Pub Date : 2023-03-31DOI: 10.1142/s1469026823410055
N. Sukanya, P. R. J. Thangaiah
Mining patterns from High-utility itemsets (HUIs) have been exploited recently in place of frequent itemset mining (FIMs) or association-rule mining (ARMs) as they highlight profitability of products where quantity and profits are taken into account. Several techniques for HUIs have been proposed and they encounter exponential search spaces which have more distinct items or voluminous databases. Alternatively, Evolutionary Computations (ECs)-based meta-heuristics algorithms can be effective in solving issues in HUIs since a set of near-optimal solutions can be obtained within restricted periods. Current ECs-based techniques consume more time to identify HUIs in transactional databases, discover unacceptable combinations of HUIs, and finally fail to discover HUIs when neighborhood searches are not executed locally and globally. To overcome these challenges, a HUI mining algorithm based on Differential Evolution (DE) and Particle Swarm Optimization (PSO) using multiple strategies including elitism, population diversifications, exclusive preservations, and neighborhood exploration techniques has been proposed. Thus, this work defines mining patterns based on DE and PSO to identify HUIs in voluminous transactional databases. The HUIM-DE-PSO-DE algorithm proposed in this work discovers more number of HUIs which is revealed in experimental results obtained from a set of benchmark data instances. Results are compared with existing approaches using several performance metrics including convergence speeds, minimum utility threshold values, and execution time consumed.
{"title":"Enhanced Differential Evolution and Particle Swarm Optimization Approaches for Discovering High Utility Itemsets","authors":"N. Sukanya, P. R. J. Thangaiah","doi":"10.1142/s1469026823410055","DOIUrl":"https://doi.org/10.1142/s1469026823410055","url":null,"abstract":"Mining patterns from High-utility itemsets (HUIs) have been exploited recently in place of frequent itemset mining (FIMs) or association-rule mining (ARMs) as they highlight profitability of products where quantity and profits are taken into account. Several techniques for HUIs have been proposed and they encounter exponential search spaces which have more distinct items or voluminous databases. Alternatively, Evolutionary Computations (ECs)-based meta-heuristics algorithms can be effective in solving issues in HUIs since a set of near-optimal solutions can be obtained within restricted periods. Current ECs-based techniques consume more time to identify HUIs in transactional databases, discover unacceptable combinations of HUIs, and finally fail to discover HUIs when neighborhood searches are not executed locally and globally. To overcome these challenges, a HUI mining algorithm based on Differential Evolution (DE) and Particle Swarm Optimization (PSO) using multiple strategies including elitism, population diversifications, exclusive preservations, and neighborhood exploration techniques has been proposed. Thus, this work defines mining patterns based on DE and PSO to identify HUIs in voluminous transactional databases. The HUIM-DE-PSO-DE algorithm proposed in this work discovers more number of HUIs which is revealed in experimental results obtained from a set of benchmark data instances. Results are compared with existing approaches using several performance metrics including convergence speeds, minimum utility threshold values, and execution time consumed.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130041569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-30DOI: 10.1142/s1469026823500013
Pham Vu Hong Son, Nguyen Thi Nha Trang
Grey Wolf optimizer (GWO) has been used in several fields of research. The main advantages of this algorithm are its simplicity, little controlling parameter, and adaptive exploratory behavior. However, similar to other metaheuristic algorithms, the GWO algorithm has several limitations. The main drawback of the GWO algorithm is its low capability to handle a multimodal search landscape. This drawback occurs because the alpha, beta, and gamma wolves tend to converge to the same solution. This paper presents HDGM – a novel hybrid optimization model of dragonfly algorithm and grey wolf optimizer, aiming to overcome the disadvantages of GWO algorithm. Dragonfly algorithm (DA) is combined with GWO in this study because DA has superior exploration ability, which allows it to search in promising areas in the search space. To verify the solution quality and performance of the HDGM algorithm, we used twenty-three test functions to compare the proposed model’s performance with that of the GWO, DA, particle swam optimization (PSO) and ant lion optimization (ALO). The results show that the hybrid algorithm provides more competitive results than the other variants in terms of solution quality, stability, and capacity to discover the global optimum.
