form the training, validation, and test sets containing the astrometric parameters (features) and corresponding binary class (targets) of the input binary candidate, respectively. There are a total of 1,568,966 binary samples:<br>1. TrainDatasetX.csv<br>2. TrainDatasetY.csv<br><br>There are also two code files, one containing the model's weights, architecture, and training configuration, and the other containing the software that produced the developed ANN:<br>1. binaries_prediction_model.keras<br>2. ann_astobinary_model.py</p>\n<p>To make predictions, the binaries_prediction_model.keras file can be utilized with the loaded model.</p>
Cited by 0Open access
Kounadis, Gerasimos · Zenodo (CERN European Organization for Nuclear Research) · 2024
Cited by 0Open access
Fabien Raphel (9421987), Tessa De Korte (9421990), Damiano Lombardi (4352779) et al. · Figshare · 2020
<p>Some concentrations were not used due to the quiescence or noisy signal observation. For each concentration, the LDA classifier returns the average probability for well classified (dotted bars) and misclassified (hatched bars) compounds.</p>
Cited by 0Open access
Dr. Amrinder Kaur · Zenodo (CERN European Organization for Nuclear Research) · 2026
No description provided.
Cited by 0Open access
Dr. Amrinder Kaur · Zenodo (CERN European Organization for Nuclear Research) · 2026
No description provided.
Cited by 0Open access
Kazi Samiul Kader, Md Tareque Hasan Tahsin, Md. Shohrab Hossain et al. · 2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · 2021
Nowadays ransomware attack is one of the most widely used tactics for cyber attacks. It is computationally infeasible to revert the damage done by a ransomware attack. Therefore, it is of utmost importance to identify a program to be ransomware during installation time. In this paper, machine learning binary classification algorithms have been used to identify ransomware through dynamic analysis of several features of ransomware. At first, manual selection of features is analyzed, and later on, we have used the automatic feature selection process using the K best algorithm. Results show that in both cases (manual and automatic selection), we achieved a significant percentage of accuracy to detect ransomware at runtime.
Cited by 2
Monica Maria Mihai, T Filimonova · Artificial Intelligence · 2025
The paper discusses the approach to binary image classification with ResNet based deep learning. Its actuality is the automatic image classification process and subject-the use of the methods of data augmentation and in the improvement of the model accuracy-deep neural networks. The goal of this research was to develop and assess the efficiency of using the pre-trained ResNet network for solving the binary classification problem. Such image preprocessing and implementation for the augmentation method and mixed learning were conducted to optimize the classification process. The experimental results discussed point towards integration in preprocessing methods, dynamic image loading, and computational process optimization that drive substantial growth in the quality of classification, which carries great practical value in further explorations in this area
Cited by 0Open access
Evgenii Chzhen · arXiv (Cornell University) · 2019
In this work we consider a problem of multi-label classification, where each instance is associated with some binary vector. Our focus is to find a classifier which minimizes false negative discoveries under constraints. Depending on the considered set of constraints we propose plug-in methods and provide non-asymptotic analysis under margin type assumptions. Specifically, we analyze two particular examples of constraints that promote sparse predictions: in the first one, we focus on classifiers with $\ell_0$-type constraints and in the second one, we address classifiers with bounded false positive discoveries. Both formulations lead to different Bayes rules and, thus, different plug-in approaches. The first considered scenario is the popular multi-label top-$K$ procedure: a label is predicted to be relevant if its score is among the $K$ largest ones. For this case, we provide an excess risk bound that achieves so called `fast' rates of convergence under a generalization of the margin assumption to this settings. The second scenario differs significantly from the top-$K$ settings, as the constraints are distribution dependent. We demonstrate that in this scenario the almost sure control of false positive discoveries is impossible without extra assumptions. To alleviate this issue we propose a sufficient condition for the consistent estimation and provide non-asymptotic upper-bound.
