Accurate Classification Research Articles

A Neural Network Approach to Understanding Employee Retention Dynamics: Insights from Feature Importance Analysis

In today’s business environment, employee retention has become a significant challenge, as employee turnover can lead to decreased productivity, increased costs, and reduced morale. This study aims to leverage neural network technology to predict employees' retention intentions and conduct in-depth analyses based on employee data. A classification model was established considering various factors, including gender, marital status, number of children, education level, years of service, weekly working hours, career development opportunities, salary, and bonuses, to identify the potential risk of employee turnover. The results indicated that the model achieved an accurate classification rate of 95.12% on the test set, demonstrating high effectiveness in identifying employee retention intentions. Feature importance analysis revealed that education level (29.63%), bonuses (27.50%), and the number of children (21.81%) were the primary factors influencing retention decisions. Additionally, working hours, marital status, and career development opportunities also impacted employees’ retention intentions. This research not only provides insights into employee mobility but also offers data support for enterprises to develop effective retention strategies, suggesting that businesses prioritize enhancing education and training opportunities, designing competitive bonus systems, and providing flexible work arrangements and benefits tailored to employees with children.

Inter-rater Agreement for Movement Disorder Classification in Children with Hyperkinetic Movement Disorders.

Accurate classification is essential for addressing childhood movement disorders (MD), but the common coexistence of multiple MDs complicates this process. The aim was to assess inter-rater agreement on classifying hyperkinetic MDs among pediatric neurologists with expertise in MDs. Five pediatric neurologists were requested to examine 112 videos of 66 pediatric patients. Based on the Movement Disorder-Childhood Rating Scale, 3 queries were posed: (Q1) Is there more than 1 MD? (Q2) What is the (predominant) MD? (Q3) What is the other MD (if present)? The final agreement rates were 57.5% for Q1, 66.6% for Q2, and 43.9% for absolute agreement. All videos with absolute agreement at the first evaluation featured 1 MD, whereas only 2 videos with multiple MDs could totally agree in the final review. This study reveals significant discordance in classification even among pediatric neurologists with expertise in MDs and highlights the necessity for a standardized approach.

Research on tire internal defect identification method based on deep learning

As an important part of automobile, the safety and durability of tire have attracted more and more attention. Tire defect detection is an important link to ensure tire quality, while traditional detection methods have problems such as low efficiency, high false detection rate and high labor intensity. Therefore, this study aims to develop an efficient and accurate tire defect identification and classification technique to improve the efficiency and accuracy of tire inspection. In this paper, based on YOLO (You Only Look Once) v5 algorithm, tire defect recognition and classification are studied. Firstly, the data sets containing various types of tire defects were collected and sorted out, and the data sets were preprocessed. Then, by constructing, training and optimizing the YOLOv5 tire defect recognition model, the fast and accurate recognition of tire defects was realized. Finally, the performance of the model was evaluated through experiments and compared with the existing methods. The experimental results show that the tire defect recognition and classification method based on YOLOv5 proposed in this study has high accuracy. Compared with traditional methods, this method has a significant improvement in detection speed and accuracy.

Heart sound classification algorithm based on bispectral feature extraction and convolutional neural networks

Cardiovascular disease (CVD) is one of the leading causes of death worldwide. Heart sound classification plays a key role in the early detection of CVD. The difference between normal and abnormal heart sounds is not obvious. In this paper, in order to improve the accuracy of the heart sound classification model, we propose a heart sound feature extraction method based on bispectral analysis and combine it with convolutional neural network (CNN) to classify heart sounds. The model can effectively suppress Gaussian noise by using bispectral analysis and can effectively extract the features of heart sound signals without relying on the accurate segmentation of heart sound signals. At the same time, the model combines with the strong classification performance of convolutional neural network and finally achieves the accurate classification of heart sound. According to the experimental results, the proposed algorithm achieves 0.910, 0.884 and 0.940 in terms of accuracy, sensitivity and specificity under the same data and experimental conditions, respectively. Compared with other heart sound classification algorithms, the proposed algorithm shows a significant improvement and strong robustness and generalization ability, so it is expected to be applied to the auxiliary detection of congenital heart disease.

