Pre-processing Approach Research Articles

A New Breast Cancer Discovery Strategy: A Combined Outlier Rejection Technique and an Ensemble Classification Method

Annually, many people worldwide lose their lives due to breast cancer, making it one of the most prevalent cancers in the world. Since the disease is becoming more common, early detection of breast cancer is essential to avoiding serious complications and possibly death as well. This research provides a novel Breast Cancer Discovery (BCD) strategy to aid patients by providing prompt and sensitive detection of breast cancer. The two primary steps that form the BCD are the Breast Cancer Discovery Step (BCDS) and the Pre-processing Step (P2S). In the P2S, the needed data are filtered from any non-informative data using three primary operations: data normalization, feature selection, and outlier rejection. Only then does the diagnostic model in the BCDS for precise diagnosis begin to be trained. The primary contribution of this research is the novel outlier rejection technique known as the Combined Outlier Rejection Technique (CORT). CORT is divided into two primary phases: (i) the Quick Rejection Phase (QRP), which is a quick phase utilizing a statistical method, and (ii) the Accurate Rejection Phase (ARP), which is a precise phase using an optimization method. Outliers are rapidly eliminated during the QRP using the standard deviation, and the remaining outliers are thoroughly eliminated during ARP via Binary Harris Hawk Optimization (BHHO). The P2S in the BCD strategy indicates that data normalization is a pre-processing approach used to find numeric values in the datasets that fall into a predetermined range. Information Gain (IG) is then used to choose the optimal subset of features, and CORT is used to reject incorrect training data. Furthermore, based on the filtered data from the P2S, an Ensemble Classification Method (ECM) is utilized in the BCDS to identify breast cancer patients. This method consists of three classifiers: Naïve Bayes (NB), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The Wisconsin Breast Cancer Database (WBCD) dataset, which contains digital images of fine-needle aspiration samples collected from patients’ breast masses, is used herein to compare the BCD strategy against several contemporary strategies. According to the outcomes of the experiment, the suggested method is very competitive. It achieves 0.987 accuracy, 0.013 error, 0.98 recall, 0.984 precision, and a run time of 3 s, outperforming all other methods from the literature.

Deep learning enables the use of ultra-high-density array in DNBSEQ.

DNBSEQ employs a patterned array to facilitate massively parallel sequencing of DNA nanoballs (DNBs), leading to a considerable boost in throughput. By employing the ultra-high-density (UHD) array with an increased density of DNB binding sites, the throughput of DNBSEQ can be further expanded. However, the typical imaging system of the DNBSEQ sequencer is unable to resolve adjacent DNBs spaced smaller than the resolution limit, resulting in poor base-calling performance of the UHD array and hindering its practical application. In this study, we propose a deep-learning-based DNB image super-resolution network named DNBSRN to address this problem. DNBSRN has a specifically designed structure for DNB images and employs a histogram-matching-based preprocessing approach. For the eight DNB image datasets generated from the DNBSEQ sequencer using UHD arrays with 360nm pitch, the base-calling performances are significantly improved after super-resolution reconstruction by DNBSRN and reached a comparable level to those of the regular density array. In terms of reconstruction speed, DNBSRN takes only 7.61ms for an input image with 500 × 500 pixels, which minimizes its influence on throughput. Furthermore, compared with state-of-the-art super-resolution networks, DNBSRN demonstrates superior performance in terms of both the quality and speed of DNB image reconstruction. DNBSRN successfully addresses the DNB image super-resolution task. Integrating DNBSRN into the image analysis workflow of DNBSEQ will allow for the application of UHD array, hence enabling a considerable improvement in throughput as well as tremendous savings in unit reagent cost.

Thinning of Balti Script : Way Forward to Balti OCR

Natural language is one of the applications of Artificial Intelligence, which trains machines to do the jobs in human language. OCR is one of the fields where the writing efforts are omitted and text images are converted into editable text. An OCR may have post and preprocessing to enhance the text image more suitable for the rest of the OCR process. Thinning is the preprocessing approach in which the characters, words and text is thinned to its one-pixel skeleton. Much of the work has been done in the various languages of the world as well as Pakistani languages. The work on Balti OCR is nonexistent. In this study, a thinning algorithm is proposed for the Balti language, a language spoken in the northern areas of Pakistan and India. Many of the Balti images were tested with the proposed algorithm and the proposed system produced accurate results by giving a one pixel skeleton of input image. The proposed algorithm tested with hundreds of Balti language images and selected results are presented in this paper. The current research has many directions including the way forward to building Balti OCR, Balti ICR (both segmentation based and segmentation free).

