Machine Learning Classification Algorithms Research Articles

Tribological analysis of titanium alloy (Ti-6Al-4V) hybrid metal matrix composite through the use of Taguchi’s method and machine learning classifiers

The preparation and tribological behavior of the titanium metal matrix (Ti-6Al-4V) composite reinforced with tungsten carbide (WCp) and graphite (Grp) particles were investigated in this study. The stir casting procedure was used to fabricate the titanium metal matrix composites (TMMCs), which had 8 weight percent of WCp and Grp. The tribological studies were designed using Taguchi’s L27 orthogonal array technique and were carried out as wear tests using a pin-on-disc device. According to Taguchi’s analysis and ANOVA, the most significant factors that affect wear rate are load and distance, followed by velocity. The wear process was ascertained by scanning electron microscopy investigation of the worn surfaces of the composite specimens. Pearson’s heatmap and Feature importance (F-test) were plotted for data analysis to study the significance of input parameters on wear. Machine learning classification algorithms such as k-nearest neighbors, support vector machine, and XGBoost algorithms accurately classified the wear rate data, giving an accuracy value of 71.25%, 65%, and 56.25%, respectively.

Demi-decadal land use land cover change analysis of Mizoram, India, with topographic correction using machine learning algorithm.

Mizoram (India) is part of UNESCO's biodiversity hotspots in India that is primarily populated by tribes who engage in shifting agriculture. Hence, the land use land cover (LULC) pattern of the state is frequently changing. We have used Landsat 5 and 8 satellite images to prepare LULC maps from 2000 to 2020 in every 5years. The atmospherically corrected images were pre-processed for removal of cloud cover and then classified into six classes: waterbodies, farmland, settlement, open forest, dense forest, and bare land. We applied four machine learning (ML) algorithms for classification, namely, random forest (RF), classification and regression tree (CART), minimum distance (MD), and support vector machine (SVM) for the images from 2000 to 2020. With 80% training and 20% testing data, we found that the RF classifier works best with the most accuracy than other classifiers. The average overall accuracy (OA) and Kappa coefficient (KC) from 2000 to 2020 were 84.00% and 0.79 when the RF classifier was used. When using SVM, CART, and MD, the average OA and KC were 78.06%, 0.73;78.60%, 0.72;and73.32%, 0.65, respectively. We utilised three methods of topographic correction, namely, C-correction, SCS (sun canopy sensor) correction, and SCS + C correction to reduce the misclassification due to shadow effects. SCS + C correction worked best for this region; hence, we prepared LULC maps on SCS + C corrected satellite image. Hence, we have used RF classifier for LULC preparation demi-decadal from 2000 to 2020. The OA for 2000, 2005, 2010, 2015, and 2020 was found to be 84%, 81%, 81%, 85%, and 89%, respectively, using RF. The dense forest decreased from 2000 to 2020 with an increase in open forest, settlement, and agriculture; nevertheless, when Farmland was low, there was an increase in the barren land. The results were significantly improved with the topographic correction, and misclassification was quite less.

Evaluation of resampling techniques for deep learning based identification of promising genotypes in sugarcane varietal trials

Deep learning is a class of machine learning algorithms that extract high-level features from the raw input for making intelligent decisions. Identification of promising genotypes in varietal trials is one of many agriculture domain applications requiring implementation of deep learning to perform intelligent decision using varietal trial data. However, it has been found that varietal trial data to be used for identification is highly imbalanced one providing great challenges for classification tasks in deep learning. For example, only 33 genotypes were identified as promising in zonal varietal trials of All India Coordinated Research Project (AICRP) on Sugarcane during 2016-21, while those of non-promising class are 148. Balancing an imbalanced class is crucial as the classification model, which is trained using the imbalanced class dataset will tend to exhibit the prediction accuracy according to the highest class of the dataset. One way to address this issue is to use resampling, which adjusts the ratio between the different classes, making the data more balanced. Study was conducted to implement and evaluate four resampling techniques viz. random undersampling, random oversampling, ensemble, SMOTE to balance varietal trial dataset in order to build deep learning model to identify promising genotypes in sugarcane. Paper describes the methodology used in our approach for building deep learning model using resampling techniques and then presented comparative performance of these approaches in identifying promising genotypes. Results indicate that SMOTE and random oversampling performed well for balancing imbalanced dataset for developing deep learning model in comparison to no-resampling of imbalanced dataset. SMOTE outperformed all resampling techniques by achieving high values of precision, recall and F1 score for both positive and negative classes. However, ensemble and random undersampling methods did not showed good results in comparison to SMOTE and random oversampling technique. Studies conducted will be useful in developing artificial intelligence based tools for automatic identification of promising genotypes in varietals trials of sugarcane in particular, as well as other crops in general.

