Proposed Classification Method Research Articles

Consistency re‐evaluation in analytic hierarchy process based on simulated consistent matrices

AbstractA new approach to re‐evaluating consistency in the analytic hierarchy process (AHP) using simulated consistent matrices is presented. The proposed consistency evaluation method makes use of statistically significant deviations from the average consistency measure for the simulated matrices. This addresses most of the deficiencies of the conventional consistency ratio (CR) method. A pairwise comparison matrix (PCM) is adjudged inconsistent by the proposed method if its consistency measure exceeds the modeled consistency threshold. Comparison of the consistency evaluation for simulated nearly‐consistent matrices using the proposed method shows a statistically significant reduction of the order‐specific bias in comparison with the CR method. The proportion of nearly consistent matrices which are evaluated as ‘inconsistent’ increases more than three‐folds when the evaluation is done using the CR method. Several examples are presented which illustrate the advantages of the proposed method and differences in classification with the CR approach. Evaluation of consistency using the proposed method of statistically derived thresholds from simulated, nearly consistent matrices is more nuanced and objective, as well as intuitive in its interpretability.

Driver Drowsiness Detection Using Gray Wolf Optimizer Based on Face and Eye Tracking

It is critical today to provide safe and collision-free transport. As a result, identifying the driver’s drowsiness before their capacity to drive is jeopardized. An automated hybrid drowsiness classification method that incorporates the artificial neural network (ANN) and the gray wolf optimizer (GWO) is presented to discriminate human drowsiness and fatigue for this aim. The proposed method is evaluated in alert and sleep-deprived settings on the driver drowsiness detection of video dataset from the National Tsing Hua University Computer Vision Lab. The video was subjected to various video and image processing techniques to detect the drivers’ eye condition. Four features of the eye were extracted to determine the condition of drowsiness, the percentage of eyelid closure (PERCLOS), blink frequency, maximum closure duration of the eyes, and eye aspect ratio (ARE). These parameters were then integrated into an ANN and combined with the proposed method (gray wolf optimizer with ANN [GWOANN]) for drowsiness classification. The accuracy of these models was calculated, and the results demonstrate that the proposed method is the best. An Adadelta optimizer with 3 and 4 hidden layer networks of (13, 9, 7, and 5) and (200, 150, 100, 50, and 25) neurons was utilized. The GWOANN technique had 91.18% and 97.06% accuracy, whereas the ANN model had 82.35% and 86.76%.

A Proposal for Classification of Additive Manufacturing in Architecture

The latest developments in computational design has caused a massive paradigm shift in contemporary architecture. While the power of the new computational tools allow the designers to design fluid and dynamic transformational forms replacing the rigid norms of current processes, it also accelerates the integration of design and making. Digital manufacturing and in particular Additive Manufacturing (AM) has shown to have a big impact on how designers think of complex mechanisms and geometries while designing. This paper is motivated by the latest developments in Additive Manufacturing (AM) in large scale structures and the opportunities arising from manufacturing components, modules and even monolith buildings. This paper is part of a larger research on Additive Manufacturing (AM) and has evolved organically out of necessity while trying to map out the latest developments about large scale AM processes. The aim of this paper is to better understand and position the latest developments therefore challenges on a number of diverse subjects through a proposed classification method.

Behavior-based ransomware classification: A particle swarm optimization wrapper-based approach for feature selection

Ransomware is malware that encrypts the victim’s data and demands a ransom for a decryption key. The increasing number of ransomware families and their variants renders the existing signature-based anti-ransomware techniques useless; thus, behavior-based detection techniques have gained popularity. A difficulty in behavior-based ransomware detection is that hundreds of thousands of system calls are obtained as analysis output, making the manual investigation and selection of ransomware-specific features infeasible. Moreover, manual investigation of the analysis output requires domain experts, who are expensive to hire and unavailable in some cases. Machine learning methods have shown success in a wide range of scientific domains to automate and address the problem of feature selection and extraction from noisy and high-dimensional data. However, automated feature selection is under-explored in malware detection. This study proposes an automated feature selection method that utilizes particle swarm optimization for behavior-based ransomware detection and classification. The proposed method considers the significance of various feature groups of the data in ransomware detection and classification and performs feature selection based on groups’ significance. The experimental results show that, in most cases, the proposed method achieves comparable or significantly better performance than other state-of-the-art methods used in this study for benchmarking. In addition, this article presents an in-depth analysis of the significance of various features groups and the features selected by the proposed method in ransomware detection and classification.