Combinatorial Order Pre-processing Search (COPS): A new pre-processing strategy for large-scale interpretable data analysis in process analytical technologies

Combinatorial Order Pre-processing Search (COPS), a novel approach for optimizing data pre-processing is proposed in this work. Unlike simultaneous hyperparameter optimization, COPS employs a priori optimization to reduce computational time while refining the search space for preprocessing sequences and combinations. It allows for setting a maximum number of pre-processing methods, while efficiently searching through combinations of methods with chemically relevant knowledge. In this work, 67 calibration datasets across various analytical techniques, including fluorescence spectroscopy, gas chromatography (GC), near-infrared spectroscopy (NIR), mid-infrared spectroscopy (MIR), visible-near-infrared spectroscopy (Vis-NIR), Raman spectroscopy, nuclear magnetic resonance (NMR) spectroscopy, and voltammetry were evaluated. COPS yielded significant improvements over existing methodologies based on design of experiment and compounded pre-processing approaches. The COPS outperformed the other methods, resulting in an average root mean square error of prediction (RMSEP) reduction of 31.7%, while also reduced the complexity (number of latent variables) of the model which allows for easier interpretation. This underscores the importance of combinatorial order set theory for the search of pre-processing method combinations (without fixing the sequence of pre-processing methods) to enhance model performance and interpretation. The novel COPS approach can be employed in process analytical technology (such as inline, online or at-line chemical sensing analytics) to enhance predictive accuracy and operational efficiency, fundamentally transforming the quality and reliability of chemical process monitoring and control.

A Novel Pre-Processing Approach and Benchmarking Analysis for Faster, Robust, and Improved Small Object Detection Methods

A Novel Pre-Processing Approach and Benchmarking Analysis for Faster, Robust, and Improved Small Object Detection Methods

A divide-and-conquer reconstruction method for defending against adversarial example attacks

In recent years, defending against adversarial examples has gained significant importance, leading to a growing body of research in this area. Among these studies, pre-processing defense approaches have emerged as a prominent research direction. However, existing adversarial example pre-processing techniques often employ a single pre-processing model to counter different types of adversarial attacks. Such a strategy may miss the nuances between different types of attacks, limiting the comprehensiveness and effectiveness of the defense strategy. To address this issue, we propose a divide-and-conquer reconstruction pre-processing algorithm via multi-classification and multi-network training to more effectively defend against different types of mainstream adversarial attacks. The premise and challenge of the divide-and-conquer reconstruction defense is to distinguish between multiple types of adversarial attacks. Our method designs an adversarial attack classification module that exploits the high-frequency information differences between different types of adversarial examples for their multi-classification, which can hardly be achieved by existing adversarial example detection methods. In addition, we construct a divide-and-conquer reconstruction module that utilizes different trained image reconstruction models for each type of adversarial attack, ensuring optimal defense effectiveness. Extensive experiments show that our proposed divide-and-conquer defense algorithm exhibits superior performance compared to state-of-the-art pre-processing methods.

A systematic literature review of neuroimaging coupled with machine learning approaches for diagnosis of attention deficit hyperactivity disorder

