Classification-based Approach Research Articles

Using the Evolution of a River Technology System to Compare Classification-Based and Citation-Based Technology Networks

With the increasing complexity of societal and environmental problems in the Anthropocene, the use of both classification-based approaches, which provide in-depth understanding within disciplinary boundaries, and citation-based approaches, which provide interdisciplinary research, has been encouraged. However, there are limited comparisons of the knowledge networks produced between these two approaches, which compromises our capacity to manage technological development. This paper aims to investigate the similarities and differences of river technology networks produced using classification-based and citation-based approaches. The World Intellectual Property Organization (WIPO) database from 1863 to 2020 was used as the data source. River technology systems contained three interactive subsystems: water demand, water supply, and water management, and the structure was measured using network-based metrics. It was found that river technology systems constructed using the classification-based and the citation-based approaches developed similarly in terms of their temporal, spatial, and compositional features. The structural differences were attributed to the addition of an external system that draws upon interdisciplinary knowledge beyond water resources. Both approaches can be used for guiding technology management, with the classification-based approach being more effective for understanding the content of innovations and the citation-based approach being more effective in gathering information beyond the water resource discipline. Technologies from more diverse disciplines should be encouraged to address increasingly complex water challenges.

WDMA-UWB Indoor Positioning Through Channel Classification-Based NLOS Mitigation Approach

WDMA-UWB Indoor Positioning Through Channel Classification-Based NLOS Mitigation Approach

Finding Out the Root of Congestion Problems in Malang City and the Best Solution with Public Policy Analysis

Traffic congestion has a significant negative impact on regional economic activities and decreases community productivity. The purpose of this study is to analyze the sources of congestion problems in Malang City and the best way to solve them with a high level of effectiveness. The method used is qualitative with secondary data study. The researcher used a classification-based analysis approach to address the congestion problem with a multidisciplinary approach and explore the root of the congestion problem in Malang City. The first step involves logical division to classify the problem situation into several components. Second, logical classification refers to the act of combining different circumstances, things, or individuals into larger groups or classes. The results showed that the source of the problem was found in the high volume of vehicles and disorderly parking due to the growing accumulative population mobility. As a result, the capacity of Malang City is not able to accommodate this. Recommendations from alternative options resulting from the satisficing method analysis were carried out. In the end, the option to reorganize the road space is the option that is considered to meet all the criteria.

Characteristics and risk management of urban surface flooding in Guangzhou, China: Insights from 2022 ground monitoring

Study RegionGuangzhou, ChinaStudy FocusOur research, based on the meticulous collection and rigorous statistical analysis of ground monitoring records for the entire year of 2022 in Guangzhou, delves into the spatio-temporal distribution patterns, evolution processes, flood formation mechanisms, and corresponding disaster mitigation strategies of urban surface flooding related to the capacity of drainage system in the region. New Hydrological InsightsThe urban surface flooding (USF) in Guangzhou in 2022 provides key insights for flood risk management. The overall spatial distribution of USF risk in Guangzhou is stable, but specific flood locations during rainstorms vary due to factors such as rainfall conditions and drainage efficiency. This complexity highlights the diverse nature of USF challenges. The frequency of USF events varies significantly across months and dates, with a higher occurrence during the flood season. However, there is a noticeable extension of flood risk into the non-flood season, challenging traditional flood season concepts. USFs peak within 50 minutes, demanding urgent action within 25 minutes, underscoring the need for an efficient emergency response. Certain areas, times, and processes contribute more to the overall flood risk, emphasizing the importance of focusing on these high-risk factors for effective management and resource allocation. The study also reveals the prevalence of Surface Runoff-type Floods, challenging existing USF simulation methods and necessitating a reevaluation and improvement in the maintenance and design of urban rainwater inlets. The study suggests vigorously promoting private proactive flood mitigation behavior and proposes a hierarchical, classification-based approach to urban flood risk control. Comprehensive intervention in the urban runoff formation process is emphasized for effective flood risk management.

