检索结果-内蒙古大学图书馆

deep learning neural network Based on PSO for Leukemia Cell Disease Diagnosis from Microscope Images

JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025年 1-10页

作者： Almahdawi, Hamsa Akbas, Ayhan Rahebi, Javad Cankiri Karatekin Univ Comp Engn Dept Cankiri Turkiye Univ Surrey Inst Commun Syst Guildford England Istanbul Topkapi Univ Software Engn Dept Istanbul Turkiye

Leukemia is a kind of cancer characterized by the proliferation of abnormal, immature White Blood Cells (WBCs) produced in the bone marrow, which subsequently circulate throughout the body. Prompt leukemia diagnosis is vital in determining the optimal treatment plan, as different types of leukemia require distinct treatments. Early detection is therefore instrumental in facilitating the use of the most effective therapies. The identification of leukemia cells from microscopic images is considered a challenging task due to the complexity of the image features. This paper presents a deep learning neural network approach that utilizes the Particle Swarm Optimization (PSO) method to diagnose leukemia cell disease from microscope images. Initially, deep learning is employed to extract features from the leukemia images, which are then optimized by the PSO method to select the most relevant features for machine learning. Three different machine learning algorithms, namely Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN) methods, are utilized to analyze the selected features. The results of the experiments demonstrate PSO accuracies of 97.4%, 92.3%, and 85.9% for SVM, K-NN, and DT algorithms with GoogLeNet, respectively. The proposed method achieved accuracies of 100%, 94.9%, and 92.3% for SVM, K-NN, and DT methods respectively, with Ant Colony Optimization (ACO) feature extraction and ResNet-50 employed as revealed by the experimental results. These findings suggest that the proposed approach is a promising tool for accurate diagnosis of leukemia cell disease using microscopic images.

关键词： deep learning neural network Particle swarm optimization Leukemia cell disease diagnosis Feature selection

来源：评论

学校读者我要写书评

暂无评论

Effects of various parameters on entropy generation and exergy destruction in a coil wire inserted heat exchanger by using deep learning neural network method

引用

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2025年 161卷

作者： Celik, Nevin Kapan, Sinan Tasar, Beyda Firat Univ Dept Mech Engn TR-23119 Elazig Turkiye

In present study mainly the effect of inserting a coil wire type turbulator into a concentric type heat exchanger on its entropy generation (Ns), efficiency (epsilon) and exergy destruction (E*), is studied experimentally. Due to inserting coil wire inside the inner pipe of the exchanger presents a challenge, the coil wires are located through the pipe with various length (l/d), thickness (e/d) and pitch (p/d). The experiments are performed by also varying the Reynolds number from 30,000 to 80,000. The results showed the entropy generation number increases with increasing l/d and p/d of the coil wire turbulator, but decreases with increasing e/d. Exergy destruction is the exergy that is destroyed within the system boundary due to the effects of irreversibilities that generate the entropy. Therefore, it is proportional to the entropy generation. Hence similar trends are observed when calculating the exergy destruction. Finally increasing the thickness, pitch and length of the coil wire results with augmentation of the efficiency. The deep learning neural network Method, namely DNN is applied to the results of the experimental study for showing the relationship of the parameters to each other. Multiple Linear Regression (MLR) model is applied to the result for model verification. Comparison of the results of MLR and DNN methods show that DNN predictions are mostly reliable considering the relationships between the dependent and independent parameters.

关键词： Entropy analysis deep learning neural network Coil wire turbulator Heat exchanger

来源：评论

学校读者我要写书评

暂无评论

LARGE EARTHQUAKE MAGNITUDE PREDICTION IN TAIWAN BASED ON deep learning neural network

引用

neural network WORLD 2018年第2期28卷 149-160页

作者： Huang, J. P. Wang, X. A. Zhao, Y. Xin, C. Xiang, H. Peking Univ Res Ctr Earthquake Monitoring & Forecasting Techn Shenzhen Grad Sch Shenzhen 518055 Guangdong Peoples R China Guangdong Med Univ Dongguan 523808 Guangdong Peoples R China

