检索结果-内蒙古大学图书馆

5th National Congress of Environmental Engineering

作者： Suchorab, Z. Sobczuk, H. Guz, L. Lagod, G. Lublin Univ Technol Fac Environm Engn Lublin Poland

ISBN: (纸本)9781138031630

Mold threat is an important problem in building industry. It is one of the most important features that cause Sick Building Syndrome occurrence. In many circumstances this problem is caused by the increase of moisture in the building envelopes but also excessive indoor air humidity. Problem of mold threat is often connected with introduction of new technologies and materials applied for the external walls of the buildings and improper performance of natural ventilation. These factors create suitable conditions for growth of mold. E-nose technique is currently often applied to evaluate air quality in environmental measurements. This paper presents the possibility of classifying mold threat in indoor air of different rooms using low-selective Metal Oxide Semiconductors (MOS) gas sensor array being the element of an e-nose device. Conducted investigation confirmed that e-nose supported by statistical data processing enables to distinguish air from different rooms affected with mold at a satisfactory level.

关键词： e-nose MOS sensors gas sensors array mold threat buildings

来源：评论

学校读者我要写书评

暂无评论

Monitoring of melanoma released volatile compounds by a gas sensors array: From in vitro to in vivo experiments

引用

sensors AND ACTUATORS B-CHEMICAL 2011年第2期154卷 288-294页

作者： Pennazza, G. Santonico, M. Martinelli, E. Paolesse, R. Tamburrelli, V. Cristina, S. D'Amico, A. Di Natale, C. Bartolazzi, A. Univ Roma Tor Vergata Dept Elect Engn I-00133 Rome Italy Univ Campus Biomed Roma Fac Engn I-00128 Rome Italy Univ Roma Tor Vergata Dept Chem Sci & Technol I-00133 Rome Italy St Andrea Univ Hosp Dept Pathol I-00189 Rome Italy Karolinska Hosp Cellular & Mol Tumor Pathol Lab Canc Ctr Karolinska S-10401 Stockholm Sweden

The analysis of the volatile organic compounds (VOCs) released by bio-systems represents a promising approach for the diagnosis of human diseases including cancers. Experimental results suggested the possibility to detect tumors in vivo through the analysis of released VOCs from different body compartments, such as breath and skin. This paper illustrates the results obtained measuring VOCs mixtures released by well-characterized tumor cells derived from human malignancies by using an array of broadly selective chemical sensors. The patterns of VOCs emitted by two different melanoma tumorigenic cell lines transplanted ad hoc in a mice model were investigated. The recorded sensors signals are compatible with the existence of a distinguishable tumor specific pattern of VOCs evolving during the exponential phase of tumor growth. (C) 2010 Elsevier B.V. All rights reserved.

关键词： gas sensors array Tumor cells cultures Melanoma Xenograft

来源：评论

学校读者我要写书评

暂无评论

Monitoring of melanoma released volatile compounds by a gas sensors array: From in vitro to in vivo experiments

Monitoring of melanoma released volatile compounds by a gas ...

引用

23rd International Conference On Solid-State sensors, Actuators, Microsystems and Nanosystems

关键词： gas sensors array Tumor cells cultures Melanoma Xenograft

来源：评论

学校读者我要写书评

暂无评论

Research on air pollution gases recognition method based on LSTM recurrent neural network and gas sensors array

Research on air pollution gases recognition method based on ...

引用

Chinese Automation Congress (CAC)

作者： Wang, Qingfeng Xie, Taiyang Wang, Shuaiqi Jilin Univ Coll Elect Sci & Engineer State Key Lab Integrated Optoelect Changchun Jilin Peoples R China Jilin Univ Coll Elect Sci & Engn Changchun Jilin Peoples R China

ISBN: (纸本)9781728113128

The integration of sensors array and pattern recognition to replace large scale analytical instruments is an important and feasible method for accurate and rapid measurement of atmospheric pollution gases. This paper proposed a quantitative detection method of mixed gases based on long short-term memory (LSTM) recurrent neural network, including data pre-processing, network structure design, model training and prediction process. This method can extract the deep characteristics of sensors array's responses automatically and match the complex nonlinear characteristics more accurately. It is proved that the proposed LSTM prediction model has a strong applicability and higher accuracy in the concentration identification of gas mixtures by comparing with the experiments of existing models.

