Classification Quality Research Articles

Spot the bot: the inverse problems of NLP

This article concerns the problem of distinguishing human-written and bot-generated texts. In contrast to the classical problem formulation, in which the focus falls on one type of bot only, we consider the problem of distinguishing texts written by any person from those generated by any bot; this involves analysing the large-scale, coarse-grained structure of the language semantic space. To construct the training and test datasets, we propose to separate not the texts of bots, but bots themselves, so the test sample contains the texts of those bots (and people) that were not in the training sample. We aim to find efficient and versatile features, rather than a complex classification model architecture that only deals with a particular type of bots. In the study we derive features for human-written and bot generated texts, using clustering (Wishart and K-Means, as well as fuzzy variations) and nonlinear dynamic techniques (entropy-complexity measures). We then deliberately use the simplest of classifiers (support vector machine, decision tree, random forest) and the derived characteristics to identify whether the text is human-written or not. The large-scale simulation shows good classification results (a classification quality of over 96%), although varying for languages of different language families.

HyperKAN: Kolmogorov-Arnold Networks Make Hyperspectral Image Classifiers Smarter.

In traditional neural network designs, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov-Arnold Network (KAN) presents a promising alternative to MLP, offering the potential to enhance prediction accuracy. In this paper, we studied KAN-based networks for pixel-wise classification of hyperspectral images. Initially, we compared baseline MLP and KAN networks with varying numbers of neurons in their hidden layers. Subsequently, we replaced the linear, convolutional, and attention layers of traditional neural networks with their KAN-based counterparts. Specifically, six cutting-edge neural networks were modified, including 1D (1DCNN), 2D (2DCNN), and 3D convolutional networks (two different 3DCNNs, NM3DCNN), as well as transformer (SSFTT). Experiments conducted using seven publicly available hyperspectral datasets demonstrated a substantial improvement in classification accuracy across all the networks. The best classification quality was achieved using a KAN-based transformer architecture.

Reducing the amount of computations at the second stage of an ensemble classifier with stacking on mine-detection drones

Using drones to search for mines is a promising area that allows accelerating the process of demining an area and reducing the danger to people. To increase the probability of detecting mines, drones use sensors with different operating principles. Each type of sensor requires specialized processing, which is carried out at the first stage of the ensemble classifier with stacking. The sensor signals are combined at the second stage of the ensemble classifier, where a multilayer perceptron is usually used as a neural network. Acceleration of terrain survey requires that processing be carried out in real time on the computing equipment of the drone itself. This, in turn, requires a reduction in the amount of computation for all algorithms used on the drone. The article is devoted to reducing the amount of computation when implementing a multilayer perceptron. The original homogeneous structure of the perceptron, when each of the neurons of the previous layer has connections with all neurons of the next layer, is redundant, since it does not take into account the features of the processed data set. The article proposes a method for finding a balance between the dimensionality and number of layers of the perceptron, the time interval between the procedures of thinning connections, the training step and the number of connections removed at a time. Using thinning connections taking into account other parameters allows you to reduce the amount of calculations by 80% or more, while saving and even increasing the quality of classification. There are removed connections that do not make a noticeable contribution to the quality of classification, but introduce additional noise into the perceptron training process and the formation of the output result.

Objects Diversity and its Impact on Classification Quality in Dispersed Data Environments

This paper studies a classification model dedicated to dispersed data, employing the k-nearest neighbors method as a base classifier and a Radial Basis Function (RBF) network as a fusion method. Focusing on classifying objects described by different attributes, the study systematically reduces common objects in local tables to assess the robustness of the model. Surprisingly, the proposed approach shows resilience in reducing common objects without significantly affecting key metrics such as F-measure, balanced accuracy and overall accuracy. Moreover, the studied model performs better on balanced data. This research contributes valuable insights into dispersed data classification, demonstrating the model’s effectiveness in handling diverse objects and attributes. The findings have implications for fields reliant on dispersed data storage, such as healthcare, banking, and surveillance, showcasing the model’s potential for real-world applications.

