Automatic Classification Algorithm Research Articles

MACHINE LEARNING FOR MOBILE LIDAR DATA CLASSIFICATION OF 3D ROAD ENVIRONMENT

Abstract. 3D road mapping is essential for intelligent transportation system in smart cities. Road features can be utilized for road maintenance, autonomous driving vehicles, and providing regulations to drivers. Currently, 3D road environment receives its data from Mobile Laser Scanning (MLS) systems. MLS systems are capable of rapidly acquiring dense and accurate 3D point clouds, which allow for effective surveying of long road corridors. They produce huge amount of point clouds, which requires automatic features classification algorithms with acceptable processing time. Road features have variant geometric regular or irregular shapes. Therefore, most researches focus on classification of one road feature such as road surface, curbs, building facades, etc. Machine learning (ML) algorithms are widely used for predicting the future or classifying information to help policymakers in making necessary decisions. This prediction comes from a pre-trained model on a given data consisting of inputs and their corresponding outputs of the same characteristics. This research uses ML algorithms for mobile LiDAR data classification. First, cylindrical neighbourhood selection method was used to define point’s surroundings. Second, geometric point features including geometric, moment and height features were derived. Finally, three ML algorithms, Random Forest (RF), Gaussian Naïve Bayes (GNB), and Quadratic Discriminant Analysis (QDA) were applied. The ML algorithms were used to classify a part of Paris-Lille-3D benchmark of about 1.5 km long road in Lille with more than 98 million points into nine classes. The results demonstrated an overall accuracy of 92.39%, 78.5%, and 78.1% for RF, GNB, and QDA, respectively.

Extracting video games rating labels from transcript files

Video games industry represents one of the most profitable activities connected with entertainment and visual arts. Video game industry involves a great number of different professionals who work together to create products expected to reach people in many countries. A substantial part of these people are teenagers, strongly attracted and influenced by video games. For these reasons, various systems of labels have been created. These systems are based on different criteria, but they have in common the presence of descriptors, or labels, whose indicate the type of contents in the game. These labels give an age range indicator to inform the buyers and users to the more suitable age for the product. One of these systems is called PEGI, and we will primarily take it in consideration for the purposes of our study. The rating procedure includes a large process of manual control of each submitted game. In order to help this large and demanding process, we propose a system of video games rating based on automatic classification of the products performed over the “transcript” or script, files that display the full transcription of dialogues in a video game. The proposed automatic classification algorithm is based on specialized dictionaries enriched with a vector semantics algorithm, and is able to provide an age rating and a genre classification of video games. It works in a more efficient way in games with a consistent amount of dialogues. The experimentation of the proposed algorithm is returning encouraging results.

ACCV: automatic classification algorithm of cataract video based on deep learning

PurposeA real-time automatic cataract-grading algorithm based on cataract video is proposed.Materials and methodsIn this retrospective study, we set the video of the eye lens section as the research target. A method is proposed to use YOLOv3 to assist in positioning, to automatically identify the position of the lens and classify the cataract after color space conversion. The data set is a cataract video file of 38 people's 76 eyes collected by a slit lamp. Data were collected using five random manner, the method aims to reduce the influence on the collection algorithm accuracy. The video length is within 10 s, and the classified picture data are extracted from the video file. A total of 1520 images are extracted from the image data set, and the data set is divided into training set, validation set and test set according to the ratio of 7:2:1.ResultsWe verified it on the 76-segment clinical data test set and achieved the accuracy of 0.9400, with the AUC of 0.9880, and the F1 of 0.9388. In addition, because of the color space recognition method, the detection per frame can be completed within 29 microseconds and thus the detection efficiency has been improved significantly.ConclusionWith the efficiency and effectiveness of this algorithm, the lens scan video is used as the research object, which improves the accuracy of the screening. It is closer to the actual cataract diagnosis and treatment process, and can effectively improve the cataract inspection ability of non-ophthalmologists. For cataract screening in poor areas, the accessibility of ophthalmology medical care is also increased.