Optimizing sustainable concrete compressive strength prediction: A new particle swarm optimization‐based metaheuristic approach to neural network modeling for circular economy and disaster resilience

AbstractThis study aims to predict the final‐age compressive strengths of sustainable concrete series produced using different aggregate types with high accuracy using an artificial intelligence model and to reduce environmental degradation and conserve rapidly decreasing natural resources within the scope of sustainable development and circular economy goals. For this purpose, 45 different sustainable concrete series containing all‐natural, recycled, natural, and recycled concrete aggregates were produced and subjected to compressive strength tests at 7 and 28 days. In addition, this study also considers whether deep neural network models, which have gained popularity in recent years but have high time and resource costs, or shallow models are more suitable for determining the compressive strength values with high accuracy. For this purpose, a method is proposed that can automatically generate the optimal neural network model using a metaheuristic approach that eliminates the human factor. For this purpose, the proposed method was extensively compared with different classical machine learning algorithms. The proposed method predicted the 7 and 28‐day compressive strength with a coefficient of determination of 0.999 and presented better compressive strength predictions than all other algorithms. Considering the number of buildings to be constructed after earthquakes, the widespread use of concrete, and the importance of compressive strength, the proposed method will likely provide significant gains within sustainable development, circular economy, and disaster risk reduction.

Explore the application of machine learning algorithms in predicting stroke

Stroke is an acute cerebrovascular disease that seriously endangers human health and life safety. It occurs suddenly and is not easy to cure. It is easy to leave sequelae after the disease, and the age of onset tends to be younger, becoming a major disease that threatens human life and quality of life. With the advent of the era of big data, people can process and analyze the data obtained from a large number of patients with cardiovascular and cerebrovascular diseases. Through Machine Learning (ML), they can master the risk factor indicators leading to stroke, so that they can effectively predict the incidence of stroke, help cardiovascular and cerebrovascular patients carry out preventive treatment as soon as possible, reduce the incidence or the symptoms. This paper introduces several classic ML algorithms such as Decision Tree, Random Forest, Support Vector Machine (SVM), Gaussian Naive Bayesian, k-NN, Logical Regression, etc. In order to explore the accuracy of these algorithms, this study obtained 15,000 patient data from the Kaggle website, including 22 characteristics, and used the above algorithms to predict. Through the evaluation of Accuracy Score indicators, we have a clear understanding of the application of various algorithms in predicting stroke.

Forecasting Future Research Trends in the Construction Engineering and Management Domain Using Machine Learning and Social Network Analysis

Construction Engineering and Management (CEM) is a broad domain with publications covering interrelated subdisciplines and considered a key source of knowledge sharing. Previous studies used scientometric methods to assess the current impact of CEM publications; however, there is a need to predict future citations of CEM publications to identify the expected high-impact trends in the future and guide new research efforts. To tackle this gap in the literature, the authors conducted a study using Machine Learning (ML) algorithms and Social Network Analysis (SNA) to predict CEM-related citation metrics. Using a dataset of 93,868 publications, the authors trained and tested two machine learning classification algorithms: Random Forest and XGBoost. Validation of the RF and XGBoost resulted in a balanced accuracy of 79.1% and 79.5%, respectively. Accordingly, XGBoost was selected. Testing of the XGBoost model revealed a balanced accuracy of 80.71%. Using SNA, it was found that while the top CEM subdisciplines in terms of the number of predicted impactful papers are “Project planning and design”, “Organizational issues”, and “Information technologies, robotics, and automation”; the lowest was “Legal and contractual issues”. This paper contributes to the body of knowledge by studying the citation level, strength, and interconnectivity between CEM subdisciplines as well as identifying areas more likely to result in highly cited publications.