In this paper, a deep learning-based method for earthquake prediction is proposed. Large-magnitude earthquakes and tsunamis triggered by earthquakes can kill thousands of people and cause millions of dollars worth of economic losses. The accurate prediction of large-magnitude earthquakes is a worldwide problem. In recent years, deep learning technology that can automatically extract features from mass data has been applied in image recognition, natural language processing, object recognition, etc., with great success. We explore to apply deep learning technology to earthquake prediction. We propose a deep learning method for continuous earthquake prediction using historical seismic events. First, we project the historical seismic events onto a topographic map. Taking Taiwan as an example, we generate the images of the dataset for deep learning and mark a label "1" or "0", depending on whether in the upcoming 30 days a greater than M6 earthquake will occur. Second, we train our deep leaning network model, using the images of the dataset. Finally, we make earthquake predictions, using the trained network model. The result shows that we can get the best result, when we predict earthquakes in the upcoming 30 days using data from the past 120 days. Here, we use R score as the performance metrics. The best R score is 0.303. Although the R score is not high enough, using the past 120 days' historic seismic event to predict the upcoming 30 days' biggest earthquake magnitude can be seen as the pattern of Taiwan earthquake because the R score is rather good compared to other datasets. The proposed method performs well without manually designing feature vectors, as in the traditional neural network method. This method can be applied to earthquake prediction in other seismic zones.

关键词： large earthquake magnitude prediction deep learning neural network taiwan pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Application of deep learning neural network for Mapping Groundwater Productivity Potential: Case of Cheliff Basin-Algeria

引用

DOKLADY EARTH SCIENCES 2023年第2期510卷 499-507页

作者： Derdous, Oussama Bouamrane, Ali Univ Kasdi Merbah Fac Appl Sci Dept Civil & Hydraul Engn Ouargla Algeria Natl Polytech Sch Lab Rech Sci Eau Algiers Algeria Lab Management Maintenance & Rehabil Facil & Urban Souk Ahras Algeria

The main purpose of this study is to assess groundwater productivity potential across the Cheliff basin (Algeria) using an integrated approach that combines deep learning neural network (DLNN) and GIS. Accordingly, eight thematic layers considered as the influencing factors of groundwater recharge in the study area were prepared in GIS platform. These factors include elevation, slope, drainage density, topographic wetness index, geology, rainfall, soil texture and vegetation cover. The relationship between these factors and groundwater productivity was investigated through the DLNN and revealed that geology and slope are respectively the most significant factors controlling groundwater recharge in the study area. Indeed, high and very high groundwater productivity zones, representing 37% of the study area, occur mostly in the southern parts of the basin, in which Triassic to Jurassic sedimentary formations coincide with mild terrain slopes. The DLNN predictions were validated using the area under the receiver operating characteristic curve model. According to the validation process, the proposed methodology has successfully assessed groundwater production potential showing a prediction accuracy of 92.59%. Hence, the study outcome will assist the decision-making authorities in finding sustainable solutions to the water shortage problem in the study area.

关键词： groundwater productivity potential Cheliff basin deep learning neural network GIS

来源：评论

学校读者我要写书评

暂无评论

MIMO detection using a deep learning neural network in a mode division multiplexing optical transmission system

引用

OPTICS COMMUNICATIONS 2019年 440卷 41-48页

作者： Poudel, Bishal Oshima, Joji Kobayashi, Hirokazu Iwashita, Katsushi Kochi Univ Technol Dept Photon Syst Engn 185 Miyanokuchi Kami City Kochi 7828502 Japan

Optimum Multiple Input Multiple Output (MIMO) detector has always been a challenge in MIMO communication systems. In this paper, a novel MIMO detector has been designed using a supervised deep learning neural network (DLNN) and has been implemented successfully in a Mode Division Multiplexing (MDM) optical transmission system. A conventional Graded-Index Multi-Mode Fiber (GI-MMF) is used to design an MDM optical transmission system. We have used a DLNN for MIMO detection in MDM optical transmission system and have compared its performance with Zero Forcing (ZF) detector and Semi-Definite Relaxation Row-by-Row (SDR-RBR). The results confirm that our DLNN outruns the performance of traditional MIMO detectors.