Clean Our City: An Automatic Urban Garbage Classification Algorithm Using Computer Vision and Transfer Learning Technologies

To improve the quality of human life in the city, the first thing to solve is the problem of urban garbage. So far, the best way to solve this problem is garbage classification. At present, many algorithms have been put forward one after another. Previous research proposed some computer vision systems to solve the problem of urban garbage classification. In recent years, with the development of computer hardware and large-scale data sets, the algorithm based on depth learning has shown superior performance in the field of image classification. Thus, the features designed by traditional methods are gradually replaced, which far exceed these traditional image classification algorithms in classification accuracy. This study proposes an algorithm based on InceptionV3 networks and test the algorithm on a large-scale garbage classification data-set. The data set was divided into 80% training sets, 10% validation set, and 10% test set and use the transfer learning approach. The model achieved an accuracy of 93.125%, which solved image garbage classification very well. What is more, the algorithm can play an important role in the medical area and help control the mechanical arm.

Microseismic Signal Classification Based on Artificial Neural Networks

The classification of multichannel microseismic waveform is essential for real-time monitoring and hazard prediction. The accuracy and efficiency could not be guaranteed by manual identification. Thus, based on 37310 waveform data of Junde Coal Mine, eight features of statistics, spectrum, and waveform were extracted to generate a complete data set. An automatic classification algorithm based on artificial neural networks (ANNs) has been proposed. The model presented an excellent performance in identifying three preclassified signals in the test set. Operated with two hidden layers and the Logistic activation function, the multiclass area under the receiver operating characteristic curve (AUC) reached 98.6%.

Using Google Earth Engine to Assess Temporal and Spatial Changes in River Geomorphology and Riparian Vegetation

AbstractWe developed a new approach using a cloud‐based remote sensing and geospatial analysis platform, Google Earth Engine, to quantify temporal changes in river channel location and adjacent riparian vegetation extent and fraction. Our new method uses publicly available 1 m aerial images and eliminates manual processing need by incorporating an automatic image classification algorithm. Classification of riparian vegetation is enhanced by increasing the temporal resolution to monthly and by mapping vegetation at high spatial resolution. We illustrate the application of our method by characterizing temporal and spatial trends in riparian vegetation and river channel position for the mainstem of the Genesee River, New York, from 2006 to 2015. Annual change in riparian vegetation extent along the Genesee River ranged from a loss of 17% to a gain of 13%, and 64 km (28%) of the river demonstrated channel migration across consecutive aerial images. Our method also successfully distinguished differences between sections of the river above and below a dam. The enhanced capacity to map vegetation monthly allowed us to identify that seasonal active vegetation fractions along the Genesee River peaked at 75% in the summer and remained lower than 25% in winter. Our method allows stakeholders and managers to process remotely sensed imagery and investigate trends in river channel and riparian vegetation dynamics over time, while reducing the costs of data processing and storage.

Anatomic Distribution of Cherry Angiomas in the General Population

Background: Cherry angiomas are common benign vascular skin lesions of unknown aetiology, found largely on the trunk. However, their exact anatomic distribution besides their truncal predisposition, and how they manifest in the general population, has not been characterised. Methods: Three-dimensional (3D) total body imaging was obtained from 163 adult participants of a general population cohort study in Brisbane, Australia. Demographic, phenotypic, and sun behaviour characteristics were collected using a standard questionnaire along with history of melanoma and keratinocyte cancers. Cherry angiomas were identified using an automated classification algorithm with a sensitivity of 87% and a specificity of 99%, developed specifically for this study population. Results: The 3D total body images of 163 participants were analysed. Participants had a median age of 57 years and 61% were male. On average, males had more angiomas than females (median of 16 vs. 12) and the number and size of cherry angiomas increased with age. In addition to male sex and age, an increase in angiomas was associated with Caucasian ancestry other than British/Irish only, fair skin colour opposed to medium/olive, having green/hazel eyes compared to blue/grey, and personal history of melanoma. The most common site for cherry angiomas was the front trunk, followed by the back. Interestingly, although males had more angiomas overall, females had more angiomas on the legs. Conclusion: Describing the distribution of cherry angiomas by body site is an important step towards further understanding of the aetiology of angiomas. While personal history of melanoma is associated with an increased number of cherry angiomas, whether this association is prognostic, co-occurs with development of melanoma, or is merely fortuitous requires further investigation.

Classification of colored spun fabric structure based on wavelet decomposition and hierarchical hybrid classifier

In view of the difficulty in extracting the feature parameters of colored spun fabric structure, this article proposes an automatic classification algorithm based on wavelet decomposition and hierarchical hybrid classifier. Based on HSV color space, the algorithm uses the wavelet function to perform multi-resolution decomposition and parameter feature extraction of colored spun fabric image. At the same time, it uses BP network and naive Bayes to build hierarchical hybrid classifier, and realizes the classification of the structure feature parameters. The experimental results show that the extracted fabric weave features not only have the ability of multi-resolution texture information representation, but also the constructed hybrid classifier has the characteristics of cascade enhancement. The average classification accuracy of 176 colored spun fabric structure with different dyeing fiber blending coefficient and twist coefficient is 96.67%, which proves the effectiveness and robustness of the method. The research in this article has important guiding significance to construct stable and effective colored spun fabric design and production system.

