Traditional Classification Research Articles

A task-dependent analysis of closed vs. open and fine vs. gross motor skills in handedness

ABSTRACT The traditional classifications of motor skills nature (open vs closed; fine vs gross) have not been considered in handedness investigations. Instead, previous research focused on comparing complex vs less complex motor behaviour, leaving a gap in the literature. We compared manual preference between different motor skill characteristics, namely: fine and closed (FC), gross and closed (GC) and gross and open (GO) tasks. The hand preference was assessed with the Global Lateral Preference Inventory in four hundred and forty participants (244 women) aged from 18 to 59 years old. By assessing the degree and direction of handedness in different motor skills, our results showed a stronger lateralization pattern for FC motor skills as compared to GC and GO, with GO also being less lateralized than GC. Our results expand those of previous investigations that used the motor skill complexity definitions by showing how handedness can also be modulated by the interaction between classic motor skills classifications. Future research should consider fine vs. gross and open vs. closed classifications when selecting tasks for analysis of asymmetries of preference.

H-QNN: A Hybrid Quantum–Classical Neural Network for Improved Binary Image Classification

Image classification is an important application for deep learning. With the advent of quantum technology, quantum neural networks (QNNs) have become the focus of research. Traditional deep learning-based image classification involves using a convolutional neural network (CNN) to extract features from the image and a multi-layer perceptron (MLP) network to create the decision boundaries. However, quantum circuits with parameters can extract rich features from images and also create complex decision boundaries. This paper proposes a hybrid QNN (H-QNN) model designed for binary image classification that capitalizes on the strengths of quantum computing and classical neural networks. Our H-QNN model uses a compact, two-qubit quantum circuit integrated with a classical convolutional architecture, making it highly efficient for computation on noisy intermediate-scale quantum (NISQ) devices that are currently leading the way in practical quantum computing applications. Our H-QNN model significantly enhances classification accuracy, achieving a 90.1% accuracy rate on binary image datasets. In addition, we have extensively evaluated baseline CNN and our proposed H-QNN models for image retrieval tasks. The obtained quantitative results exhibit the generalization of our H-QNN for downstream image retrieval tasks. Furthermore, our model addresses the issue of overfitting for small datasets, making it a valuable tool for practical applications.

Comparative Analysis of CNN Algorithms for Mushroom Classification with Proposed Lightweight CNN Model

The classification of mushroom species presents significant ecologic and health-related challenges; advancement in classification techniques is required to gain reliable identifications. This study aims to explain a methodology that was devised and evaluated in the development of a novel, lightweight Convolutional Neural Network (CNN) designed specifically for the task of mushroom classification. The paper provides a custom CNN model that is computationally cost-effective and capable of high-precision classification, fit for real-time usage. Hence, the proposed model was evaluated on this dataset of curated mushroom images with traditional classifiers and state-of-the-art CNN architectures, such as EfficientNet-B7, ResNet50, InceptionV3, and MobileNetV2. The custom model is depth-wise separations engineered in such a way that while they reduce the computational load, they don't compromise the effectiveness of the model. The custom model achieved a test score of 0.68, which is moderate compared to more established models such as EfficientNet-B7 or ResNet50. This approach helps the model function effectively even on platforms having low computational resources. A comprehensive evaluation reveals that a custom CNN has reasonable accuracy in the identification of different mushroom species vis-à-vis existing models, but also significantly lightens the classification process.

Computational Approaches for Anxiety and Depression: A Meta- Analytical Perspective

INTRODUCTION: Psychological disorders are a critical issue in today’s modern society, yet it remains to be continuously neglected. Anxiety and depression are prevalent psychological disorders that persuade a generous number of populations across the world and are scrutinized as global problems. METHODS: The three-step methodology is employed in this study to determine the diagnosis of anxiety and depressive disorders. In this survey, a methodical review of ninety-nine articles related to depression and anxiety disorders using different traditional classifiers, metaheuristics and deep learning techniques was done. RESULTS: The best performance and publication trend of traditional classifiers, metaheuristic and deep learning techniques have also been presented. Eventually, a comparison of these three techniques in the diagnosis of anxiety and depression disorders has been appraised. CONCLUSION: There is further scope in the diagnosis of anxiety disorders such as social anxiety disorder, phobia disorder, panic disorder, generalized anxiety, and obsessive-compulsive disorders. Already, there has been a lot of work has been done on conventional approaches to the prognosis of these disorders. So, there is need to need to scrutinize the prognosis of depression and anxiety disorders using the hybridization of metaheuristic and deep learning techniques. Also, the diagnosis of these two disorders among academic fraternity using metaheuristic and deep learning techniques need to be explored.

