Classification Methodology Research Articles

Implementation of Smart Vehicle Assistant using Computer vision and Deep Learning

bstract: Autonomous cars are a popular research topic in the field of intelligent transportation systems because they have the potential to greatly reduce traffic and improve travel efficiency. Scene classification is a key technology for autonomous cars because it forms the basis of these vehicles' decision-making. In recent years, deep learning-based methods have demonstrated promise in resolving the scene classification issue. However, further research is needed on a few difficulties related to scene classification methodologies, such as how to treat similarities and contrasts within the same category. To tackle these problems, this research suggests an improved deep network-based scene classification method. Autonomous cars are a popular research topic in the field of intelligent transportation systems because they have the potential to greatly reduce traffic and improve travel efficiency.

Spatio-Temporal Detection of Land Use/Land Cover Changes in Kokrajhar District of Assam

The use of multi-temporal satellite images in digital change detection algorithms aids in the comprehension of landscape dynamics. The present study illustrates the spatio temporal dynamics of land use/land cover of Kokrajhar district of Assam, India. Landsat Satellite imageries of four different time periods. i.e., Landsat Thematic Mapper (TM) of 1991, 2001, 2011 and 2021 were acquired from Google Earth Explorer site and quantify the changes of Kokrajhar district from 1991 to 2021 over a period of 30 years. Supervised classification methodology has been employed using maximum likelihood technique in ArcMap 10.8 Software. The images of the study area were categorised into four different classes namely vegetation, agriculture, built up and water body. The results indicate that during the last three decades, built up have been increased by 3.8% (658.75 km2) while agriculture, vegetation and water body have been decreased by 0.74 (708.9 km2) %, 0.56(1494.46 km2) % and 2.46 (273.5 km2) % respectively.

Chest x-ray has low sensitivity to detect silicosis in artificial stone benchtop industry workers.

Chest x-ray (CXR) remains a core component of health monitoring guidelines for workers at risk of exposure to crystalline silica. There has however been a lack of evidence regarding the sensitivity of CXR to detect silicosis in artificial stone benchtop industry workers. Paired CXR and high-resolution computed tomography (HRCT) images were acquired from 110 artificial stone benchtop industry workers. Blinded to the clinical diagnosis, each CXR and HRCT was independently read by two thoracic radiologists from a panel of seven, in accordance with International Labour Office (ILO) methodology for CXR and International Classification of HRCT for Occupational and Environmental Respiratory Diseases. Accuracy of screening positive (ILO major category 1, 2 or 3) and negative (ILO major category 0) CXRs were compared with identification of radiological features of silicosis on HRCT. CXR was positive for silicosis in 27/110 (24.5%) workers and HRCT in 40/110 (36.4%). Of the 83 with a negative CXR (ILO category 0), 15 (18.1%) had silicosis on HRCT. All 11 workers with ILO category 2 or 3 CXRs had silicosis on HRCT. In 99 workers ILO category 0 or 1 CXRs, the sensitivity of screening positive CXR compared to silicosis identified by HRCT was 48% (95%CI 29-68) and specificity 97% (90-100). Compared to HRCT, sensitivity of CXR was low but specificity was high. Reliance on CXR for health monitoring would provide false reassurance for many workers, delay management and underestimate the prevalence of silicosis in the artificial stone benchtop industry.

Amazon Deforestation and Global Meat Consumption Trends: An Assessment of Land Use Change and Market Data from Rondônia That Shows Why We Should Consider Changing Our Diets

This paper seeks to elucidate the interrelationship between global meat consumption and deforestation in the Amazon region. To this end, empirical research is conducted to investigate land use changes in Rondônia and the expansion of pasture areas and beef production. Brazil is one of the largest beef producers in the world, with products destined for local and global markets. Based on bibliographical research, the paper analyzes maps of land use change between 1985 and 2021, using Landsat satellite imagery and the MapBiomas methodology for Landsat mosaic and classification. The research shows that beef from Rondônia is primarily purchased and consumed in Brazil, but it is also bought and sold on the international market. Landsat imagery analysis shows the predominance of forest conversion to pasture in Rondônia. The results show that deforestation in the Amazon is directly linked to the growth of cattle ranching. Land use change from native forest to pasture for beef cattle production is a reality in the Brazilian Amazon, especially in Rondônia. It suggests the urgent need for more conscious consumption and production practices as well as ethical and sustainable eating habits.