An automatic classification algorithm for submerged aquatic vegetation in shallow lakes using Landsat imagery

Submerged aquatic vegetation (SAV) is one of the main producers in inland lakes. Tracking the temporal and spatial changes in SAV is crucial for the identification of state changes in lacustrine ecosystems, such as changes in light, nutrients, and temperature. However, the available SAV classification algorithms based on remote sensing are highly dependent on field survey data and/or human interventions, prohibiting the extraction of large-scale and/or long-term patterns. Here, we developed an automatic SAV classification algorithm using Landsat imagery, where the thresholds of two key parameters (the floating algae index (FAI) and reflectance in the shortwave-infrared (SWIR) band) are automatically determined. The algorithm was applied to eight Landsat images of four Yangtze Plain lakes and obtained a mean producer accuracy of 82.9% when gauged against field-surveyed datasets. The algorithm was further employed to obtain long-term SAV areal data from Changdang Lake on the Yangtze Plain from 1984 to 2018, and the result was highly consistent with lake transparency data. Numerical simulations indicated that our developed algorithm is insensitive to the Chl-a concentration of the water column. Yet, it has a detection limit of ~0.35 m below the water surface, and such a limit changes with different fractions of vegetation coverage within a pixel. The automatic classification algorithm proposed in this study has the potential to obtain the temporal and spatial distribution patterns of SAV in other shallow lakes where SAV grows in lakes sharing similar hydrological characteristics as the lakes in the Yangtze Plain.

Richer fusion network for breast cancer classification based on multimodal data

BackgroundDeep learning algorithms significantly improve the accuracy of pathological image classification, but the accuracy of breast cancer classification using only single-mode pathological images still cannot meet the needs of clinical practice. Inspired by the real scenario of pathologists reading pathological images for diagnosis, we integrate pathological images and structured data extracted from clinical electronic medical record (EMR) to further improve the accuracy of breast cancer classification.MethodsIn this paper, we propose a new richer fusion network for the classification of benign and malignant breast cancer based on multimodal data. To make pathological image can be integrated more sufficient with structured EMR data, we proposed a method to extract richer multilevel feature representation of the pathological image from multiple convolutional layers. Meanwhile, to minimize the information loss for each modality before data fusion, we use the denoising autoencoder as a way to increase the low-dimensional structured EMR data to high-dimensional, instead of reducing the high-dimensional image data to low-dimensional before data fusion. In addition, denoising autoencoder naturally generalizes our method to make the accurate prediction with partially missing structured EMR data.ResultsThe experimental results show that the proposed method is superior to the most advanced method in terms of the average classification accuracy (92.9%). In addition, we have released a dataset containing structured data from 185 patients that were extracted from EMR and 3764 paired pathological images of breast cancer, which can be publicly downloaded from http://ear.ict.ac.cn/?page_id=1663.ConclusionsWe utilized a new richer fusion network to integrate highly heterogeneous data to leverage the structured EMR data to improve the accuracy of pathological image classification. Therefore, the application of automatic breast cancer classification algorithms in clinical practice becomes possible. Due to the generality of the proposed fusion method, it can be straightforwardly extended to the fusion of other structured data and unstructured data.

A nonparametric algorithm for automatic classification of large multivariate statistical data sets and its application