{"title":"Development of a Novel Artificial Intelligence Model for Better Balancing Exploration and Exploitation","authors":"Pham Vu Hong Son, Nguyen Thi Nha Trang","doi":"10.1142/s1469026823500013","DOIUrl":"https://doi.org/10.1142/s1469026823500013","url":null,"abstract":"Grey Wolf optimizer (GWO) has been used in several fields of research. The main advantages of this algorithm are its simplicity, little controlling parameter, and adaptive exploratory behavior. However, similar to other metaheuristic algorithms, the GWO algorithm has several limitations. The main drawback of the GWO algorithm is its low capability to handle a multimodal search landscape. This drawback occurs because the alpha, beta, and gamma wolves tend to converge to the same solution. This paper presents HDGM – a novel hybrid optimization model of dragonfly algorithm and grey wolf optimizer, aiming to overcome the disadvantages of GWO algorithm. Dragonfly algorithm (DA) is combined with GWO in this study because DA has superior exploration ability, which allows it to search in promising areas in the search space. To verify the solution quality and performance of the HDGM algorithm, we used twenty-three test functions to compare the proposed model’s performance with that of the GWO, DA, particle swam optimization (PSO) and ant lion optimization (ALO). The results show that the hybrid algorithm provides more competitive results than the other variants in terms of solution quality, stability, and capacity to discover the global optimum.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126789928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-27DOI: 10.1142/s1469026823410080
Akila Rathakrishnan, Revathi Sathiyanarayanan
Spreading rumors on social media is a phenomenon that has destructive implication of societal interaction, diverts attention toward destructive behavior. The impact will be more influenced in healthcare management. This research aims to detect the rumors and identify the sources using deep learning algorithms. In our proposed system, after pre-processing, the tweet comments are extracted from topics and ranked as deny, support, query and comment. Then the comments are classified as positive, negative and neutral using Artificial Neural Network Neuro-fuzzy Inference System Spline-based pi-shaped Membership Function (ANISPIMF). Then the negative comments are classified into offensive, violence, misogyny and hate mongering by using Improved Deep Learning Neural Network (IDLNN) which is the combination of Deep Neural Network with Cuckoo Search–Flower Pollination Algorithm to optimize the weight values. The optimized ANISPIMF performs very well for the COVID-19 dataset in terms of Accuracy, Precision and Recall. The proposed system attains better performance and efficiency when weighted against prevailing methodologies — regarding the performance measures, there is an improvement of accuracy by 0.6%, recall by 0.7%, and precision by 1%, together with an [Formula: see text]1-score of 1.2% than the Multiloss Hierarchical Bi-LSTM with Attenuation Factor (MHA).
{"title":"Rumor Detection on Social Media Using Deep Learning Algorithms with Fuzzy Inference System for Healthcare Analytics System Using COVID-19 Dataset","authors":"Akila Rathakrishnan, Revathi Sathiyanarayanan","doi":"10.1142/s1469026823410080","DOIUrl":"https://doi.org/10.1142/s1469026823410080","url":null,"abstract":"Spreading rumors on social media is a phenomenon that has destructive implication of societal interaction, diverts attention toward destructive behavior. The impact will be more influenced in healthcare management. This research aims to detect the rumors and identify the sources using deep learning algorithms. In our proposed system, after pre-processing, the tweet comments are extracted from topics and ranked as deny, support, query and comment. Then the comments are classified as positive, negative and neutral using Artificial Neural Network Neuro-fuzzy Inference System Spline-based pi-shaped Membership Function (ANISPIMF). Then the negative comments are classified into offensive, violence, misogyny and hate mongering by using Improved Deep Learning Neural Network (IDLNN) which is the combination of Deep Neural Network with Cuckoo Search–Flower Pollination Algorithm to optimize the weight values. The optimized ANISPIMF performs very well for the COVID-19 dataset in terms of Accuracy, Precision and Recall. The proposed system attains better performance and efficiency when weighted against prevailing methodologies — regarding the performance measures, there is an improvement of accuracy by 0.6%, recall by 0.7%, and precision by 1%, together with an [Formula: see text]1-score of 1.2% than the Multiloss Hierarchical Bi-LSTM with Attenuation Factor (MHA).","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131335225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-25DOI: 10.1142/s1469026823020017
Er Meng Joo, D. Pelusi, Shixian Wen