Cited by 1Open access
Shreelaxmi Shenoy (12981408), Asha K. Rajan (12981411), Muhammed Rashid (10822590) et al. · Figshare · 2022
Cited by 0Open access
Disambiguation In Statistical, Jesús Tomás, Francisco Casacuberta · 2002
In statistical machine translation, there are many source words that can present different translations. The usual approach to disambiguating these words is to use a target language model. These models are based on local phenomena and in many cases are not capable of properly translating some of these words. To deal with this problem, a new approach is proposed that is based on the so-called naive Bayesian classifier. After a process of automatic selection of ambiguous words, an adequate binary feature set that maximizes the information gain is chosen. A Bayesian classifier can be used to choose the most adequate translation of a word, using this feature set. Experimental results on a parallel corpus (approximately 650,000 Spanish-Catalan sentence pairs) show the benefits that the proposed method can achieve.
Cited by 0
Mahwish Ilyas (17118167), Khalid Mahmood Aamir (17118170), Sana Manzoor (17118173) et al. · Figshare · 2023
<div><p>Cancer is a serious public health concern worldwide and is the leading cause of death. Blood cancer is one of the most dangerous types of cancer. Leukemia is a type of cancer that affects the blood cell and bone marrow. Acute leukemia is a chronic condition that is fatal if left untreated. A timely, reliable, and accurate diagnosis of leukemia at an early stage is critical to treating and preserving patients’ lives. There are four types of leukemia, namely acute lymphocytic leukemia, acute myelogenous leukemia, chronic lymphocytic in extracting, and chronic myelogenous leukemia. Recognizing these cancerous development cells is often done via manual analysis of microscopic images. This requires an extraordinarily skilled pathologist. Leukemia symptoms might include lethargy, a lack of energy, a pale complexion, recurrent infections, and easy bleeding or bruising. One of the challenges in this area is identifying subtypes of leukemia for specialized treatment. This Study is carried out to increase the precision of diagnosis to assist in the development of personalized plans for treatment, and improve general leukemia-related healthcare practises. In this research, we used leukemia gene expression data from Curated Microarray Database (CuMiDa). Microarrays are ideal for studying cancer, however, categorizing the expression pattern of microarray information can be challenging. This proposed study uses feature selection methods and machine learning techniques to predict and classify subtypes of leukemia in gene expression data CuMiDa (GSE9476). This research work utilized linear programming (LP) as a machine-learning technique for classification. Linear programming model classifies and predicts the subtypes of leukemia Bone_Marrow_CD34, Bone Marrow, AML, PB, and PBSC CD34. Before using the LP model, we selected 25 features from the given dataset of 22283 features. These 25 significant features were the most distinguishing for classification. The classification accuracy of this work is 98.44%.</p></div>
Cited by 0Open access
Prasanna Date, Wyatt Smith · Scientific Reports · 2024
Quantum computers have the unique ability to operate relatively quickly in high-dimensional spaces-this is sought to give them a competitive advantage over classical computers. In this work, we propose a novel quantum machine learning model called the Quantum Discriminator, which leverages the ability of quantum computers to operate in the high-dimensional spaces. The quantum discriminator is trained using a quantum-classical hybrid algorithm in [Formula: see text] time, and inferencing is performed on a universal quantum computer in [Formula: see text] time. The quantum discriminator takes as input the binary features extracted from a given datum along with a prediction qubit, and outputs the predicted label. We analyze its performance on the Iris and Bars and Stripes data sets, and show that it can attain 99% accuracy in simulation.