A nonparametric algorithm for automatic classification of large statistical data sets is proposed. The algorithm is based on a procedure for optimal discretization of the range of values of a random variable. A class is a compact group of observations of a random variable corresponding to a unimodal fragment of the probability density. The considered algorithm of automatic classification is based on the «compression» of the initial information based on the decomposition of a multidimensional space of attributes. As a result, a large statistical sample is transformed into a data array composed of the centers of multidimensional sampling intervals and the corresponding frequencies of random variables. To substantiate the optimal discretization procedure, we use the results of a study of the asymptotic properties of a kernel-type regression estimate of the probability density. An optimal number of sampling intervals for the range of values of one- and two-dimensional random variables is determined from the condition of the minimum root-mean square deviation of the regression probability density estimate. The results obtained are generalized to the discretization of the range of values of a multidimensional random variable. The optimal discretization formula contains a component that is characterized by a nonlinear functional of the probability density. An analytical dependence of the detected component on the antikurtosis coefficient of a one-dimensional random variable is established. For independent components of a multidimensional random variable, a methodology is developed for calculating estimates of the optimal number of sampling intervals for random variables and their lengths. On this basis, a nonparametric algorithm for the automatic classification is developed. It is based on a sequential procedure for checking the proximity of the centers of multidimensional sampling intervals and relationships between frequencies of the membership of the random variables from the original sample of these intervals. To further increase the computational efficiency of the proposed automatic classification algorithm, a multithreaded method of its software implementation is used. The practical significance of the developed algorithms is confirmed by the results of their application in processing remote sensing data.

Potassium di-hydrogen phosphate identification based on wide energy X-ray absorption spectrum and an artificial neural network

In order to accurately distinguish potassium di-hydrogen phosphate (KH2PO4) from common counterfeit products (NH4H2PO4, KCl, Na2SO4, MgSO4 and white sugar), a wide X-ray absorption spectrum detection system based on photon count detector (PCD) was used to scan six samples leading to wide X-ray absorption spectrum (XAS). Principal component analysis (PCA) was used to extract the main features of XAS (normalized) and an artificial neural network (ANN) was used for automatic identification. The experimental results showed that the absorption of X-rays in the energy range of 12 keV to 40 keV was different among samples. The overall accuracy was 86.67%. The precision, recall and F1-score of potassium di-hydrogen phosphate all reached 100%. Therefore, it is feasible to use the difference of XAS between potassium di-hydrogen phosphate and other counterfeit products to realize product identification, and PCA-ANN algorithm can achieve an ideal automatic recognition result. Wide XAS combined with PCA-ANN automatic classification algorithm provides a new idea for the identification of the potassium di-hydrogen phosphate authenticity.

Motor synergies: Evidence for a novel motor signature in autism spectrum disorder

In autism spectrum disorder (ASD), socio-communicative impairments and stereotypical behaviours are paralleled by sensorimotor deficits. Individuals with ASD show an altered selection of motor parameters, resulting in clumsy and fragmented actions. Here, we investigated inter-joint coordination and motor synergies as a potential substrate of motor control problems in ASD. Synergies enable co-controlling redundant motor degrees of freedom (DoF, e.g. joint angles, muscles) by mapping behavioural goals into a flexible and low-dimensional set of variables. This mechanism simplifies motor control and helps to find unambiguous solutions for motor tasks. In a reaching-grasping paradigm, children with ASD showed reduced coupling between DoF, which correlated with socio-communicative symptoms severity. Impaired synergies may help to frame well-established motor problems in ASD, including impaired motor sequencing and abnormal trial-to-trial motor variability. On the other hand, synergies also provide an effective and compact coding system of observed actions. Impaired synergies may thus jeopardize motor interaction by initiating bottom-up cascade effects, leading to pervasive impairments of social behaviour. Finally, we trained an automatic classification algorithm to distinguish between ASD and typically developing (TD) participants based on reaching-grasping kinematics. Classification accuracy reached up to 0.947. This result corroborates and expands previous accounts claiming that motor-based early recognition is feasible and effective in ASD.

A novel feature representation approach for single-lead heartbeat classification based on adaptive Fourier decomposition

This paper proposes a novel feature representation approach for heartbeat classification using single-lead electrocardiogram (ECG) signals based on adaptive Fourier decomposition (AFD). AFD is a recently developed signal processing tool that provides useful morphological features, which are referred as AFD-derived instantaneous frequency (IF) features and differ from those provided by traditional tools. The AFD-derived IF features, together with ECG landmark features and RR interval features, are trained by a support vector machine to perform the classification. The proposed method improves the average accuracy of the feature extraction-based methods, reaching a level comparable to deep learning but with less training data, and at the same time being interpretable for the learned features. It also greatly reduces the dimension of the feature set, which is a disadvantage of the feature extraction-based methods, especially for ECG signals. To evaluate the performance, the Association for the Advancement of Medical Instrumentation standard is applied to publicly available benchmark databases, including the MIT-BIH arrhythmia and MIT-BIH supraventricular arrhythmia databases, to classify heartbeats from the single-lead ECG. The overall performance is compared to selected state-of-the-art automatic heartbeat classification algorithms, including one-lead and even several two-lead-based methods. The proposed approach achieves superior balanced performance and real-time implementation.