{"title":"Guest Editorial - Introduction to the Special Issue on Smart Fuzzy Optimization for Decision-Making in Uncertain Environments","authors":"Er Meng Joo, D. Pelusi, Shixian Wen","doi":"10.1142/s1469026823020017","DOIUrl":"https://doi.org/10.1142/s1469026823020017","url":null,"abstract":"","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121488665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-21DOI: 10.1142/s1469026823410109
S. BharaniNayagi, T. S. S. Angel
Multi-focus images can be fused by the deep learning (DL) approach. Initially, multi-focus image fusion (MFIF) is used to perform the classification task. The classifier of the convolutional neural network (CNN) is implemented to determine whether the pixel is defocused or focused. The lack of available data to train the system is one of the demerits of the MFIF methodology. Instead of using MFIF, the unsupervised model of the DL approach is affordable and appropriate for image fusion. By establishing a framework of feature extraction, fusion, and reconstruction, we generate a Deep CNN of [Formula: see text] End-to-End Unsupervised Model. It is defined as a Siamese Multi-Scale feature extraction model. It can extract only three different source images of the same scene, which is the major disadvantage of the system. Due to the possibility of low intensity and blurred images, considering only three source images may lead to poor performance. The main objective of the work is to consider [Formula: see text] parameters to define [Formula: see text] source images. Many existing systems are compared to the proposed method for extracting features from images. Experimental results of various approaches show that Enhanced Siamese Multi-Scale feature extraction used along with Structure Similarity Measure (SSIM) produces an excellent fused image. It is determined by undergoing quantitative and qualitative studies. The analysis is done based on objective examination and visual traits. By increasing the parameters, the objective assessment increases in performance rate and complexity with time.
{"title":"An Efficiency Correlation between Various Image Fusion Techniques","authors":"S. BharaniNayagi, T. S. S. Angel","doi":"10.1142/s1469026823410109","DOIUrl":"https://doi.org/10.1142/s1469026823410109","url":null,"abstract":"Multi-focus images can be fused by the deep learning (DL) approach. Initially, multi-focus image fusion (MFIF) is used to perform the classification task. The classifier of the convolutional neural network (CNN) is implemented to determine whether the pixel is defocused or focused. The lack of available data to train the system is one of the demerits of the MFIF methodology. Instead of using MFIF, the unsupervised model of the DL approach is affordable and appropriate for image fusion. By establishing a framework of feature extraction, fusion, and reconstruction, we generate a Deep CNN of [Formula: see text] End-to-End Unsupervised Model. It is defined as a Siamese Multi-Scale feature extraction model. It can extract only three different source images of the same scene, which is the major disadvantage of the system. Due to the possibility of low intensity and blurred images, considering only three source images may lead to poor performance. The main objective of the work is to consider [Formula: see text] parameters to define [Formula: see text] source images. Many existing systems are compared to the proposed method for extracting features from images. Experimental results of various approaches show that Enhanced Siamese Multi-Scale feature extraction used along with Structure Similarity Measure (SSIM) produces an excellent fused image. It is determined by undergoing quantitative and qualitative studies. The analysis is done based on objective examination and visual traits. By increasing the parameters, the objective assessment increases in performance rate and complexity with time.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132742241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-21DOI: 10.1142/s1469026823410079
R. Prasad, T. Jaya
Wireless spectrum has been allocated to licensees for large geographic areas on a long-term basis in recent years. Cognitive Radio Networks (CRN) will offer mobile users with a huge amount of available bandwidth. Due to spectrum management issues such as spectrum sensing and sharing, CRN networks pose some challenges. Hence in this paper, Adaptive Rider Optimization (AROA) is developed to improve the energy efficiency for different spectrum sensing conditions. The proposed algorithm is utilized to compute the sensing time, sequence length, and detection threshold. In order to detect the spectrum with optimal values of transmission power and sensing bandwidth, the AROA uses the adaptive threshold detection method. The spectrum sensing and sharing of the CRN network are achieved with the help of the AROA algorithm. The proposed method is implemented in MATLAB and the performances such as Normalized Energy consumption, delay, SNR, Jitter, blocking probability, convergence analysis, and Throughput are evaluated. The proposed method is contrasted with the existing methods such as Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO), respectively.