Spectral mixture analysis for weed traits identification under varying resolutions and growth stages

Spectral and spatial resolutions are critical factors in Site-Specific Weed Management (SSWM) applications, which aim to adjust and apply herbicides according to the weed composition and coverage during early growth. Thus, a reliable SSWM requires high spectral and spatial resolution data to create informative maps indicating and spatially localizing the weed species. Besides, upscaling and improving the mapping process are essential to motivate farmers to adopt SSWM practices. However, high-resolution data in spectral and spatial domains is not always available, and mixed pixels are highly probable. Therefore, evaluating approaches that deal with such pixels that pose a significant problem for weed classification tasks is vital. In this regard, Spectral Mixture Analysis (SMA) can exploit subpixel information from coarse-resolution data. However, despite its potential, SMA has not been examined for subpixel weed mapping. In this work, we aim to evaluate the potential advantages of SMA for coverage estimation of different weed traits (weed botanical group, photosynthetic pathway, and species). For this purpose, we first created a dataset containing weed species characterized by different botanical groups and photosynthetic pathways. Then, we evaluated the performance of SMA in estimating the weed’s coverage at varying growth stages and spectral and spatial resolutions. The experimental results revealed that using botanical weed groups as Endmembers (EM) is advantageous over other traits. A quantitative evaluation revealed strong correlation values between the actual and predicted weed coverage and a Mean Absolute Error (MAE) lower than 10 % for the different EM at all resolutions and growth stages. Besides, SMA outperformed the traditional classification-based approach in estimating weed coverage with up to ∼ 30 % lower Mean Absolute Error. Finally, our study establishes a basis for incorporating SMA in various SSWM practices.

Aorta Segmentation in 3D CT Images by Combining Image Processing and Machine Learning Techniques.

Aorta segmentation is extremely useful in clinical practice, allowing the diagnosis of numerous pathologies, such as dissections, aneurysms and occlusive disease. In such cases, image segmentation is prerequisite for applying diagnostic algorithms, which in turn allow the prediction of possible complications and enable risk assessment, which is crucial in saving lives. The aim of this paper is to present a novel fully automatic 3D segmentation method, which combines basic image processing techniques and more advanced machine learning algorithms, for detecting and modelling the aorta in 3D CT imaging data. An initial intensity threshold-based segmentation procedure is followed by a classification-based segmentation approach, based on a Markov Random Field network. The result of the proposed two-stage segmentation process is modelled and visualized. The proposed methodology was applied to 16 3D CT data sets and the extracted aortic segments were reconstructed as 3D models. The performance of segmentation was evaluated both qualitatively and quantitatively against other commonly used segmentation techniques, in terms of the accuracy achieved, compared to the actual aorta, which was defined manually by experts. The proposed methodology achieved superior segmentation performance, compared to all compared segmentation techniques, in terms of the accuracy of the extracted 3D aortic model. Therefore, the proposed segmentation scheme could be used in clinical practice, such as in treatment planning and assessment, as it can speed up the evaluation of the medical imaging data, which is commonly a lengthy and tedious process.

A classification-based generative approach to selective targeting of global slow oscillations during sleep.

Given sleep's crucial role in health and cognition, numerous sleep-based brain interventions are being developed, aiming to enhance cognitive function, particularly memory consolidation, by improving sleep. Research has shown that Transcranial Alternating Current Stimulation (tACS) during sleep can enhance memory performance, especially when used in a closed-loop (cl-tACS) mode that coordinates with sleep slow oscillations (SOs, 0.5-1.5Hz). However, sleep tACS research is characterized by mixed results across individuals, which are often attributed to individual variability. This study targets a specific type of SOs, widespread on the electrode manifold in a short delay ("global SOs"), due to their close relationship with long-term memory consolidation. We propose a model-based approach to optimize cl-tACS paradigms, targeting global SOs not only by considering their temporal properties but also their spatial profile. We introduce selective targeting of global SOs using a classification-based approach. We first estimate the current elicited by various stimulation paradigms, and optimize parameters to match currents found in natural sleep during a global SO. Then, we employ an ensemble classifier trained on sleep data to identify effective paradigms. Finally, the best stimulation protocol is determined based on classification performance. Our study introduces a model-driven cl-tACS approach that specifically targets global SOs, with the potential to extend to other brain dynamics. This method establishes a connection between brain dynamics and stimulation optimization. Our research presents a novel approach to optimize cl-tACS during sleep, with a focus on targeting global SOs. This approach holds promise for improving cl-tACS not only for global SOs but also for other physiological events, benefiting both research and clinical applications in sleep and cognition.