ECG CLASSIFICATION COMPARISON BETWEEN MF-DFA AND MF-DXA

In this paper, automatic electrocardiogram (ECG) recognition and classification algorithms based on multifractal detrended fluctuation analysis (MF-DFA) and multifractal detrended cross-correlation analysis (MF-DXA) were studied. As human heart is a complex, nonlinear, chaotic system, using multifractal analysis to analyze chaotic systems is also a trend. We performed a comparison study of the multifractal nature of the healthy subjects and that of the cardiac dysfunctions ones. To analyze multifractal property quantitatively, the ranges of the Hurst exponent ([Formula: see text]) are computed by MF-DFA and MF-DXA. We found that for MF-DFA, the area of Hurst exponents for atrial premature beat (APB) people was narrower than normal sinus rhythm (NSR) subjects, and for MF-DXA, the difference of [Formula: see text] ([Formula: see text]) of NSR and APB subjects was larger than that of MF-DFA. We then regarded the Hurst exponents ([Formula: see text]) as the input vectors and took them into support vector machine (SVM) for classification. The results showed that [Formula: see text] obtained from MF-DXA led to a higher classification accuracy than that of MF-DFA. This is related to the widening of the difference in the values of Hurst exponents in MF-DFA and MF-DXA. The proposed MF-DFA-SVM and MF-DXA-SVM systems achieved classification accuracy of [Formula: see text] and [Formula: see text], achieved classification sensitivity of [Formula: see text] and [Formula: see text], achieved classification specificity of [Formula: see text] and [Formula: see text], respectively. In general, the Hurst exponents obtained from MF-DXA played an important role in classifying ECG of the healthy and that of the cardiac dysfunctions subjects. Moreover, MF-DXA was more accurate than MF-DFA in the classification of ECG studied in this paper. The research in automatic medical diagnosis and early warning of major diseases has very important practical value.

Automatic Classification of Coarse Aggregate Particle Size Based on Light Gradient Boost Machine

Aggregate plays an important role in the performance of asphalt mixture. In order to complete the intelligent online monitoring of asphalt aggregate quality, an automatic classification algorithm for coarse aggregate particle size based on LightGBM classification algorithm is proposed. Firstly, OpenCV is used to extract the two-dimensional morphological features of coarse aggregates, and then the correlation between these features and the classification of aggregates is analyzed. Finally, the accurate classification of coarse aggregate particles is achieved through grid search and cross-validation optimization model. The results show that the average classification precision of coarse aggregate can reach 84.7%. Compared with the classification method based only on image processing technology, the precision is increased by about 20%, and the efficiency of classification is greatly improved.

Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm.

Introduction: Several methods offer free volumetry services for MR data that adequately quantify volume differences in the hippocampus and its subregions. These methods are frequently used to assist in clinical diagnosis of suspected hippocampal sclerosis in temporal lobe epilepsy. A strong association between severity of histopathological anomalies and hippocampal volumes was reported using MR volumetry with a higher diagnostic yield than visual examination alone. Interpretation of volumetry results is challenging due to inherent methodological differences and to the reported variability of hippocampal volume. Furthermore, normal morphometric differences are recognized in diverse populations that may need consideration. To address this concern, we highlighted procedural discrepancies including atlas definition and computation of total intracranial volume that may impact volumetry results. We aimed to quantify diagnostic performance and to propose reference values for hippocampal volume from two well-established techniques: FreeSurfer v.06 and volBrain-HIPS.Methods: Volumetry measures were calculated using clinical T1 MRI from a local population of 61 healthy controls and 57 epilepsy patients with confirmed unilateral hippocampal sclerosis. We further validated the results by a state-of-the-art machine learning classification algorithm (Random Forest) computing accuracy and feature relevance to distinguish between patients and controls. This validation process was performed using the FreeSurfer dataset alone, considering morphometric values not only from the hippocampus but also from additional non-hippocampal brain regions that could be potentially relevant for group classification. Mean reference values and 95% confidence intervals were calculated for left and right hippocampi along with hippocampal asymmetry degree to test diagnostic accuracy.Results: Both methods showed excellent classification performance (AUC:> 0.914) with noticeable differences in absolute (cm3) and normalized volumes. Hippocampal asymmetry was the most accurate discriminator from all estimates (AUC:1~0.97). Similar results were achieved in the validation test with an automatic classifier (AUC:>0.960), disclosing hippocampal structures as the most relevant features for group differentiation among other brain regions.Conclusion: We calculated reference volumetry values from two commonly used methods to accurately identify patients with temporal epilepsy and hippocampal sclerosis. Validation with an automatic classifier confirmed the principal role of the hippocampus and its subregions for diagnosis.