Graph classification using high-difference-frequency subgraph embedding

With the rapid growth of big data analysis, graphs have become an important data structure in relationship extraction and learning. However, the complexity of graph structure increases the difficulty of downstream learning tasks, e.g., graph classification. For example, some traditional graph classification methods rely on the attributes of nodes and edges; the attributes may be incomplete or missing in large-scale graph datasets, e.g., online social networks and knowledge graphs. Focusing on the node-level features overlooks the global characteristics, leading to decreased classification accuracy. This paper proposes a novel graph classification method based on the subgraph-level feature the high-difference-frequency subgraph. We measure the difference in subgraph appearing frequency and use the high difference frequency subgraphs as features in graph learning and classification. The experiments demonstrate that the proposed method outperforms the state-of-the-art graph classification methods.

Utilizing Large Language Models to Illustrate Constraints for Construction Planning

Effective construction project planning relies on addressing constraints related to materials, labor, equipment, and others. Planning meetings are typical venues for stakeholders to identify, communicate, and remove constraints. However, a critical gap exists in lacking an automated approach to identify, classify, analyze, and track constraint discussions during onsite planning meetings. Therefore, this research aims to 1. develop a natural language processing model to classify constraints in meeting discussions; 2. uncover the discussion patterns of managers and foremen regarding various constraints; and 3. extract the root causes for constraints, evaluate their impacts, and prepare managers to develop practical solutions for constraint removal. This research collected meeting transcripts from 94 onsite planning meetings of a building project, spanning 263,836 words. Next, this research leveraged a general pretrained transformer (GPT) to segment discussion dialogs into topics. A Bidirectional Encoder Representations from Transformers (BERT)-based model was developed to categorize constraint types for each topic. The constraint patterns among meeting attendees were assessed. Furthermore, a GPT-based tool was devised to track root causes, impacts, and solutions for various constraints. Test results revealed an 8.8% improvement in constraint classification accuracy compared with the traditional classification model. An occupational characteristic in constraint discussion was observed in that the management team tended to balance their focus on various constraints, while foremen concentrated on more practical issues. This research contributes to the body of knowledge by leveraging language models to analyze construction planning meetings. The findings facilitate project managers in establishing constraint logs for diagnosing and prognosticating planning issues.

Application of Machine Learning in Identifying Premature Aging

Previously pathological ageing is known to be mainly associated with the development of cardiovascular disease, which is caused by a combination of socioeconomic, metabolic, behavioural, and environmental risk factors. These include sex differences, age, high blood pressure, obesity, low physical activity, smoking, heavy alcohol consumption, high cholesterol and glucose levels, and diabetes mellitus. All processes occurring in the human body are reflected in biochemical and immunological analyses, which may be markers of early cardiovascular aging. The authors investigated correlations between social factors such as education, work, gender, family life, disability, physical activity, smoking and alcohol, and clinical findings such as coronary heart disease (CHD), postinfarct cardiosclerosis (PICS), chronic heart failure (CHF), diabetes mellitus (DM), body mass index (BMI), glucose levels, total cholesterol (TC) and blood pressure (BP) in older individuals. The authors implemented the basic model using R programming language, RStudio version 2023.09.0+463 on a device running MacBook Air M1, 8 GB RAM to identify the association between clinical data and social life. Also, two mathematical models (1)-(3) were proposed to calculate the correlation in combination with traditional machine learning classifiers between clinical data (biomarkers) and the social life of a patient in the age group of 60-74 years, 75-89 years and 90 and above.

