Classification Model Research Articles

A hybrid CNN with transfer learning for skin cancer disease detection.

The leading cause of cancer-related deaths worldwide is skin cancer. Effective therapy depends on the early diagnosis of skin cancer through the precise classification of skin lesions. However, dermatologists may find it difficult and time-consuming to accurately classify skin lesions. The use of transfer learning to boost skin cancer classification model precision is a promising strategy. In this work, we proposed a hybrid CNN with a transfer learning model and a random forest classifier for skin cancer disease detection. To evaluate the efficacy of the proposed model, it was verified over two datasets of benign skin moles and malignant skin moles. The proposed model is able to classify images with an accuracy of up to 90.11%. The empirical results and analysis assure the feasibility and effectiveness of the proposed model for skin cancer classification.

A Comparative Analysis of the Machine Learning Methods for Predicting Diabetes

Diabetes can lead to various health problems and complications, such as cardiovascular disease, kidney damage (nephropathy), eye issues, neuropathy, and foot ailments. Therefore, early diagnosis of diabetes can be immensely beneficial in preventing the development of these conditions. Utilizing machine learning is one method to detect diabetes in individuals at an early stage. In this study, we compare the performance of nine machine-learning classification models in predicting diabetes. These models include XGBoost, gradient boosting, AdaBoost, logistic regression, decision tree, KNN, perceptron, random forest, and naïve bayes. We utilize several evaluation metrics, focusing on the f1-score, area under the curve (AUC), and computational runtime. Our comparison reveals that complex tree-based models exhibit the highest f1-score and AUC, albeit with longer execution times.

Public health nurse perspectives on predicting nonattendance for cervical cancer screening through classification, ensemble, and deep learning models.

Women's attendance to cervical cancer screening (CCS) is a major concern for healthcare providers in community. This study aims to use the various algorithms that can accurately predict the most barriers of women for nonattendance to CS. The real-time data were collected from women presented at OPD of primary health centers (PHCs). About 1046 women's data regarding attendance and nonattendance to CCS were included. In this study, we have used three models, classification, ensemble, and deep learning models, to compare the specific accuracy and AU-ROC for predicting non-attenders for CC. The current model employs 22 predictors, with soft voting in ensemble models showing slightly higher specificity (96%) and sensitivity (93%) than weighted averaging. Bagging excels with the highest accuracy (98.49%), specificity (97.3%), and ideal sensitivity (100%) with an AUC of 0.99. Classification models reveal Naive Bayes with higher specificity (97%) but lower sensitivity (91%) than Logistic Regression. Random Forest and Neural Network achieve the highest accuracy (98.49%), with an AUC of 0.98. In deep learning, LSTM has an accuracy of 95.68%, higher specificity (97.60%), and lower sensitivity (93.42%) compared to other models. MLP and NN showed the highest AUC values of 0.99. Employing ensemble and deep learning models proved most effective in predicting barriers to nonattendance in cervical screening.

SEMG-based automatic characterization of swallowed materials

Monitoring of ingestive activities is critically important for managing the health and wellness of individuals with various health conditions, including the elderly, diabetics, and individuals seeking better weight control. Monitoring swallowing events can be an ideal surrogate for developing streamlined methods for effective monitoring and quantification of eating or drinking events. Swallowing is an essential process for maintaining life. This seemingly simple process is the result of coordinated actions of several muscles and nerves in a complex fashion. In this study, we introduce automated methods for the detection and quantification of various eating and drinking activities. Wireless surface electromyography (sEMG) was used to detect chewing and swallowing from sEMG signals obtained from the sternocleidomastoid muscle, in addition to signals obtained from a wrist-mounted IMU sensor. A total of 4675 swallows were collected from 55 participants in the study. Multiple methods were employed to estimate bolus volumes in the case of fluid intake, including regression and classification models. Among the tested models, neural networks-based regression achieved an R2 of 0.88 and a root mean squared error of 0.2 (minimum bolus volume was 10 ml). Convolutional neural networks-based classification (when considering each bolus volume as a separate class) achieved an accuracy of over 99% using random cross-validation and around 66% using cross-subject validation. Multiple classification methods were also used for solid bolus type detection, including SVM and decision trees (DT), which achieved an accuracy above 99% with random validation and above 94% in cross-subject validation. Finally, regression models with both random and cross-subject validation were used for estimating the solid bolus volume with an R2 value that approached 1 and root mean squared error values as low as 0.00037 (minimum solid bolus weight was 3 gm). These reported results lay the foundation for a cost-effective and non-invasive method for monitoring swallowing activities which can be extremely beneficial in managing various chronic health conditions, such as diabetes and obesity.