Resource building and classification of Mizo folk songs

Abstract Folk culture represents the social, ethnic, and traditional livelihood of people belonging to a certain tribe or community and is important in keeping their culture and tradition alive. The Mizo people are a Tibeto-Burmese ethnic group, native to the Indian state of Mizoram and neighboring regions of Northeast India. Mizo folk culture is an amalgamation of festivity, celebration, liveliness, kinship, brotherhood, and merriment, and above all, preserves the ethnicity of this tribal community that is fundamentally entrenched. Unfortunately, the Mizos are fast giving up their old customs and adopting the new mode of life that is greatly influenced by the western culture. This makes it all the more crucial to preserve the intangible cultural heritage of this ethnic tribe whose folk cultures are vanishing day by day. To the best of our knowledge, this work is the first attempt at preservation and classification of Mizo folk songs. The first part of this paper presents a literature survey on preservation, analysis, and classification of folk songs. The second part presents the methodology for preliminary classification of Mizo folk songs. Three categories of Mizo folk songs—Hunting chants (Hlado), Children’s songs (Pawnto hla), and Elderly songs (Pi pu zai)—are used in this study. A total of 29 acoustic features are used. A long short-term memory network using custom attention layer has been proposed for classification, whose results are compared with four supervised models (Support Vector Machines, K-Nearest Neighbor, Naive Baye’s, and Ensemble). Experimental results from the proposed model are promising, with an implication of scope for future research in acoustic analysis and classification of Mizo folk songs using recent unsupervised methods.

Evaluation of High-Dimensional Data Classification for Skin Malignancy Detection Using DL-Based Techniques

Skin cancer can be detected through visual screening and skin analysis based on the biopsy and pathological state of the human body. The survival rate of cancer patients is low, and millions of people are diagnosed annually. By determining the different comparative analyses, the skin malignancy classification is evaluated. Using the Isomap with the vision transformer, we analyze the high-dimensional images with dimensionality reduction. Skin cancer can present with severe cases and life-threatening symptoms. Overall performance evaluation and classification tend to improve the accuracy of the high-dimensional skin lesion dataset when completed. In deep learning methodologies, the distinct phases of skin malignancy classification are determined by its accuracy, specificity, F1 recall, and sensitivity while implementing the classification methodology. A nonlinear dimensionality reduction technique called Isomap preserves the data’s underlying nonlinear relationships intact. This is essential for the categorization of skin malignancies, as the features that separate malignant from benign skin lesions may not be linearly separable. Isomap decreases the data’s complexity while maintaining its essential characteristics, making it simpler to analyze and explain the findings. High-dimensional datasets for skin lesions have been evaluated and classified more effectively when evaluated and classified using Isomap with the vision transformer.

Data-Driven Policy Learning Methods from Biological Behavior: A Systematic Review

Policy learning enables agents to learn how to map states to actions, thus enabling adaptive and flexible behavioral generation in complex environments. Policy learning methods are fundamental to reinforcement learning techniques. However, as problem complexity and the requirement for motion flexibility increase, traditional methods that rely on manual design have revealed their limitations. Conversely, data-driven policy learning focuses on extracting strategies from biological behavioral data and aims to replicate these behaviors in real-world environments. This approach enhances the adaptability of agents to dynamic substrates. Furthermore, this approach has been extensively applied in autonomous driving, robot control, and interpretation of biological behavior. In this review, we survey developments in data-driven policy-learning algorithms over the past decade. We categorized them into the following three types according to the purpose of the method: (1) imitation learning (IL), (2) inverse reinforcement learning (IRL), and (3) causal policy learning (CPL). We describe the classification principles, methodologies, progress, and applications of each category in detail. In addition, we discuss the distinct features and practical applications of these methods. Finally, we explore the challenges these methods face and prospective directions for future research.

