检索结果-内蒙古大学图书馆

Leveraging explainable artificial intelligence with ensemble of deep learning model for dementia prediction to enhance clinical decision support systems

引用

Scientific Reports 2025年第1期15卷 1-17页

作者： Medani, Mohamed Elhessewi, Ghada Moh. Samir Alqahtani, Mohammed Asklany, Somia A. Alamro, Sulaiman Albalawneh, Da’ad Alshammeri, Menwa Assiri, Mohammed Department of Information Systems Applied College at Mahayil King Khalid University Abha Saudi Arabia Department of Health Sciences College of Health and Rehabilitation Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia Department of Information System and Cyber Security College of Computing and Information Technology University of Bisha Bisha 61922 Saudi Arabia Department of Computer Science and Information Technology Faculty of Sciences and Arts Northern Border University Turaif Arar 91431 Saudi Arabia Department of Computer Science College of Computer Qassim University Buraydah 51452 Saudi Arabia Department of Computer Science University College in Umluj University of Tabuk Tabuk Saudi Arabia Department of Computer Science College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University P.O. BOX 16273 Al-Kharj 3963 Saudi Arabia

The prevalence of dementia is growing worldwide due to the fast ageing of the population. Dementia is an intricate illness that is frequently produced by a mixture of genetic and environmental risk factors. There is no treatment for dementia yet;therefore, the early detection and identification of persons at greater risk of emerging dementia becomes crucial, as this might deliver an opportunity to adopt lifestyle variations to decrease the risk of dementia. Many dementia risk prediction techniques to recognize individuals at high risk have progressed in the past few years. Accepting a structure uniting explainability in artificial intelligence (XAI) with intricate systems will enable us to classify analysts of dementia incidence and then verify their occurrence in the survey as recognized or suspected risk factors. Deep learning (DL) and machine learning (ML) are current techniques for detecting and classifying dementia and making decisions without human participation. This study introduces a Leveraging Explainability Artificial Intelligence and optimization algorithm for Accurate Dementia Prediction and Classification Model (LXAIOA-ADPCM) technique in medical diagnosis. The main intention of the LXAIOA-ADPCM technique is to progress a novel algorithm for dementia prediction using advanced techniques. Initially, data normalization is performed by utilizing min–max normalization to convert input data into a beneficial format. Furthermore, the feature selection process is performed by implementing the naked mole‐rat algorithm (NMRA) model. For the classification process, the proposed LXAIOA-ADPCM model implements ensemble classifiers such as the bidirectional long short-term memory (BiLSTM), sparse autoencoder (SAE), and temporal convolutional network (TCN) techniques. Finally, the hyperparameter selection of ensemble models is accomplished by utilizing the gazelle optimization algorithm (GOA) technique. Finally, the Grad‐CAM is employed as an XAI technique to enhance

关键词： Data normalization Dementia prediction Explainability artificial intelligence Feature selection gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Chronological gazelle optimization with Deep Learning-Based pixel prediction for video steganography in H.264 video for defence applications

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2024年 98卷

作者： Sriram, K. V. Havaldar, R. H. Angadi Inst Technol & Management Dept Elect & Commun Engn Belagavi Karnataka India KLE Dr MS Sheshgiri Coll Engn & Technol Dept Biomed Engn Belagavi Karnataka India

With the recent progress in Information technology and the internet, there has been an increase in violations of information security and privacy, particularly in the defence domain. In this work, a secure video steganography method using deep learning-based pixel prediction in H.264 video is presented. The pixels in the keyframe on which the secret image is embedded are predicted using a Deep Convolutional Neural Network (DCNN) optimized by the Chronological gazelle optimization algorithm (CGOA). Later, embedding is carried out using Haar Wavelet Transform (HWT). The security of the proposed steganography technique has been analysed by performing steganalysis using a Convolutional Neural Network (CNN). The efficiency of the approach is examined by considering evaluation measures, like structural Similarity Index measure (SSIM), Normalized Correlation (NC), Peak Signal to Noise Ratio (PSNR), Bit Error Rate (BER), and Mean Squared Error (MSE), and has attained values of 0.979, 0.974, 49.624, 4.655, and 0.790, revealing imperceptibility and robustness.