Enhanced Quantum Entanglement Detection of General Two Qubits Systems Based on Modified CNN‐BiLSTM Model

AbstractEntanglement is a key element in quantum information processing. The detection of entanglement is crucial in many long‐range quantum information tasks, including secure communication and fundamental tests of quantum physics, but it is also highly resource‐intensive. Even for simple 2‐qubits systems, satisfactory detection is challenging. In this work, a modified entanglement detection model combining a convolutional neural network (CNN) and a bidirectional long short‐term memory network (BiLSTM) is proposed. It shows that the proposed model can effectively extract the deep features and correlations, enabling accurate classification of simple quantum states, even with only a few tens of training samples. When trained with a large number of highly random samples, the model exhibits outstanding fitting capability, resulting in the reliable classification of nearly all common 2‐qubits systems. Furthermore, the model exhibits exceptional adaptability and significant application potential in higher‐dimensional systems.

Feature Extraction and Identification of Rheumatoid Nodules Using Advanced Image Processing Techniques

Background/Objectives: Accurate detection and classification of nodules in medical images, particularly rheumatoid nodules, are critical due to the varying nature of these nodules, where their specific type is often unknown before analysis. This study addresses the challenges of multi-class prediction in nodule detection, with a specific focus on rheumatoid nodules, by employing a comprehensive approach to feature extraction and classification. We utilized a diverse dataset of nodules, including rheumatoid nodules sourced from the DermNet dataset and local rheumatologists. Method: This study integrates 62 features, combining traditional image characteristics with advanced graph-based features derived from a superpixel graph constructed through Delaunay triangulation. The key steps include image preprocessing with anisotropic diffusion and Retinex enhancement, superpixel segmentation using SLIC, and graph-based feature extraction. Texture analysis was performed using Gray-Level Co-occurrence Matrix (GLCM) metrics, while shape analysis was conducted with Fourier descriptors. Vascular pattern recognition, crucial for identifying rheumatoid nodules, was enhanced using the Frangi filter. A Hybrid CNN–Transformer model was employed for feature fusion, and feature selection and hyperparameter tuning were optimized using Gray Wolf Optimization (GWO) and Particle Swarm Optimization (PSO). Feature importance was assessed using SHAP values. Results: The proposed methodology achieved an accuracy of 85%, with a precision of 0.85, a recall of 0.89, and an F1 measure of 0.87, demonstrating the effectiveness of the approach in detecting and classifying rheumatoid nodules in both binary and multi-class classification scenarios. Conclusions: This study presents a robust tool for the detection and classification of nodules, particularly rheumatoid nodules, in medical imaging, offering significant potential for improving diagnostic accuracy and aiding in the early identification of rheumatoid conditions.

Geo-spatial based cyclone shelter suitability assessment using analytical hierarchy process (AHP) in the coastal region of Bangladesh

The coastal district of Bangladesh is susceptible to cyclones, which cause significant damage to infrastructure, economy, and social structures every year. The importance of protecting lives and property in these vulnerable areas is a top priority, especially in times of cyclones and storm surges. Therefore, the identification of potentially suitable shelter locations is essential for disaster risk resilience planning and implementation in the coastal regions. In this context, our research focuses on Barguna, which has witnessed severe damage from previous cyclones over the last several decades. We aim to identify and map feasible cyclone shelter suitability by utilizing GIS, AHP, Hotspot Analysis, and Remote Sensing techniques. The use of advanced techniques enables a comprehensive assessment of multiple variables that influence shelter suitability, ensuring the selection of the most strategically significant locations. The goal is to enhance disaster preparedness and resilience in Barguna District, reducing the risk and vulnerability of its coastal communities to cyclones. Seven variables associated with cyclone hazards, such as elevation, slope, distance from roads and rivers, population density, land use, and cover, and proximity to healthcare facilities, are considered to identify the safest and most suitable cyclone shelter areas. The assessment of the appropriateness of shelter locations for the study area was facilitated by the collection of 181 GPS locations regarding existing cyclone shelters. The findings reveal that approximately 15.53 % (1956 ha) of the total land area is considered less suitable, 67.31 % (84763 ha) moderately suitable, 16.70 % (21024 ha) suitable, and 0.29 % (362 ha) highly suitable for optimal cyclone shelter establishment in the study area. This study has a major limitation due to the use of Landsat imagery, which may not always provide fully accurate image classification. To validate our methods, we collected existing cyclone shelter data and performed a pixel-based accuracy assessment, achieving high accuracy and confirming the reliability of our approach. This research addresses a critical gap in cyclone shelter planning, offering valuable insights for residents and decision-makers to mitigate cyclone risks not only in the Barguna district but also in similar coastal regions of Bangladesh. The framework developed in this study can aid non-government organizations and the government in determining the most appropriate locations to construct cyclone shelters to build a safer, more resilient future for the region, capable of withstanding the relentless threats posed by cyclones every year.