ProblemAttention deficit hyperactivity disorder (ADHD) is the most commonly found neurodevelopmental condition among children with an estimated 2.5% to 9% global prevalence. While ADHD has been regarded as a lifelong condition, its early diagnosis elevates the probability of recovery and normal life for children. Despite clinical diagnosis being the primary one, substantial developments in ADHD diagnosis have been made during the past decade.AimSeveral imaging-based technologies and approaches have been presented in the existing literature including magnetic resonance imaging (MRI) and functional MRI (fMRI). In addition, the deployment of machine learning and deep learning models has paved the way for automated diagnosis of ADHD which increases both accuracy and robustness of ADHD detection. A comprehensive and systematic literature review (SLR) of imaging technologies and machine learning approaches is highly desired to comprehend the current status of such approaches concerning their potential and challenges to outline future directions. Although a substantial body of literature exists on imaging-based ADHD diagnosis, comprehensive SRL on such approaches is scarce. This SLR aims to provide a comprehensive overview of imaging-based ADHD diagnosis with emphasis on machine learning approaches, reveals their pros and cons, and provides potential future research directions thereby contributing to the scientific community to accelerate further research for ADHD diagnosis.MethodsThis SRL focuses on analyzing recently published studies between 2010 and 2023. For this purpose, preferred reporting items for systematic review and meta-analyses (PRISMA) approach is performed in this study. Five eminent academic databases Web of Science, ACM, Springerlink, Elsevier, and PubMed are selected for article search. The SLR follows a systematic methodology comprising article search, selection based on inclusion and exclusion criteria, and rigorous assessment for categorization.ResultsIt is found that MRI and fMRI are the dominant approaches integrated with machine learning models for ADHD detection and function near-infrared spectroscopy is also adopted by a few studies. Predominantly, the ATHENA preprocessing approach is used to preprocess MRI data before model training. Due to the public availability of the ADHD-200 dataset, it is widely used in the existing literature while a few studies utilized their self-collected datasets. Machine learning models are the choice of the majority of the studies, particularly, the support vector machines model has been widely used for ADHD detection. Feature fusion is observed to be a better choice for obtaining more accurate results.ConclusionMachine learning and deep learning models provide automated ADHD detection with better accuracy and robustness, however, such models are not generalizable and their performance varies concerning the locality of data used for experiments. In addition, the heterogeneity of data collection from various devices is a challenge, and the use of a standard device may provide better solutions. The lack of labeled data also adds difficulties to training models. Besides the use of MRI and fMRI, other novel technologies should be explored for better ADHD detection performance.

Revolutionizing Time Series Data Preprocessing with a Novel Cycling Layer in Self-Attention Mechanisms

This paper introduces an innovative method for enhancing time series data preprocessing by integrating a cycling layer into a self-attention mechanism. Traditional approaches often fail to capture the cyclical patterns inherent to time series data, which affects the predictive model accuracy. The proposed method aims to improve models’ ability to identify and leverage these cyclical patterns, as demonstrated using the Jena Climate dataset from the Max Planck Institute for Biogeochemistry. Empirical results show that the proposed method enhances forecast accuracy and speeds up model fitting compared to the conventional techniques. This paper contributes to the field of time series analysis by providing a more effective preprocessing approach.

Predicting Methanol Space-Time Yield from CO? Hydrogenation Using Machine Learning: Statistical Evaluation of Penalized Regression Techniques

This study investigates the effectiveness of machine learning techniques, specifically penalized regression models Ridge Regression, Lasso Regression, and Elastic Net Regression in predicting methanol space-time yield (STY) from CO? hydrogenation data. Using a dataset derived from Cu-based catalyst research, the study implemented a comprehensive preprocessing approach, including data cleaning, imputation, outlier removal, and normalization. The models were rigorously evaluated through 10-fold cross-validation and tested on unseen data. Ridge Regression outperformed the other models, achieving the lowest Root Mean Squared Error (RMSE) of 0.7706, Mean Absolute Error (MAE) of 0.5627, and Mean Squared Error (MSE) of 0.5938. In comparison, Lasso and Elastic Net Regression models exhibited higher error metrics. Feature importance analysis revealed that Gas Hourly Space Velocity (GHSV) and Molar Masses of Support significantly influence catalytic activity. These findings suggest that Ridge Regression is a promising tool for accurately predicting methanol production, providing valuable insights for optimizing catalytic processes and advancing sustainable practices in chemical engineering.