Optimized machine learning algorithm for thyroid tumour type classification: A hybrid approach Random Forest, and intelligent optimization algorithms

Thyroid tumours are a common form of cancer, and accurate classification of their type is crucial for effective treatment planning. This research presents a hybrid approach for the classification of thyroid tumours based on their type. The proposed approach combines the use of advanced machine learning techniques with a comprehensive database of thyroid tumour samples. The database includes various features such as tumour size, shape, and texture, as well as patient-specific information. The hybrid approach aims to optimize the classification process by leveraging the diverse set of features and utilizing the power of machine learning algorithms. By harnessing the power of machine learning algorithms, this approach has the potential to revolutionize the field of thyroid tumour classification and significantly improve patient outcomes. The optimization strategy is Particle Swarm Optimization, refining the classification performance and ensuring optimal accuracy in identifying and categorizing four types of thyroid tumours. The utilization of advanced diagnostic tools and state-of-the-art Random forest classifier techniques in this approach marks a significant advancement in the field of thyroid tumour classification. Through the augmentation of the dataset and the pre-processing techniques employed, the hybrid classification system demonstrates enhanced accuracy and reliability in distinguishing between different types of thyroid tumours. This innovative approach not only provides a more comprehensive understanding of thyroid tumours but also paves the way for personalized and effective treatment strategies, ultimately improving patient care and outcomes.

Machine Learning Algorithms for Power System Sign Classification and a Multivariate Stacked LSTM Model for Predicting the Electricity Imbalance Volume

The energy transition to a cleaner environment has been a concern for many researchers and policy makers, as well as communities and non-governmental organizations. The effects of climate change are evident, temperatures everywhere in the world are getting higher and violent weather phenomena are more frequent, requiring clear and firm pro-environmental measures. Thus, we will discuss the energy transition and the support provided by artificial intelligence (AI) applications to achieve a cleaner and healthier environment. The focus will be on applications driving the energy transition, the significant role of AI, and collective efforts to improve societal interactions and living standards. The price of electricity is included in almost all goods and services and should be affordable for the sustainable development of economies. Therefore, it is important to model, anticipate and understand the trend of electricity markets. The electricity price includes an imbalance component which is the difference between notifications and real-time operation. Ideally it is zero, but in real operation such differences are normal due to load variation, lack of renewable energy sources (RES) accurate prediction, unplanted outages, etc. Therefore, additional energy has to be produced or some generating units are required to reduce generation to balance the power system. Usually, this activity is performed on the balancing market (BM) by the transmission system operator (TSO) that gathers offers from generators to gradually reduce or increase the output. Therefore, the prediction of the imbalance volume along with the prices for deficit and surplus is of paramount importance for producers’ decision makers to create offers on the BM. The main goal is to predict the imbalance volume and minimize the costs that such imbalance may cause. In this chapter, we propose a method to predict the imbalance volume based on the classification of the imbalance sign that is inserted into the dataset for predicting the imbalance volume. The imbalance sign is predicted using several classifiers and the output of the classification is added to the input dataset. The rest of the exogenous variables are shifted to the values from previous day d − 1. Therefore, the input variables are either predicted (like the imbalance sign) or are known from d − 1. Several metrics, such as mean average percentage error (MAPE), determination coefficient R2 and mean average error (MAE) are calculated to assess the proposed method of combining classification machine learning (ML) algorithms and recurrent neural networks (RNN) that memorize variations, namely long short-term memory (LSTM) model.

IoT Based Crop Prediction using Machine Learning

To enhance agricultural productivity and resource allocation. Leveraging historical data encompassing various agricultural factors such as soil composition, weather conditions, and crop types, a predictive model is developed to forecast crop yields. Machine learning techniques, including regression and classification algorithms, are employed to analyze the intricate relationships within the dataset and predict the most likely outcomes for specific crops in different regions. The model is trained on a diverse dataset, considering variations in climate and soil characteristics, ensuring robustness and adaptability across different agricultural environments . The proposed crop prediction system not only provides accurate yield forecasts but also assists farmers in making informed decisions regarding crop selection and resource optimization. By harnessing the power of machine learning, this research contributes to sustainable agriculture by promoting precision farming practices. The integration of technology in crop prediction not only improves yield predictions but also supports the overall resilience of agricultural systems, fostering a data-driven approach that aligns with the evolving needs of the agricultural sector in a rapidly changing world.

Exploring the Potential of Machine Learning Algorithms to Improve Diffusion Nuclear Magnetic Resonance Imaging Models Analysis.