Transfer Learning Models for Detecting Six Categories of Phonocardiogram Recordings.

Background and aims: Auscultation is a cheap and fundamental technique for detecting cardiovascular disease effectively. Doctors’ abilities in auscultation are varied. Sometimes, there may be cases of misdiagnosis, even when auscultation is performed by an experienced doctor. Hence, it is necessary to propose accurate computational tools to assist auscultation, especially in developing countries. Artificial intelligence technology can be an efficient diagnostic tool for detecting cardiovascular disease. This work proposed an automatic multiple classification method for cardiovascular disease detection by heart sound signals. Methods and results: In this work, a 1D heart sound signal is translated into its corresponding 3D spectrogram using continuous wavelet transform (CWT). In total, six classes of heart sound data are used in this experiment. We combine an open database (including five classes of heart sound data: aortic stenosis, mitral regurgitation, mitral stenosis, mitral valve prolapse and normal) with one class (pulmonary hypertension) of heart sound data collected by ourselves to perform the experiment. To make the method robust in a noisy environment, the background deformation technique is used before training. Then, 10 transfer learning networks (GoogleNet, SqueezeNet, DarkNet19, MobileNetv2, Inception-ResNetv2, DenseNet201, Inceptionv3, ResNet101, NasNet-Large, and Xception) are used for comparison. Furthermore, other models (LSTM and CNN) are also compared with our proposed algorithm. The experimental results show that four transfer learning networks (ResNet101, DenseNet201, DarkNet19 and GoogleNet) outperformed their peer models with an accuracy of 0.98 to detect the multiple heart diseases. The performances have been validated both in the original heart sound and the augmented heart sound using 10-fold cross validation. The results of these 10 folds are reported in this research. Conclusions: Our method obtained high classification accuracy even under a noisy background, which suggests that the proposed classification method could be used in auxiliary diagnosis for cardiovascular diseases.

Fast computation of binary search tree for PWA functions representation using intersection classification

Explicit Model Predictive Control (eMPC) aims to overcome the runtime computational effort from Model Predictive Control (MPC) by computing offline the overall optimization procedure. The result from eMPC is a Piecewise Affine (PWA) function that defines a relationship between the system state and the optimal control action. To improve the PWA evaluation during runtime, Binary Search Trees (BST) are employed to represent PWA functions, which may be time prohibitive considering the total time to obtain the tree. This note presents a new classification strategy of polyhedral regions with respect to hyperplanes to build BST for PWA functions. The proposed solution is based on the verification of intersection between regions and hyperplanes, resulting in a decrease by almost half in the number of optimization problems, and consequently, in the total time to build the BST, which is the main time-consuming task. The computational time improvement is verified on numerical examples of different sizes, where the same BST is obtained for the original and the proposed classification methods.

Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals Based on Compressed Sensing

In recent years, driver fatigue has become one of the main causes of road accidents. As a result, fatigue detection systems have been developed to warn drivers, and, among the available methods, EEG signal analysis is recognized as the most reliable method for detecting driver fatigue. This study presents an automated system for a two-stage classification of driver fatigue, using a combination of compressed sensing (CS) theory and deep neural networks (DNNs), that is based on EEG signals. First, CS theory is used to compress the recorded EEG data in order to reduce the computational load. Then, the compressed EEG data is fed into the proposed deep convolutional neural network for automatic feature extraction/selection and classification purposes. The proposed network architecture includes seven convolutional layers together with three long short-term memory (LSTM) layers. For compression rates of 40, 50, 60, 70, 80, and 90, the simulation results for a single-channel recording show accuracies of 95, 94.8, 94.6, 94.4, 94.4, and 92%, respectively. Furthermore, by comparing the results to previous methods, the accuracy of the proposed method for the two-stage classification of driver fatigue has been improved and can be used to effectively detect driver fatigue.