Метод класифікації аритмій на ЕКГ-сигналі

This paper proposes an improved arrhythmia classification method based on a convolutional neural network (CNN) applied to ECG signals. To improve the quality of classification, ECG signals were split into fragments containing three cardiac cycles with the current cardiac cycle in the center. The improved CNN architecture includes the addition of batch normalization layers, an additional convolutional layer, and a dropout layer, which improvs the model's accuracy. In addition, hyperparameters were optimized for new CNN architecture. The model was trained data of the MIT-BIH Arrhythmia Database to classify nine classes of ECG. The achieved average accuracy of 99.26% confirms the effectiveness of the proposed method in diagnosing various types of arrhythmias

Analysis of the effectiveness of using U-net architecture for classification and segmentation of glioma in MRI images

The purpose of the research is to analyze the efficiency of the U-net neural network architecture in decision support systems for glioma diagnostics and segmentation of brain areas affected by it on MRI images.Methods. To conduct experimental studies, a training dataset was generated and the data was normalized. A software implementation of the U-Net neural network architecture was performed using the Keras framework in the Python programming language. The neural network model was trained.Results. A series of experiments were conducted, during which error and classification matrices were obtained, the efficiency of classification of the trained neural network model for the "Tumor" and "No tumor" classes was assessed using metrics such as Recall, Precision and F1-measure, and the quality of segmentation of glioma-affected areas on the test data set was assessed. The quality of segmentation was assessed using the IoU metric, which reflects the ratio of the areas of the bounding boxes and is used to assess the accuracy of the spatial correspondence of the predicted segmented areas highlighted on the masks. Based on the results of testing the neural network model in solving the problem of segmenting brain areas affected by glioma, the average value of the IoU metric was 0.812, which is an acceptable result.Conclusion. The testing results showed that the neural network model based on the U-net architecture is able to effectively diagnose the presence of glioma with acceptable values of the classification and segmentation quality metrics, which indicates the possibility of using this neural network model in medical decision support systems for glioma diagnostics, as well as its segmentation on MRI images. However, it is advisable to refine this neural network model to reduce the number of false negative classification results, which is critically important in medical diagnostics.

Hyperdimensional Brain-Inspired Learning for Phoneme Recognition With Large-Scale Inferior Colliculus Neural Activities.

Develop a novel and highly efficient framework that decodes Inferior Colliculus (IC) neural activities for phoneme recognition. We propose using Hyperdimensional Computing (HDC) to support an efficient phoneme recognition algorithm, in contrast to widely applied Deep Neural Networks (DNN). The high-dimensional representation and operations in HDC are rooted in human brain functionalities and naturally parallelizable, showing the potential for efficient neural activity analysis. Our proposed method includes a spatial and temporal-aware HDC encoder that effectively captures global and local patterns. As part of our framework, we deploy the lightweight HDC-based algorithm on a highly customizable and flexible hardware platform, i.e., Field Programmable Gate Arrays (FPGA), for optimal algorithm speedup. To evaluate our method, we record IC neural activities on gerbils while playing the sound of different phonemes. We compare our proposed method with multiple baseline machine learning algorithms in recognition quality and learning efficiency, across different hardware platforms. The results show that our method generally achieves better classification quality than the best-performing baseline. Compared to the Deep Residual Neural Network (i.e., ResNet), our method shows a speedup up to 74×, 67×, 210× on CPU, GPU, and FPGA respectively. We achieve up to 15% (10%) higher accuracy in consonant (vowel) classification than ResNet. By leveraging brain-inspired HDC for IC neural activity encoding and phoneme classification, we achieve orders of magnitude runtime speedup while improving accuracy in various challenging task settings. Decoding IC neural activities is an important step to enhance understanding about human auditory system. However, these responses from the central auditory system are noisy and contain high variance, demanding large-scale datasets and iterative model fine-tuning. The proposed HDC-based framework is more scalable and viable for future real-world deployment thanks to its fast training and overall better quality.

Revised Clinical Practice Guideline of Korean Pancreatobiliary Association for Common Bile Duct Stones: Purpose and Process of Guidelines

Common bile duct (CBD) stones carry a risk of complications including biliary obstruction, acute cholangitis and pancreatitis. Endoscopic retrograde cholangiopancreatography (ERCP) is regarded as the standard of treatment for CBD stones nowadays. However, ERCP can cause severe adverse events such as bleeding, post-ERCP pancreatitis and perforation. Therefore, it is important to provide practical guideline to manage CBD stones for clinicians. The Korean Pancreatobiliary Association (KPBA) established the first Korean guidelines for the management of CBD stones in 2013. Taking together the recently developed techniques for CBD stones and evidence newly obtained, the committee of the KPBA decided to perform an extensive revision of the guidelines. These revised guidelines were developed based on consensusbased guideline using Delphi methods. The main topics of these guidelines fall under the following topics: 1) diagnosis, 2) endoscopic management, 3) endoscopic management for difficult CBD stones. The specific recommendations are presented with the quality of evidence and classification of recommendations.