Identification of damage states of load-bearing rocks using infrared radiation monitoring methods

The online identification of rock damage states is crucial for safety monitoring in geotechnical and mining engineering. By analyzing spatiotemporal evolution patterns of infrared radiation in various rock damage states, we established the first infrared temperature field dataset for rock damage state identification. We then constructed a deep convolutional neural network, RESD-CNN, and performed its training and optimization. Results showed that infrared radiation patterns of different rock samples exhibit similarities. RESD-CNN achieved outstanding performance in identifying rock damage states with metrics of ACC 99.04%, Precision 99.39%, Recall 99.52%, and F1-score 99.46% on the validation set. Generalization tests on datasets of different rock types revealed that RESD-CNN significantly outperformed traditional classification methods, demonstrating the feasibility of infrared radiation technology for intelligent coal rock damage identification. This research provides a crucial foundation for developing online identification and early warning systems for rock damage evolution in engineering.

Retail category management under shelf-space dependent demand: The effectiveness of category captainship

Category captainship is a retail category management practice where the retailer delegates certain category decisions to a vendor, known as the category captain, to leverage the vendor’s market expertise and reduce the retailer’s workload in managing the category. We examine the effectiveness of category captainship compared to traditional retailer category management, focusing on scenarios where shelf space capacity decisions are delegated to the category captain, and demand is dependent on shelf space capacity. Our study considers two competing manufacturers, each selling a substitutable product through a common retailer. We find that when the retailer’s profit-sharing ratio is sufficiently but not excessively high, category captainship can enhance profits for both the retailer and the captain manufacturer. These profit improvements are more pronounced at intermediate values of shelf space elasticity of demand. Although the non-captain manufacturer may suffer from competitive exclusion under certain conditions, “win-win-win” outcomes in profits and sales occur when the products are highly differentiated by price or shelf-space elasticity. The retailer benefits from increasing demand elasticity of shelf space and prefers to designate the manufacturer with the higher elasticity as the category captain. When the profit-sharing ratio is determined through a retailer-led bargaining framework, the retailer benefits most by negotiating sequentially with the manufacturers, inducing the manufacturer with lower bargaining power to take on the category captain role. Our findings provide valuable insights into developing category management strategies under shelf-space elastic demand.

Hierarchical Clustering Analysis to Inform Classification of Congenital Malformations for Surveillance of Medication Safety in Pregnancy.

There is growing interest in the secondary use of healthcare data to evaluate medication safety in pregnancy. Tree-based scan statistics (TBSS) offer an innovative approach to help identify potential safety signals. TBSS utilize hierarchically organized outcomes, generally based on existing clinical coding systems that group outcomes by organ system. When assessing teratogenicity, such groupings often lack a sound embryologic basis given the etiologic heterogeneity of congenital malformations. The study objective was to enhance the grouping of congenital malformations to be used in scanning approaches through implementation of hierarchical clustering analysis (HCA) and to pilot test an HCA-enhanced TBSS approach for medication safety surveillance in pregnancy in two test cases using >4.2 million mother-child dyads from two US-nationwide databases. HCA identified (1) malformation combinations belonging to the same organ system already grouped in existing classifications, (2) known combinations across different organ systems not previously grouped, (3) unknown combinations not previously grouped, and (4) malformations seemingly standing on their own. Testing the approach with valproate and topiramate identified expected signals, and a signal for an HCA-cluster missed by traditional classification. Augmenting existing classifications with clusters identified through large data exploration may be promising when defining phenotypes for surveillance and causal inference studies.

Closing the gap: prognostic and predictive biomarker validation for personalized care in a Latin American hormone-dependent breast cancer cohort.