{"title":"Intelligent Spectrum Sharing and Sensing in Cognitive Radio Network by Using AROA (Adaptive Rider Optimization Algorithm)","authors":"R. Prasad, T. Jaya","doi":"10.1142/s1469026823410079","DOIUrl":"https://doi.org/10.1142/s1469026823410079","url":null,"abstract":"Wireless spectrum has been allocated to licensees for large geographic areas on a long-term basis in recent years. Cognitive Radio Networks (CRN) will offer mobile users with a huge amount of available bandwidth. Due to spectrum management issues such as spectrum sensing and sharing, CRN networks pose some challenges. Hence in this paper, Adaptive Rider Optimization (AROA) is developed to improve the energy efficiency for different spectrum sensing conditions. The proposed algorithm is utilized to compute the sensing time, sequence length, and detection threshold. In order to detect the spectrum with optimal values of transmission power and sensing bandwidth, the AROA uses the adaptive threshold detection method. The spectrum sensing and sharing of the CRN network are achieved with the help of the AROA algorithm. The proposed method is implemented in MATLAB and the performances such as Normalized Energy consumption, delay, SNR, Jitter, blocking probability, convergence analysis, and Throughput are evaluated. The proposed method is contrasted with the existing methods such as Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO), respectively.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126798453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-20DOI: 10.1142/s1469026823500050
Junan Huang, Zhiqiu Huang, Guohua Shen, Jinyong Wang, Xiaohua Yin
Forecasting the motion of surrounding vehicles is necessary for a self-driving vehicle to plan a safe and efficient trajectory for the future. Like experienced human drivers, the self-driving vehicle needs to perceive the interaction of surrounding vehicles and decide the best trajectory from many choices. However, previous methods either lack modeling of interactions or ignore the multi-modal nature of this problem. In this paper, we focus on two important cues of trajectory prediction: interaction and maneuver, and propose Maneuver conditioned Attentional Network named MAN. MAN learns the interactions of all vehicles in a scenario in parallel by self-attention social pooling and the attentional decoder generates the future trajectory conditioned on the predicted maneuver among 3 classes: Lane Changing Left (LCL), Lane Changing Right (LCR) and Lane Keeping (LK). Experiments demonstrate the improvement of our model in prediction on the publicly available NGSIM and HighD datasets. We also present quantitative analysis to study the relationship between maneuver prediction accuracy and trajectory error.
{"title":"Maneuver Conditioned Vehicle Trajectory Prediction Using Self-Attention","authors":"Junan Huang, Zhiqiu Huang, Guohua Shen, Jinyong Wang, Xiaohua Yin","doi":"10.1142/s1469026823500050","DOIUrl":"https://doi.org/10.1142/s1469026823500050","url":null,"abstract":"Forecasting the motion of surrounding vehicles is necessary for a self-driving vehicle to plan a safe and efficient trajectory for the future. Like experienced human drivers, the self-driving vehicle needs to perceive the interaction of surrounding vehicles and decide the best trajectory from many choices. However, previous methods either lack modeling of interactions or ignore the multi-modal nature of this problem. In this paper, we focus on two important cues of trajectory prediction: interaction and maneuver, and propose Maneuver conditioned Attentional Network named MAN. MAN learns the interactions of all vehicles in a scenario in parallel by self-attention social pooling and the attentional decoder generates the future trajectory conditioned on the predicted maneuver among 3 classes: Lane Changing Left (LCL), Lane Changing Right (LCR) and Lane Keeping (LK). Experiments demonstrate the improvement of our model in prediction on the publicly available NGSIM and HighD datasets. We also present quantitative analysis to study the relationship between maneuver prediction accuracy and trajectory error.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"17 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123448614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-21DOI: 10.1142/s1469026823500037
Teny Handhayani, Ageng Hadi Pawening, J. Hendryli
Indonesia is one of the archipelago countries located in Asia and it has diverse cultures. In modern society, Indonesian traditional houses have become rare and need to be preserved. This research is conducted to build a digital collection and to develop an image-based automatic recognition system for Indonesian traditional houses. In this paper, the traditional house images are collected in several ways: on-site image captures, receiving images from volunteers, and collecting public images from Google. The dataset is limited to the collection of building shape images, excluding the interior design. The authors implement Convolutional Neural Networks (ConvNets) to build a model for an automatic recognition system. The experiments run some deep network models: VGG, DenseNet, Inception, Xception, MobileNetV2, NasNetMobile, and EfficientNet. The experiments involve 1526 images of 16 classes. EfficientNet-Lite0 outperforms other models and produces the average F1-score and accuracy of 90.1% and 91.8%, respectively. ConvNets also outperform conventional classifiers.