Cited by 7Open access
Juan R. Martinez-Rico (18990506), Lourdes Araujo (310347), Juan Martinez-Romo (310346) · Figshare · 2024
<div><p>Disinformation in the medical field is a growing problem that carries a significant risk. Therefore, it is crucial to detect and combat it effectively. In this article, we provide three elements to aid in this fight: 1) a new framework that collects health-related articles from verification entities and facilitates their check-worthiness and fact-checking annotation at the sentence level; 2) a corpus generated using this framework, composed of 10335 sentences annotated in these two concepts and grouped into 327 articles, which we call KEANE (faKe nEws At seNtence lEvel); and 3) a new model for verifying fake news that combines specific identifiers of the medical domain with triplets subject-predicate-object, using Transformers and feedforward neural networks at the sentence level. This model predicts the fact-checking of sentences and evaluates the veracity of the entire article. After training this model on our corpus, we achieved remarkable results in the binary classification of sentences (check-worthiness F1: 0.749, fact-checking F1: 0.698) and in the final classification of complete articles (F1: 0.703). We also tested its performance against another public dataset and found that it performed better than most systems evaluated on that dataset. Moreover, the corpus we provide differs from other existing corpora in its duality of sentence-article annotation, which can provide an additional level of justification of the prediction of truth or untruth made by the model.</p></div>
Cited by 0Open access
Raju Gudla, Satyanarayana Vollala, Ruhul Amin · Communications in computer and information science · 2023
Cited by 0
Jyun‐You Chiang, Yuhlong Lio, Chien-Ya Hsu et al. · Entropy · 2023
When the binary response variable contains an excess of zero counts, the data are imbalanced. Imbalanced data cause trouble for binary classification. To simplify the numerical computation to obtain the maximum likelihood estimators of the zero-inflated Bernoulli (ZIBer) model parameters with imbalanced data, an expectation-maximization (EM) algorithm is proposed to derive the maximum likelihood estimates of the model parameters. The logistic regression model links the Bernoulli probabilities with the covariates in the ZIBer model, and the prediction performance among the ZIBer model, LightGBM, and artificial neural network (ANN) procedures is compared by Monte Carlo simulation. The results show that no method can dominate the other methods regarding predictive performance under the imbalanced data. The LightGBM and ZIBer models are more competitive than the ANN model for zero-inflated-imbalanced data sets.
Cited by 8Open access
Chan-Young Ahn (22683343), Jin-Ha Kim (10300456), Sojung Kim (46675) et al. · Figshare · 2025
<div> Non-Suicidal Self-Injury (NSSI) is a prevalent and complex behavior among adolescents, often linked to negative emotions such as loneliness, anxiety, and emptiness. Traditional self-report and experimental methods rely on autobiographical recall and are therefore vulnerable to bias and low ecological validity. Accordingly, approaches that repeatedly sample NSSI-related feelings and contexts in daily life such as Ecological Momentary Assessment (EMA) are needed. This study aimed to identify emotional predictors of NSSI thoughts among adolescents using machine learning and multilevel logistic regression. The study included 42 adolescents (aged 12–15 years) who had engaged in NSSI in the past year. Participants reported their mood and NSSI behaviors three times daily over a 14-day EMA period via a smartphone application. Predictor variables included depression, anxiety, loneliness, self-anger, anger towards others, shame, and emptiness. A random forest model identified loneliness (feature importance: 0.40), anxiety (0.18), and emptiness (0.14) as the most significant predictors of NSSI thoughts. Multilevel logistic regression confirmed these findings, showing that each one-unit increase in anxiety, loneliness, and emptiness corresponded to a 24%, 19%, and 24% increase in the odds of experiencing NSSI thoughts, respectively. The ICC value of 0.26 indicated substantial between-individual variance, justifying multilevel modeling. However, random effects analysis revealed no significant individual differences, suggesting uniform effects across participants. These findings highlight loneliness as the most influential predictor, emphasizing the need to address social connections in interventions. Combining machine learning with traditional statistical methods enhanced interpretability, providing practical insights for developing tailored, emotion-focused interventions for adolescents engaging in NSSI. </div>
Cited by 0Open access
Dan Liu (108669), Francesca Young (4226095), Kieran D. Lamb (17847545) et al. · Figshare · 2024
<p>This figure separately shows the heatmap of AUC, accuracy, F1 score, sensitivity, specificity, and precision on 15 prokaryotic (A) and 5 eukaryotic host binary classifiers (C), negative samples are selected by <b>strategy 1</b>; ROC curves of 15 prokaryotic hosts (B) and 5 eukaryotic hosts (D) corresponding with heatmap plots A and C; AUC of different taxonomy on prokaryotic (E) and eukaryotic hosts (F) where negative samples are selected using <b>strategy 2</b>.</p>