SkinSwinViT: A Lightweight Transformer-Based Method for Multiclass Skin Lesion Classification with Enhanced Generalization Capabilities

In recent decades, skin cancer has emerged as a significant global health concern, demanding timely detection and effective therapeutic interventions. Automated image classification via computational algorithms holds substantial promise in significantly improving the efficacy of clinical diagnoses. This study is committed to mitigating the challenge of diagnostic accuracy in the classification of multiclass skin lesions. This endeavor is inherently formidable owing to the resemblances among various lesions and the constraints associated with extracting precise global and local image features within diverse dimensional spaces using conventional convolutional neural network methodologies. Consequently, this study introduces the SkinSwinViT methodology for skin lesion classification, a pioneering model grounded in the Swin Transformer framework featuring a global attention mechanism. Leveraging the inherent cross-window attention mechanism within the Swin Transformer architecture, the model adeptly captures local features and interdependencies within skin lesion images while additionally incorporating a global self-attention mechanism to discern overarching features and contextual information effectively. The evaluation of the model’s performance involved the ISIC2018 challenge dataset. Furthermore, data augmentation techniques augmented training dataset size and enhanced model performance. Experimental results highlight the superiority of the SkinSwinViT method, achieving notable metrics of accuracy, recall, precision, specificity, and F1 score at 97.88%, 97.55%, 97.83%, 99.36%, and 97.79%, respectively.

Performance comparison analysis of classification methodologies for effective detection of intrusions

Intrusion detection systems (IDS) are critical in many applications, including cloud environments. The intrusion poses a security threat and extracts privacy data and information from the cloud. Additionally, intrusions can cause damage to system hardware, resulting in significant financial losses and exposing critical IT infrastructure to risk. To overcome these issues, this study employs the performance comparison analysis for IDS, which has been performed with different models like Autoencoder Convolutional neural network (AE+CNN), Random forest K-means clustering assisted deep neural network (RF+K-means+DNN), Autoencoder K-means clustering assisted long short term memory (AE+K-means+LSTM), Alexnet+Bi-GRU, AE+Alexnet+Bi-GRU and Wild horse AlexNet assisted Bi-directional Gated Recurrent Unit (WABi-GRU) models to choose the best methodology for effective detection of intrusions. The data needed for the analysis is collected from CICIDS2018, UNSW-NB15, NSL-KDD and ToN-IoT datasets. The collected data are pre-processed using data normalization and data cleaning. Finally, the best model has been chosen for effective intrusion detection, which is used for further processes. Various performances, such as accuracy, precision, recall, and f1-score, are analyzed for various existing and proposed models. From this performance comparison of six models such as AE+CNN, RF+K-means+DNN, AE+K-means+LSTM, Alexnet+Bi-GRU, AE+Alexnet+Bi-GRU and WABi-GRU. WABi-GRU can attain an accuracy of 99.890 % for multi-class classification in the CICIDS 2018 dataset, 99.7 % in the NSL-KDD dataset, 99.53 % in the UNSW-NB 15 dataset and 99.988 % for the ToN-IoT dataset. In this analysis, the models containing AlexNet Bi-GRU-based models can obtain better performances than other existing models. The WABi-GRU model can obtain better results than other models.

A graph-based cardiac arrhythmia classification methodology using one-lead ECG recordings

In this study, we present a novel graph-based methodology for an accurate classification of cardiac arrhythmia diseases using a single-lead electrocardiogram (ECG). The proposed approach employs the visibility graph technique to generate graphs from time signals. Subsequently, informative features are extracted from each graph and then fed into classifiers to match the input ECG signal with the appropriate target arrhythmia class. The six target classes in this study are normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), premature ventricular contraction (PVC), atrial premature contraction (A), and fusion (F) beats. Three classification models were explored, including graph convolutional neural network (GCN), multi-layer perceptron (MLP), and random forest (RF). ECG recordings from the MIT-BIH arrhythmia database were utilized to train and evaluate these classifiers. The results indicate that the multi-layer perceptron model attains the highest performance, showcasing an average accuracy of 99.02%. Following closely, the random forest achieves a strong performance as well, with an accuracy of 98.94% while providing critical intuitions.