FOntCell: Fusion of Ontologies of Cells.

High-throughput cell-data technologies such as single-cell RNA-seq create a demand for algorithms for automatic cell classification and characterization. There exist several cell classification ontologies with complementary information. However, one needs to merge them to synergistically combine their information. The main difficulty in merging is to match the ontologies since they use different naming conventions. Therefore, we developed an algorithm that merges ontologies by integrating the name matching between class label names with the structure mapping between the ontology elements based on graph convolution. Since the structure mapping is a time consuming process, we designed two methods to perform the graph convolution: vectorial structure matching and constraint-based structure matching. To perform the vectorial structure matching, we designed a general method to calculate the similarities between vectors of different lengths for different metrics. Additionally, we adapted the slower Blondel method to work for structure matching. We implemented our algorithms into FOntCell, a software module in Python for efficient automatic parallel-computed merging/fusion of ontologies in the same or similar knowledge domains. FOntCell can unify dispersed knowledge from one domain into a unique ontology in OWL format and iteratively reuse it to continuously adapt ontologies with new data endlessly produced by data-driven classification methods, such as of the Human Cell Atlas. To navigate easily across the merged ontologies, it generates HTML files with tabulated and graphic summaries, and interactive circular Directed Acyclic Graphs. We used FOntCell to merge the CELDA, LifeMap and LungMAP Human Anatomy cell ontologies into a comprehensive cell ontology. We compared FOntCell with tools used for the alignment of mouse and human anatomy ontologies task proposed by the Ontology Alignment Evaluation Initiative (OAEI) and found that the Fβ alignment accuracies of FOntCell are above the geometric mean of the other tools; more importantly, it outperforms significantly the best OAEI tools in cell ontology alignment in terms of Fβ alignment accuracies.

Multi-feature integration and machine learning for guided wave structural health monitoring: Application to switch rail foot

Switch rails are weak but essential components of high-speed railway systems that have urgent nondestructive testing requirements owing to aging and the associated potential for fatigue damage accumulation. This study presents a multi-feature integration and automatic classification algorithm for switch rail damage using guided wave monitoring signals. A combination of piezoelectric transducers and magnetostrictive patch transducers is adopted to improve the monitoring performance and meet actual monitoring requirements. Furthermore, multiple features extracted from various signal processing domains—such as the time domain, power spectrum domain, and time–frequency domain—are proposed and defined according to the structure and characteristics of the switch rail and guided wave to represent the complex nature of the damage. A damage index is defined to eliminate the influence of various environmental and operational conditions, signal power, and other factors. In addition, a feature selection method based on binary particle swarm optimization with a new fitness function is proposed to select the most damage-sensitive features and eliminate irrelevant and redundant features to improve the classification performance. Moreover, considering that the results are easily influenced by experts’ subjective judgment and experience, the least-squares support-vector machine is used to construct automatic classification models to reduce the probability of artificial incorrect diagnosis and improve the generalization ability to unknown environments. Finally, three types of experiments on the foot of a switch rail are presented to evaluate the proposed method. The results indicate that the proposed method is capable of identifying damage in challenging cases and is superior to conventional methods.

RETRACTED ARTICLE: Application of AI in image recognition technology for power line inspection

Artificial Intelligence (AI) is an energetic consideration in the electric power company for the scrutiny of the power lines in the forest area. The inspection is escorted to reduce input resources, less cost, rehabilitate electricity, and avoid overhead transmission and distribution lines. The imperfection in the electric companies is deliberate outage management, safety hazards, and diversified system, expensive and not flexible, which disturb the inspection in the forest areas. To recognize the images and status of the power lines, the Naive Bayesian classifier with Automatic Classification (NBC-AC) algorithms is implemented to classify the observed probabilistic variables of inspection accurately. To monitor the images in long-distance, an Unmanned Aerial Vehicle–Hunter (UAV-H) is proposed to predict the different features of power lines. Hence NBC-AC algorithms with UAV-H systems are used to recognize and classify the characteristics of the power line images with 95% accuracy in the forest area for the electric power company. This encouraging technique contributes to high efficiency and accuracy with the best quality of images and the results were obtained for many AI applications.