检索结果-内蒙古大学图书馆

Artificial Intelligence Method for Detecting Brain Cancer using Advanced Intelligent Algorithms 4

学校读者我要写书评

暂无评论

Artificial Intelligence Method for Detecting Brain Cancer us...

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Armstrong Joseph, J. Keshav Kumar, K. Veerraju, N. Ramadass, Sudhir Narayanan, Sreekumar Vidhya, R.G. Thamirabharani Engineering College Department of CSE Tamilnadu Tirunelveli India Shaikpet Department of Humanities and Mathematics Telangana Hyderabad India Srkr Engineering College China Amiram Department of Engineering Mathematics West Godavari District Andhra Pradesh Bhimavaram India Sterck Systems Private Limited Data Analytics Chennai India Botho University Network and Infrastructure Management Faculty of Engineering and Technology Gaborone Botswana Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798350300093

Because of the gravity of this condition, the development of trustworthy detection tools for brain cancer is an absolute need. The K-Nearest Neighbors (KNN) algorithm and the genetic algorithm are only two examples of the machine learning algorithms that have been deployed in recent years to identify brain cancer in scans. Other examples include the neural network algorithm and the ensemble learning algorithm. This study proposes a combination of KNN algorithm with the genetic algorithm in order to identify cases of brain cancer based only on MRI scans. In order to preprocess the MRI images, the median filter is used, and after that, the genetic algorithm is utilized for the purposes of feature extraction as well as feature selection. The KNN algorithm is then used to determine whether or not the photos of the brain indicate cancerous or normal tissue. The photographs of the brain are then classed accordingly. This, in turn, is beneficial to the feature extraction and feature selection phases. These repercussions may be positive or negative. This strategy provides a solid groundwork for the development of efficient diagnostic tools, and it is also applicable to a variety of other medical imaging applications. © 2023 IEEE.

关键词： Magnetic resonance imaging

Predicting Drying Performance of Osmotically Treated Heat Sensitive Products Using Artificial Intelligence

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第6期67卷 3143-3160页

作者： S.M.Atiqure Rahman Hegazy Rezk Mohammad Ali Abdelkareem M.Enamul Hoque Tariq Mahbub Sheikh Khaleduzzaman Shah Ahmed M.Nassef Department of Sustainable and Renewable Energy Engineering University of SharjahSharjahUAE College of Engineering at Wadi Addawaser Prince Sattam Bin Abdulaziz University11911Al-KharjSaudi Arabia Electrical Engineering Department Faculty of EngineeringMinia University61517MiniaEgypt Chemical Engineering Department Faculty of EngineeringMinia University61517MiniaEgypt Department of Biomedical Engineering Military Institute of Science and TechnologyDhakaBangladesh Department of Mechanical Engineering Military Institute of Science and TechnologyDhakaBangladesh Department of Infrastructure Engineering Melbourne School of EngineeringThe University of MelbourneAustralia Computers and Automatic Control Engineering Department Faculty of EngineeringTanta UniversityEgypt

The main goal of this research is to develop and apply a robust Artificial Neural Networks(ANNs)model for predicting the characteristics of the osmotically drying treated potato and apple samples as a model heat-sensitive product in vacuum contact *** salt and sugar solutions were used as the osmotic solutions at 27◦*** of experiments were performed at various temperatures of 35◦C,40◦C,and 55◦C for conduction heat input under vacuum(−760 mm Hg)*** experiments were also performed in a pure vacuum without heat *** moisture content(DMC),effective moisture diffusivity,and mass flux were considered as the performance parameters in this *** revealed that the osmotic dehydration using a concentrated sugar solution shows a higher reduction in the initial moisture loss of 19.87%compared to 5.3%in the salt ***,a significant enhancement of drying performance of about 27%in DMC was observed for both samples at vacuum and 40◦C compared to pure vacuum drying *** the experimental data,a robust artificial neural network(ANN)was proposed to describe the osmotic dehydration’s behavior on the drying *** ANN model outputs are the dimensionless moisture contents(DMC),the diffusivity,and the mass *** the ANN inputs were the drying time,the percent of sugar solution,and the percent of salt *** the ANN apple’s model,the minimum root mean square error(RMSE)values were 0.0261,0.0349 and 0.0406,for DMC,diffusivity,and mass flux,*** the best correlation coefficients of the above three parameters’determination values were 0.9909,0.9867 and 0.9744,*** the ANN potato’s model,the minimum RMSE values were 0.0124,0.0140 and 0.0333,for DMC,diffusivity,and mass flux,*** the best correlation coefficients of the parameters’values were found 0.9969,0.9968 and 0.9736,***,the ANN model’s prediction has a perfect agreement with th