关键词： Deep Convolutional Neural Network Pixel prediction Haar Wavelet Transform Chronological concept gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic grouping maintenance optimization by considering the probabilistic remaining useful life prediction of multiple equipment

引用

EKSPLOATACJA I NIEZAWODNOSC-MAINTENANCE AND RELIABILITY 2024年第3期26卷

作者： Cao, Xiangang Shi, Xinyu Zhao, Jiangbin Duan, Yong Yang, Xin Xian Univ Sci & Technol Sch Mech Engn Dept Intelligence Mfg Xian Peoples R China

For multi-equipment maintenance of modern production equipment, the economic correlation and degradation uncertainty may lead to insufficient or excessive maintenance, increasing maintenance costs. This paper proposes a dynamic grouping maintenance method based on probabilistic remaining useful life (RUL) prediction for multiple equipment. Long short term memory (LSTM) is developed to predict the equipment probability RUL by the Variational Auto-Encoder (VAE) resampling. Then, the dynamic grouping maintenance model is constructed to minimize the maintenance cost rate under the known probabilistic RUL information. The gazelle optimization algorithm (GOA) is used to determine the optimal maintenance time for each equipment. To better verify the effectiveness of the proposed method, a numerical case with six wind turbines is introduced to analyse the performance of GOA. Moreover, the advantages of dynamic grouping maintenance is verified by comparing with independent maintenance, whose maintenance cost rate is reduced by 10.01%.

关键词： long short term memory probabilistic remaining useful life prediction Variational Auto-Encoder Dynamic grouping maintenance gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Cloud intrusion detection framework using variational auto encoder Wasserstein generative adversarial network optimized with archerfish hunting optimization algorithm

引用

WIRELESS NETWORKS 2024年第3期30卷 1383-1400页

作者： Senthilkumar, G. Tamilarasi, K. Periasamy, J. K. Panimalar Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India Vellore Inst Technol Sch Comp Chennai Campus Chennai Tamil Nadu India Sri Sairam Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India

The cloud computing environment has been severely harmed by security issues, which has a negative impact on the healthy and sustainable development of the cloud. Intrusion detection technologies are protecting the cloud computing environment from malicious attacks. To overcome this problem, Variational auto encoder Wasserstein generative adversarial networks enhanced by gazelle optimization algorithm embraced cloud intrusion detection (CIDF-VAWGAN-GOA) is proposed in this manuscript. Here, the data is collected via NSL-KDD dataset. Then the data is supplied to pre-processing. In pre-processing, it purges the redundancy and missing value is restored using Difference of Gaussian filtering. Then the pre-processing output is fed to the feature selection. In feature selection, the optimal feature is selected using archerfish hunting optimizer (AHOA). The optimal features based, data is characterized by normal and anomalous under VAWGAN. Generally, VAWGAN does not adopt any optimization techniques to compute the optimum parameters for assuring accurate detection of intruder in cloud intrusion detection. Therefore, in this work, GOA is used for optimizing VAWGAN. The proposed CIDF-VAWGAN-GOA technique is implemented in Python under NSL-KDD data set. The performance metrics, like accuracy, sensitivity, specificity, precision, F-Score, Computation Time, Error rate, AUC are examined. The proposed method provides higher recall of 17.58%, 23.18% and 13.92%, high AUC of 19.43%, 12.84% and 21.63% and lower computation Time of 15.37%, 1.83%,18.34% compared to the existing methods, like Cloud intrusion detection depending on stacked contractive auto-encoder with support vector machine (CIDF-SVM), Efficient feature selection with classification using ensemble method for network intrusion detection on cloud computing (CIDF-DNN) and Deep belief network under chronological salp swarm approach for intrusion detection in cloud utilizing fuzzy entropy (CIDF-DBN) respectively.