关键词： Multiple Input Multiple Output deep learning neural network Mode division multiplexing Optical transmission system Optimum detector

来源：评论

学校读者我要写书评

暂无评论

IoT medical tooth mounted sensor for monitoring teeth and food level using bacterial optimization along with adaptive deep learning neural network

引用

MEASUREMENT 2019年 135卷 672-677页

作者： Vellappally, Sajith Al Kheraif, Abdulaziz A. Anil, Sukumaran Wahba, Ashraf A. King Saud Univ Coll Appl Med Sci Dent Biomat Res Chair Dent Hlth Dept POB 10219 Riyadh 11433 Saudi Arabia Saveetha Univ Saveetha Dent Coll & Hosp Dept Periodont Poonamallee High Rd Chennai 600077 Tamil Nadu India Helwan Univ Biomed Engn Dept Fac Engn Helwan Egypt

The development of the technology creates the lot of changes in food processing which leads to alter human life style. Due to the change of their food habits and lack of attention to the dietary habits there is an increase in the prevalence of diseases such as obesity, heart attack, diabetics and so on. Hence it is important to monitor the food consumption which will help to avoid health issues associated with it. For this purpose, IoT medical tooth chip is placed in the teeth via filling or bonding process, which is one of the electrochemical sensors that collect information of the consumed food such as salt, sugar, fat etc. The gathered information can be analyzed to assess the quality of food intake. The collected information is processed by using the bacterial optimization along with adaptive deep learning neural network that examines the collected IoT information using self-learning process. The IoT device is embedded in teeth that reduce the difficulties during mastication. The excellence of IoT device based food quality level prediction system is analyzed using MATLAB implementation setup in which data were collected from 53 patients and 15 patients was used to construct the testing model to assess the efficiency of the food quality examined using IoT device up to 99.23% of accuracy process. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Food processing IoT medical tooth chip Bacterial optimization along with adaptive deep learning neural network Self-learning

来源：评论

学校读者我要写书评

暂无评论

Verification of novel integrations of swarm intelligence algorithms into deep learning neural network for flood susceptibility mapping

引用

JOURNAL OF HYDROLOGY 2020年第0期581卷 124379-000页

作者： Quang-Thanh Bui Quoc-Huy Nguyen Xuan Linh Nguyen Vu Dong Pham Huu Duy Nguyen Van-Manh Pham VNU Univ Sci Fac Geog Ctr Appl Res Remote Sensing & GIS CARGIS 334 Nguyen Trai Hanoi Vietnam VNU Univ Sci Fac Geog 334 Nguyen Trai Hanoi Vietnam

This study proposed and compared several novel hybrid models that combined swarm intelligence algorithms and deep learning neural network for flood susceptibility mapping. Lai Chau, a province in the northwest mountainous region of Vietnam was chosen as a case study since it had recently undergone severe flashflood in 2018. For this purpose, numerical predictor variables such as topographically derived factors (Digital Elevation Model, Aspect, Slope, Curvature, Topographic Wetness Index), climatic variables (Rain), and hydrological variables (stream density, stream power index, distance to river) and multiple remote sensing indices (Normalized Difference Vegetation Index, Normalized Difference Buildup Index) were used. These predictor variables were selected because they are globally collectible and reproducible. The performances of these models were evaluated by using common statistical indicators, namely Root Mean Square Error, Mean Absolute Error, Overall Accuracy and Area under Receiving Operating Characteristics, and the statistical test of differences. The results showed that the proposed swarm intelligence models outperformed benchmarked methods, namely Particle Swarm Optimization, Support Vector Machine, Random Forest in almost all comparing indicators. It is suggested that proposed models are more robust than the classifiers, which were used for benchmarking and they are good alternatives for flood susceptibility mapping given the availability of dataset.

关键词： Swarm Intelligence Optimization Algorithm deep learning neural network Flash flood

来源：评论

学校读者我要写书评

暂无评论

Detection of areas prone to flood-induced landslides risk using certainty factor and its hybridization with FAHP, XGBoost and deep learning neural network