关键词： Artificial neural network prediction modeling osmotic drying kinetics

Hydrogeochemical characterization and spatial analysis of groundwater quality in the Bono East Region, Ghana

学校读者我要写书评

暂无评论

International Journal of Energy and Water Resources 2025年第2期9卷 955-972页

作者： Debrah, S.K. Issahaku, T. Obiri-Nyarko, F. Sunkari, E.D. Seidu, J. Groundwater and Geosciences Division CSIR-Water Research Institute P. O. Box M 32 Accra Ghana Department of Earth Sciences and Geography RWTH Aachen University Aachen 52056 Germany Department of Geological Engineering Faculty of Geosciences and Environmental Studies University of Mines and Technology P.O. Box 237 Tarkwa Ghana Department of Geology Faculty of Science University of Johannesburg P.O. Box 524 Auckland Park 2006 Kingsway Campus Johannesburg South Africa School of Railways and Infrastructure Development University of Mines and Technology (UMaT) Essikado Sekondi-Takoradi Ghana

Reliance on groundwater for municipal, agricultural, and industrial water supplies is steadily growing in the Bono East Region of Ghana. However, much of the region lacks adequate groundwater characterization, which is essential for its sustainable management and equitable distribution. This study was, therefore, undertaken to analyze groundwater quality for drinking and irrigation as well as identify the factors influencing its chemistry in the Bono East Region of Ghana. A total of 26 groundwater samples were collected and analysed using hydrogeochemical, geostatistical, and GIS-based methods. The results indicate that the abundance of major cations and anions in groundwater follows the order: Na⁺ > Ca²⁺ > Mg²⁺ > K⁺ and Cl⁻ > HCO₃⁻ > SO₄²⁻, respectively. Five hydrochemical facies, namely Ca–HCO₃, Na–HCO₃, Ca–Na–HCO₃, Na–Cl, and Ca–Cl were identified in the study area. These facies are influenced by natural processes such as rock weathering, ion exchange, precipitation, and evaporation, along with human activities like fertilizer application and domestic wastewater discharge. In the southern and central parts of the study area, the groundwater is generally soft (total hardness < 75 mg/L), fresh (total dissolved solids < 1000 mg/L), and suitable for drinking (water quality index < 50) and irrigation. However, in the northern part, especially in the Kintampo North Municipality, the levels of EC, TDS, SO₄²⁻, Ca²⁺, TH, Cl⁻, K⁺, and Na⁺ in the groundwater are high, making it unsuitable for drinking and irrigation. Measures to safeguard public health and sustain agricultural productivity in these areas are proposed. © The Author(s), under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2024.

关键词： Bono East region Groundwater quality assessment Hydrogeochemistry Remediation Water governance

Sustainable Construction Materials: Evaluating the Effects of Ternary Blend Cementitious Systems with Ceramic Waste and Silica Fume

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Rukzon, Sumrerng Rungruang, Suthon Chaisakulkiet, Udomvit Posi, Patcharapol Chindaprasirt, Prinya Department of Civil Engineering Faculty of Engineering Rajamangala University of Technology Rattanakosin Nakhon Pathom73170 Thailand Department of Civil Engineering Faculty of Engineering Rajamangala University of Technology Isan Khon Kaen40000 Thailand Sustainable Infrastructure Research and Development Center Department of Civil Engineering Faculty of Engineering Khon Kaen University Khon Kaen40002 Thailand Academy of Science Royal Society of Thailand Dusit Bangkok10300 Thailand

This study investigates the compressive strength, porosity, water absorption chloride penetration and corrosion resistance of mortar in a ternary blend cementitious system, substituting Portland cement type 1 (CT) with varying proportions (15%, 20%, 25%, 30%, and 40%) of finely ground ceramic electrical insulator (CE) and silica fume (SF). We employed superplasticizer (SP) with a consistent water-to-binder ratio (W/B) of 0.50 to enhance the workability of the mortar. The SEM-EDS microstructural analysis revealed a homogeneous composition with a high content of calcium silicate hydrate (C-S-H) gel, especially when combining CE and SF. Notably, the incorporation of 5% to 20% by weight of CE and SF into the cementitious materials resulted in mortars exhibiting superior compressive strength compared to both the control sample and those containing only 10% SF. The use of very fine of CE and SF improved properties of mortars in term of the water absorption and chloride penetration of mortar. Moreover, the addition of CE and SF significantly improved the mortar's porosity and enhanced its resistance to corrosion. These findings not only demonstrate the potential of ground ceramic electrical insulators as a viable cementitious material, but they also emphasize the environmental benefits of reducing waste and easing the burden of disposal by repurposing industrial by-products. © 2024, The Authors. All rights reserved.