A new classification-based approach for multi-focus image fusion

A new classification-based approach for multi-focus image fusion

Estimation of Forest Stock Volume Combining Airborne LiDAR Sampling Approaches with Multi-Sensor Imagery

Timely and reliable estimation of forest stock volume is essential for sustainable forest management and conservation. Light detection and ranging (LiDAR) data can provide an effective depiction of the three-dimensional structure information of forests, but its large-scale application is hampered by spatial continuity. This study aims to construct a LiDAR sampling framework, combined with multi-sensor imagery, to estimate the regional forest stock volume of natural secondary forests in Northeast China. Two sampling approaches were compared, including systematic sampling and classification-based sampling. First, the forest stock volume was mapped using a combination of field measurement data and full-coverage LiDAR data. Then, the forest stock volume obtained in the first step of estimation was used as a reference value, and optical images and topographic features were combined for secondary modeling to compare the effectiveness and accuracy of different sampling methods, including 12 systematic sampling and classification-based sampling methods. Our results show that the root mean square error (RMSE) of the 12 systematic sampling approaches ranged from 55.81 to 57.42 m3/ha, and the BIAS ranged from 21.55 to 24.89 m3/ha. The classification-based LiDAR sampling approach outperformed systematic sampling, with an RMSE of 55.56 (<55.81 m3/ha) and a BIAS of 20.68 (<21.55 m3/ha). This study compares different LiDAR sampling approaches and explores an effective LiDAR sample collection scheme for estimating forest stock, while balancing cost and accuracy. The classification-based LiDAR sampling approach described in this study is easy to apply and portable and can provide a reference for future LiDAR sample collection.

Anomaly Detection for Modbus over TCP in Control Systems Using Entropy and Classification-Based Analysis

This article presents a statistical approach using entropy and classification-based analysis to detect anomalies in industrial control systems traffic. Several statistical techniques have been proposed to create baselines and measure deviation to detect intrusion in enterprise networks with a centralized intrusion detection approach in mind. Looking at traffic volume alone to find anomalous deviation may not be enough—it may result in increased false positives. The near real-time communication requirements, coupled with the lack of centralized infrastructure in operations technology and limited resources of the sensor motes, require an efficient anomaly detection system characterized by these limitations. This paper presents extended results from our previous work by presenting a detailed cluster-based entropy analysis on selected network traffic features. It further extends the analysis using a classification-based approach. Our detailed entropy analysis corroborates with our earlier findings that, although some degree of anomaly may be detected using univariate and bivariate entropy analysis for Denial of Service (DOS) and Man-in-the-Middle (MITM) attacks, not much information may be obtained for the initial reconnaissance, thus preventing early stages of attack detection in the Cyber Kill Chain. Our classification-based analysis shows that, overall, the classification results of the DOS attacks were much higher than the MITM attacks using two Modbus features in addition to the three TCP/IP features. In terms of classifiers, J48 and random forest had the best classification results and can be considered comparable. For the DOS attack, no resampling with the 60–40 (training/testing split) had the best results (average accuracy of 97.87%), but for the MITM attack, the 80–20 non-attack vs. attack data with the 75–25 split (average accuracy of 82.81%) had the best results.

RoBERTa-Based Keyword Extraction from Small Number of Korean Documents

Keyword extraction is the task of identifying essential words in a lengthy document. This process is primarily executed through supervised keyword extraction. In instances where the dataset is limited in size, a classification-based approach is typically employed. Therefore, this paper introduces a novel keyword extractor based on a classification approach. The proposed keyword extractor comprises three key components: RoBERTa, a keyword estimator, and a decision rule. RoBERTa encodes an input document, the keyword estimator calculates the probability of each token in the document becoming a keyword, and the decision rule ultimately determines whether each token is a keyword based on these probabilities. However, training the proposed model with a small dataset presents two challenges. One problem is the case that all tokens in the documents are not a keyword, and the other problem is that a single word can be composed of keyword tokens and non-keyword tokens. Two novel heuristics are thus proposed to tackle these problems. To address these issues, two novel heuristics are proposed. These heuristics have been extensively tested through experiments, demonstrating that the proposed keyword extractor surpasses both the generation-based approach and the vanilla RoBERTa in environments with limited data. The efficacy of the heuristics is further validated through an ablation study. In summary, the proposed heuristics have proven to be effective in developing a supervised keyword extractor with a small dataset.