{"title":"An Automatic Recognition System for Digital Collections of Indonesian Traditional Houses Using Convolutional Neural Networks for Cultural Heritage Preservation","authors":"Teny Handhayani, Ageng Hadi Pawening, J. Hendryli","doi":"10.1142/s1469026823500037","DOIUrl":"https://doi.org/10.1142/s1469026823500037","url":null,"abstract":"Indonesia is one of the archipelago countries located in Asia and it has diverse cultures. In modern society, Indonesian traditional houses have become rare and need to be preserved. This research is conducted to build a digital collection and to develop an image-based automatic recognition system for Indonesian traditional houses. In this paper, the traditional house images are collected in several ways: on-site image captures, receiving images from volunteers, and collecting public images from Google. The dataset is limited to the collection of building shape images, excluding the interior design. The authors implement Convolutional Neural Networks (ConvNets) to build a model for an automatic recognition system. The experiments run some deep network models: VGG, DenseNet, Inception, Xception, MobileNetV2, NasNetMobile, and EfficientNet. The experiments involve 1526 images of 16 classes. EfficientNet-Lite0 outperforms other models and produces the average F1-score and accuracy of 90.1% and 91.8%, respectively. ConvNets also outperform conventional classifiers.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114284907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-23DOI: 10.1142/s1469026822500274
V. Nyemeesha, M. Kavitha, B. M. Ismail
Skin cancer is one of the most dangerous cancers that may occur for different age groups of people. As a result, early identification of skin cancer has the potential to save millions of lives. In Traditional machine learning approaches, there are various drawbacks in detection and classification of skin lesions. As a result, to achieve the robust performance, initially the joint trilateral and bilateral filter (JTBF) with convolutional auto encoder and decoder (CAED)-based preprocessing method is used to enhance the skin lesion and also removes hair from lesions. Then, transfer learning-based probabilistic multi-layer dense networks (PMDN) method-based unmanned Transfer learning segmentation method is adapted for accurately detecting the cancer region on skin lesions. Further, transfer learning convolution neural network (TL-CNN) is used to extract the features from the segmented region, which extracts the detailed inter-disease-dependent (IDD) and intra-disease specific (IDS) features. Finally, Alexa Net model is trained and tested with the IDD, IDS features and classifies the eight different skin cancer types. The complexity of the transfer learning networks is optimized by the using the Adam optimizer. Finally, the simulation results show that the proposed model resulted in superior segmentation, feature extraction, and classification performances as compared to conventional approaches. Further, the proposed method achieved 99.937% segmentation accuracy, 99.47% feature extraction accuracy, and 99.27% classification accuracy on ISIC-2019 public challenge dataset.