Surface Water Change Detection via Water Indices and Predictive Modeling Using Remote Sensing Imagery: A Case Study of Nuntasi-Tuzla Lake, Romania

Water body feature extraction using a remote sensing technique represents an important tool in the investigation of water resources and hydrological drought assessment. Nuntasi-Tuzla Lake, a component of the Danube Delta Natural Reserve, is located on the Romanian Black Sea littoral. On account of an event in summer 2020, when the lake surface water decreased significantly, this study aims to identify the variation of the Nuntasi-Tuzla Lake surface water over a long-term period in correlation with human intervention and climate change. To this end, it provides an analysis in the period 1965–2021 via hydrological drought indices and data mining classification. The latter approach is based on several water indices derived from Landsat TM/ETM+/OLI and MODIS full-time series datasets: Normalized Difference Vegetation Index (NDVI), Normalized Difference Vegetation Index (NDVI), Modified NDWI (MNDWI), Weighted Normalized Difference Water Index (WNDWI), and Water Ratio Index (WRI). The experimental results indicate that the proposed classification methods can extract relevant features from waterbodies using remote sensing imagery with a high accuracy. Moreover, the study shows a similarity in the evolution of surface water cover identified with the data mining classification and the drought periods detected in the flow data series for the Nuntasi and Sacele Rivers that supply the Nuntasi-Tuzla Lake. Overall, the results of our investigation show that human intervention and hydrological drought had an extensive impact on the long-term changes in surface water of the Nuntasi-Tuzla Lake.

On the Use of Uncertainty in Classifying Aedes Albopictus Mosquitoes

The re-emergence of mosquito-borne diseases (MBDs), which kill hundreds of thousands of people each year, has been attributed to increased human population, migration, and environmental changes. Convolutional neural networks (CNNs) have been used by several studies to recognise mosquitoes in images provided by projects such as Mosquito Alert to assist entomologists in identifying, monitoring, and managing MBD. Nonetheless, utilising CNNs to automatically label input samples could involve incorrect predictions, which may mislead future epidemiological studies. Furthermore, CNNs require large numbers of manually annotated data. In order to address the mentioned issues, this paper proposes using the Monte Carlo Dropout method to estimate the uncertainty scores in order to rank the classified samples to reduce the need for human supervision in recognising Aedes albopictus mosquitoes. The estimated uncertainty was also used in an active learning framework, where just a portion of the data from large training sets was manually labelled. The experimental results show that the proposed classification method with rejection outperforms the competing methods by improving overall performance and reducing entomologist annotation workload. We also provide explainable visualisations of the different regions that contribute to a set of samples' uncertainty assessment.

Method of Classification the Mobile Robot Workspace Based on the Analysis of a 3D Point Cloud

One of the main and most difficult tasks in the development of automotive systems is the classification of the workspace of a mobile robot. Based on the classification results, a local map of the area is built, with the help of which, then, the robot trajectory is planned. The article describes a method of classification the working area of an autonomous mobile robot moving in rough terrain. The developed classification method is based on the analysis of a three-dimensional point cloud obtained by a laser scan- ning 3D rangefinder. Using a scanning laser rangefinder allows you to classify the robot  s motion zone at any time of the day or year. A set of classification features is proposed, the calculation of which is carried out using the least square method and elements of probability theory and mathematical statistics. The classification of the robot workspace is carried out by four classes: "Flat surface", "Small roughness", "Large roughness" and "Obstacle". Each class characterizes the degree of passability of the robot movement surface. Classification results are saved as a local map of passability. In each cell of such a map a number is written that characterizes the passability of the region of the working area bounded by this cell. The developed classifier is integrated into the on-board control system of the wheeled mobile robot. The results of experimental studies confirming the efficiency and effectiveness of the proposed classification method are presented. The accuracy of class recognition of the mobile robot workspace has been determined. The developed classifier successfully operates in various conditions, including in winter and at dusk, but at the same time it has limitations when working in conditions of natural noise, such as rain, snow. The average classification accuracy with the minimal influence of natural noise is 92.3 %, and the execution time of each iteration does not exceed 0.085 s, which allows using developed classifier as a part of on-board control systems of autonomous mobile robots.