Using machine learning algorithms and techniques for defining the impact of affective temperament types, content search and activities on the internet on the development of problematic internet use in adolescents’ population

BackgroundBy using algorithms and Machine Learning – ML techniques, the aim of this research was to determine the impact of the following factors on the development of Problematic Internet Use (PIU): sociodemographic factors, the intensity of using the Internet, different contents accessed on the Internet by adolescents, adolescents’ online activities, life habits and different affective temperament types.MethodsSample included 2,113 adolescents. The following instruments were used: questionnaire about: socio-demographic characteristics, intensity of the Internet use, content categories and online activities on the Internet; Facebook (FB) usage and life habits; The Internet Use Disorder Scale (IUDS). Based on their scores on the scale, subjects were divided into two groups – with or without PIU; Temperament Evaluation of Memphis, Pisa, Paris, and San Diego scale for adolescents (A-TEMPS-A).ResultsVarious ML classification models on our data set were trained. Binary classification models were created (class-label attribute was PIU value). Models hyperparameters were optimized using grid search method and models were validated using k-fold cross-validation technique. Random forest was the model with the best overall results and the time spent on FB and the cyclothymic temperament were variables of highest importance for these model. We also applied the ML techniques Lasso and ElasticNet. The three most important variables for the development of PIU with both techniques were: cyclothymic temperament, the longer use of the Internet and the desire to use the Internet more than at present time. Group of variables having a protective effect (regarding the prevention of the development of PIU) was found with both techniques. The three most important were: achievement, search for contents related to art and culture and hyperthymic temperament. Next, 34 important variables that explain 0.76% of variance were detected using the genetic algorithms. Finally, the binary classification model (with or without PIU) with the best characteristics was trained using artificial neural network.ConclusionVariables related to the temporal determinants of Internet usage, cyclothymic temperament, the desire for increased Internet usage, anxious and irritable temperament, on line gaming, pornography, and some variables related to FB usage consistently appear as important variables for the development of PIU.

Identification of cancer risk groups through multi-omics integration using autoencoder and tensor analysis.

Identifying cancer risk groups by multi-omics has attracted researchers in their quest to find biomarkers from diverse risk-related omics. Stratifying the patients into cancer risk groups using genomics is essential for clinicians for pre-prevention treatment to improve the survival time for patients and identify the appropriate therapy strategies. This study proposes a multi-omics framework that can extract the features from various omics simultaneously. The framework employs autoencoders to learn the non-linear representation of the data and applies tensor analysis for feature learning. Further, the clustering method is used to stratify the patients into multiple cancer risk groups. Several omics were included in the experiments, namely methylation, somatic copy-number variation (SCNV), micro RNA (miRNA) and RNA sequencing (RNAseq) from two cancer types, including Glioma and Breast Invasive Carcinoma from the TCGA dataset. The results of this study are promising, as evidenced by the survival analysis and classification models, which outperformed the state-of-the-art. The patients can be significantly (p-value<0.05) divided into risk groups using extracted latent variables from the fused multi-omics data. The pipeline is open source to help researchers and clinicians identify the patients' risk groups using genomics.

ACME: A Classification Model for Explaining the Risk of Preeclampsia Based on Bayesian Network Classifiers and a Non-Redundant Feature Selection Approach

While preeclampsia is the leading cause of maternal death in Guayas province (Ecuador), its causes have not yet been studied in depth. The objective of this research is to build a Bayesian network classifier to diagnose cases of preeclampsia while facilitating the understanding of the causes that generate this disease. Data for the years 2017 through 2023 were gathered retrospectively from medical histories of patients treated at “IESS Los Ceibos” hospital in Guayaquil, Ecuador. Naïve Bayes (NB), The Chow–Liu Tree-Augmented Naïve Bayes (TANcl), and Semi Naïve Bayes (FSSJ) algorithms have been considered for building explainable classification models. A proposed Non-Redundant Feature Selection approach (NoReFS) is proposed to perform the feature selection task. The model trained with the TANcl and NoReFS was the best of them, with an accuracy close to 90%. According to the best model, patients whose age is above 35 years, have a severe vaginal infection, live in a rural area, use tobacco, have a family history of diabetes, and have had a personal history of hypertension are those with a high risk of developing preeclampsia.