Development of a neural network with a layer of trainable activation functions for the second stage of the ensemble classifier with stacking

One of the promising directions for improving the quality of object recognition in images and parallelizing calculations is the use of ensemble classifiers with stacking. A neural network at the second level makes it possible to achieve the resulting quality of classification, which is significantly higher than each of the networks of the first level separately. The classification quality of the entire ensemble classifier with stacking depends on the efficiency of the neural networks at the first stage, their number, and the quality of the classification of the neural network of the second stage. This paper proposes a neural network architecture for the second stage of the ensemble classifier, which combines the approximating properties of traditional neurons and learning activation functions. Gaussian Radial Basis Functions (RBFs) were chosen to implement the learned activation functions, which are summed with the learned weights. The experimental studies showed that when working with the CIFAR-10 data set, the best results are obtained when six RBFs are used. A comparison with the use of multilayer perceptron (MLP) in the second stage showed a reduction in classification errors by 0.45–1.9 % depending on the number of neural networks in the first stage. At the same time, the proposed neural network architecture for the second degree had 1.69–3.7 times less learning coefficients than MLP. This result is explained by the fact that the use of an output layer with ordinary neurons allowed us not to enter into the architecture many learning activation functions for each output signal of the first stage, but to limit ourselves to only one. Since the results were obtained on the CIFAR-10 universal data set, a similar effect could be obtained on a large number of similar practical data sets.

An ensemble deep learning model for fast classification of Twitter spam

Twitter spam needs to be detected and arrested quickly. The paper examines methods for classification of spam in terms of determination of important features, comparative performance of classification models, and improvement in time performance for classification. It presents a conceptualization of several novel rich, deep, and naïve features. The extraction processes for rich and deep features increase the time complexity of spam classification. To address this, the proposed model selectively segregates and combines features to enable near real-time processing. This supersedes the time performance of standard machine learning and deep learning models, with no compromise on the quality of classification.

Evolutionary Grid Optimization and Deep Learning for Improved In Vitro Cellular Spheroid Localization

The recently developed high-throughput system for cell spheroid generation (SpheroWell) is a promising technology for cost- and time-efficient in vitro analysis of, for example, chondrogenic differentiation. It is a compartmental growth surface where spheroids develop from a cell monolayer by self-assembling and aggregation. In order to automatize the analysis of spheroids, we aimed to develop imaging software and improve the localization of cell compartments and fully formed spheroids. Our workflow provides automated detection and localization of spheroids in different formation stages within Petri dishes based on images created with a low-budget camera imaging setup. This automated detection enables a fast and inexpensive analysis workflow by processing a stack of images within a short period of time, which is essential for the extraction of early readout parameters. Our workflow combines image processing algorithms and deep learning-based image localization/segmentation methods like Mask R-CNN and Unet++. These methods are refined by an evolution strategy for automated grid detection, which is able to improve the overall segmentation and classification quality. Besides the already pre-trained neural networks and predefined image processing parameters, our evolution-based post-processing provides the required adaptability for our workflow to deliver a consistent and reproducible quality. This is especially important due to the use of a low-budget imaging setup with various light conditions. The to-be-detected objects of the three different stages show improved results using our evolutionary post-processing for monolayer and starting aggregation with Dice coefficients of 0.7301 and 0.8562, respectively, compared with the raw scores of 0.2879 and 0.8187. The Dice coefficient of the fully formed spheroids in both cases is 0.8829. With our algorithm, we provide automated analyses of cell spheroid by self-assembling in SpheroWell dishes, even if the images are created using a low-budget camera setup.

Analysis of the Biennial Productivity of Arabica Coffee with Google Earth Engine in the Northeast Region of São Paulo, Brazil

Numerous challenges are associated with the classification of satellite images of coffee plantations. The spectral similarity with other types of land use, variations in altitude, topography, production system (shaded and sun), and the change in spectral signature throughout the phenological cycle are examples that affect the process. This research investigates the influence of biennial Arabica coffee productivity on the accuracy of Landsat-8 image classification. The Google Earth Engine (GEE) platform and the Random Forest algorithm were used to process the annual and biennial mosaics of the Média Mogiana Region, São Paulo (Brazil), from 2017 to 2023. The parameters evaluated were the general hits of the seven classes of land use and coffee errors of commission and omission. It was found that the seasonality of the plant and its development phases were fundamental in the quality of coffee classification. The use of biennial mosaics, with Landsat-8 images, Brightness, Greenness, Wetness, SRTM data (elevation, aspect, slope), and LST data (Land Surface Temperature) also contributed to improving the process, generating a classification accuracy of 88.8% and reducing coffee omission errors to 22%.