A Delay Classification-Based Approach to Distributed Consensus of Nonlinear Time-Delay Multiagent Systems

This paper investigates the problem of the fixed directed topology-based leader-following consensus control for nonlinear multiagent systems with output delays. Diverging from existing results, this study focuses on large time-varying output delay. Taking this condition into account, a novel delay classification-based distributed output feedback consensus algorithm is developed. First, we divide the output delay into two types through a designed constant and introduce a switching signal to distinguish these two types. Then, we build a distributed compensator for each follower using relevant outputs to reconstitute the leader-following tracking errors. This compensator relies on the output delay and is irrelevant to the nonlinear dynamics of the system. Then, we design a distributed linear controller for each follower with the compensator's assistance. Subsequently, a new unified Lyapunov-Krasovskii functional is developed to prove that all agents can realize leader-following full-state consensus with the action of the controller. We also provide sufficient conditions to demonstrate the controller's validity. Finally, a simulation example is supplied to validate the efficiency of our algorithm.

On the use of QDE-SVM for gene feature selection and cell type classification from scRNA-seq data.

Cell type identification is one of the fundamental tasks in single-cell RNA sequencing (scRNA-seq) studies. It is a key step to facilitate downstream interpretations such as differential expression, trajectory inference, etc. scRNA-seq data contains technical variations that could affect the interpretation of the cell types. Therefore, gene selection, also known as feature selection in data science, plays an important role in selecting informative genes for scRNA-seq cell type identification. Generally speaking, feature selection methods are categorized into filter-, wrapper-, and embedded-based approaches. From the existing literature, methods from filter- and embedded-based approaches are widely applied in scRNA-seq gene selection tasks. The wrapper-based method that gives promising results in other fields has yet been extensively utilized for selecting gene features from scRNA-seq data; in addition, most of the existing wrapper methods used in this field are clustering instead of classification-based. With a large number of annotated data available today, this study applied a classification-based approach as an alternative to the clustering-based wrapper method. In our work, a quantum-inspired differential evolution (QDE) wrapped with a classification method was introduced to select a subset of genes from twelve well-known scRNA-seq transcriptomic datasets to identify cell types. In particular, the QDE was combined with different machine-learning (ML) classifiers namely logistic regression, decision tree, support vector machine (SVM) with linear and radial basis function kernels, as well as extreme learning machine. The linear SVM wrapped with QDE, namely QDE-SVM, was chosen by referring to the feature selection results from the experiment. QDE-SVM showed a superior cell type classification performance among QDE wrapping with other ML classifiers as well as the recent wrapper methods (i.e., FSCAM, SSD-LAHC, MA-HS, and BSF). QDE-SVM achieved an average accuracy of 0.9559, while the other wrapper methods achieved average accuracies in the range of 0.8292 to 0.8872.

A text classification-based approach for evaluating and enhancing the machine interpretability of building codes

Interpreting regulatory documents or building codes into computer-processable formats is essential for the intelligent design and construction of buildings and infrastructures. Although automated rule interpretation (ARI) methods have been investigated for years, most of them are highly dependent on the early and manual filtering of interpretable clauses from a building code. While few of them considered machine interpretability, which represents the potential to be transformed into a computer-processable format, from both clause- and document-level. Therefore, this research aims to propose a novel approach to automatically evaluate and enhance the machine interpretability of single clauses and building codes. First, a few categories are introduced to classify each clause in a building code considering the requirements for rule interpretation, and a dataset is developed for model training. Then, an efficient text classification model is developed based on a pretrained domain-specific language model and transfer learning techniques. Finally, a quantitative evaluation method is proposed to assess the overall interpretability of building codes. Experiments show that the proposed text classification algorithm outperforms the existing CNN- or RNN-based methods, by improving the F1-score from 72.16% to 93.60%. It is also illustrated that the proposed classification method can enhance downstream ARI methods with an improvement of 4%. Furthermore, analysis of more than 150 building codes in China showed that their average interpretability is only 34.40%, which implies that it is still difficult to fully transform an entire regulatory document into computer-processable formats. It is also argued that the interpretability of building codes should be further improved both from the human side (considering certain constraints when writing building codes) and the machine side (developing more powerful algorithms, tools, etc.).