Enhancing multi-class lung disease classification in chest x-ray images: A hybrid manta-ray foraging volcano eruption algorithm boosted multilayer perceptron neural network approach

ABSTRACT One of the most used diagnostic imaging techniques for identifying a variety of lung and bone-related conditions is the chest X-ray. Recent developments in deep learning have demonstrated several successful cases of illness diagnosis from chest X-rays. However, issues of stability and class imbalance still need to be resolved. Hence in this manuscript, multi-class lung disease classification in chest x-ray images using a hybrid manta-ray foraging volcano eruption algorithm boosted multilayer perceptron neural network approach is proposed (MPNN-Hyb-MRF-VEA). Initially, the input chest X-ray images are taken from the Covid-Chest X-ray dataset. Anisotropic diffusion Kuwahara filtering (ADKF) is used to enhance the quality of these images and lower noise. To capture significant discriminative features, the Term frequency-inverse document frequency (TF-IDF) based feature extraction method is utilized in this case. The Multilayer Perceptron Neural Network (MPNN) serves as the classification model for multi-class lung disorders classification as COVID-19, pneumonia, tuberculosis (TB), and normal. A Hybrid Manta-Ray Foraging and Volcano Eruption Algorithm (Hyb-MRF-VEA) is introduced to further optimize and fine-tune the MPNN’s parameters. The Python platform is used to accurately evaluate the proposed methodology. The performance of the proposed method provides 23.21%, 12.09%, and 5.66% higher accuracy compared with existing methods like NFM, SVM, and CNN respectively.

Exploring different classification-dependent QSAR modelling strategies for HDAC3 inhibitors in search of meaningful structural contributors.

Histone deacetylase 3 (HDAC3), a Zn2+-dependent class I HDACs, contributes to numerous disorders such as neurodegenerative disorders, diabetes, cardiovascular disease, kidney disease and several types of cancers. Therefore, the development of novel and selective HDAC3 inhibitors might be promising to combat such diseases. Here, different classification-based molecular modelling studies such as Bayesian classification, recursive partitioning (RP), SARpy and linear discriminant analysis (LDA) were conducted on a set of HDAC3 inhibitors to pinpoint essential structural requirements contributing to HDAC3 inhibition followed by molecular docking study and molecular dynamics (MD) simulation analyses. The current study revealed the importance of hydroxamate function for Zn2+ chelation as well as hydrogen bonding interaction with Tyr298 residue. The importance of hydroxamate function for higher HDAC3 inhibition was noticed in the case of Bayesian classification, recursive partitioning and SARpy models. Also, the importance of substituted thiazole ring was revealed, whereas the presence of linear alkyl groups with carboxylic acid function, any type of ester function, benzodiazepine moiety and methoxy group in the molecular structure can be detrimental to HDAC3 inhibition. Therefore, this study can aid in the design and discovery of effective novel HDAC3 inhibitors in the future.

A reduced proteomic signature in critically ill Covid-19 patients determined with plasma antibody micro-array and machine learning