Several guidelines recommend the use of different classifiers to determine the risk of recurrence (ROR) and treatment decisions in patients with HR+HER2- breast cancer. However, data are still lacking for their usefulness in Latin American (LA) patients. Our aim was to evaluate the comparative prognostic and predictive performance of different ROR classifiers in a real-world LA cohort. The Molecular Profile of Breast Cancer Study (MPBCS) is an LA case-cohort study with 5-year follow-up. Stages I and II, clinically node-negative HR+HER2- patients (n = 340) who received adjuvant hormone therapy and/or chemotherapy, were analyzed. Time-dependent receiver-operator characteristic-area under the curve, univariate and multivariate Cox proportional hazards regression (CPHR) models were used to compare the prognostic performance of several risk biomarkers. Multivariate CPHR with interaction models tested the predictive ability of selected risk classifiers. Within this cohort, transcriptomic-based classifiers such as the recurrence score (RS), EndoPredict (EP risk and EPClin), and PAM50-risk of recurrence scores (ROR-S and ROR-PC) presented better prognostic performances for node-negative patients (univariate C-index 0.61-0.68, adjusted C-index 0.77-0.80, adjusted hazard ratios [HR] between high and low risk: 4.06-9.97) than the traditional classifiers Ki67 and Nottingham Prognostic Index (univariate C-index 0.53-0.59, adjusted C-index 0.72-0.75, and adjusted HR 1.85-2.54). RS (and to some extent, EndoPredict) also showed predictive capacity for chemotherapy benefit in node-negative patients (interaction P = .0200 and .0510, respectively). In summary, we could prove the clinical validity of most transcriptomic-based risk classifiers and their superiority over clinical and immunohistochemical-based methods in the heterogenous, real-world node-negative HR+HER2- MPBCS cohort.

Rapid and Non-Destructive Geographical Origin Identification of Chuanxiong Slices Using Near-Infrared Spectroscopy and Convolutional Neural Networks

Ligusticum Chuanxiong, a perennial herb of considerable medicinal value commonly known as Chuanxiong, holds pivotal importance in sliced form for ensuring quality and regulating markets through geographical origin identification. This study introduces an integrated approach utilizing Near-Infrared Spectroscopy (NIRS) and Convolutional Neural Networks (CNNs) to establish an efficient method for rapidly determining the geographical origin of Chuanxiong slices. A dataset comprising 300 samples from 6 distinct origins was analyzed using a 1D-CNN model. In this study, we initially established a traditional classification model. By utilizing the Spectrum Outlier feature in TQ-Analyst 9 software to exclude outliers, we have enhanced the performance of the model. After evaluating various spectral preprocessing techniques, we selected Savitzky–Golay filtering combined with Multiplicative Scatter Correction (S-G + MSC) to process the raw spectral data. This approach significantly improved the predictive accuracy of the model. After 2000 iterations of training, the CNN model achieved a prediction accuracy of 92.22%, marking a 12.09% improvement over traditional methods. The application of the Class Activation Mapping algorithm not only visualized the feature extraction process but also enhanced the traditional model’s classification accuracy by an additional 7.41% when integrated with features extracted from the CNN model. This research provides a powerful tool for the quality control of Chuanxiong slices and presents a novel perspective on the quality inspection of other agricultural products.

A novel voice classification based on Gower distance for Parkinson disease detection

BackgroundTraditional classifier for the classification of diseases, such as K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM), often struggle with high-dimensional medical datasets. ObjectiveThis study presents a novel classifier to overcome the limitations of traditional classifiers in Parkinson’s disease (PD) detection based on Gower distance. MethodsWe present the Gower distance metric to handle diverse feature sets in voice recordings, which acts as a dissimilarity measure for all feature types, making the model adept at identifying subtle patterns indicative of PD. Additionally, the Cuckoo Search algorithm is employed for feature selection, reducing dimensionality by focusing on key features, thereby lessening the computational load associated with high-dimensional datasets. ResultsThe proposed classifier based on Gower distance resulted in an accuracy rate of 98.3% with feature selection and achieved an accuracy of 94.92% without the feature selection method. It outperforms traditional classifiers and recent studies in PD detection from voice recordings. ConclusionsThis accuracy shows the capability of the approach in the correct classification of instances and points out the potential of the approach as a reliable diagnostic tool for the medical practitioner. The findings state that the proposed approach holds promise for improving the diagnosis and monitoring of PD, both within medical institutions and at homes for the elderly.

Current development of molecular classifications of gastric cancer based on omics (Review).