One-Class Machine Learning Classifiers-Based Multivariate Feature Extraction for Grid-Connected PV Systems Monitoring under Irradiance Variations

In recent years, photovoltaic (PV) energy production has witnessed overwhelming growth, which has inspired the search for more effective operations. Nevertheless, different PV faults may appear, which leads to various degradation stages. Furthermore, under different irradiance levels, these faults may be misclassified as a healthy mode owing to the high resemblances between them, thus provoking serious challenges in terms of power losses and maintenance costs. Hence, interposing the irradiance variation in grid-connected PV (GCPV) systems modeling is important for monitoring tasks to ensure the effective operation of these systems, to increase their reliability and to prevent false alarms. Therefore, in this paper, a fault detection and diagnosis (FDD) method for the GCPV systems using machine learning (ML) based on principal component analysis (PCA) is proposed in order to ensure the reliability and security of the whole system under irradiance variations. The proposed strategy consists of three main steps: (i) introduce the irradiance variations in PV system modeling because of its great impact on power production; (ii) feature extraction and selection through PCA; and (iii) fault classification using ML techniques. In this study, we generate a database that is used to compare the proposed strategy with the standard strategy (considering a fixed irradiance during FDD), to make, at first, a complete and significant comparative assessment of fault diagnosis and to demonstrate the efficiency of the proposed strategy. The achieved results show the high effectiveness of the proposed one-class classification-based approach to detect and diagnose PV array anomalies, reaching an accuracy up to 99.68%.

Predicting HIV infection in the decade (2005-2015) pre-COVID-19 in Zimbabwe: A supervised classification-based machine learning approach.

The burden of HIV and related diseases have been areas of great concern pre and post the emergence of COVID-19 in Zimbabwe. Machine learning models have been used to predict the risk of diseases, including HIV accurately. Therefore, this paper aimed to determine common risk factors of HIV positivity in Zimbabwe between the decade 2005 to 2015. The data were from three two staged population five-yearly surveys conducted between 2005 and 2015. The outcome variable was HIV status. The prediction model was fit by adopting 80% of the data for learning/training and 20% for testing/prediction. Resampling was done using the stratified 5-fold cross-validation procedure repeatedly. Feature selection was done using Lasso regression, and the best combination of selected features was determined using Sequential Forward Floating Selection. We compared six algorithms in both sexes based on the F1 score, which is the harmonic mean of precision and recall. The overall HIV prevalence for the combined dataset was 22.5% and 15.3% for females and males, respectively. The best-performing algorithm to identify individuals with a higher likelihood of HIV infection was XGBoost, with a high F1 score of 91.4% for males and 90.1% for females based on the combined surveys. The results from the prediction model identified six common features associated with HIV, with total number of lifetime sexual partners and cohabitation duration being the most influential variables for females and males, respectively. In addition to other risk reduction techniques, machine learning may aid in identifying those who might require Pre-exposure prophylaxis, particularly women who experience intimate partner violence. Furthermore, compared to traditional statistical approaches, machine learning uncovered patterns in predicting HIV infection with comparatively reduced uncertainty and, therefore, crucial for effective decision-making.

Identifying and Combating Unlawful Fishing Activities: A Classification-Based Approach

Identifying and Combating Unlawful Fishing Activities: A Classification-Based Approach

A classification-based approach to mapping particulate organic matter (POM) in inland water using OLCI images.