关键词： Mortar

Vibration Mitigation of Barge-Type Floating Offshore Wind Turbine Using Tuned Liquid Column Damper Under Typical Limit States

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Han, Dongdong Wang, Wenhua Li, Xin Su, Xiaohui State Key Laboratory of Coastal and Offshore Engineering Dalian University of Technology Dalian116024 China Institute of Earthquake Engineering Faculty of Infrastructure Engineering Dalian University of Technology Dalian116024 China School of Hydraulic Engineering Dalian University of Technology Dalian China

This study models a passively tuned liquid column damper (TLCD) and optimizes its parameters to achieve effective vibration reduction in a barge-type floating offshore wind turbine (OWT). First, based on Lagrange’s equations, a simplified dynamic model with three degrees of freedom of a barge-type floating OWT with a TLCD installed in the nacelle is proposed and developed. Second, the reliability of the recommended simplified model with the estimated parameters is verified by comparing its results with those of OpenFAST. Third, an exhaustive search strategy is adopted to optimize the essential parameters of TLCD. Finally, the ideal TLCD design parameters for the coupled dynamic responses of the barge-type floating OWT under combiend wind-wave loadings are utilized in OpenFAST. Moreover, the coupled dynamic responses of the barge-type floating OWT are calculated and evaluated. This study provides a basis for the parameter optimization design of TLCDs applied to floating OWTs. © 2023, The Authors. All rights reserved.

关键词： Dynamic models

Long-Distance Fiber-Optic Polarization Sensors in Hazardous Areas

学校读者我要写书评

暂无评论

Long-Distance Fiber-Optic Polarization Sensors in Hazardous ...

National Conference on Communications (NCC)

作者： Martin Kyselak Zdenek Vylezich Jiri Vavra David Grenar Karel Slavicek Department of Electrical Engineering Faculty of Military Technology University of Defence Brno Czech Republic Dept. of Telecommunications Faculty of Electrical Eng. and Communication University of Technology Brno Czech Republic IT Infrastructure Division Institute of Computer Science Masaryk University Brno Czech Republic

ISBN: (数字)9798331536015

ISBN: (纸本)9798331536022

Due to their non-electrical characteristics, fiber-optic sensors are finding broad applications in high-risk environments. The safety of these sensors is ensured by the absence of potential differences and low detectability. This article aims to introduce polarization fiber-optic sensors and their connections, which allow for the effective placement of sensors at great distances from control rooms and sources of electrical signals. Furthermore, the research presented here focuses on maintaining high sensitivity of the sensors while also being economically efficient compared to other fiber-optic technologies. The key output of the article is the design of an arrangement of optical fiber components that ensures optimal use of sensors in challenging conditions, with an emphasis on the detection of variable non-electrical quantities. The results of the work confirm that the proposed sensors offer high reliability even in extreme conditions, making them ideal for use in special applications, including long-distance detection and utilization in military or chemical environments.

关键词： Optical fiber polarization Military communication Wiring Optical fiber sensors Chemical sensors Ultraviolet sources Optical fiber networks Sensor phenomena and characterization Optical fiber testing Chemicals

Water Quality Prediction Based on Improved Multi-Point Joint Learning

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Xu, Xinghan Su, Ziyan Song, Zhao Xia, Huijuan Liu, Jianwei Yan, Xiaohui Han, Min Faculty of Infrastructure Engineering Dalian University of Technology Liaoning Dalian116024 China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Liaoning Dalian116024 China School of Water Resources Engineering Faculty of Infrastructure Engineering Dalian University of Technology Liaoning Dalian116024 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Liaoning Dalian116024 China Professional Technology Innovation Center of Distributed Control for Industrial Equipment of Liaoning Province Liaoning Dalian116024 China

Water quality prediction is an effective method that can be used to prevent water pollution incidents. By accurately predicting the concentration of pollutants in waterbodies, water pollution can be more effectively controlled and prevented. In water quality data prediction, people usually predict the concentration of pollutants in future water bodies based on historical single-point water quality data, but this ignores the potential spatial characteristics between multiple water body points with similar geographical spaces. In order to solve this problem, this paper adopts the principle of data association and deep learning technology to establish the concentration prediction model of water quality indicators. The model consists of two parts: a deep learning network model based on Improved Neural Basis Unfolding Analysis of Interpretable Time Series (N-BEATS) and a deep learning network model based on Graph Neural Network (GNN). The GNN network is used to extract the spatial distribution characteristics and meteorological data of the pollutant concentration of multiple water quality collection points, and use the semivariogram function to quantify the data characteristics between © 2023, The Authors. All rights reserved.