Gastric cancer (GC) is a complex and heterogeneous disease with significant phenotypic and genetic variation. Traditional classification systems rely mainly on the evaluation of clinical pathological features and conventional biomarkers and might not capture the diverse clinical processes of individual GCs. The latest discoveries in omics technologies such as next‑generation sequencing, proteomics and metabolomics have provided crucial insights into potential genetic alterations and biological events in GC. Clustering strategies for identifying subtypes of GC might offer new tools for improving GC treatment and clinical trial outcomes by enabling the development of therapies tailored to specific subtypes. However, the feasibility and therapeutic significance of implementing molecular classifications of GC in clinical practice need to addressed. The present review examines the current molecular classifications, delineates the prevailing landscape of clinically relevant molecular features, analyzes their correlations with traditional GC classifications, and discusses potential clinical applications.

Image classification based on few-shot learning algorithms: a review

Image classification is a critical task in the field of computer vision, and its importance has significantly increased over the past few years. Machine learning and deep learning techniques have demonstrated immense potential in this field. However, traditional image classification models require a vast amount of training data, which can be challenging and expensive to obtain. To overcome this limitation, researchers are turning to few-shot learning, which aims to classify images with limited training samples. This paper presents a detailed analysis of the field of image classification using few-shot learning. First, it investigates the use of data augmentation, transfer learning, and meta-learning methods in this field. Then, it introduces several commonly used datasets and evaluation metrics in few-shot classification, compares several classical few-shot classification methods, and summarizes the experimental results obtained from public datasets. Finally, this paper analyzes the current challenges in few-shot image classification and suggests potential future directions.

Enhancing the Classification of Congenital Heart Defects for Outcome Association Studies in Birth Defects Registries.

Traditional strategies for grouping congenital heart defects (CHDs) using birth defect registry data do not adequately address differences in expected clinical consequences between different combinations of CHDs. We report a lesion-specific classification system for birth defect registry-based outcome studies. For Core Cardiac Lesion Outcome Classifications (C-CLOC) groups, common CHDs expected to have reasonable clinical homogeneity were defined. Criteria based on combinations of Centers for Disease and Control-modified British Pediatric Association (BPA) codes were defined for each C-CLOC group. To demonstrate proof of concept and retention of reasonable case counts within C-CLOC groups, Texas Birth Defect Registry data (1999-2017 deliveries) were used to compare case counts and neonatal mortality between traditional vs. C-CLOC classification approaches. C-CLOC defined 59 CHD groups among 62,262 infants with CHDs. Classifying cases into the single, mutually exclusive C-CLOC group reflecting the highest complexity CHD present reduced case counts among lower complexity lesions (e.g., 86.5% of cases with a common atrium BPA code were reclassified to a higher complexity group for a co-occurring CHD). As expected, C-CLOC groups had retained larger sample sizes (i.e., representing presumably better-powered analytic groups) compared to cases with only one CHD code and no occurring CHDs. This new CHD classification system for investigators using birth defect registry data, C-CLOC, is expected to balance clinical outcome homogeneity in analytic groups while maintaining sufficiently large case counts within categories, thus improving power for CHD-specific outcome association comparisons. Future outcome studies utilizing C-CLOC-based classifications are planned.

Study on environmental monitoring classification system based on improved bayesian algorithm

Abstract The commonly used methods for classifying water quality data are based on water quality parameters. The naive Bayesian classification method can be applied to substitute different evaluation criteria and selected water quality parameters for different water bodies. Compared to other water quality data classification methods, naive Bayesian classification methods have advantages such as simple calculation, high classification accuracy, and strong universality. However, this method overlooks the correlation between various water quality parameters and categories. To address the issues of poor universality, computational complexity, and low accuracy of traditional water quality data classification methods, a water quality data classification method based on weighted naive Bayes is proposed. This method comprehensively considers the impact of water quality attributes and their values on the classification results and replaces the original naive Bayes with weighted attribute conditional probabilities to make the classification results as close as possible to the actual category of the sample. The results indicate that this method exceeds 94% accuracy and can be directly utilized as a water quality classification module in water quality monitoring systems.