SoftLungX: leveraging transfer learning with convolutional neural networks for accurate respiratory disease classification in chest X-ray images

Medical imaging is an indispensable and very important step in the diagnosis and treatment of illnesses. However, due to large amounts of resources necessary for training the model, training from scratch may not invariably emerge as the optimal recourse. Transfer learning has emerged as a viable solution, where pretrained weights from ImageNet are initially utilized and fine-tuninned afterwards. This paper presents a novel approach employing transfer learning to classify both respiratory diseases and radiological findings from chest X-rays. The dataset comprises 191 660 X-ray images gathered from public databases and 752 chest X-ray images obtained from a retrospective study at the University Clinical Center of Kragujevac, forming the foundation of Big data analysis. It includes various conditions such as atelectasis, cardiomegaly, infiltration, pleural thickening, non-viral pneumonia, pneumothorax, COVID-19 viral pneumonia, tuberculosis, etc. as well as masses and nodules indicative of tumors and images of healthy subjects. Although there are existing solutions with some diseases, this is the first paper that inlcludes differentiation between healthy and diseased cases, as well as in case of present disease, as much as 18 different classes are inlcuded in the analysis, which has not been done so far. The proposed methodology included transfer learning with DenseNet121 as the backbone and CheXNeXt weights as initialisation scheme, upon which additional layers were added for fine tuning. The results demonstrate the model’s capacity to distinguish between healthy and diseased, with an average area under curve (AUC) of 0.99. The AUC ranges from 0.86 for nodules to 0.99 for pneumonia and 0.99 for COVID-19. Our method outperforms the state-of-the-art in accuracy across all 18 classes, with the exception of classes consolidation, mass, and nodule. These findings are promising for a tested clinical site, though further validation in clinical environment accros multiple sites may be necessary before using the model as a standalone decision system, rather than a decision support system for disease diagnosis based on chest X-rays.

Enhanced MRI-based brain tumour classification with a novel Pix2pix generative adversarial network augmentation framework.

The scarcity of medical imaging datasets and privacy concerns pose significant challenges in artificial intelligence-based disease prediction. This poses major concerns to patient confidentiality as there are now tools capable of extracting patient information by merely analysing patient's imaging data. To address this, we propose the use of synthetic data generated by generative adversarial networks as a solution. Our study pioneers the utilisation of a novel Pix2Pix generative adversarial network model, specifically the 'image-to-image translation with conditional adversarial networks,' to generate synthetic datasets for brain tumour classification. We focus on classifying four tumour types: glioma, meningioma, pituitary and healthy. We introduce a novel conditional deep convolutional neural network architecture, developed from convolutional neural network architectures, to process the pre-processed generated synthetic datasets and the original datasets obtained from the Kaggle repository. Our evaluation metrics demonstrate the conditional deep convolutional neural network model's high performance with synthetic images, achieving an accuracy of 86%. Comparative analysis with state-of-the-art models such as Residual Network50, Visual Geometry Group 16, Visual Geometry Group 19 and InceptionV3 highlights the superior performance of our conditional deep convolutional neural network model in brain tumour detection, diagnosis and classification. Our findings underscore the efficacy of our novel Pix2Pix generative adversarial network augmentation technique in creating synthetic datasets for accurate brain tumour classification, offering a promising avenue for improved disease prediction and treatment planning.