皮肤癌是最危险的癌症之一，可能发生在不同年龄组的人身上。因此，皮肤癌的早期识别有可能挽救数百万人的生命。在传统的机器学习方法中，在皮肤病变的检测和分类方面存在各种缺陷。因此，为了实现鲁棒性，首先采用基于卷积自动编码器和解码器(CAED)的预处理方法联合三边和双边滤波器(JTBF)来增强皮肤病变，同时去除病变部位的毛发。然后，将基于迁移学习的概率多层密集网络(PMDN)方法的无人迁移学习分割方法应用于准确检测皮肤病变的癌变区域。进一步，利用迁移学习卷积神经网络(TL-CNN)对分割区域进行特征提取，提取出详细的inter-disease dependent (IDD)和intra-disease specific (IDS)特征。最后，对Alexa Net模型进行IDD、IDS特征的训练和测试，并对八种不同的皮肤癌类型进行分类。利用Adam优化器对迁移学习网络的复杂度进行了优化。最后，仿真结果表明，与传统方法相比，该模型具有更好的分割、特征提取和分类性能。在ISIC-2019公共挑战数据集上，该方法实现了99.937%的分割准确率、99.47%的特征提取准确率和99.27%的分类准确率。
{"title":"Detection and Classification of Skin Cancer Using Unmanned Transfer Learning Based Probabilistic Multi-Layer Dense Networks","authors":"V. Nyemeesha, M. Kavitha, B. M. Ismail","doi":"10.1142/s1469026822500274","DOIUrl":"https://doi.org/10.1142/s1469026822500274","url":null,"abstract":"Skin cancer is one of the most dangerous cancers that may occur for different age groups of people. As a result, early identification of skin cancer has the potential to save millions of lives. In Traditional machine learning approaches, there are various drawbacks in detection and classification of skin lesions. As a result, to achieve the robust performance, initially the joint trilateral and bilateral filter (JTBF) with convolutional auto encoder and decoder (CAED)-based preprocessing method is used to enhance the skin lesion and also removes hair from lesions. Then, transfer learning-based probabilistic multi-layer dense networks (PMDN) method-based unmanned Transfer learning segmentation method is adapted for accurately detecting the cancer region on skin lesions. Further, transfer learning convolution neural network (TL-CNN) is used to extract the features from the segmented region, which extracts the detailed inter-disease-dependent (IDD) and intra-disease specific (IDS) features. Finally, Alexa Net model is trained and tested with the IDD, IDS features and classifies the eight different skin cancer types. The complexity of the transfer learning networks is optimized by the using the Adam optimizer. Finally, the simulation results show that the proposed model resulted in superior segmentation, feature extraction, and classification performances as compared to conventional approaches. Further, the proposed method achieved 99.937% segmentation accuracy, 99.47% feature extraction accuracy, and 99.27% classification accuracy on ISIC-2019 public challenge dataset.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120938433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-20DOI: 10.1142/s1469026822500262
Ha Che-Ngoc, Luan Nguyenhuynh, Dan Nguyen-Thihong, Tai Vo-Van
Forecasting for time series has always been of interest to statisticians and data scientists because it offers a lot of benefits in reality. This study proposes the fuzzy time series model which can both interpolate historical data, and forecast effectively for the future with the important contributions. First, we build the universal set based on the percentage of the original data variation, and divide it to clusters with the suitable number by the developed automatic algorithm. Next, the new fuzzy relationship between each element in series and the obtained clusters is established. The bigger the variation is, the more the clusters are divided. Finally, combining the two above improvements, we propose the new principle to forecast for the future. The experiments on many well-known data sets, including 3003 series of M3-competition data show that the proposed model has shown the outstanding advantage in comparing to the existing ones. Because the proposed model is established by the Matlab procedure, it can apply effectively for real series.
{"title":"Building the Forecasting Model for Time Series Based on the Improved Fuzzy Relationship for Variation of Data","authors":"Ha Che-Ngoc, Luan Nguyenhuynh, Dan Nguyen-Thihong, Tai Vo-Van","doi":"10.1142/s1469026822500262","DOIUrl":"https://doi.org/10.1142/s1469026822500262","url":null,"abstract":"Forecasting for time series has always been of interest to statisticians and data scientists because it offers a lot of benefits in reality. This study proposes the fuzzy time series model which can both interpolate historical data, and forecast effectively for the future with the important contributions. First, we build the universal set based on the percentage of the original data variation, and divide it to clusters with the suitable number by the developed automatic algorithm. Next, the new fuzzy relationship between each element in series and the obtained clusters is established. The bigger the variation is, the more the clusters are divided. Finally, combining the two above improvements, we propose the new principle to forecast for the future. The experiments on many well-known data sets, including 3003 series of M3-competition data show that the proposed model has shown the outstanding advantage in comparing to the existing ones. Because the proposed model is established by the Matlab procedure, it can apply effectively for real series.","PeriodicalId":422521,"journal":{"name":"Int. J. Comput. Intell. Appl.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117288384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：