State-of-the-Art Results with the Fashion-MNIST Dataset

In September 2024, the Fashion-MNIST dataset will be 7 years old. Proposed as a replacement for the well-known MNIST dataset, it continues to be used to evaluate machine learning model architectures. This paper describes new results achieved with the Fashion-MNIST dataset using classical machine learning models and a relatively simple convolutional network. We present the state-of-the-art results obtained using the CNN-3-128 convolutional network and data augmentation. The developed CNN-3-128 model containing three convolutional layers achieved an accuracy of 99.65% in the Fashion-MNIST test image set. In addition, this paper presents the results of computational experiments demonstrating the dependence between the number of adjustable parameters of the convolutional network and the maximum acceptable classification quality, which allows us to optimise the computational cost of model training.

Testing the Impact of Pansharpening Using PRISMA Hyperspectral Data: A Case Study Classifying Urban Trees in Naples, Italy

Urban trees support vital ecological functions and help with the mitigation of and adaption to climate change. Yet, their monitoring and management require significant public resources. remote sensing could facilitate these tasks. Recent hyperspectral satellite programs such as PRISMA have enabled more advanced remote sensing applications, such as species classification. However, PRISMA data’s spatial resolution (30 m) could limit its utility in urban areas. Improving hyperspectral data resolution with pansharpening using the PRISMA coregistered panchromatic band (spatial resolution of 5 m) could solve this problem. This study addresses the need to improve hyperspectral data resolution and tests the pansharpening method by classifying exemplative urban tree species in Naples (Italy) using a convolutional neural network and a ground truths dataset, with the aim of comparing results from the original 30 m data to data refined to a 5 m resolution. An evaluation of accuracy metrics shows that pansharpening improves classification quality in dense urban areas with complex topography. In fact, pansharpened data led to significantly higher accuracy for all the examined species. Specifically, the Pinus pinea and Tilia x europaea classes showed an increase of 10% to 20% in their F1 scores. Pansharpening is seen as a practical solution to enhance PRISMA data usability in urban environments.

An Approach to a Priori Assessment of Fuzzy Classification Models in Monitoring Tasks

The article addresses the problems of using automation tools to perform monitoring and management tasks applicable to assessing the quality of fuzzy classification models, where the classification procedure is implemented on the basis of knowledge (rules) in the absence of the training set. An approach is proposed to obtain a priori assessments of the classification quality based on the study of the used model sensitivity to changes in the values of internal parameters during the corresponding modeling. The interpretation of the modeling results in the form of risk assessment caused by the self-imperfection of the classification models is obtained. The article provides an example of a fuzzy classification model based on a comparison of the current state of a monitoring object described using fuzzy features with a set of predefined typical states, which form corresponding fuzzy equal (close) states (monitoring situations). The comparison is carried out using the fuzzy implication operation provided that the required reliability is met. The example of this model demonstrates how the type of implication operation, as well as the internal features of the model, affect the results of classification, and appropriate indicators are proposed, which are both an interpretation of generally accepted indicators for assessing the classification quality, and unique, inherent in the considered model. Computational experiments were carried out, which made it possible to obtain graphs of changes in classification quality assessment indicators for the considered model and its modification and visualize the influence of internal parameters of the model on the results of its application. A number of indicators are proposed that allow for an a priori assessment of the risks arising from the application of the model before its actual application.

Evaluation of geomorphological classification uncertainty using rough set theory: A case study of Shaanxi Province, China

AbstractGeomorphological classification is affected by classification principles, indicators, methods, and data resolution, which can lead to uncertainty in the results. Such uncertainty directly affects the quality and subsequent applications of geomorphological classification. To quantify and control the uncertainty, it is important to select an appropriate and effective method for evaluating the uncertainty of geomorphological classification. This study evaluated the uncertainty of geomorphological classification of Shaanxi Province at the ground‐feature class and image scales, which derived from rough set theory: rough entropy, approximate classification quality, and approximate classification accuracy. The three indicators helped effectively assess the uncertainty of geomorphological classification at multi‐scale and measured the degree to which different factors affected the uncertainty of geomorphological classification. The relative impacts of three factors on the uncertainty of classification decreased in the order of classification methods, data resolution, and classification indicators. This finding is helpful to objectively evaluate and control the uncertainty generated in the process and results of geomorphological classification, and can provide targeted reference and guidance for future geomorphological classification work, which is more conducive to decision‐making and application. At the same time, this study is also a beneficial supplement to the geomorphological research based on digital terrain analysis.