引用

GEOCARTO INTERNATIONAL 2022年第25期37卷 7303-7338页

作者： Costache, Romulus Ali, Sk Ajim Parvin, Farhana Quoc Bao Pham Arabameri, Alireza Hoang Nguyen Craciun, Anca Duong Tran Anh Transilvania Univ Brasov Dept Civil Engn Brasov Romania Danube Delta Natl Inst Res & Dev Tulcea Romania Natl Inst Hydrol & Water Management Bucharest Romania Aligarh Muslim Univ AMU Fac Sci Dept Geog Aligarh Uttar Pradesh India Thu Dau Mot Univ Inst Appl Technol Thu Dau Mot City Vietnam Tarbiat Modares Univ Dept Geomorphol Tehran Iran Hanoi Univ Min & Geol Min Fac Dept Surface Min Hanoi Vietnam Ho Chi Minh City Univ Technol HUTECH Inst Appl Sci Ho Chi Minh City Vietnam

This article is intended to assess the flood-induced landslide susceptibility in the Indian state of Assam. This study area has high frequency and severity of landslides that are triggered by heavy rainfall and floods. In order to obtain the results, two machine learning models (XGBoost and DLNN) and one of the fuzzy-multi-criteria decision-making methods (FAHP) were combined with certainty factor (CF) bivariate statistic model. Firstly, 16 landslide predictors and 198 flood-induced landslide locations were prepared, this data set being split into training (70%) and validating data sets (30%). The analysis of the results shows that the region's most prone to flood-induced landslide occurrence can be found in the southern part, while those less prone to these phenomena are generally located in the northern part of the study area. Receiver Operating Characteristic (ROC) curve indicator shows that XGBoost-CF is the most performance model (area under the curve [AUC] = 0.977), followed by FAHP-CF (AUC = 0.976), DLNN-CF (AUC= 0.974) and CF (AUC = 0.963).

关键词： deep learning neural network bivariate statistics flood-induced landslide susceptibility GIS India

来源：评论

学校读者我要写书评

暂无评论

Optimized deep learning neural network model for doubly fed induction generator in wind energy conversion systems

引用

SOFT COMPUTING 2019年第18期23卷 8453-8470页

作者： Rajasingam, N. Rasi, D. deepa, S. N. Anna Univ Dept Elect & Elect Engn Reg Campus Coimbatore 641046 Tamil Nadu India Hindusthan Coll Engn & Technol Dept CSE Othakalmandapam PO Coimbatore 641032 Tamil Nadu India

Design of controller for a doubly fed induction generator driven by a variable speed wind turbine employing deep learning neural networks whose weights are tuned by grey artificial bee colony algorithm is developed and simulated in this work. This paper presents the mathematical modelling of the doubly fed induction generator (DFIG) and the controller design is implemented using the third generation deep learning neural network (DLNN). In the proposed work, the variable speed wind turbine generator torque is regulated employing a proportional-integral-derivative (PID) controller. The gains of the PID controller are tuned using DLNN model. The proposed density-based grey artificial bee colony (D-GABC) algorithm provides the optimal dataset required for training DLNN model. As well, the weights of the developed neural network controller are also optimized by D-GABC algorithm to avoid premature convergence and to reduce the incurred computational time of the network model. The effectiveness of the proposed DLNN-based controller for DFIG in wind energy conversion is proved and observed to be better than that of the other methods proposed in the previous literature works in respect of the simulated results obtained.

关键词： PID controller Doubly fed induction generator deep learning neural network Grey artificial bee colony algorithm Wind energy system

来源：评论

学校读者我要写书评

暂无评论

iDahon: An Android Based Terrestrial Plant Disease Detection Mobile Application Through Digital Image Processing Using deep learning neural network Algorithm 4

iDahon: An Android Based Terrestrial Plant Disease Detection...

引用

4th International Conference on Information Technology (InCIT)

作者： Valdoria, John C. Caballeo, Arlene R. Fernandez, Brian Irvin D. Condino, John Marco M. Lyceum Philippines Univ Coll Technol Manila Philippines

ISBN: (纸本)9781728110196

This research focuses on the detection of common diseases on terrestrial plants found in the Philippines through the use of image processing through deep learning neural network. Android-based smartphones were used to capture images of the terrestrial plant to detect the disease of the plant while deep learning neural network Algorithm is utilized to distinguish the disease of the terrestrial plants. The results were trained using classification models that could identify the diseases at certain rate and accuracy considering the number of images used. Therefore, the deep learning neural network classification demonstrates the identification of the common disease terrestrial plants found in the Philippines

关键词： Digital Image Processing deep learning neural network Terrestrial Plant Plant Pathology

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：