An efficient tomato diseases detection and classification methodology using CNN Deep Learning Network

In this paper, an efficient methodology for detecting and classifying tomato diseases using a Convolutional Neural Network (CNN) deep learning network is presented as an efficient aided tool to classify different tomato diseases based on their leaf appearence, where plant diseases and insects are considered as a main challenges for farmers to overcome. The proposed methodology structure is based on 20 layers using convolution, Maxpooling, Batch normalization and ReLU process as main operations in the adopted architecture. The obtained results using Plant Village database show that our proposed methodology outclasses the best recent methods of tomato diseases detection and classification with scores of 97.3% 96.8% 97.0% and 97.5% for precision, Recall, F1-Score and accuracy coefficient criteria respectively. Our methodology of tomato diseases detection and classification is found as effective, accurate and aided diagnostic tool that aims to aid farmers to make a precise plant treatments and enhancing productivity while promoting environmental sustainability.

AnarMitra: Enhancing Pomegranate Farming with CNN Technology

Abstract: This study introduces AnarMitra, a mobile application designed to revolutionize pomegranate cultivation practices. AnarMitra employs machine learning algorithms to swiftly assess ripeness levels and detect prevalent diseases in pomegranates, such as bacterial blight and fungal infections. Utilizing smartphone cameras, farmers can effortlessly capture images for immediate feedback on fruit quality and health. The paper details AnarMitra's development process, including model training with diverse datasets and algorithmic methodologies for classification and disease detection. Field trials validate AnarMitra's efficacy in enhancing productivity and fostering sustainable agricultural practices, empowering farmers with timely insights for informed decision-making and crop management.

Forward Head Posture Classification Using Deep Learning Models on Facial Recognition Data

Forward Head Posture (FHP) refers to a condition where the head protrudes forward, significantly contributing to neck pain and being associated with decreased productivity and psychological distress. This study investigates the nuanced classification of FHP and proposes a universally applicable methodology for its identification and analysis using deep learning. Leveraging the Korean Facial Image (K-FACE) dataset, rigorous image preprocessing with the Yolo-v8 model was conducted to facilitate accurate measurement of the CranioVertebral Angle (CVA) from various perspectives. The study meticulously evaluated the classification effectiveness of three advanced deep learning models: EfficientNet-B7, NFNet-F7, and ResNet-152. Among these, EfficientNet-B7 demonstrated superior performance with an accuracy of 0.69 and a recall score of 0.69 compared to other models. Additionally, comparisons based on camera angles within the EfficientNet-B7 model highlighted its excellence, particularly at the ±75° angle. The importance of image regions in EfficientNet-B7 was confirmed through Grad-CAM analysis, emphasizing the critical role of the neck region in accurately classifying FHP images. This comprehensive performance comparison and the proposed detailed classification methodology underscore the potential for generalization in FHP classification. Furthermore, by leveraging a unique dataset and employing state-of-the-art classification techniques, this research offers a novel perspective on the discourse surrounding FHP. Future research could integrate expanded facial image datasets and apply transfer learning techniques to further enhance the precision of FHP classification, thereby improving diagnostic accuracy and offering targeted interventions for individuals experiencing neck pain associated with FHP.