关键词： gas sensors array pattern recognition air pollution gases deep learning recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

gas recognition by activated WO₃ thin-film sensors array

引用

sensors AND ACTUATORS B-CHEMICAL 2001年第1期81卷 115-121页

作者： Penza, M Cassano, G Tortorella, F PASTIS CNRSM SCpA I-72100 Brindisi Italy

We have designed and fabricated a sensors array using WO3 thin films for gas analysis purposes. The sensing surface of the rf sputtered WO3 thin films has been differently activated by evaporated Pd, Au, Bi, Sb catalysts. The sensors have been characterized by d.c. electrical measurements for different gases such as H2S, SO2, CH4, NO, NO2 in a proper concentration range from 1 to 7000 ppm in dry air, at 180 degreesC. Operation of the sensors under these conditions proved to be a useful way of providing a sensitive, reproducible, reversible, stable system for gas detection of ppm level. Principal component analysis (PCA) has been used in order to classify and identify different classes of target gases. Good separation among classes of sample gases has been obtained by applied PCA methods. The preliminary results show the feasibility of the electronic nose system to discriminate and recognize various tested reducing and oxidizing gases. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： gas sensors array WO3 thin films principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of CO and CH₄ gas mixtures by using a micromachined sensor array

引用

sensors AND ACTUATORS B-CHEMICAL 2001年第1-3期78卷 40-48页

作者： Capone, S Siciliano, P Bârsan, N Weimar, U Vasanelli, L Univ Lecce Dipartimento Ingn Innovaz I-73100 Lecce Italy CNR IME Ist Studio Nuovi Mat Elettr I-73100 Lecce Italy Univ Tubingen Inst Phys & Theoret Chem D-72076 Tubingen Germany

An array of highly sensitive and mechanically stable gas sensors based on different sol-gel fabricated Pd-doped SnO2 nanocrystalline thick films has been developed for the analysis of ternary mixtures in the concentration ranges of 0-100 ppm CO, 0-4000 ppm CH4 and 0-50% relative humidity. The selectivity of the sensors has been modulated by varying the percentage of Pd content and the contacts geometry, while the use of micromachined hotplates as substrates for the sensors allowed a reduction of heater power consumption and a fast and accurate temperature control. Principal component analysis (PCA) as pattern recognition and principal component regression (PCR) as multicomponent analysis method have been used to analyze these mixtures qualitatively and quantitatively obtaining good results. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： gas sensors array micro-hotplates pattern recognition multicomponent analysis

来源：评论

学校读者我要写书评

暂无评论

Unsupervised On-Line Selection of Training Features for a robust classification with drifting and faulty gas sensors

引用

sensors AND ACTUATORS B-CHEMICAL 2018年 258卷 1242-1251页

作者： Magna, Gabriele Mosciano, Francesco Martinelli, Eugenio Di Natale, Corrado Univ Roma Tor Vergata Dept Elect Engn Via Politecn 1 I-00133 Rome Italy

Inconstancy and scarce reproducibility limit the online application of chemical sensor arrays. Most of the attempts to counteract these issues are based on adaptive classifiers, namely models that also change to keep pace with fluctuations in the information content. In this paper, we introduce a decision making process to remove ambiguous components from the input data. This approach provides robustness towards fault and drift and, at the same time, maintains the use of standard classifiers. The heart of the method is characterized by an online feature selection for single test measurements. With the selected features, a completely new model is trained to classify the sample. After the class assignment, the dataset used for the model training is updated exploiting the most recent measurements. The algorithm of feature selection has been applied to a number of standard classifiers such as k-NN, PLS-DA and LDA. Synthetic and real sensors dataset have been used to validate the method. In particular synthetic data have been used to test the algorithm in complex drifting sensors scenario and real data provided the basis to study the performance of feature selection procedure. Fault sensors events were included in each dataset. Results confirm an excellent capability to counteract drift and to identify and exclude those features that are either temporarily or permanently faulting. (C) 2017 Elsevier B.V. All rights reserved.