Towards the definition of a standard in TMS-EEG data preprocessing

Combining Non-Invasive Brain Stimulation (NIBS) techniques with the recording of brain electrophysiological activity is an increasingly widespread approach in neuroscience. Particularly successful has been the simultaneous combination of Transcranial Magnetic Stimulation (TMS) and Electroencephalography (EEG). Unfortunately, the strong magnetic pulse required to effectively interact with brain activity inevitably induces artifacts in the concurrent EEG acquisition. Therefore, a careful but aggressive pre-processing is required to efficiently remove artifacts. Unfortunately, as already reported in the literature, different preprocessing approaches can introduce variability in the results. Here we aim at characterizing the three main TMS-EEG preprocessing pipelines currently available, namely ARTIST (Wu et al., 2018), TESA (Rogasch et al., 2017) and SOUND/SSP-SIR (Mutanen et al., 2018, 2016), providing an insight to researchers who need to choose between different approaches. Differently from previous works, we tested the pipelines using a synthetic TMS-EEG signal with a known ground-truth (the artifacts-free to-be-reconstructed signal). In this way, it was possible to assess the reliability of each pipeline precisely and quantitatively, providing a more robust reference for future research. In summary, we found that all pipelines performed well, but with differences in terms of the spatio-temporal precision of the ground-truth reconstruction. Crucially, the three pipelines impacted differently on the inter-trial variability, with ARTIST introducing inter-trial variability not already intrinsic to the ground-truth signal.

Chemometrics and analytical blank on the at-line monitoring of Zika-VLP production using near-infrared spectroscopy

The Zika disease caused by the Zika virus was declared a Public Health Emergency by the World Health Union (WHO), with microcephaly as the most critical consequence. Aiming to reduce the spread of the virus, biopharmaceutical organizations invest in vaccine research and production, based on multiple platforms. A crescent vaccine production approach is based on virus-like particles (VLP), for not having genetic material in its composition, hypoallergenic and non-mutant character. For bioprocess, it is essential to have means of real-time monitoring, which can be assessed using process analysis techniques such as Near-infrared (NIR) spectroscopy, that can be combined with chemometric methods, like Partial-Least Squares (PLS) and Artificial Neural Networks (ANN) for prediction of biochemical variables. This work proposes a biochemical Zika VLP upstream production at-line monitoring model using NIR spectroscopy comparing sampling conditions (with or without cells), analytical blank (air, ultrapure water), and spectra pre-processing approaches. Seven experiments in a benchtop bioreactor using recombinant baculovirus/Sf9 insect cell platform in serum-free medium were performed to obtain biochemical and spectral data for chemometrics modeling (PLS and ANN), composed by a random data split (80 % calibration, 20 % validation) for cross-validation of the PLS models and 70 % training, 15 % testing, 15 % validation for ANN. The best models generated in the present work presented an average absolute error of 1.59 × 105 cell/mL for density of viable cells, 2.37 % for cell viability, 0.25 g/L for glucose, 0.007 g/L for lactate, 0.138 g/L for glutamine, 0.18 g/L for glutamate, 0,003 g/L for ammonium, and 0.014 g/L for potassium.

A Fresh Revisit of the Issues and Improvements in Impulse Invariance Filter Design for Infinite Impulse Response Filters

The objective of this paper is to first present some issues with impulse invariance filter (IIF) design during the design of digital infinite impulse response (IIR) filters. Engineers are often confused about some inconsistent observations. For instance, if the impulse response of a digital filter is designed using the impulse invariance procedure, then the analog and digital filters’ frequency and step responses are very different. Two simple remedies are presented in this paper. One is a post-processing approach that scales the frequency and step responses of the digital filter by the sampling interval T. Another one is a pre-processing approach that scales the impulse response of the analog filter by T. However, even after these remedies, there is still a steady state bias in the step response of the digital filter for certain cases where there is discontinuity in the analog impulse response. A recommendation is to include a correction term in the digital filter. After that, the steady state bias in the digital filter is then suppressed. Moreover, the MATLAB R2021a command “impinvar” needs to also include a correction term so that the frequency and step responses can be more accurate in the digital filter. Two comparative studies were carried out to compare the improved IIF filter with three competing digital IIR filter design methods. Although the above issues and improvements have been proposed by researchers in the past, many researchers, engineers, and students are still not aware of them. This paper provides a fresh revisit of these issues and improvements by using figures, equations, and examples. Proper credits are also given to those researchers who first pointed out those issues and improvements. It is hoped that through an open access journal, future rediscovery of issues and improvements in IIF can be prevented.