This paper explores different machine learning (ML) algorithms for analyzing diffusion nuclear magnetic resonance imaging (dMRI) models when analytical fitting shows restrictions. It reviews various ML techniques for dMRI analysis and evaluates their performance on different b-values range datasets, comparing them with analytical methods. After standard fitting for reference, four sets of diffusion-weighted nuclear magnetic resonance images were used to train/test various ML algorithms for prediction of diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f), and kurtosis (K). ML classification algorithms, including extra-tree classifier (ETC), logistic regression, C-support vector, extra-gradient boost, and multilayer perceptron (MLP), were used to determine the existence of diffusion parameters (D, D*, f, and K) within single voxels. Regression algorithms, including linear regression, polynomial regression, ridge, lasso, random forest (RF), elastic-net, and support-vector machines, were used to estimate the value of the diffusion parameters. Performance was evaluated using accuracy (ACC), area under the curve (AUC) tests, and cross-validation root mean square error (RMSECV). Computational timing was also assessed. ETC and MLP were the best classifiers, with 94.1% and 91.7%, respectively, for the ACC test and 98.7% and 96.3% for the AUC test. For parameter estimation, RF algorithm yielded the most accurate results The RMSECV percentages were: 8.39% for D, 3.57% for D*, 4.52% for f, and 3.53% for K. After the training phase, the ML methods demonstrated a substantial decrease in computational time, being approximately 232 times faster than the conventional methods. The findings suggest that ML algorithms can enhance the efficiency of dMRI model analysis and offer new perspectives on the microstructural and functional organization of biological tissues. This paper also discusses the limitations and future directions of ML-based dMRI analysis.

FEATURES OF THE AUTOMATIC MACHINE LEARNING TOOLS IN THE TASKS OF FRACTOGRAPHIC ANALYSIS

The article is devoted to the development of an information system for analyzing the mechanisms of metal destruction based on automatic machine learning (AutoML). The theoretical foundations of AutoML are investigated, a number of tasks and AutoML tools suitable for them are presented, and the characteristics of their application in the analysis of fractographic images in the framework of quantitative metallography are given. The principles of creating an information system for analyzing the mechanisms of metal destruction based on AutoML, using modern software development tools and tools, are described. Attention is paid to the collection and preparation of fractographic images for further analysis, as well as the development of machine learning algorithms for automatic analysis and classification of damage characteristics and causes of destruction of metal materials. Various AutoML tools are compared through the prism of the tasks they solve, and the choice of the tool is justified Liner.io as an optimal option in solving problems of automation of fractographic analysis. The practical results of using the most suitable automatic machine learning tool for the analysis of fractographic images Liner.ai are presented, and also an assessment of the prospects of using this tool to solve problems both in metallographic research and in other industries is given. The examples are provided with visualization of the learning results of the neural network model and comparative analysis of the marked-up fractographic image and the prediction result of the neural network model.

An Optimal Framework Based on the GentleBoost Algorithm and Bayesian Optimization for the Prediction of Breast Cancer Patients' Survivability

Breast cancer is a primary cause of cancer-associated mortality among women globally, and early detection and personalized treatment are critical for improving patient outcomes. In this study, we propose an optimal framework for predicting breast cancer patient survivability using the GentleBoost algorithm and Bayesian optimization. The proposed framework combines the strengths of the GentleBoost algorithm, which is a powerful machine-learning algorithm for classification, and Bayesian optimization, which is a powerful optimization technique for hyperparameter tuning. We evaluated the proposed framework using the publicly available breast cancer dataset provided by The Surveillance, Epidemiology, and End Results (SEER) program and compared its performance with several popular single algorithms, including support vector machine (SVM), artificial neural network (ANN), and k-nearest neighbors (KNN). The experimental results demonstrate that the proposed framework outperforms these methods in terms of accuracy (mean= 95.16%, best = 95.35, worst = 95.1%, and SD = 0.008). The values of precision, recall, and f1-score of the best experiment were 92.3 %, 98.2 %, and 95.2 %, respectively, with hyperparameters of (number of learners = 246, learning rate = 0.0011, and maximum number of splits = 1240). The proposed framework has the potential to improve breast cancer patient survival predictions and personalized treatment plans, leading to the improved patient outcomes and reduced healthcare costs.