Particulate organic matter (POM) plays a major role in freshwater ecosystems by serving as a bridge for the conversion of various nutrients. The composition and sources of POM in inland lakes are complex, making it difficult to estimate its concentration accurately via remote sensing. Therefore, a classification-based method based on the sources and composition of POM is proposed for estimating POM concentrations in inland lakes. In this study, 379 samples were collected from ten lakes in the Yangtze River Delta (YRD) at different times. A water-type classification method based on OLCI [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text] was developed for POM estimation based on biological and optical characteristics. Water type 1 is relatively clear, and POM may originate from aquatic vegetation or sediment. Water type 2 was dominated by inorganic suspended matter, and POM mainly originated from the attachment and entrainment of inorganic minerals. Water type 3 is an algae-dominated water body, and POM is mainly derived from fresh algal particles and the microbial degradation of phytoplankton. Therefore, specific POM estimation algorithms were developed for each water type. OLCI [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text] were used for water type 1; [Formula: see text], [Formula: see text], and [Formula: see text] were adopted for water type 2; and [Formula: see text], [Formula: see text], and [Formula: see text] were selected for water type 3. Using an independent dataset to evaluate the estimation accuracy of the developed algorithm, the results show that the estimation performance of this algorithm is significantly improved compared to the two other algorithms used; the mean absolute percentage errors (MAPE) decreased from 72.56% and 52.21% to 32.61%, and the root mean square errors (RMSE) decreased from 3.05mg/L and 2.24mg/L to 1.75mg/L. A random error analysis of the atmospheric correction demonstrated that this algorithm is robust and can still perform well within a random error of 30%. Finally, this method was successfully applied to map the POM concentrations in the YRD using OLCI images acquired on November 12, 2020.

Efficient Machine Learning-based Approach for Brain Tumor Detection Using the CAD System

Medical research has focused on improving diagnosis through medical imaging in recent decades. Computer Assisted Diagnosis (CAD) systems have been developed to help doctors identify suspicious areas of interest, particularly those with cancer-like characteristics. CAD systems employ various algorithms and techniques to extract important numerical measurements from medical images that clinicians can use to evaluate patient conditions. This study proposes a statistical classification-based approach to efficient brain cancer detection. The proposed approach operates in three stages: first, Gradient Vector Flow (GVF) Snake models and mathematical morphology techniques retrieve regions of interest. The second stage characterizes these regions using morphological and textural parameters. Finally, a Bayesian network uses this description as input to identify malignant and benign cancer classes. We also compared the performance of the Bayesian network with other popular classification algorithms, including SVM, MLP, KNN, Random Forest, Decision Tree, XGBoost, LGBM, Gaussian Process, and RBF SVM. The results showed the superiority of the Bayesian network for the task of brain tumor classification. The proposed approach has been experimentally validated, with a sensitivity of 100% and a classification accuracy of over 98% for tumors, demonstrating the high efficiency of cancer cell segmentation.

Mortality Prediction of Various Cancer Patients via Relevant Feature Analysis and Machine Learning

Breast, lung, prostate, and stomach cancers are the most frequent cancer types globally. Early-stage detection and diagnosis of these cancers pose a challenge in the literature. When dealing with cancer patients, physicians must select among various treatment methods that have a risk factor. Since the risks of treatment may outweigh the benefits, treatment schedule is critical in clinical decision making. Manually deciding which medications and treatments are going to be successful takes a lot of expertise and can be hard. In this paper, we offer a computational solution to predict the mortality of various types of cancer patients. The solution is based on the analysis of diagnosis, medication, and treatment parameters that can be easily acquired from electronic healthcare systems. A classification-based approach introduced to predict the mortality outcome of cancer patients. Several classifiers evaluated on the Medical Information Mart in Intensive Care IV (MIMIC-IV) dataset. Diagnosis, medication, and treatment features extracted for breast, lung, prostate, and stomach cancer patients and relevant feature selection done with Logistic Regression. Best F1 scores were 0.74 for breast, 0.73 for lung, 0.82 for prostate, and 0.79 for stomach cancer. Best AUROC scores were 0.94 for breast, 0.91 for lung, 0.96 for prostate, and 0.88 for stomach cancer. In addition, using relevant features, results were very similar to the baseline for each cancer type. Using less features and a robust machine-learning model, the proposed approach can be easily implemented in hospitals when there are limited data and resources available.