Integrating urban morphology and land surface temperature characteristics for urban functional area classification

ABSTRACT The classification of urban functional areas plays an important role in urban planning and resource management. Although previous studies have confirmed that different urban functional areas have different morphological structures and Land Surface Temperature (LST) characteristics, these two types of characteristics have rarely been fully integrated and used for functional area classification. In this paper, a new framework for classifying urban functional areas is proposed by combining urban morphological features and LST features. First, metrics are constructed from three levels, namely, building, road and region, which are used to portray urban morphology; LST is retrieved using thermal infrared remote sensing to reflect LST features with four metrics: the average temperature, maximum temperature, temperature difference and standard deviation of temperature. Then, the functional areas are classified into four categories: service/public land, commercial land, residential land and industrial land. A random forest algorithm is used to effectively fuse the features of these two categories and classify the functional areas. The effectiveness of the proposed framework is tested in the study area of Shenzhen City, Guangdong Province. The results show that the combined classification accuracy of the proposed classification method is 0.85, which is 0.26 higher than that of the classification model based on urban morphology and 0.1 higher than that of the classification model based on LST features. The proposed framework verifies that the integration of LST features into urban functional area classification is reliable and effectively combines urban morphology and LST features for functional area classification.

Detection of alertness-related EEG signals based on decision fused BP neural network

Alertness detection has been used to monitor operators in key positions to avoid accidents. The widely used methods (such as machine vision) are susceptible to external factors and cannot quantify alertness. In contrast, EEG has the advantages of intuitively reflecting brain activities and not being easily affected. Based on EEG signals, an alertness detection method using decision fused BP (back propagation, BP) neural network was presented. In this paper, we analyzed the EEG changes of 20 participants while performing tasks. During PVT (Psychomotor Vigilance Task, PVT), EEG signals were collected through the acquisition platform we designed, and KSS (Karolinska Sleepiness Scale, KSS) was completed. AR (autoregressive model, AR) and PSD (power spectral density, PSD) were applied to extract frequency domain features of EEG signals. The extracted features were then input into BP neural network separately. Afterwards, we used DS (Dempster–Shafer, DS) method to fuse output results of BP neural network. When comparing results of the proposed classification methods, we concluded that BP-DS method had the finest classification results (including AUC-ROC curve, accuracy, precision, and recall rate) with the accuracy increasing considerably from 0.661 to 0.911. In addition, among six EEG indices, Rβ,α+θ/β,α/β presented prominent changes during alertness variation. The proposed alertness classification algorithm monitors alertness continuously and avoids potential catastrophes caused by decreased alertness. It can be applied in monitoring systems to prevent mental fatigue and declined work efficiency of air traffic controllers, medical staff and other fields.

Towards an Improved Large-Scale Gridded Population Dataset: A Pan-European Study on the Integration of 3D Settlement Data into Population Modelling

Large-scale gridded population datasets available at the global or continental scale have become an important source of information in applications related to sustainable development. In recent years, the emergence of new population models has leveraged the inclusion of more accurate and spatially detailed proxy layers describing the built-up environment (e.g., built-area and building footprint datasets), enhancing the quality, accuracy and spatial resolution of existing products. However, due to the consistent lack of vertical and functional information on the built-up environment, large-scale gridded population datasets that rely on existing built-up land proxies still report large errors of under- and overestimation, especially in areas with predominantly high-rise buildings or industrial/commercial areas, respectively. This research investigates, for the first time, the potential contributions of the new World Settlement Footprint—3D (WSF3D) dataset in the field of large-scale population modelling. First, we combined a Random Forest classifier with spatial metrics derived from the WSF3D to predict the industrial versus non-industrial use of settlement pixels at the Pan-European scale. We then examined the effects of including volume and settlement use information into frameworks of dasymetric population modelling. We found that the proposed classification method can predict industrial and non-industrial areas with overall accuracies and a kappa-coefficient of ~84% and 0.68, respectively. Additionally, we found that both, integrating volume and settlement use information considerably increased the accuracy of population estimates between 10% and 30% over commonly employed models (e.g., based on a binary settlement mask as input), mainly by eliminating systematic large overestimations in industrial/commercial areas. While the proposed method shows strong promise for overcoming some of the main limitations in large-scale population modelling, future research should focus on improving the quality of the WFS3D dataset and the classification method alike, to avoid the false detection of built-up settlements and to reduce misclassification errors of industrial and high-rise buildings.