Wide-TSNet: A Novel Hybrid Approach for Bitcoin Price Movement Classification

In this paper, we introduce Wide-TSNet, a novel hybrid approach for predicting Bitcoin prices using time-series data transformed into images. The method involves converting time-series data into Markov transition fields (MTFs), enhancing them using histogram equalization, and classifying them using Wide ResNets, a type of convolutional neural network (CNN). We propose a tripartite classification system to accurately represent Bitcoin price trends. In addition, we demonstrate the effectiveness of Wide-TSNet through various experiments, in which it achieves an Accuracy of approximately 94% and an F1 score of 90%. It is also shown that lightweight CNN models, such as SqueezeNet and EfficientNet, can be as effective as complex models under certain conditions. Furthermore, we investigate the efficacy of other image transformation methods, such as Gramian angular fields, in capturing the trends and volatility of Bitcoin prices and revealing patterns that are not visible in the raw data. Moreover, we assess the effect of image resolution on model performance, emphasizing the importance of this factor in image-based time-series classification. Our findings explore the intersection between finance, image processing, and deep learning, providing a robust methodology for financial time-series classification.

Remote Sensing and Machine Learning for Accurate Fire Severity Mapping in Northern Algeria

Forest fires pose a significant threat worldwide, with Algeria being no exception. In 2020 alone, Algeria witnessed devastating forest fires, affecting over 16,000 hectares of land, a phenomenon largely attributed to the impacts of climate change. Understanding the severity of these fires is crucial for effective management and mitigation efforts. This study focuses on the Akfadou forest and its surrounding areas in Algeria, aiming to develop a robust method for mapping fire severity. We employed a comprehensive approach that integrates satellite imagery analysis, machine learning techniques, and geographic information systems (GIS) to assess fire severity. By evaluating various remote sensing attributes from the Sentinel-2 and Planetscope satellites, we compared different methodologies for fire severity classification. Specifically, we examined the effectiveness of reflectance indices-based metrics such as Relative Burn Ratio (RBR) and Difference Burned Area Index for Sentinel-2 (dBIAS2), alongside machine learning algorithms including Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), implemented in ArcGIS Pro 3.1.0. Our analysis revealed promising results, particularly in identifying high-severity fire areas. By comparing the output of our methods with ground truth data, we demonstrated the robust performance of our approach, with both SVM and CNN achieving accuracy scores exceeding 0.84. An innovative aspect of our study involved semi-automating the process of training sample labeling using spectral indices rasters and masks. This approach optimizes raster selection for distinct fire severity classes, ensuring accuracy and efficiency in classification. This research contributes to the broader understanding of forest fire dynamics and provides valuable insights for fire management and environmental monitoring efforts in Algeria and similar regions. By accurately mapping fire severity, we can better assess the impacts of climate change and land use changes, facilitating proactive measures to mitigate future fire incidents.

Text Classification in Natural Language Processing

This paper presents an overview of text classification techniques, focusing on the pre-processing steps, feature extraction methods, and model selection strategies employed in the process. Algorithms such as Naive Bayes, Support Vector Machines (SVM), logistic regression, and neural networks are used. Furthermore, recent advancements in deep learning models for text classification, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are used. Comprehensive understanding of text classification methodologies in NLP and insights into current trends and challenges in the field are mentioned

Crop classification in Google Earth Engine: leveraging Sentinel-1, Sentinel-2, European CAP data, and object-based machine-learning approaches

ABSTRACT In contemporary agriculture and environmental management, the need for precise and accurate crop maps has never been more vital. Although object-based (OB) methods within Google Earth Engine (GEE) improve accuracy and output quality in contrast to pixel-based approaches, their application to crop classification remains relatively rare. Therefore, this study aimed to develop an OB classification methodology for crops located in central Italy’s Lake Trasimeno area. This methodology employed spectral bands, spectral indices (Normalized Difference Vegetation Index and Modified Radar Vegetation Index), and textural information (Gray-Level Co-occurrence Matrix) derived from Sentinel-2 L2A (S2) and Sentinel-1 GRD (S1) data within the GEE platform. Moreover, European Common Agricultural Policy (CAP) data associated with cadastral parcels were employed and served as ground information during the training and validation stages. The CAP crop classes were aggregated into three levels (Level 1–3 crop types, Level 2–5 crop types, and Level 3–7 crop types). Subsequently, optimized Random Forest (RF) classifiers were applied to map crops effectively. Feature selection analysis highlighted the importance of certain textural features. Additionally, findings demonstrated high overall accuracy results (89% for Level 1, 86% for Level 2, and 82% for Level 3). It was found that winter crops achieved the highest F-score at Level 1, while specific subclasses, such as winter cereals and warm-season cereals, excelled at Level 2. Overall, this study provides a promising approach for improved crop mapping and precision agriculture in the GEE environment.