BackgroundCOVID-19 is a complex, multi-system disease with varying severity and symptoms. Identifying changes in critically ill COVID-19 patients’ proteomes enables a better understanding of markers associated with susceptibility, symptoms, and treatment. We performed plasma antibody microarray and machine learning analyses to identify novel proteins of COVID-19.MethodsA case-control study comparing the concentration of 2000 plasma proteins in age- and sex-matched COVID-19 inpatients, non-COVID-19 sepsis controls, and healthy control subjects. Machine learning was used to identify a unique proteome signature in COVID-19 patients. Protein expression was correlated with clinically relevant variables and analyzed for temporal changes over hospitalization days 1, 3, 7, and 10. Expert-curated protein expression information was analyzed with Natural language processing (NLP) to determine organ- and cell-specific expression.ResultsMachine learning identified a 28-protein model that accurately differentiated COVID-19 patients from ICU non-COVID-19 patients (accuracy = 0.89, AUC = 1.00, F1 = 0.89) and healthy controls (accuracy = 0.89, AUC = 1.00, F1 = 0.88). An optimal nine-protein model (PF4V1, NUCB1, CrkL, SerpinD1, Fen1, GATA-4, ProSAAS, PARK7, and NET1) maintained high classification ability. Specific proteins correlated with hemoglobin, coagulation factors, hypertension, and high-flow nasal cannula intervention (P < 0.01). Time-course analysis of the 28 leading proteins demonstrated no significant temporal changes within the COVID-19 cohort. NLP analysis identified multi-system expression of the key proteins, with the digestive and nervous systems being the leading systems.ConclusionsThe plasma proteome of critically ill COVID-19 patients was distinguishable from that of non-COVID-19 sepsis controls and healthy control subjects. The leading 28 proteins and their subset of 9 proteins yielded accurate classification models and are expressed in multiple organ systems. The identified COVID-19 proteomic signature helps elucidate COVID-19 pathophysiology and may guide future COVID-19 treatment development.

Identification of patients' smoking status using an explainable AI approach: a Danish electronic health records case study.

Smoking is a critical risk factor responsible for over eight million annual deaths worldwide. It is essential to obtain information on smoking habits to advance research and implement preventive measures such as screening of high-risk individuals. In most countries, including Denmark, smoking habits are not systematically recorded and at best documented within unstructured free-text segments of electronic health records (EHRs). This would require researchers and clinicians to manually navigate through extensive amounts of unstructured data, which is one of the main reasons that smoking habits are rarely integrated into larger studies. Our aim is to develop machine learning models to classify patients' smoking status from their EHRs. This study proposes an efficient natural language processing (NLP) pipeline capable of classifying patients' smoking status and providing explanations for the decisions. The proposed NLP pipeline comprises four distinct components, which are; (1) considering preprocessing techniques to address abbreviations, punctuation, and other textual irregularities, (2) four cutting-edge feature extraction techniques, i.e. Embedding, BERT, Word2Vec, and Count Vectorizer, employed to extract the optimal features, (3) utilization of a Stacking-based Ensemble (SE) model and a Convolutional Long Short-Term Memory Neural Network (CNN-LSTM) for the identification of smoking status, and (4) application of a local interpretable model-agnostic explanation to explain the decisions rendered by the detection models. The EHRs of 23,132 patients with suspected lung cancer were collected from the Region of Southern Denmark during the period 1/1/2009-31/12/2018. A medical professional annotated the data into 'Smoker' and 'Non-Smoker' with further classifications as 'Active-Smoker', 'Former-Smoker', and 'Never-Smoker'. Subsequently, the annotated dataset was used for the development of binary and multiclass classification models. An extensive comparison was conducted of the detection performance across various model architectures. The results of experimental validation confirm the consistency among the models. However, for binary classification, BERT method with CNN-LSTM architecture outperformed other models by achieving precision, recall, and F1-scores between 97% and 99% for both Never-Smokers and Active-Smokers. In multiclass classification, the Embedding technique with CNN-LSTM architecture yielded the most favorable results in class-specific evaluations, with equal performance measures of 97% for Never-Smoker and measures in the range of 86 to 89% for Active-Smoker and 91-92% for Never-Smoker. Our proposed NLP pipeline achieved a high level of classification performance. In addition, we presented the explanation of the decision made by the best performing detection model. Future work will expand the model's capabilities to analyze longer notes and a broader range of categories to maximize its utility in further research and screening applications.