Investigating Brain Responses to Transcutaneous Electroacupuncture Stimulation: A Deep Learning Approach

This study investigates the neurophysiological effects of transcutaneous electroacupuncture stimulation (TEAS) on brain activity, using advanced machine learning techniques. This work analyzed the electroencephalograms (EEG) of 48 study participants, in order to analyze the brain’s response to different TEAS frequencies (2.5, 10, 80, and sham at 160 pulses per second (pps)) across 48 participants through pre-stimulation, during-stimulation, and post-stimulation phases. Our approach introduced several novel aspects. EEGNet, a convolutional neural network specifically designed for EEG signal processing, was utilized in this work, achieving over 95% classification accuracy in detecting brain responses to various TEAS frequencies. Additionally, the classification accuracies across the pre-stimulation, during-stimulation, and post-stimulation phases remained consistently high (above 92%), indicating that EEGNet effectively captured the different time-based brain responses across different stimulation phases. Saliency maps were applied to identify the most critical EEG electrodes, potentially reducing the number needed without sacrificing accuracy. A phase-based analysis was conducted to capture time-based brain responses throughout different stimulation phases. The robustness of EEGNet was assessed across demographic and clinical factors, including sex, age, and psychological states. Additionally, the responsiveness of different EEG frequency bands to TEAS was investigated. The results demonstrated that EEGNet excels in classifying EEG signals with high accuracy, underscoring its effectiveness in reliably classifying EEG responses to TEAS and enhancing its applicability in clinical and therapeutic settings. Notably, gamma band activity showed the highest sensitivity to TEAS, suggesting significant effects on higher cognitive functions. Saliency mapping revealed that a subset of electrodes (Fp1, Fp2, Fz, F7, F8, T3, T4) could achieve accurate classification, indicating potential for more efficient EEG setups.

The Body Knows Better: Sensorimotor signals reveal the interplay between implicit and explicit Sense of Agency in the human mind

Sense of Agency (SoA) is the feeling of control over our actions. SoA has been suggested to arise from both implicit sensorimotor integration as well as higher-level decision processes. SoA is typically measured by collecting participants' subjective judgments, conflating both implicit and explicit processing. Consequently, the interplay between implicit sensorimotor processing and explicit agency judgments is not well understood. Here, we evaluated in one exploratory and one preregistered experiment (N = 60), using a machine learning approach, the relation between a well-known mechanism of implicit sensorimotor adaptation and explicit SoA judgments. Specifically, we examined whether subjective judgments of SoA and sensorimotor conflicts could be inferred from hand kinematics in a sensorimotor task using a virtual hand (VH). In both experiments participants performed a hand movement and viewed a virtual hand making a movement that could either be synchronous with their action or include a parametric temporal delay. After each movement, participants judged whether their actual movement was congruent with the movement they observed. Our results demonstrated that sensorimotor conflicts could be inferred from implicit motor kinematics on a trial by trial basis. Moreover, detection of sensorimotor conflicts from machine learning models of kinematic data provided more accurate classification of sensorimotor congruence than participants' explicit judgments. These results were replicated in a second, preregistered, experiment. These findings show evidence of diverging implicit and explicit processing for SoA and suggest that the brain holds high-quality information on sensorimotor conflicts that is not fully utilized in the inference of conscious agency.