Varying coefficient linear discriminant analysis for dynamic data

Linear discriminant analysis (LDA) is an important classification tool in statistics and machine learning. This paper investigates the varying coefficient LDA model for dynamic data, with Bayes’ discriminant direction being a function of some exposure variable to address the heterogeneity. We propose a new least-square estimation method based on the B-spline approximation. The data-driven discriminant procedure is more computationally efficient than the dynamic linear programming rule [21]. We also establish the convergence rates for the corresponding estimation error bound and the excess misclassification risk. The estimation error in L2 distance is optimal for the low-dimensional regime and is near optimal for the high-dimensional regime. Numerical experiments on synthetic data and real data both corroborate the superiority of our proposed classification method.

Weighted Correlation Embedding Learning for Domain Adaptation.

Domain adaptation leverages rich knowledge from a related source domain so that it can be used to perform tasks in a target domain. For more knowledge to be obtained under relaxed conditions, domain adaptation methods have been widely used in pattern recognition and image classification. However, most of the existing domain adaptation methods only consider how to minimize different distributions of the source and target domains, which neglects what should be transferred for a specific task and suffers negative transfer by distribution outliers. To address these problems, in this paper, we propose a novel domain adaptation method called weighted correlation embedding learning (WCEL) for image classification. In the WCEL approach, we seamlessly integrated correlation learning, graph embedding, and sample reweighting into a unified learning model. Specifically, we extracted the maximum correlated features from the source and target domains for image classification tasks. In addition, two graphs were designed to preserve the discriminant information from interclass samples and neighborhood relations in intraclass samples. Furthermore, to prevent the negative transfer problem, we developed an efficient sample reweighting strategy to predict the target with different confidence levels. To verify the performance of the proposed method in image classification, extensive experiments were conducted with several benchmark databases, verifying the superiority of the WCEL method over other state-of-the-art domain adaptation algorithms.

Anomaly-based Network Intrusion Detection using Ensemble Machine Learning Approach

In this study, an Intrusion Detection System (IDS) is designed based on Machine Learning classifiers, and its performance is evaluated for the set of attacks entailed in the UNSW- NB15 dataset. UNSW- NB15 dataset contains 2,540,226 realistic network data instances and 49 features. Most research uses a representative sample of this dataset with present training and testing subsets, which includes 257,673 records in total. The dataset was submitted to visual data analysis to discover poten-tial reasons or flaws which likely challenge Machine Learning classifiers. Pre-processing strategies are necessary before this data can be used for data-driven prototype development for IDS because of the class representation imbalance with pattern counts and feature overlap. The method used for pre-processing is implemented by min-max scaling in the normalization phase, followed by applying Elastic Net and Sequential Feature Selection (SFS) algorithms. This work employed ensemble methods using three base classifiers, namely Balanced Bagging, XGBoost, and RF-HDDT, augmented to address the imbalance issue. Parameters of Balanced Bagging and XGBoost are tuned for the imbalanced data, and the Hellinger distance metric supplements random Forest to address the limitations of the default distance metric. Two new algorithms are proposed to address the class overlap issue in the dataset and applied during training. These two algorithms are leveraged to help improve the performance on the testing dataset by affecting the final classification decision made by three base classifiers as part of the ensemble classifier, which employs a majority vote combiner. The performance evaluation of the proposed method for binary and multi-category classification was evaluated using standard metrics, including those generated from the confusion matrix, and compared to other studies using the same dataset. The proposed design outperforms those reported in the literature by a significant margin for binary and multi-category classification cases.

Event Detection and Classification Using Deep Compressed Convolutional Neural Network

Recently, the number of different kinds of events on social media platforms show a tremendous increase in each second. Hence, event detection holds a very important role in the current scenario. However, event detection is challenging in information technology (IT). Several machine learning-based approaches are established for the event detection process, but it generates a high error and makes various information loss, affecting the system’s performance. Thus, the proposed work introduces a new detection strategy based on a deep learning architecture. In this, both text and image data are utilized for event detection. The different procedures for image and text databases are pre-processing, extraction and classification. The text data is pre-processed using four methods: lower case filter, tokenization, stemming, and stop word filter. An adaptive median filter (AMF) is utilized for pre-processing the image data. After the pre-processing stage, feature extraction is performed for text and image-based data in which most useful features are extracted. Finally, the varied events are detected and classified using the proposed Deep Compressed Convolutional Neural Network (DCCNN). The entire work is implemented using the PYTHON platform. The efficiency of the proposed model is measured by evaluating the performance metrics such as accuracy, recall, precision and F-measure. The simulation validation exhibits that the proposed classification method attains an improved accuracy of 97.1%, obtained precision is about 95.06%, recall value is 91.69%, and f-measure is 93.35%. The efficacy of the proposed deep learning method is proved by comparing the attained results with various state-of-the-art techniques.