Random forest predictive modeling of prolonged hospital length of stay in elderly hip fracture patients

BackgroundIn elderly individuals suffering from hip fractures, a prolonged hospital length of stay (PLOS) not only heightens the probability of patient complications but also amplifies mortality risks. Yet, most elderly hip fracture patients present compromised baseline health conditions. Additionally, PLOS leads to increased expenses for patient treatment and care, while also diminishing hospital turnover rates. This, in turn, jeopardizes the prompt allocation of beds for urgent cases.MethodsA retrospective study was carried out from October 2021 to November 2023 on 360 elderly hip fracture patients who underwent surgical treatment at West China Hospital. The 75th percentile of the total patient cohort’s hospital stay duration, which was 12 days, was used to define prolonged hospital length of stay (PLOS). The cohort was divided into training and testing datasets with a 70:30 split. A predictive model was developed using the random forest algorithm, and its performance was validated and compared with the Lasso regression model.ResultsOut of 360 patients, 103 (28.61%) experienced PLOS. A Random Forest classification model was developed using the training dataset, identifying 10 essential variables. The Random Forest model achieved perfect performance in the training set, with an area under the curve (AUC), balanced accuracy, Kappa value, and F1 score of 1.000. In the testing set, the model’s performance was assessed with an AUC of 0.846, balanced accuracy of 0.7294, Kappa value of 0.4325, and F1 score of 0.6061.ConclusionThis study aims to develop a prognostic model for predicting delayed discharge in elderly patients with hip fractures, thereby improving the accuracy of predicting PLOS in this population. By utilizing machine learning models, clinicians can optimize the allocation of medical resources and devise effective rehabilitation strategies for geriatric hip fracture patients. Additionally, this method can potentially improve hospital bed turnover rates, providing latent benefits for the healthcare system.

Ensemble Machine Learning Classification Models for Predicting Pavement Condition

Forecasting pavement performance condition is essential within the pavement management system to optimize decisions with regard to planning maintenance and rehabilitation projects. Accurate forecasts facilitate timely interventions and assist in formulating cost-effective asset management plans. Data-driven machine learning models that utilize historical data to improve forecasting precision have gained attention in the field of asset management. Although numerous studies have employed regression-based models to forecast pavement condition, transportation asset management often operates according to condition index ranges rather than exact values. Therefore, classification models are suitable for predicting pavement condition grades and determining the appropriate maintenance type for pavement assets. This research focuses on developing five machine learning classification models to predict pavement condition: random forest; gradient boost; support vector machine; k-nearest neighbors; and artificial neural network. To enhance prediction performance, these models are integrated using ensemble methods, including voting and stacking. The classification models are developed using a dataset from the Georgia Department of Transportation that documented the condition of asphalt pavements for predefined maintenance sections between 2017 and 2021. A voting ensemble model constructed with the two best-performing individual classification models reached the highest accuracy rate at 83%. Although the performance of individual models fluctuates, ensemble models consistently produce a top-tier performance regardless of the variations in data sampling. Therefore, ensemble methods are recommended for developing pavement condition prediction models to improve accuracy and achieve a more consistent quality of predictions. The findings of this research will provide transportation agencies with information to help them strengthen their forecasting practices in relation to pavement condition, thereby improving their maintenance planning and cost savings.

Radiomics-based Analysis of Intestinal Ultrasound Images for Inflammatory Bowel Disease: A Feasibility Study

Abstract Background The increasing adoption of intestinal ultrasound (IUS) for monitoring inflammatory bowel diseases (IBD) by IBD providers has uncovered new challenges regarding standardized image interpretation and limitations as a research tool. Artificial intelligence approaches can help address these challenges. We aim to determine the feasibility of radiomic analysis of IUS images and to determine if a radiomics-based classification model can accurately differentiate between normal and abnormal IUS images. We will also compare the radiomic-based model’s performance to a convolutional neural network (CNN)-based classification model to understand which method is more effective for extracting meaningful information from IUS images. Methods Retrospectively analyzing IUS images obtained during routine outpatient visits, we developed and tested radiomic-based and CNN-based models to distinguish between normal and abnormal images, with abnormal images defined as bowel wall thickness &amp;gt;3mm or bowel hyperemia with modified Limberg score &amp;gt; 1 (both are surrogate markers for inflammation). Model performances were measured by area under the receiver operator curve (AUC). Results For this feasibility study, 125 images (33% abnormal) were analyzed. A radiomic-based model using XG boost yielded the best classifier model with average test AUC 0.98, 93.8% sensitivity, 93.8% specificity, and 93.7% accuracy. The CNN-based classification model yielded an average testing AUC of 0.75. Conclusions Radiomic analysis of IUS images is feasible, and a radiomic-based classification model could accurately differentiate abnormal from normal images. Our findings establish methods to facilitate future radiomic-based IUS studies that can help standardize image interpretation and expand IUS research capabilities.