A search-and-fill strategy to code generation for complex software requirements

Context:The realm of software development has seen significant transformations with the rise of Low-Code Development (LCD) and the integration of Artificial Intelligence (AI), particularly large language models, into coding practices. The proliferation of open-source software also offers vast resources for developers. Objective:We aim to combine the benefits of modifying retrieved code with the use of an extensive code repository to tackle the challenges of complex control structures and multifunctional requirements in software development. Method:Our study introduces a Search-and-Fill strategy that utilizes natural language processing (NLP) to dissect complex software requirements. It extracts control structures and identifies atomic function points. By leveraging large-scale pre-trained models, the strategy searches for these elements to fill in the automatically transformed program structures derived from descriptions of control structures. This process generates a code snippet that includes program control structures and the implementations of various function points, thereby facilitating both code reuse and efficient development. Results:We have validated the effectiveness of our strategy in generating code snippets. For natural language requirements involving multifunctional complex structures, we constructed two datasets: the Basic Complex Requirements Dataset (BCRD) and the Advanced Complex Requirements Dataset (ACRD). These datasets are based on natural language descriptions and Python code that were randomly extracted and combined. For the code snippets to be generated, we achieved the best results with the ACRD dataset, with BLEU-4 scores reaching up to 0.6326 and TEDS scores peaking at 0.7807. Conclusion:The Search-and-Fill strategy successfully generates a comprehensive code snippets, integrating essential control structures and functions to streamline the development process. Experimental results substantiate our strategy’s efficacy in optimizing code reuse by effectively integrating preprocessing and selection optimization approach. Future research will focus on enhancing the recognition of complex software requirements and further refining the code snippets.

BFFN: A novel balanced feature fusion network for fair facial expression recognition

Facial expression recognition (FER) technology has become increasingly mature and applicable in recent years. However, it still suffers from the bias of expression class, which can lead to unfair decisions for certain expression classes in applications. This study aims to mitigate expression class bias through both pre-processing and in-processing approaches. First, we analyze the output of existing models and demonstrate the existence of obvious class bias, particularly for underrepresented expressions. Second, we develop a class-balanced dataset constructed through data generation, mitigating unfairness at the data level. Then, we propose the Balanced Feature Fusion Network (BFFN), a class fairness-enhancing network. The BFFN mitigates the class bias by adding facial action units (AU) to enrich expression-related features and allocating weights in the AU feature fusion process to improve the extraction ability of underrepresented expression features. Finally, extensive experiments on datasets (RAF-DB and AffectNet) provide evidence that our BFFN outperforms existing FER models, improving the fairness by at least 16%.

Raman laser intensity and sample clarification on biochemical monitoring over Zika-VLP upstream stages

In the current biopharmaceutical scenario, constant bioprocess monitoring is crucial for the quality and integrity of final products. Thus, process analytical techniques, such as those based on Raman spectroscopy, have been used as multiparameter tracking methods in pharma bioprocesses, which can be combined with chemometric tools, like Partial Least Squares (PLS) and Artificial Neural Networks (ANN). In some cases, applying spectra pre-processing techniques before modeling can improve the accuracy of chemometric model fittings to observed values. One of the biological applications of these techniques could have as a target the virus-like particles (VLP), a vaccine production platform for viral diseases. A disease that has drawn attention in recent years is Zika, with large-scale production sometimes challenging without an appropriate monitoring approach. This work aimed to define global models for Zika VLP upstream production monitoring with Raman considering different laser intensities (200 mW and 495 mW), sample clarification (with or without cells), spectra pre-processing approaches, and PLS and ANN modeling techniques. Six experiments were performed in a benchtop bioreactor to collect the Raman spectral and biochemical datasets for modeling calibration. The best models generated presented a mean absolute error and mean relative error respectively of 3.46 × 105 cell/mL and 35 % for viable cell density (Xv); 4.1 % and 5 % for cell viability (CV); 0.245 g/L and 3 % for glucose (Glc); 0.006 g/L and 18 % for lactate (Lac); 0.115 g/L and 26 % for glutamine (Gln); 0.132 g/L and 18 % for glutamate (Glu); 0.0029 g/L and 3 % for ammonium (NH4+); and 0.0103 g/L and 2 % for potassium (K+). Sample without conditioning (with cells) improved the models' adequacy, except for Glutamine. ANN better predicted CV, Gln, Glu, and K+, while Xv, Glc, Lac, and NH4+ presented no statistical difference between the chemometric tools. For most of the assessed experimental parameters, there was no statistical need for spectra pre-filtering, for which the models based on the raw spectra were selected as the best ones. Laser intensity impacts quality model predictions in some parameters, Xv, Gln, and K+ had a better performance with 200 mW of intensity (for PLS, ANN, and ANN, respectively), for CV the 495 mW laser intensity was better (for PLS), and for the other biochemical variables, the use of 200 or 495 mW did not impact model fitting adequacy.