Smart Farming: Bridging Farmers and Consumers through Machine Learning-Enabled E-commerce Platforms

Abstract: This research paper proposes the development of an e-commerce platform tailored specifically for farmers, integrating machine learning algorithms for fruit detection and classification, alongside blockchain technology for enhanced authentication. The platform aims to streamline the agricultural supply chain, facilitating direct transactions between farmers and consumers while ensuring product quality and authenticity. The machine learning models will enable automated fruit recognition and categorization, allowing farmers to efficiently showcase their produce online. Additionally, blockchain technology will provide a secure and transparent framework for verifying the origin and quality of agricultural products, fostering trust among buyers. The synergistic combination of machine learning and blockchain holds promise for revolutionizing the agricultural sector, promoting fair trade practices, and empowering farmers in the digital marketplace.

Evaluating the Performance of Machine Learning Classifier Algorithms for Software Estimation in Software Development Projects

The major aim of this research is to rank the best performing features in order to classify the Software estimation dataset using SVM, Naïve Bayes, Random forest, Decision tree, and KNN classifiers and evaluate their accuracy. Two steps are involved in the classification process: first, the dataset with all attributes is analyzed; second, the information gain methodology is used to rank the attributes, and only the highly rated ones are used to generate the model of classification. Using several folds of cross-validation, we assess the accuracy rank of SVM, Naïve Bayes, Decision tree, Random forest, and KNN classifier

Machine Learning and Deep Learning Models for Nocturnal High- and Low-Glucose Prediction in Adults with Type 1 Diabetes.

Glucose management at night is a major challenge for people with type 1 diabetes (T1D), especially for those managed with multiple daily injections (MDIs). In this study, we developed machine learning (ML) and deep learning (DL) models to predict nocturnal glucose within the target range (3.9-10 mmol/L), above the target range, and below the target range in subjects with T1D managed with MDIs. The models were trained and tested on continuous glucose monitoring data obtained from 380 subjects with T1D. Two DL algorithms-multi-layer perceptron (MLP) and a convolutional neural network (CNN)-as well as two classic ML algorithms, random forest (RF) and gradient boosting trees (GBTs), were applied. The resulting models based on the DL and ML algorithms demonstrated high and similar accuracy in predicting target glucose (F1 metric: 96-98%) and above-target glucose (F1: 93-97%) within a 30 min prediction horizon. Model performance was poorer when predicting low glucose (F1: 80-86%). MLP provided the highest accuracy in low-glucose prediction. The results indicate that both DL (MLP, CNN) and ML (RF, GBTs) algorithms operating CGM data can be used for the simultaneous prediction of nocturnal glucose values within the target, above-target, and below-target ranges in people with T1D managed with MDIs.

Classification of Genetics Based on Machine Learning Algorithms: A Review

The multifaceted applications of drones in addressing humanitarian challenges, enhancing governance services, medical assistance, and security considerations. Drones are showcased as adaptable and swift responders in conflict or disaster-affected areas, mitigating risks for humanitarian workers and delivering crucial supplies to remote locations. The integration of digital technology in governance services is discussed, emphasizing transparency, efficacy, and reduced corruption. The study also introduces a taxonomy for GPS- guided drones in medical supply delivery, highlighting challenges in accuracy and cost reduction. Drones' wide- ranging potential uses, from police operations to advertising and shipment transportation, are outlined. A comprehensive evaluation of drone security, from consumer drones to military systems, is provided, along with preventive suggestions. Machine learning algorithms for drone detection and classification, showcasing the proposed DDI system's capability to accurately identify intruding drones and their operational modes. machine learning in the context of used drones, focusing on detection and classification. The study assesses various machine learning algorithms, including image processing, sound analysis, and RF signal-based techniques, to identify and classify drones effectively. Data from diverse sensors are utilized for feature extraction, employing algorithms such as Deep Neural Networks, Support Vector Machines, and deep belief networks. The proposed DDI system adopts an RF-based approach and integrates a Deep Learning algorithm for precise detection and identification of used or intruding drones.

Detecting cyberbullying using deep learning techniques: a pre-trained glove and focal loss technique.

This study investigates the effectiveness of various deep learning and classical machine learning techniques in identifying instances of cyberbullying. The study compares the performance of five classical machine learning algorithms and three deep learning models. The data undergoes pre-processing, including text cleaning, tokenization, stemming, and stop word removal. The experiment uses accuracy, precision, recall, and F1 score metrics to evaluate the performance of the algorithms on the dataset. The results show that the proposed technique achieves high accuracy, precision, and F1 score values, with the Focal Loss algorithm achieving the highest accuracy of 99% and the highest precision of 86.72%. However, the recall values were relatively low for most algorithms, indicating that they struggled to identify all relevant data. Additionally, the study proposes a technique using a convolutional neural network with a bidirectional long short-term memory layer, trained on a pre-processed dataset of tweets using GloVe word embeddings and the focal loss function. The model achieved high accuracy, precision, and F1 score values, with the GRU algorithm achieving the highest accuracy of 97.0% and the NB algorithm achieving the highest precision of 96.6%.