Research on grammatical error correction algorithm in English translation via deep learning

Abstract This study provides a concise overview of a grammatical error correction algorithm that is based on an encoder-decoder machine translation structure. Additionally, it incorporates the attention mechanism to enhance the algorithm’s performance. Subsequently, simulation experiments were conducted to compare the improved algorithm with an algorithm based on a classification model and an algorithm based on the traditional translation model using open corpus data and English translations from freshmen. The results demonstrated that the optimized algorithm yielded superior intuitive error correction outcomes. When applied to both the open corpus and the English translations of college freshmen, the optimized error correction algorithm outperformed the others. The traditional translation model-based algorithm came in second, while the classification model-based algorithm showed the least favorable performance. Furthermore, all three error correction algorithms experienced a decrease in performance when dealing with English compositions from freshmen. However, the optimized algorithm exhibited a relatively smaller decline.

Autism spectrum disorder identification using multi‐model deep ensemble classifier with transfer learning

AbstractIdentifying autism spectrum disorder (ASD) symptoms accurately is a challenging task. The traditional subjective diagnostic process of ASD relies on time‐consuming behavioural and psychological observations. In this study, we introduce an ensemble learning‐based classification model using an open‐access database focusing on functional magnetic resonance imaging (fMRI). We propose a novel multi‐model ensemble classifier (MMEC) and multisite ensemble classifier (MSEC) with transfer learning (TL) for ASD classification to improve the prediction accuracy. The MMEC utilizes four base classifiers, Inception V3, ResNet50, MobileNet, and DenseNet to boost the performance of the individual convolutional neural network (CNN) models. The MSEC combined the base classifiers trained from different data sites. We evaluate the two models with ensemble averaging, weighted averaging, and stacking methods. The proposed MMEC with stacking shows the state of art performance compared to MSEC, improving the prediction accuracy by 3.25%. The obtained results have shown an accuracy of 97.82%, 97.82%, and 97.78% for ensemble averaging, weighted averaging, and stacking methods, respectively, on multi‐site datasets. The ensemble classifier MMEC performed better than a single classifier on the multi‐site dataset. The proposed MMEC opens a new paradigm to design a universal ASD classification framework.

Expanding the defect image dataset of composite material coating with enhanced image-to-image translation

In the defect detection based on machine vision, the limited datasets have consistently impeded the efficacy of deep learning in defect identification. Restricted datasets lead to inadequate model generalization and reduced detection accuracy. Creating simulated images is one proposed solution to address this challenge. However, existing defect image generation methods have limitations in diversity and realism. An enhanced Image-to-image translation method, named E-Pix2Pix, is proposed for enhancing defect image datasets of composite material coating on solid motors to expand the current dataset and enhance the precision of classification models. This method not only improves the quality of generated images, but also has strong generalization ability. This study examines how different convolution kernel sizes and the coefficient of the L1 loss function affect the generation performance. The results of the experiments show that the defect images generated by E-Pix2Pix have realistic visual effects and better capture the essential features of defects. The structure similarity index measurement (SSIM) value reaches approximately 0.9 under appropriate parameters. Moreover, this study intends to investigate how the content of generated images impacts the classification model. By doubling the dataset size using the generated images, the accuracy of ResNet50 model recognition can be improved by 7%. The accuracy of ResNet101 model recognition can be improved by 5% when the dataset is expanded to 1.5 times. The generated images have harmful effects on the weaker models. Our method has also been validated on two public datasets, and satisfactory results have been obtained.

Measurement errors and implications for preprocessing in miniaturised near-infrared spectrometers: Classification of sweet and bitter almonds as a case of study.