The image description reduction in the set of descriptors on informativeness metric criteria base

The subject of the research is the methods of image classification on a set of key point descriptors in computer vision systems. The goal is to improve the performance of structural classification methods by introducing indexed hash structures on the set of the dataset reference images descriptors and a consistent chain combination of several stages of data analysis in the classification process. Applied methods: BRISK detector and descriptors, data hashing tools, search methods in large data arrays, metric models for the vector relevance estimation, software modeling. The obtained results: developed an effective method of image classification based on the introduction of high-speed search using indexed hash structures, that speeds up the calculation dozens of times; the gain in computing time increases with an increase of the number of reference images and descriptors in descriptions; the peculiarity of the classifier is that not an exact search is performed, but taking into account the permissible deviation of data from the reference; experimentally verified the effectiveness of the classification, which indicates the efficiency and effectiveness of the proposed method. The practical significance of the work is the construction of classification models in the transformed space of the hash data representation, the efficiency confirmation of the proposed classifiers modifications on image examples, development of applied software models implementing the proposed classification methods in computer vision systems.

Methodological foundation of a numerical taxonomy of urban form

Cities are complex products of human culture, characterised by a startling diversity of visible traits. Their form is constantly evolving, reflecting changing human needs and local contingencies, manifested in space by many urban patterns. Urban morphology laid the foundation for understanding many such patterns, largely relying on qualitative research methods to extract distinct spatial identities of urban areas. However, the manual, labour-intensive and subjective nature of such approaches represents an impediment to the development of a scalable, replicable and data-driven urban form characterisation. Recently, advances in geographic data science and the availability of digital mapping products open the opportunity to overcome such limitations. And yet, our current capacity to systematically capture the heterogeneity of spatial patterns remains limited in terms of spatial parameters included in the analysis and hardly scalable due to the highly labour-intensive nature of the task. In this paper, we present a method for numerical taxonomy of urban form derived from biological systematics, which allows the rigorous detection and classification of urban types. Initially, we produce a rich numerical characterisation of urban space from minimal data input, minimising limitations due to inconsistent data quality and availability. These are street network, building footprint and morphological tessellation, a spatial unit derivative of Voronoi tessellation, obtained from building footprints. Hence, we derive homogeneous urban tissue types and, by determining overall morphological similarity between them, generate a hierarchical classification of urban form. After framing and presenting the method, we test it on two cities – Prague and Amsterdam – and discuss potential applications and further developments. The proposed classification method represents a step towards the development of an extensive, scalable numerical taxonomy of urban form and opens the way to more rigorous comparative morphological studies and explorations into the relationship between urban space and phenomena as diverse as environmental performance, health and place attractiveness.

An improvement for the automatic classification method for ultrasound images used on CNN

It is no secret today that quality software has a higher superiority than leading technology solutions in computer vision. Remarkable advancement has been achieved in ultrasound image classification, essentially because of the availability of large-scale annotated datasets and deep convolutional neural networks (CNN). Applying CNN in the sphere of medicine is also becoming an active and attractive research area for researchers. In this paper, we introduce an efficient method for the classification of fetal ultrasound images using CNN. To classify these images, we collected four types of fetal ultrasound images from hospitals and internet sources. We first analyze and evaluate various CNN models such as AlexNet, Inception_v3, and MobileNet_v1 for training and testing. Then, the results of these CNN models are quantitatively compared with the proposed model in accuracy and speed. The results show that the proposed classification method can be recognized faster without compromising performance and adjust the ultrasound image parameters quickly and automatically. The proposed CNN model’s weight size is less than 1[Formula: see text]Mb and can be used on mobile or embedded operating systems. We also developed and tested the application on the Android operating system-based mobile device.