Visitor’s Perception towards Event Management in Kathmandu Valley

Background: Events are significant drivers of tourism and play a key role in the development and marketing of destinations. In Kathmandu Valley, the increasing trend of event organization has raised questions about visitor perceptions toward event management. However, no previous study has explored this topic in Nepal. Objective: The study aims to analyze visitor perceptions of event management in Kathmandu Valley, focusing on how affective engagement influences these perceptions and identifying areas for improvement. Method: An exploratory research design was adopted to uncover the realities of visitor perceptions. Quantitative data was collected from 343 respondents and analyzed using both descriptive and inferential statistics. Structural Equation Modeling (SEM) was employed to examine the relationships between variables. Result: The study found that affective engagement significantly impacts visitor perceptions. Attendees expect high-quality service from event companies and are likely to share their experiences on social media platforms like Facebook. Most respondents were between the ages of 21-30, indicating a strong youth interest in event attendance. The analysis revealed that one independent variable, affective engagement, had a significant effect on one hypothesis related to contingent factors, while another hypothesis was rejected. Conclusion: Event management companies in Kathmandu Valley should prioritize affective engagement, addressing attendees' emotions and feelings. Enhancing internal management practices can lead to better service delivery, addressing common issues such as overcrowding, location, and security. Additionally, adopting modern technologies could further attract and satisfy attendees, improving overall event experiences. Paper Types: Research Paper Key words: Event management, Planned behavior, Affective engagement, SEM, Quality of the event JEL Classification: C38, D9, N95, N3

Classification of Logging Data Using Machine Learning Algorithms

A log data analysis plays an important role in the uranium mining process. Automating this analysis using machine learning methods improves the results and reduces the influence of the human factor. In particular, the identification of reservoir oxidation zones (ROZs) using machine learning allows a more accurate determination of ore reserves, and correct lithological classification allows the optimization of the mining process. However, training and tuning machine learning models requires labeled datasets, which are hardly available for uranium deposits. In addition, in problems of interpreting logging data using machine learning, data preprocessing is of great importance, in other words, a transformation of the original dataset that allows improving the classification or prediction result. This paper describes a uranium well log (UWL) dataset generated with the employment of floating data windows and designed to solve the problems of identifying ROZ and lithological classification (LC) on sandstone-type uranium deposits. Comparative results of the ways of solving these problems using classical machine learning methods and ensembles of machine learning algorithms are presented. It has been shown that an increase in the size of the floating data window can improve the quality of ROZ classification by 7–9% and LC by 6–12%. As a result, the best-quality indicators for solving these problems were obtained, f1_score_macro = 0.744 (ROZ) and accuracy = 0.694 (LC), using the light gradient boosting machine and extreme gradient boosting, respectively.

A multi-task deep learning approach for real-time view classification and quality assessment of echocardiographic images

High-quality standard views in two-dimensional echocardiography are essential for accurate cardiovascular disease diagnosis and treatment decisions. However, the quality of echocardiographic images is highly dependent on the practitioner’s experience. Ensuring timely quality control of echocardiographic images in the clinical setting remains a significant challenge. In this study, we aimed to propose new quality assessment criteria and develop a multi-task deep learning model for real-time multi-view classification and image quality assessment (six standard views and “others”). A total of 170,311 echocardiographic images collected between 2015 and 2022 were utilized to develop and evaluate the model. On the test set, the model achieved an overall classification accuracy of 97.8% (95%CI 97.7–98.0) and a mean absolute error of 6.54 (95%CI 6.43–6.66). A single-frame inference time of 2.8 ms was achieved, meeting real-time requirements. We also analyzed pre-stored images from three distinct groups of echocardiographers (junior, senior, and expert) to evaluate the clinical feasibility of the model. Our multi-task model can provide objective, reproducible, and clinically significant view quality assessment results for echocardiographic images, potentially optimizing the clinical image acquisition process and improving AI-assisted diagnosis accuracy.

CNN based fault event classification and power quality enhancement in hybrid power system

CNN based fault event classification and power quality enhancement in hybrid power system