Near-infrared (NIR) spectroscopy is a well-established analytical technique that has been used in many applications over the years. Due to the advancements in the semiconductor industry, NIR instruments have evolved from benchtop instruments to miniaturised portable devices. The miniaturised NIR instruments have gained more interest in recent years because of the fast and robust measurements they provide with almost no sample pretreatments. However, due to the very different configurations and characteristics of these instruments, they need a dedicated optimization of the measurement conditions, which is crucial for obtaining reliable results. To comprehensively grasp the capabilities and potentials offered by these sensors, it is imperative to examine errors that can affect the raw data, which is a facet frequently overlooked. In this study, measurement error covariance and correlation matrices were calculated and then visually inspected to gain insight into the error structures associated with the devices, and to find the optimal preprocessing technique that may result in the improvement of the models built. This strategy was applied to the classification of sweet and bitter almonds, which were measured with the three portable low-cost NIR devices (SCiO, FlameNIR+ and NeoSpectra Micro Development Kit) after removing the shelled, since their classification is of utmost importance for the almond industry. The results showed that bitter almonds can be classified from sweet almonds using any of the instruments after selecting the optimal preprocessing, obtained through inspection of covariance and correlation matrices. Measurements obtained with FlameNIR+device provided the best classification models with an accuracy of 98%. The chosen strategy provides new insight into the performance characterization of the fast-growing miniaturised NIR instruments.

Negative rivalry in use: toward a knowledge-sharing perspective in the digital economy era

Purpose This study aims to introduce and prove the existence of negative rivalry in use, which should be an integral part of goods taxonomy, from the perspective of knowledge sharing and further present the critical role of knowledge sharing in the digital economy era by reviewing the literature, theoretical analysis and real-world cases. It also aims to open a new door for re-recognizing knowledge sharing through an interdisciplinary framework. Design/methodology/approach This study proves the existence of negative rivalry through both theoretical analysis (4-E model) and real-world cases, especially the cases of Tesla and ChatGPT, and puts up new reasons for knowledge sharing in the era of digital economy through interdisciplinary methods. Findings The authors find out that there are many new phenomena beyond the spectrum of current goods taxonomy, especially beyond the priori understanding of rivalry in use. Digital platforms such as ChatGPT should have been “used up” in no time, for they have attracted so massive users according to (positive) rivalry in use, or should have been unchanged at most according to non-rivalry in use. But what we see is their rapid upgrading with the help of billions of users. The reason is that negative rivalry in use has completely been neglected. The authors find out that the process of knowledge sharing unveils the unrecognized attribute of rivalry in use, i.e. negative rivalry in use, which serves as the fundamental driving force of the breathtaking growth of all kinds of digital platforms. Originality/value This study originally put up a 4-E model of goods’ rivalry in use, the brand new term, i.e. negative rivalry in use, and proves its existence and working mechanism from the perspective of knowledge sharing. With the introduction of negative rivalry in use, the traditional four-type goods classification model is extended into a six-type model, which may be a sound marginal contribution, to the best of the authors’ knowledge. The study may reshape people’s mindsets on goods usage, especially knowledge management, into a more open-sharing model because it shows that there is very likely a positive-sum game instead of a zero- or negative-sum game for shared knowledge per se and its platform in the process of knowledge sharing in the era of digital economy.

Performance Evaluation of Convolutional Neural Network Models for Classification of Highway Hidden Distresses with GPR B-Scan Images

Despite the considerable advancements in automated identification methods of highway hidden distress with ground-penetrating radar (GPR) images, there still exist challenges in realizing automated identification of highway hidden distress owing to the quantity, variability, and reliability of the distress samples and diversity of classification models. Firstly, the dataset collected contains 31,640 samples categorized into four categories: interlayer debonding, interlayer loosening, interlayer water seepage, and structural loosening from 1500 km highway, for obtaining larger enough samples and covering the variable range of distress samples. Secondly, the distresses were labeled by experienced experts, and the labels were verified with drilled cores to ensure their reliability. Lastly, 18 exemplary convolutional neural network (CNN) models from 8 different architectures were evaluated using evaluation metrics such as precision, recall, and f1-score. Further, confusion matrix and Grad-CAM techniques were utilized to analyze these models. The experimental results show that VGG13 performed most prominently and stably, while the lightweight network SqueezeNet1_1 performed particularly well with a batch size of 64. Furthermore, this study indicates that models with fewer layers can achieve comparable or better performance than deeper models.