A Novel Approach to Detection of Alzheimer’s Disease from Handwriting: Triple Ensemble Learning Model

The irreversible degeneration of nerve cells in the body dramatically affects the motor skills and cognitive abilities used effectively in daily life. There is no known cure for neurodegenerative diseases such as Alzheimer’s. However, in the early diagnosis of such diseases, the progression of the disease can be slowed down with specific rehabilitation techniques and medications. Therefore, early diagnosis of the disease is essential in slowing down the disease and improving patients’ quality of life. Neurodegenerative diseases also affect patients’ ability to use fine motor skills. Losing fine motor skills causes patients’ writing skills to deteriorate gradually. Information about Alzheimer’s disease can be obtained based on the deterioration in the patient’s writing skills. However, manual detection of Alzheimer’s disease (AD) from handwriting is a time-consuming and challenging task that varies from physician to physician. Machine learning-based classifiers are extremely popularly used with high-performance scores to solve the challenging manual detection of AD. In this study, Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Adaptive Boosting (AdaBoost), and eXtreme Gradient Boosting (XGBoost) machine learning classification algorithms were combined with a Voting Classifier and trained and tested on the publicly available DARWIN (Diagnosis Alzheimer’s With haNdwriting) dataset. As a result of the experimental studies, the proposed Ensemble methodology achieved 97.14% Acc, 95% Prec, 100% Recall, 90.25% Spec, and 97.44% F1-score (Dice) performance values. Studies have shown that the proposed work is exceptionally robust.

Automatic Detection of Epileptic Seizures from EEG Signals Using Artificial Intelligence Methods

Epilepsy is a neurological disorder in which involuntary contractions, sensory abnormalities, and changes occur as a result of abrupt and uncontrolled discharges in the neurons in the brain, which disrupt the systems regulated by the brain. In epilepsy, abnormal electrical impulses from cells in various brain areas are noticed. The accurate interpretation of these electrical impulses is critical in the illness diagnosis. This study aims to use different machine-learning algorithms to diagnose epileptic seizures. The frequency components of EEG data were extracted using parametric approaches. This feature extraction approach was fed into machine learning classification algorithms, including Artificial Neural Network (ANN), Gradient Boosting, and Random Forest. The ANN classifier was shown to have the most significant test performance in this investigation, with roughly 97% accuracy and a 91% F1 score in recognizing epileptic episodes. The Gradient Boosting classifier, on the other hand, performed similarly to the ANN, with 96% accuracy and a 93% F1 score.

Developing an expansion‐based obstacle detection using panoptic segmentation

AbstractSafe Micro Aerial Vehicle (MAV) navigation requires detecting and avoiding obstacles. For safe MAV navigation, expansion‐based algorithms are effective for detecting obstacles. However, accurate and real‐time obstacle detection is a fundamental challenge. Some traditional methods focus on extracting geometric features from images and applying geometric constraints to identify potential obstacles. Others may leverage machine learning algorithms for object detection and classification, using features such as texture, shape, and context to distinguish obstacles from background clutter. The choice of approach depends on factors such as the specific requirements of the application, the complexity of the scene, and the available computational resources. Since obstacles, in reality, take the form of objects (e.g., persons, walls, pillars, trees, automobiles, and other structures), it is preferable to represent them according to human comprehension and as objects. Therefore, the objective of this study is to reflect on the previous research and address the issues mentioned above by extracting objects from the fisheye image using a panoptic deep‐learning network. The extracted object regions are, then, used to identify obstacles with a novel area‐based expansion rate we developed in a previous study. We compared the accuracy of obstacle detection in our proposed method to the existing method when moving forward and to the right; thus, we improved it between 10% and 18%, respectively. In addition, compared with the existing method, and due to replacing a single object with multiple regions, obstacle‐detection runtime for forward and right direction is 15.71 and 25.5 times faster, respectively, and the required match points have decreased by 49% and 55%.