关键词： Water quality

Geotechnical "facial Recognition" Challenge

学校读者我要写书评

暂无评论

ASCE-ASME Journal of Risk and Uncertainty in engineering Systems, Part A: Civil engineering 2025年第3期11卷

作者： Phoon, Kok-Kwang Cai, Yongmin Tang, Chong Information Systems Technology and Design/Architecture and Sustainable Design Singapore Univ. of Technology and Design Somapah Rd. 487372 Singapore Architecture and Sustainable Design Singapore Univ. of Technology and Design Somapah Rd. 487372 Singapore Faculty of Infrastructure Engineering Dalian Univ. of Technology Liaoning Dalian116024 China

The site recognition challenge is to quantify site uniqueness, directly or indirectly, so that sparse site-specific data can be supplemented by big indirect data (BID) to produce a quasi-site-specific model. Engineers appreciate that every site is unique to some extent, but they do not have the ability to quantify this uniqueness. In all likelihood, the difference between two sites depends on the feature of interest (stratification, spatial variability, properties, anomaly, etc.). All sites in a region share common general features as a result of their geologic origin, but they are different at a detailed level when investigated using site investigation tools. This is broadly similar to the facial recognition challenge. However, the training set for facial recognition (photographs) is much bigger and more complete than the available training set for the site recognition challenge. In fact, there is no 3D photograph of a ground volume for any feature of engineering interest. Nonetheless, for the case of soil properties, this paper shows that it is possible to construct a quasi-site-specific (or quasilocal) transformation model from site specific small data and big indirect data. The strategies include the hierarchical Bayesian method, tailored clustering method, outlier detection, dimension reduction, and dictionary learning. These Bayesian machine learning methods can be combined to produce inferences that are more accurate and less biased than those from the classical probabilistic multiple regression (PMR) method. The computational cost of PMR is the lowest, but its disadvantages are significant. One example is that PMR cannot handle multivariate, uncertain and unique, sparse, incomplete, and potentially corrupted (MUSIC) which is a common set of data attributes for real site data. This paper reviews the state-of-The-Art research in the site recognition challenge in the presence of MUSIC. Spatial variability and geologic uncertainty are not included in this review

关键词： Hierarchical clustering

Characterization of Nanomaterials Tio2 Photocatalytic Composite Mgo Alkali-Activated Cementitious Material for Performances and Applications

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Jia, Yuan Wang, Wenjie Zhang, Jingxi Cong, Haoran Zhao, Enci Zhu, Junwei Zhang, Tingting Zou, Yuxin Ma, Wangkun College of Materials Science and Engineering North China University of Science and Technology Tangshan063000 China Faculty of Infrastructure Engineering Dalian University of Technology Dalian116024 China Technical Information Research Institute of Building Materials Industry Beijing100024 China

Magnesium silicate hydrated (MSH) gel as a porous and composite material in the MgO alkali-activated cementitious (MAA) system, was combined with nanometer TiO2 (nano-TiO2) at room temperature to form TiO2 photocatalytic composite MgO alkali-activated cementitious material (TiO2/MAA) with high concentration adsorption-degradation performance. The adsorption-degradation properties of TiO2/MAA were evaluated by adsorption and photocatalytic degradation of rhodamine B (RhB). Results indicated that a lower doping level of TiO2 could promote the hydration of MAA, with an optimal range observed between 5 wt.% to 10 wt.%. Comparative analysis with the nano-TiO2 photocatalytic composite CaO alkali-activated cementitious material (TiO2/CAA), the adsorption-degradation performance of TiO2/MAA in high concentration RhB environment can reach 96.02%, better than TiO2/CAA. This study introduces a highly efficient, and durable inorganic photocatalytic degradation adsorbent for application in high concentration wastewater treatment. © 2024, The Authors. All rights reserved.

关键词： Porous materials