Cited by 0Open access
Savenko, Oksana, Li, Haoyang · King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) · 2019
SEMI-AUTOMATED BINARY CLASSIFICATION WORKFLOW\n\nMOTIVATION\n\nNowadays, there is a recent call to build a human-independent intelligence which can assist clinicians during medical diagnosis. In our research, we focus on development of a standartized and tunable workflow for the binary classification problem whithin variuos biological signals (EEG, fMRI, NIRS). This workflow can be openly used by others in their own studies, research and clinical practice.\n\nOBJECTIVES\n\n1. Evaluate efficiency of different classification methods on well- known in community datasets\n\n2. Merge produced code into separate workflows for datasets depending on their dimentionality (single-channel, multi- channel, volumetric)\n\nCHALLENGES\n\n1. Absence of default data formating among researchers which requires human intervention.\n\n2. Optimization of the code architecture and workflow parallelization (choosing among a range of preprocessing steps, feature generation and classification methods.\n\nMETHODS\n\nIn the central part of the poster one may see a picture of two best performing on fMRI Star-Plus dataset workflows we have inside our generalized workflow for multi-dimensional data. Below we describe other options we provide the user whithin the project.\n\nPREPROCESSING\n\nFrequency filtering\n\nIndependent Component Analysis\n\nSmoothing (exponentional, rollong mean)\n\nGlobal Signal Regression\n\nFEATURE GENERATION\n\nFast Fourier Transform\n\nSemi-Classical Signal Analysis\n\nUTILIZED CLASSIFIERS\n\nSupport Vector Classifier\n\nLogistic Regression\n\nDecision Tree Classifier\n\nK-Nearest Neighbours\n\nNeural Network\n\nConvolutional Neural Network\n\nCONCLUSIONS\n\nWe tried to include state of the art practics of brain data analysis and include some novel methods like SCSA. Currently the project is still under development but if you findit interesting and prospectively useful for yourself we suggest to pass our tutorial on single-channel data analysis which is a part of the project and explains the methods behind the workflow.
Cited by 0
Xiaoli Yang (314226), Jiayi Zhou (2228527), Chenchen Wang (12690) et al. · Figshare · 2025
<div> Alzheimer’s disease (AD) is a common type of dementia, with mild cognitive impairment (MCI) being a key precursor. Early MCI diagnosis is crucial for slowing AD progression, but distinguishing MCI from normal controls (NC) is challenging due to subtle imaging differences. Furthermore, differentiating early MCI (EMCI) from late MCI (LMCI) is also important for interventions. This study proposes a deep learning-based approach using a weighted probability-based ensemble method to integrate results from three-dimensional residual networks (3D ResNet). (1) This study employs 3D ResNet-18, 3D ResNet-34, and 3D ResNet-50 architectures with the Convolutional Block Attention Module (CBAM). The attention mechanism enhances performance by helping the model focus on pertinent information. Data augmentation techniques are applied to address limited data and improve accuracy. (2) To overcome the limitation of the individual convolutional neural network (CNN), an ensemble learning method is adopted. The method assigns weights to each 3D CNN model based on prediction accuracy and integrates them to obtain the final result. Our method achieves accuracy of 94.87%, 92.31%, 95.49%, and 95.97% for MCI vs. NC, MCI vs. AD, EMCI vs. LMCI, and NC vs. EMCI vs. LMCI vs. AD, respectively. The results demonstrate the effectiveness of our method for AD diagnosis. </div>
Cited by 0Open access
Noriaki Takemura (1991890), Yuya Shinkawa (6593705), Kazuo Ishii (683499) · Figshare · 2024
<div><p>We established a diagnostic method for cerebral white matter lesions using MRI images and examined the relationship between the MRI images and the medical checkup data. There were approximately 25 MRI images for each patient’s head, from the top of the head to near the eyes. To order these images, we defined the unit of axial for convenience. We varied conditions, such as the location and extent of the images to be loaded, into a convolutional neural network model and verified the changes in discrimination performance on the test data. Co-occurrence network diagrams were also used to determine the relationship between the grade of cerebral white matter lesions and the biochemical test items, which were treated as categorical variables, the progression of cerebral white matter lesions, and patient health status. The convolutional neural network showed the highest discrimination performance when the images were loaded into the model with 80 pixels per side, axial from 9 to 15, along with FLAIR and T1-weighted images. The area under the curve for each grade was 0.9814 for grade 0, 0.9800 for grade 1, 0.9905 for grade 2, 0.9977 for grade 3, and 0.9998 for grade 4. In the co-occurrence network diagram, patients with no or mild cerebral white matter lesions, such as grade 0 and grade 1, had near normal blood pressure, whereas grade 2 patients were closer to (isolated) systolic hypertension. This indicates that patients with higher-grade cerebral white matter lesions tend to experience more severe hypertension.</p></div>
Cited by 0Open access