Equipment Sounds’ Event Localization and Detection Using Synthetic Multi-Channel Audio Signal to Support Collision Hazard Prevention

Construction workplaces often face unforeseen collision hazards due to a decline in auditory situational awareness among on-foot workers, leading to severe injuries and fatalities. Previous studies that used auditory signals to prevent collision hazards focused on employing a classical beamforming approach to determine equipment sounds’ Direction of Arrival (DOA). No existing frameworks implement a neural network-based approach for both equipment sound classification and localization. This paper presents an innovative framework for sound classification and localization using multichannel sound datasets artificially synthesized in a virtual three-dimensional space. The simulation synthesized 10,000 multi-channel datasets using just fourteen single sound source audiotapes. This training includes a two-staged convolutional recurrent neural network (CRNN), where the first stage learns multi-label sound event classes followed by the second stage to estimate their DOA. The proposed framework achieves a low average DOA error of 30 degrees and a high F-score of 0.98, demonstrating accurate localization and classification of equipment near workers’ positions on the site.

Enhanced QSVM with elitist non‐dominated sorting genetic optimisation algorithm for breast cancer diagnosis

AbstractMachine learning has emerged as a promising method for predicting breast cancer using quantum computation techniques. Quantum machine learning algorithms, such as quantum support vector machines (QSVMs), are demonstrating superior efficiency and economy in tackling complex problems compared to traditional machine learning methods. When compared with classical support vector machine, the quantum machine produces remarkably accurate results. The suggested quantum SVM model in this study effectively resolved the binary classification problem for diagnosing malignant breast cancer. This work introduces an enhanced approach to breast cancer diagnosis by integrating QSVM with elitist non‐dominated sorting genetic optimization (ENSGA), leveraging the strengths of both techniques to achieve more accurate and efficient classification results. ENSGA plays a crucial role in optimising QSVM parameters, ensuring that the model attains the best possible classification accuracy while considering multiple objectives simultaneously. Moreover, the quantum kernel estimation method demonstrated exceptional performance by achieving high accuracy within an impressive execution time of 0.14 in the IBM QSVM simulator. The seamless integration of quantum computation techniques with optimisation strategies such as ENSGA highlights the potential of quantum machine learning in revolutionising the field of healthcare, particularly in the domain of breast cancer diagnosis.

Evaluating novel in silico tools for accurate pathogenicity classification in epilepsy-associated genetic missense variants.

Determining the pathogenicity of missense variants in clinical genetic tests for individuals with epilepsy is crucial for guiding personalized treatment. However, achieving a definitive pathogenic classification remains challenging, with most missense variants still classified as variants of uncertain significance (VUS) and with the availability of many computational tools which may provide conflicting predictions. Here, we aim to evaluate the performance of state-of-the-art computational tools in pathogenicity prediction of missense variants in epilepsy-associated genes. This will assist in selecting the most appropriate tool and critically assess their use in clinical setting. We assessed the performance of nine in silico pathogenicity prediction tools for missense variants in epilepsy-associated genes on three carefully curated data sets. The first two data sets comprise missense variants in epilepsy associated genes that have been uploaded to ClinVar in the last year and were, therefore, not part of the training set of any of the nine considered tools. These two data sets are based on two different lists of epilepsy-associated genes and comprise ~700 and ~ 250 missense variants, respectively. The third data set includes ~400 missense variants within epilepsy-associated genes for which the functional effects have been determined experimentally and are therefore used here to infer pathogenicity. These three data sets represent the best available approximation to blind and independent test sets. Among the nine assessed tools, AlphaMissense (area under the curve [AUC]: .93, .88, and .95) and REVEL (AUC: .93, .88, and .93) showed the best classification performance, also outperforming other tools in the number of classified variants. We show which recently developed prediction tools achieve higher performance in epilepsy-associated genes and should be integrated, therefore, into the American College of Medical Genetics and Genomics/Association of Molecular Pathology (AGMC/AMP) variant classification process. Periodic reevaluation of genetic test results with newly developed or updated tools should be incorporated into standard clinical practice to improve diagnostic yield and better inform precision medicine.