A detection method of oil content for maize kernels based on CARS feature selection and deep sparse autoencoder feature extraction

To achieve accurate, rapid, and non-destructive oil content determination in maize, a neural fitting model that combines feature selection and feature extraction is proposed. Competitive adaptive re-weighted sampling (CARS) is used to choose features, while the deep sparse autoencoder (DSAE) network is utilized to extract features. The 160 spectral data from the near-infrared spectra public datasets of maize served as experimental samples. Several preprocessing approaches were tested, and the first-order derivatives fared the best. To capture the various degrees of abstract features in spectral data, SSAE networks with two or three hidden layers are developed. The number of nodes in the network's hidden layer (30, 50, 70, 100, 200, 300, respectively) and the network's sparsity parameter (0.001, 0.004, 0.007, 0.01, 0.04, 0.07, 0.1, 0.2, …, 1) are tuned to generate partial least squares regression (PLSR) models for testing the feature learning effect. The highest performance comes from a three-layer network with 200 hidden layer nodes and a sparsity parameter of 0.04. This network extracts three levels of features from the preprocessed spectral data: F1, F2, and F3. Full_cars, F1_cars, F2_cars, and F3_cars are obtained using the CARS algorithm for variable selection on the preprocessed spectral data, F1, F2, and F3, respectively. They are then integrated into a final feature set to build a neural-fitting network (FNN). After training and testing, the test set has a correlation coefficient of 0.964205 and an mean square error (MSE) of 0.00636809. Comparing this model to support vector machine regression (SVR), PLSR, and gaussian process regression (GPR), the findings demonstrate that the model described in this study outperforms the others in terms of fitting accuracy and generalization performance. To summarize, this paper introduces a new regression analysis method based on near-infrared spectra.

Deep learning based capsule networks for breast cancer classification using ultrasound images

Purposes: Breast cancer (BC) is a disease in which the breast cells multiply uncontrolled. Breast cancer is one of the most often diagnosed malignancies in women worldwide. Early identification of breast cancer is critical for limiting the impact on affected people's health conditions. The influence of technology and artificial intelligence approaches (AI) in the health industry is tremendous as technology advances. Deep learning (DL) techniques are used in this study to classify breast lumps. Materials and Methods: The study makes use of two distinct breast ultrasound images (BUSI) with binary and multiclass classification. To assist the models in understanding the data, the datasets are exposed to numerous preprocessing and hyperparameter approaches. With data imbalance being a key difficulty in health analysis, due to the likelihood of not having a condition exceeding that of having the disease, this study applies a cutoff stage to impact the decision threshold in the datasets data augmentation procedures. The capsule neural network (CapsNet), Gabor capsule network (GCN), and convolutional neural network (CNN) are the DL models used to train the various datasets. Results: The findings showed that the CapsNet earned the maximum accuracy value of 93.62% while training the multiclass data, while the GCN achieved the highest model accuracy of 97.08\% when training the binary data. The models were also evaluated using a variety of performance assessment parameters, which yielded consistent results across all datasets. Conclusion: The study provides a non-invasive approach to detect breast cancer; and enables stakeholders, medical practitioners, and health research enthusiasts a fresh view into the analysis of breast cancer detection with DL techniques to make educated judgements.