Different Approaches of Forest Type Classifications for Argentina Based on Functional Forests and Canopy Cover Composition by Tree Species

Modern forestry systems rely on typologies of forest types (FTs). In Argentina, several proposals have been developed, but they lack unified criteria. The objective was to compare different approaches, specifically focusing on (i) phenoclusters (functional forests based on vegetation phenology variations and climate variables) and (ii) forest canopy cover composition by tree species. We conducted comparative uni-variate analyses using data from national forest inventories, forest models (biodiversity, carbon, structure), and regional climate. We assessed the performance of phenoclusters in differentiating the variability of native forests (proxy: forest structure), biodiversity (proxy: indicator species), and environmental factors (proxies: soil carbon stock, elevation, climate). Additionally, we proposed a simple FT classification methodology based on species composition, considering the basal area of tree species. Finally, we compared the performance of both proposals. Our findings showed that classifications based on forest canopy cover composition are feasible to implement in regions dominated by mono-specific forests. However, phenoclusters allowed for the increased complexity of categories at the landscape level. Conversely, in regions where multi-specific stands prevailed, classifications based on forest canopy cover composition proved ineffective; however, phenoclusters facilitated a reduction in complexity at the landscape level. These results offer a pathway to harmonize national FT classifications by employing criteria and indicators to achieve sustainable forest management and conservation initiatives.

A novel reservoir classification method for sandstone reservoir evaluation using multi-scale digital rock method

The formulation of an effective development plan, optimizing exploitation efficiency, relies heavily on accurate reservoir characterization. However, existing reservoir classification methodologies, which rely on macroscopic geological observations and well-logging data, have limitations in data availability and fail to capture micro-scale pore structure characteristics accurately. The emerging technology of digital rock, widely employed in the petroleum industry, also faces challenges in accurately capturing reservoir heterogeneity due to its single-scale nature and limited application for reservoir classification. To overcome these challenges, this study presents an innovative reservoir classification approach based on the multi-scale digital rock method. This approach integrates qualitative assessment of micro-CT images for particle contact relationships and pore types with quantitative evaluation of multi-scale characteristic parameters, obtained from micro-CT and scanning electron microscopy (SEM) images. The proposed classification method demonstrates excellent agreement with the prioritization of development and production data for offshore sandstone reservoirs. By establishing a robust evaluation methodology, this classification method facilitates exploration potential assessment and development strategy optimization within the field.

Detection of Emerging Stress in Trees Using Hyperspectral Indices as Classification Features

This research presents a classification methodology for the detection of new or emerging stress in trees using indices derived from hyperspectral data and tests whether existing hyperspectral indices are effective when used as the classification features for this problem. We tested six existing indices—Water Band Index (WBI), Gitelson–Merzlyak B Index (GMb), Normalized Phaeophytization Index (NPQI), Combined Carotenoid/Chlorophyll Ratio Index (CCRI), Photochemical Reflectance Index (PRI), and Red-Edge Chlorophyll Index (CIre)—along with a seventh Test Index—generated as a composite of PRI and Cire—as classification features. Analysis was conducted using data collected from trees with and without emerald ash borer (EAB) infestation to develop a methodology that could be adapted to measure emerging stress from other pathogens or invasive pests in other tree species. Previous work has focused specifically on the identification of damage or stress symptoms caused by a specific pathogen. In this study, we adapted that work to develop a system of classification that can be applied to the identification of stress symptoms from a range of sources, measurable in trees based on spectral response and, in some cases, detectable prior to the onset of visible symptoms that can be measured through human observation. Our data indicate that existing indices derived from hyperspectral data are effective as classification features when measuring spectral responses indicative of emerging stress in trees.