Android malware detection using GIST based machine learning and deep learning techniques

In today’s digital world, Android phones play a vital part in a variety of facets of both professionals and individuals’ personal and professional lives. Android phones are great for getting things done faster and more organized. The proportionate increase in the number of malicious applications has also been seen to be expanding. Since the play store offers millions of apps, detection of malware apps is challenging task. In this paper, a methodology is introduced for detecting malware in Android applications through the utilization of global image shape transform (GIST) features extracted from grayscale images of the applications. The dataset comprises samples of both malware and benign apps collected from the virus share website. After converting the apps into grayscale images, GIST features are extracted to capture their global spatial layout. Various machine learning (ML) algorithms, such as logistic regression (LR), k-nearest neighbour (KNN), AdaBoost, decision tree (DT), Naïve Bayes (NB), random forest (RF), support vector machine (SVM), extra tree classifier (ETC), and gradient boosting (GB), are employed to classify the applications according to their GIST features. Furthermore, a feed forward neural network (FFNN) is utilized as a deep learning (DL) technique to further improve the accuracy of classification. The performance of each algorithm is evaluated using metrics such as accuracy, precision and recall. The results demonstrated that the FFNN achieves superior accuracy compared to traditional ML classifiers, indicating its effectiveness in detecting malware in Android apps.

Aggregated Pattern Classification Method for improving neural disorder stage detection.

Neurological disorders pose a significant health challenge, and their early detection is critical for effective treatment planning and prognosis. Traditional classification of neural disorders based on causes, symptoms, developmental stage, severity, and nervous system effects has limitations. Leveraging artificial intelligence (AI) and machine learning (ML) for pattern recognition provides a potent solution to address these challenges. Therefore, this study focuses on proposing an innovative approach-the Aggregated Pattern Classification Method (APCM)-for precise identification of neural disorder stages. The APCM was introduced to address prevalent issues in neural disorder detection, such as overfitting, robustness, and interoperability. This method utilizes aggregative patterns and classification learning functions to mitigate these challenges and enhance overall recognition accuracy, even in imbalanced data. The analysis involves neural images using observations from healthy individuals as a reference. Action response patterns from diverse inputs are mapped to identify similar features, establishing the disorder ratio. The stages are correlated based on available responses and associated neural data, with a preference for classification learning. This classification necessitates image and labeled data to prevent additional flaws in pattern recognition. Recognition and classification occur through multiple iterations, incorporating similar and diverse neural features. The learning process is finely tuned for minute classifications using labeled and unlabeled input data. The proposed APCM demonstrates notable achievements, with high pattern recognition (15.03%) and controlled classification errors (CEs) (10.61% less). The method effectively addresses overfitting, robustness, and interoperability issues, showcasing its potential as a powerful tool for detecting neural disorders at different stages. The ability to handle imbalanced data contributes to the overall success of the algorithm. The APCM emerges as a promising and effective approach for identifying precise neural disorder stages. By leveraging AI and ML, the method successfully resolves key challenges in pattern recognition. The high pattern recognition and reduced CEs underscore the method's potential for clinical applications. However, it is essential to acknowledge the reliance on high-quality neural image data, which may limit the generalizability of the approach. The proposed method allows future research to refine further and enhance its interpretability, providing valuable insights into neural disorder progression and underlying biological mechanisms.

Optimizing breast cancer diagnosis: combining hybrid architectures through Apache Spark

Early detection and diagnosis of breast cancer are critical for saving lives. This paper addresses two major challenges associated with this task: the vast amount of data processing involved and the need for early detection of breast cancer. To tackle these issues, we developed thirty hybrid architectures by combining five deep learning techniques (Xception, Inception-V3, ResNet50, VGG16, VGG19) as feature extractors and six classifiers (random forest, logistic regression, naive Bayes, gradient-boosted tree, decision tree, and support vector machine) implemented on the Spark framework. We evaluated the performance of these architectures using four classification criteria. The results, analyzed using Scott Knott's statistical test, demonstrated the effectiveness of merging deep learning feature extraction techniques with traditional classifiers for classifying breast cancer into malignant and benign tumors. Notably, the hybrid architecture using logistic regression as the classifier and ResNet50 for feature extraction (RESLR) emerged as the top performer. It achieved impressive accuracy scores of 98.20%, 96.59%, 96.64%, and 94.84% across the Break-His dataset at different magnifications (40X, 100X, 200X, and 400X) respectively. Additionally, RESLR achieved an accuracy of 97.05% on the ICIAR dataset and a remarkable accuracy of 95.31% on the FNAC dataset.