Advancing thyroid care: An accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques

The worldwide prevalence of thyroid disease is on the rise, representing a chronic condition that significantly impacts global mortality rates. Machine learning (ML) approaches have demonstrated potential superiority in mitigating the occurrence of this disease by facilitating early detection and treatment. However, there is a growing demand among stakeholders and patients for reliable and credible explanations of the generated predictions in sensitive medical domains. Hence, we propose an interpretable thyroid classification model to illustrate outcome explanations and investigate the contribution of predictive features by utilizing explainable AI. Two real-time thyroid datasets underwent various preprocessing approaches, addressing data imbalance issues using the Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTE-ENN). Subsequently, two hybrid classifiers, namely RDKVT and RDKST, were introduced to train the processed and selected features from Univariate and Information Gain feature selection techniques. Following the training phase, the Shapley Additive Explanation (SHAP) was applied to identify the influential characteristics and corresponding values contributing to the outcomes. The conducted experiments ultimately concluded that the presented RDKST classifier achieved the highest performance, demonstrating an accuracy of 98.98 % when trained on Information Gain selected features. Notably, the features T3 (triiodothyronine), TT4 (total thyroxine), TSH (thyroid-stimulating hormone), FTI (free thyroxine index), and T3_measured significantly influenced the generated outcomes. By balancing classification accuracy and outcome explanation ability, this study aims to enhance the clinical decision-making process and improve patient care.

ConjunctiveNet: an improved deep learning-based conjunctive-eyes segmentation and severity detection model

PurposeThe study aims to enhance the detection and classification of conjunctival eye diseases' severity through the development of ConjunctiveNet, an innovative deep learning framework. This model incorporates advanced preprocessing techniques and utilizes a modified Otsu’s method for improved image segmentation, aiming to improve diagnostic accuracy and efficiency in healthcare settings.Design/methodology/approachConjunctiveNet employs a convolutional neural network (CNN) enhanced through transfer learning. The methodology integrates rescaling, normalization, Gaussian blur filtering and contrast-limited adaptive histogram equalization (CLAHE) for preprocessing. The segmentation employs a novel modified Otsu’s method. The framework’s effectiveness is compared against five pretrained CNN architectures including AlexNet, ResNet-50, ResNet-152, VGG-19 and DenseNet-201.FindingsThe study finds that ConjunctiveNet significantly outperforms existing models in accuracy for detecting various severity stages of conjunctival eye conditions. The model demonstrated superior performance in classifying four distinct severity stages – initial, moderate, high, severe and a healthy stage – offering a reliable tool for enhancing screening and diagnosis processes in ophthalmology.Originality/valueConjunctiveNet represents a significant advancement in the automated diagnosis of eye diseases, particularly conjunctivitis. Its originality lies in the integration of modified Otsu’s method for segmentation and its comprehensive preprocessing approach, which collectively enhance its diagnostic capabilities. This framework offers substantial value to the field by improving the accuracy and efficiency of conjunctival disease severity classification, thus aiding in better healthcare delivery.

Detecting information from Twitter on landslide hazards in Italy using deep learning models

BackgroundMass media are a new and important source of information for any natural disaster, mass emergency, pandemic, economic or political event, or extreme weather event affecting one or more communities in a country. Several techniques have been developed for data mining in social media for many natural events, but few of them have been applied to the automatic extraction of landslide events. In this study, Twitter has been investigated to detect data about landslide events in Italian-language. The main aim is to obtain an automatic text classification on the basis of information about natural hazards. The text classification for landslide events in Italian-language has still not been applied to detect this type of natural hazard.ResultsOver 13,000 data were extracted within Twitter considering five keywords referring to landslide events. The dataset was classified manually, providing a solid base for applying deep learning. The combination of BERT + CNN has been chosen for text classification and two different pre-processing approaches and bert-model have been applied. BERT-multicase + CNN without preprocessing archived the highest values of accuracy, equal to 96% and AUC of 0.96.ConclusionsTwo advantages resulted from this studio: the Italian-language classified dataset for landslide events fills that present gap of analysing natural events using Twitter. BERT + CNN was trained to detect this information and proved to be an excellent classifier for the Italian language for landslide events.