关键词： Archerfish hunting optimizer Cloud intrusion detection Difference of Gaussian filtering Variational auto encoder Wasserstein generative adversarial networks gazelle optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing steam condenser efficiency: integrating logarithmic spiral search and greedy selection mechanisms in gazelle optimizer for PI controller tuning

引用

RESULTS IN ENGINEERING 2024年 24卷

作者： Ekinci, Serdar Turkeri, Cebrail Izci, Davut Abualigah, Laith Bajaj, Mohit Blazek, Vojtech Batman Univ Dept Comp Engn TR-72100 Batman Turkiye Appl Sci Private Univ Appl Sci Res Ctr Amman 11931 Jordan Al Al Bayt Univ Comp Sci Dept Mafraq 25113 Jordan Chitkara Univ Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India Graph Era Deemed Univ Dept Elect Engn Dehra Dun 248002 India Univ Business & Technol Coll Engn Jeddah 21448 Saudi Arabia Graph Era Hill Univ Dehra Dun 248002 India VSB Tech Univ Ostrava ENET Ctr Ostrava 70800 Czech Republic

Steam condensers are critical for maintaining efficiency and stability in thermal power plants by converting exhaust steam back into water. Controlling the pressure within the condenser is essential for optimal performance and operational safety. This paper presents a dynamic model of a steam condenser, with pressure control achieved through a proportional-integral (PI) controller. The PI controller parameters are optimized using the gazelle optimization algorithm (GOA), which is applied for the first time to this system in the literature. Additionally, novel enhancements, the logarithmic spiral (Ls) search with greedy selection, are integrated into GOA to further enhance control effectiveness. The performance of the optimized PI controller is evaluated using nonlinear simulations, which include statistical analysis and fitness function assessments. To validate the effectiveness of the proposed approach, comparisons are made with other widely used optimization techniques. The results reveal that the GOA notably enhances control accuracy and stability, with the enhanced GOA (LsGOA) achieving the most significant improvements. This underscores its potential for enhancing steam condenser efficiency in thermal power plants.

关键词： Condenser pressure control Thermal energy systems Dynamic modelling gazelle optimization algorithm Logarithmic spiral search PI controller

来源：评论

学校读者我要写书评

暂无评论

Enhancing IIR system identification: Harnessing the synergy of gazelle optimization and simulated annealing algorithms

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2023年 5卷

作者： Ekinci, Serdar Izci, Davut Department of Computer Engineering Batman University Batman 72100 Turkey MEU Research Unit Middle East University Amman Jordan

In the field of digital filter design and system identification, accurately modeling Infinite Impulse Response (IIR) systems is of utmost importance. This paper introduces a new adaptive algorithm that combines the gazelle optimization algorithm with simulated annealing to achieve superior optimization performance for digital IIR filters used in system identification. To evaluate the algorithm's effectiveness, extensive experiments were conducted on two fronts: the challenging CEC2020 benchmark functions and a fifth order IIR system identification problem. The proposed algorithm proves its effectiveness by achieving optimal solutions on the CEC2020 benchmark functions when compared to other well-known optimization algorithms such as arithmetic optimization, particle swarm optimization, differential evolution, sine cosine algorithm, gray wolf optimizer, biogeography-based optimization, salp swarm algorithm, and the original gazelle optimization algorithm. The algorithm's performance is measured by its ability to find the best solutions for these benchmark functions. For the IIR system identification problem, the study considers both the same order and reduced order cases. The system to be identified is represented by a fifth order plant. The algorithm's statistical analysis and convergence behavior are compared to the original gazelle optimization algorithm, artificial hummingbird algorithm, mountain gazelle optimization algorithm, and the widely used artificial bee colony algorithm. These comparisons demonstrate the proposed algorithm's superior capability and efficiency in accurately identifying the parameters of IIR systems. © 2023 The Author(s)

关键词： Digital filter design gazelle optimization algorithm IIR system identification Simulated annealing technique

来源：评论

学校读者我要写书评

暂无评论

An automated learning model for twitter sentiment analysis using Ranger AdaBelief optimizer based Bidirectional Long Short Term Memory

引用

EXPERT SYSTEMS 2024年第9期41卷 e13610-e13610页

作者： Natarajan, Sasirekha Kurian, Smitha Bidare Divakarachari, Parameshachari Falkowski-Gilski, Przemyslaw Sona Coll Technol Dept Elect & Commun Engn Salem India HKBK Coll Engn Dept Comp Sci & Engn Bengaluru Karnataka India Nitte Meenakshi Inst Technol Dept Elect & Commun Bengaluru 560064 India Gdansk Univ Technol Fac Elect Telecommun & Informat Gdansk Poland

Sentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day-to-day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi-LSTM RAO) to classify sentiment of tweets. Initially, data is obtained from Twitter API, Sentiment 140 and Stanford Sentiment Treebank-2 (SST-2). The raw data is pre-processed and it is subjected to feature extraction which is performed using Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF). The feature selection is performed using gazelle optimization algorithm (GOA) which removes the irrelevant or redundant features that maximized model performance and classification is performed using Bi LSTM-RAO. The RAO optimizes the loss function of Bi-LSTM model that maximized accuracy. The classification accuracy of proposed method for Twitter API, Sentiment 140 and SST 2 dataset is obtained as 909.44%, 99.71% and 99.86%, respectively. These obtained results are comparably higher than ensemble framework, Robustly Optimized BERT and Gated Recurrent Unit (RoBERTa-GRU), Logistic Regression-Long Short Term Memory (LR-LSTM), Convolutional Bi-LSTM, Sentiment and Context Aware Attention-based Hybrid Deep Neural Network (SCA-HDNN) and Stochastic Gradient Descent optimization based Stochastic Gate Neural Network (SGD-SGNN).

关键词： Bidirectional Long Short Term Memory deep learning model gazelle optimization algorithm sentiment analysis tweets

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of the gazelle Optimizer and its variants

引用

HELIYON 2024年第17期10卷 e36425页

作者： Mahajan, Raghav Sharma, Himanshu Arora, Krishan Joshi, Gyanendra Prasad Cho, Woong Lovely Profess Univ Sch Elect & Elect Engn Phagwara 144411 India Sejong Univ Dept Comp Sci & Engn Seoul 05006 South Korea Kangwon Natl Univ Dept Elect Informat & Commun Engn Samcheok 25913 South Korea

The gazelle optimization algorithm (GOA) is an innovative nature-inspired metaheuristic algorithm, designed to mimic the agile and efficient hunting strategies of gazelles. Despite its promising performance in solving complex optimization problems, there is still a significant scope for enhancing its efficiency and robustness. This paper introduces several novel variants of GOA, integrating adaptive strategy, Levy flight strategy, Roulette wheel selection strategy, and random walk strategy. These enhancements aim to address the limitations of the original GOA and improve its performance in diverse optimization scenarios. The proposed algorithms are rigorously tested on CEC 2014 and CEC 2017 benchmark functions, five engineering problems, and a Total Harmonic Distortion (THD) minimization problem. The results demonstrate the superior performance of the proposed variants compared to the original GOA, providing valuable insights into their applicability and effectiveness.

关键词： gazelle optimization algorithm Benchmark functions Total harmonic distortion Engineering design problem

来源：评论

学校读者我要写书评

暂无评论

Fractional order controller design via gazelle optimizer for efficient speed regulation of micromotors

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2023年 6卷

作者： Izci, Davut Ekinci, Serdar Department of Computer Engineering Batman University Batman 72100 Turkey MEU Research Unit Middle East University Amman Jordan

In this paper, the design of an efficient fractional-order proportional-integral-derivative (FOPID) controller, tailored specifically for the regulation of micro direct current (DC) motors, is explored. A fresh approach is introduced using the gazelle optimization algorithm (GOA), a cutting-edge method set to manage the speed control of these small but vital motors. With the adoption of GOA, fine-tuning the parameters of the FOPID controller is aimed. This is achieved by employing a time-based performance metrics-based cost function as the guiding compass. The GOA is implemented to discover the optimal controller settings for the attainment of peak performance. Through thorough simulations and careful statistical analysis, the worth of GOA-based FOPID controller is demonstrated. Not only are top-notch cost function values achieved, but excellence across various time domain-based performance metrics is also excelled in. The results suggest that the GOA proves to be efficient in fine-tuning of FOPID controller parameters. A comprehensive analysis in the time domain further solidifies the superiority of GOA-based FOPID-controlled micro-DC motor system. Outperformance is observed when compared to alternative algorithms employing different controllers, such as an advanced hybrid stochastic fractal search-based FOPID controller, a grey wolf optimizer-based FOPID controller, a slime mold algorithm-based PID controller, an enhanced arithmetic Harris hawks optimization-based PID controller, and a hybrid atom search optimization and simulated annealing-based PID controller. In essence, the results highlight the potential of the GOA as a powerful tool poised to reshape the optimization of FOPID controllers for micro-DC motor speed regulation. © 2023 The Author(s)

关键词： FOPID controller gazelle optimization algorithm Metaheuristics Micro DC motor Speed regulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：