Research on music genre recognition method based on deep learning

In this paper, we explore music genre recognition using deep learning methods, examining the application of feature extraction, model construction, and performance evaluation for different music genres. During the data preparation and preprocessing stages, data augmentation and normalization techniques were employed to enhance the model’s generalization capabilities. By constructing multilayer convolutional neural networks (CNNs) and recurrent neural networks (RNNs), we achieved automatic recognition of music genres. In the experimental results analysis, we compared the accuracy and training time of different models, validating the effectiveness of deep learning in the field of music genre recognition. The limitations of deep learning methods and future research directions are also discussed, providing a reference for further studies in music information processing. This study delves into the issue of music genre recognition and proposes a deep learning-based approach. This method leverages neural networks to extract features and learn from audio data, enabling accurate classification of different music genres. Extensive experiments have demonstrated that our method achieves highly satisfactory results in music genre recognition tasks. Furthermore, we optimized the deep learning models, improving their generalization capabilities and accuracy. Our research offers the music industry an efficient and accurate method for music genre recognition, providing new perspectives and technical support for research and applications in the music field.

Development of an Artificial Intelligence System for Distinguishing Malignant from Benign Soft Tissue Tumors Using Contrast-Enhanced MR Images.

The integration of artificial intelligence (AI) into orthopedics has enhanced the diagnosis of various conditions; however, its use in diagnosing soft-tissue tumors remains limited owing to its complexity. This study aimed to develop and assess an AI-driven diagnostic support system for magnetic resonance imaging (MRI)-based soft-tissue tumor diagnosis, potentially improving accuracy and aiding radiologists and orthopedic surgeons. Experienced orthopedic oncologists and radiologists annotated 720 images from 77 cases (41 benign and 36 malignant soft-tissue tumors). Eleven tumor subtypes were identified and classified into benign and malignant groups based on histological diagnosis. Utilizing the standard machine learning classifier pipeline, we examined and down-selected imaging protocols and their predominant radiomic features within the tumor's three-dimensional region to differentiate between benign and malignant tumors. Among the scan protocols, contrast-enhanced T1 weighted fat-suppressed images showed the most accurate classification based on radiomics features. We focused on the two-dimensional features from the largest tumor boundary surface and its neighboring slices, leveraging texture-based radiomic and deep convolutional neural network features from a pretrained VGG19 model. The test data comprised 44 contrast-enhanced images (22 benign and 22 malignant soft-tissue tumors) containing six malignant and five benign subtypes distinct from the training data. We compared expert and non-expert human performances against AI by assessing malignancy detection and the time required for classification. The AI model showed comparable accuracy (AUC 0.91) to that of radiologists (AUC 0.83) and orthopedic surgeons (AUC 0.73). Notably, the AI model processed data approximately 400 times faster than its human counterparts, showcasing its capacity to significantly boost diagnostic efficiency. We developed an AI-driven diagnostic support system for MRI-based soft-tissue tumor diagnosis. While additional refinement is necessary for clinical applications, our system has exhibited promising potential in differentiating between benign and malignant soft-tissue tumors based on MRI.

Molecular phylogeny reveals a new genus and species of freshwater mussel (Bivalvia, Unionidae, Gonideinae) from Jiangxi, China

Freshwater mussels of the tribe Gonideini (Bivalvia: Unionidae: Gonideinae) constitute one of the most taxonomically diverse groups and serve as keystone species in riverine and lacustrine ecosystems across East Asia. A new genus and species of Gonideini (Bivalvia: Unionidae) is described from Jiangxi, China, as Pseudopostolata angulagen. et sp. nov. based on an integrative analysis of shell morphology and molecular data. The validity of the new genus and species is supported by distinct conchological features: a short, rounded anterior; a long, wide posterior; a slightly downward-curved dorsal margin; and a distinctly obtuse angle at the center of the posterior margin. The multi-locus (COI + 16S rRNA + 28S rRNA) phylogeny showed that the species formed a monophyletic group in the tribe Gonideini of the subfamily Gonideinae. Pseudopostolata angulagen. et sp. nov. is identified as the sister group to a clade comprising the genera Postolata, Cosmopseudodon, Obovalis, Ptychorhynchus, Parvasolenaia, and Koreosolenaia. We emphasize the significant morphological convergence in freshwater mussels, particularly within Gonideini, highlighting the necessity of an integrated taxonomic approach for accurate generic classification of this group.