关键词： On-line feature selection Adaptive classifier Drift counteraction Fault tolerance gas sensors array

来源：评论

学校读者我要写书评

暂无评论

Design and Construction of Electronic Nose for Multi-purpose Applications by Sensor array Arrangement Using IBGSA

引用

JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 2018年第2期92卷 205-221页

作者： Estakhroyeh, Hossein Rezaei Rashedi, Esmat Mehran, Mahdiyeh Grad Univ Adv Technol Dept Elect Engn POB 76315-117 Kerman Iran Shahid Bahonar Univ Kerman Dept Elect Engn RF MEMS & Bionano Elect Lab Kerman Iran

Technological progresses in the gas sensor fields provide the possibility of designing and construction of Electronic nose (E-nose) based on the Biological nose. E-nose uses specific hardware and software units;Sensor array is one of the critical units in the E-nose and its types of sensors are determined based on the application. So far, many achievements have been reported for using the E-nose in different fields of application. In this work, an E-nose for handling multi-purpose applications is proposed, and the employed hardware and pattern recognition techniques are depicted. To achieve higher recognition rate and lower power consumption, the improved binary gravitational search algorithm (IBGSA) and the K-nearest neighbor (KNN) classifier are used for automatic selecting the best combination of the sensors. The designed E-nose is tested by classifying the odors in different case studies, including moldy bread recognition in food and beverage field, herbs recognition in the medical field, and petroleum products recognition in the industrial field. Experimental results confirm the efficiency of the proposed method for E-nose realization.

关键词： Electronic nose (E-nose) Odor classification Multi-purpose applications gas sensors array Sensor array configuration Binary gravitational search algorithm

来源：评论

学校读者我要写书评

暂无评论

A sensor array and GC study about VOCs and cancer cells

引用

sensors AND ACTUATORS B-CHEMICAL 2010年第2期146卷 483-488页

作者： Bartolazzi, A. Santonico, M. Pennazza, G. Martinelli, E. Paolesse, R. D'Amico, A. Di Natale, C. Univ Campus BioMed Fac Engn I-00128 Rome Italy St Andrea Univ Hosp Dept Pathol I-00189 Rome Italy Univ Roma Tor Vergata Dept Elect Engn I-00133 Rome Italy Univ Roma Tor Vergata Dept Chem Sci & Technol I-00133 Rome Italy

In recent years a body of evidences about the relationship between volatile compounds released in body compartments and diseases have been provided. These researches did not indicate if anomalous volatile patterns are a consequence of a general alteration of body metabolism or if they originate from cancer cells. In order to approach a solution to this question, in this paper, an experiment aimed at discriminating cultured tumoral cells lines from their volatile compounds is illustrated. Volatile organic compounds have been fingerprinted with a gas sensor array and a gas-chromatography/mass-spectrometer. These results suggest that cell lines from human tumors are characterized by a distinct volatile compounds profile and that these patterns when fingerprinted by a chemical sensor array tend to cluster according to the kind of tumor. These findings provide a hint about the possibility to identify a specific volatile fingerprint for each tumor type. (C) 2009 Elsevier B.V. All rights reserved.

关键词： gas sensors array Cancer cells headspace Volatile compounds fingerprint

来源：评论

学校读者我要写书评

暂无评论

Quantification of Multiple gases Mixture Based on Fuzzy Partition and Model Ensemble 38

Quantification of Multiple Gases Mixture Based on Fuzzy Part...

引用

38th Chinese Control Conference (CCC)

作者： Wang, Qingfeng Min, Jiaxing Cai, Mao Jilin Univ Coll Elect Sci & Engn Changchun 130012 Peoples R China

ISBN: (纸本)9789881563972

gases concentration estimation based on the integration of fuzzy partition and model ensemble with drift compensation for metal oxide gas sensors array is proposed in this paper. The sensors response data is divided into several sub-data sets newly according to the drift variation of sensors baseline over time using fuzzy clustering method, and then regression models of these sub-data sets are established based on weighted multi-output support vector regression. The optimal weights of sub-regression models are obtained by traversing search during training process. Based on least squares support vector regression, the optimal weight functions in model ensemble are fitted by training the clustering center and the optimal weights of sub-regression models. In the testing stage, the weights of ensemble models are calculated from the optimal weight function and clustering center. This method can adaptively change the recognition models so that it can cope with the change of sensors drift and ensure the long-term accuracy of concentration quantification.

关键词： gas sensors array Fuzzy clustering Support vector regression Model ensemble

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：