Data mining techniques for analyzing healthcare conditions of urban space-person lung using meta-heuristic optimized neural networks

Abugabah, Ahed; AlZubi, Ahmad Ali; Al-Obeidat, Feras; Alarifi, Abdulaziz; Alwadain, Ayed

doi:10.1007/s10586-020-03127-w

Cited by 22 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, most of the premature phenomenon will be caused; and if the individual speed iterates at the initialization rate until the end of the particle swarm optimization algorithm, it is equivalent to no longer affecting the individual's own cognitive part and the social part. It is not conducive to the search of the global optimal prediction value, and the adaptability of the algorithm will also be greatly reduced [26].…”

Section: Central Usermentioning

confidence: 99%

Construction and Analysis of Urban Cultural Plane Space Mode considering Particle Swarm Cultural Scientific Computing Algorithm

2022

Security and Communication Networks

View full text Add to dashboard Cite

In the tide of economic and social internationalization and high-speed urbanization, urban culture has increasingly attracted widespread attention from all walks of life and has a very critical strategic significance in the construction of urban space. This paper aims to construct and analyze the plane space mode of urban culture based on the particle swarm cultural scientific computing algorithm. This article first explains the concept of urban cultural space. Urban cultural space uses urban spatial structure as a media carrier and uses urban cultural time for vertical extension and development; then we proposed the particle swarm cultural scientific calculation algorithm and gave the particle swarm algorithm flowchart; then based on the particle swarm optimization algorithm, the evaluation of the configuration performance of urban cultural facilities is researched and discussed, and at the same time, the evolution law of urban spatial morphology is explored based on the particle swarm optimization algorithm. The particle swarm algorithm is a random search algorithm based on group cooperation developed by simulating the foraging behavior of birds. Urban cultural space is the development of urban space based on urban culture. It plays a special and important role in urban cultural development and urban space planning. According to the statistics of the survey and research results, the utilization rate of city-level cultural facilities in City A is 77, the utilization rate of district-level cultural facilities is 72, the utilization rate of street-community cultural facilities is 69, and the overall evaluation score is 70. It shows that there are significant differences in the actual use of cultural facilities, so it is particularly important to eliminate the differences in the use of cultural facilities between urban and rural areas. In the exploration of the law of urban spatial morphology evolution, it is found that the number of college students, total real estate investment, urban population, and total commercial housing sales have a significant impact on urban spatial expansion and evolution.

show abstract

Section: Central Usermentioning

confidence: 99%

Construction and Analysis of Urban Cultural Plane Space Mode considering Particle Swarm Cultural Scientific Computing Algorithm

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Due to the increasing availability of labeled data, computing power, better optimization algorithms, and better neural net models and architectures, deep learning techniques have started to outperform humans in some domains such as image recognition and classification. Therefore, deep learning applications on big data are gaining increasing popularity in various domains including natural language processing, medical diagnosis, speech recognition and computer vision [2,11,19,23,26]. Recently, we have been witnessing an increasing growth in the number of open source deep learning frameworks.…”

Section: Introductionmentioning

confidence: 99%

DLBench: a comprehensive experimental evaluation of deep learning frameworks

et al. 2021

View full text Add to dashboard Cite

Deep Learning (DL) has achieved remarkable progress over the last decade on various tasks such as image recognition, speech recognition, and natural language processing. In general, three main crucial aspects fueled this progress: the increasing availability of large amount of digitized data, the increasing availability of affordable parallel and powerful computing resources (e.g., GPU) and the growing number of open source deep learning frameworks that facilitate and ease the development process of deep learning architectures. In practice, the increasing popularity of deep learning frameworks calls for benchmarking studies that can effectively evaluate and understand the performance characteristics of these systems. In this paper, we conduct an extensive experimental evaluation and analysis of six popular deep learning frameworks, namely, TensorFlow, MXNet, PyTorch, Theano, Chainer, and Keras, using three types of DL architectures Convolutional Neural Networks (CNN), Faster Region-based Convolutional Neural Networks (Faster R-CNN), and Long Short Term Memory (LSTM). Our experimental evaluation considers different aspects for its comparison including accuracy, training time, convergence and resource consumption patterns. Our experiments have been conducted on both CPU and GPU environments using different datasets. We report and analyze the performance characteristics of the studied frameworks. In addition, we report a set of insights and important lessons that we have learned from conducting our experiments.

show abstract

“…Now the researchers are working to handle scalability and the high dimension of the databases with high processing needs. Volume defines the size of the data, and velocity defines the arrival of data streams continuously from which most valuable information is gathered [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Internet of Medical Things (IoMT) and Reflective Belief Design-Based Big Data Analytics with Convolution Neural Network-Metaheuristic Optimization Procedure (CNN-MOP)

Sampathkumar

Tesfayohani²,

Shandilya

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In recent times, the Internet of Medical Things (IoMT) is a new loomed technology, which has been deliberated as a promising technology designed for various and broadly connected networks. In an intelligent healthcare system, the framework of IoMT observes the health circumstances of the patients dynamically and responds to backings their needs, which helps detect the symptoms of critical rare body conditions based on the data collected. Metaheuristic algorithms have proven effective, robust, and efficient in deciphering real-world optimization, clustering, forecasting, classification, and other engineering problems. The emergence of extraordinary, very large-scale data being generated from various sources such as the web, sensors, and social media has led the world to the era of big data. Big data poses a new contest to metaheuristic algorithms. So, this research work presents the metaheuristic optimization algorithm for big data analysis in the IoMT using gravitational search optimization algorithm (GSOA) and reflective belief network with convolutional neural networks (DBN-CNNs). Here the data optimization has been carried out using GSOA for the collected input data. The input data were collected for the diabetes prediction with cardiac risk prediction based on the damage in blood vessels and cardiac nerves. Collected data have been classified to predict abnormal and normal diabetes range, and based on this range, the risk for a cardiac attack has been predicted using SVM. The performance analysis is made to reveal that GSOA-DBN_CNN performs well in predicting diseases. The simulation results illustrate that the GSOA-DBN_CNN model used for prediction improves accuracy, precision, recall, F1-score, and PSNR.

show abstract

Data mining techniques for analyzing healthcare conditions of urban space-person lung using meta-heuristic optimized neural networks

Cited by 22 publications

References 36 publications

Construction and Analysis of Urban Cultural Plane Space Mode considering Particle Swarm Cultural Scientific Computing Algorithm

Construction and Analysis of Urban Cultural Plane Space Mode considering Particle Swarm Cultural Scientific Computing Algorithm

DLBench: a comprehensive experimental evaluation of deep learning frameworks

Internet of Medical Things (IoMT) and Reflective Belief Design-Based Big Data Analytics with Convolution Neural Network-Metaheuristic Optimization Procedure (CNN-MOP)

Contact Info

Product

Resources

About