Accurate crop disease identification and classification in smart agriculture using a three-tier model and optimized fully conventional network

Accurate crop disease identification and classification in smart agriculture using a three-tier model and optimized fully conventional network

A proof of concept for wear/non-wear classification using accelerometer data in daily activity recording: Synthetic algorithm leveraging probability and continuity of zero counts.

Wearable devices are increasingly utilized to monitor physical activity and sedentary behaviors. Accurately determining wear/non-wear time is complicated by zero counts, where the acceleration-based indexes do not estimate activity intensity, often leading to misclassifications. We propose a novel synthetic classification algorithm that leverages both the probability and continuity of zero counts, aiming to enhance the accuracy of activity estimation. The physical activity data were obtained from 12 office workers wearing wearable devices with 3-axis accelerometers. The wear/non-wear times are classified by the commonly used current method (zero counts lasting longer than 60 minutes are classified as non-wear) and the proposed method. In the proposed method, only times that satisfy the following two criteria are classified as the wear time. (1) The appearance probability preceding and following 60 minutes must be less than the threshold value. (2) The number of consecutive zeros must be less than 10 minutes. The effectiveness of both the current and proposed classification methods was evaluated against the actual behavioral records. This evaluation utilized simulation-based augmented data, which was implemented to address the limited variability inherent in the original dataset. The range of recall, specificity, precisions, and accuracy classified by the current method were 0.93-1.00, 0.93-0.96, 0.85-0.88, and 0.94-0.97, respectively. Indeed, the proposed method shows 0.95-1.00, 0.99-1.00, 0.97-1.00, and 0.98-1.00, respectively. The reduction of misclassification of non-wear time as wear time was achieved by the synthetic classification algorithm. The performance of the proposed approach showed accurate classification of the wear/non-wear time of wearable sensors in office workers.

Performance Comparison of Random Forest (RF) and Classification and Regression Trees (CART) for Hotel Star Rating Prediction

Purpose: This study proposes to evaluate the effectiveness of Random Forest (RF) compared to Classification and Regression Trees (CART) in prediction of hotel star ratings. The objective is to identify the algorithm that provides the most reliable and accurate classification outcomes based on diverse hotel attributes in accordance with the standard categorization of star hotel categories. This is necessary due to the important role of accurate star ratings in guiding consumer choices and enhancing competitive positioning in the hospitality industry. Method: This study conducted a comprehensive dataset about Hotel in Banyumas Regency, including location, facilities, the size of rooms, type of rooms, price of rooms, and customer reviews, subjected to training through both RF and CART algorithms. Both algorithms are evaluated using accuracy, precision, recall, and F1 score. Additionally, both algorithms due to in the same preprocessing while performing hyperparameter tuning improve the efficacy of each model. Result: The results showed that RF achieved the best overall accuracy and robustness than CART across all tests conducted. Furthermore, RF also outperformed CART in classification effectiveness among classes, including enhanced precision and recall scores across multiple stars rating categories, signifying increased generalization and consistency in classification tasks. RF classifier consistently surpassed the CART classifier in terms of both accuracy and F1-score throughout all random states and test sizes, with a highest score of 0.9932 at a random state of 100 and a test size of 0.4. The most reliable results were obtained using RF with 42 random states and a test size of 0.2, resulting in an accuracy of 0.9909, precision of 1.0, recall of 1.0, and F1 score of 1.0. Simultaneously, CART shows values of 0.9818, 1.0, 1.0, and 1.0, respectively, while maintaining the same variation. This consistent performance, regardless of fluctuations, illustrates the robustness and suitability of RF for classification tasks compared to CART. Novelty: This study offered new insights about the implementation of machine learning about hotel star rating predictions using RF and CART algorithms. Also, the novelty of the collected hotel dataset used in this study. A detailed comparative analysis was also provided, contributing to the existing literature by showing the effectiveness of RF over CART for this specific application. Future studies could explore the integration of additional machine learning methods to further enhance prediction accuracy and operational efficiency in the hospitality industry.