Natnicha Putthakasem, N. Limphitakphong, O. Chavalparit
As a consequence of rapid urbanization and population growth, many cities have faces issues of waste management. Landfill approach is generally decided for handling most of municipal solid waste, resulting the impacts of environment especially land occupation and global warming. As commercial building plays an importance role not only for economic value but also for environmental aspects, a supermarket located in community mall was selected as a case study towards sustainable cities. This study was aimed to investigate the current MSW management system of supermarket in order to quantify its environmental performance and to propose suitable options for improving municipal solid waste management. The findings revealed that at the business-as-usual, 397 tCO2e was emitted annually from landfilling waste of a supermarket in Thailand. However, if waste management has improved by recycling plus bio-gasification approach, not only 374 tCO2e/year will not be emitted from landfilling, but 243 tCO2e/year also be reduced due to the activities in relevant to recycling and bio-gasification process. Moreover, applying such approach provides benefit in economic term about 18,321 USD a year. The results of this study could inspire another commercial buildings or others sector to adopting waste management practices together for creating a network of sustainable cities through suitable waste management system.
{"title":"Scenarios of Municipal Solid Waste Management for Mitigating Greenhouse Gas Emission: A Case Study of Supermarket in Bangkok, Thailand","authors":"Natnicha Putthakasem, N. Limphitakphong, O. Chavalparit","doi":"10.1145/3208854.3208889","DOIUrl":"https://doi.org/10.1145/3208854.3208889","url":null,"abstract":"As a consequence of rapid urbanization and population growth, many cities have faces issues of waste management. Landfill approach is generally decided for handling most of municipal solid waste, resulting the impacts of environment especially land occupation and global warming. As commercial building plays an importance role not only for economic value but also for environmental aspects, a supermarket located in community mall was selected as a case study towards sustainable cities. This study was aimed to investigate the current MSW management system of supermarket in order to quantify its environmental performance and to propose suitable options for improving municipal solid waste management. The findings revealed that at the business-as-usual, 397 tCO2e was emitted annually from landfilling waste of a supermarket in Thailand. However, if waste management has improved by recycling plus bio-gasification approach, not only 374 tCO2e/year will not be emitted from landfilling, but 243 tCO2e/year also be reduced due to the activities in relevant to recycling and bio-gasification process. Moreover, applying such approach provides benefit in economic term about 18,321 USD a year. The results of this study could inspire another commercial buildings or others sector to adopting waste management practices together for creating a network of sustainable cities through suitable waste management system.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125751055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a strategic emerging industry in China, new energy vehicles have received wide attention and favour from consumers and have been developing rapidly. Up to now, few researches on fire safety of new energy vehicles in the field of tunnel engineering are carried out at domestic and overseas. Based on the statistical data of fire accidents in new energy vehicles, the region, application area, power type and reasons of new energy vehicles fire were analysed. The formation mechanism, spread characteristics, combustion mode and dangerousness of fire on new energy vehicles and traditional internal combustion engine vehicles are compared and analysed. On account of new problems caused by the combustion or explosion of new energy vehicles in tunnel, the difficulties of tunnel fire rescue, the applicability of fire extinguishing agent, the new challenges faced by firemen, and the rescue measures in tunnel are discussed. In the context of the increasing number of highway tunnels, the research results can provide a reference for the study of fire safety of new energy vehicle tunnels.
{"title":"Challenges of New Energy Vehicles in Tunnel Fire and Discussion on Emergency Rescue Technology","authors":"Jianchun Sun, Heng Zhang, Fen Xiang","doi":"10.1145/3208854.3208859","DOIUrl":"https://doi.org/10.1145/3208854.3208859","url":null,"abstract":"As a strategic emerging industry in China, new energy vehicles have received wide attention and favour from consumers and have been developing rapidly. Up to now, few researches on fire safety of new energy vehicles in the field of tunnel engineering are carried out at domestic and overseas. Based on the statistical data of fire accidents in new energy vehicles, the region, application area, power type and reasons of new energy vehicles fire were analysed. The formation mechanism, spread characteristics, combustion mode and dangerousness of fire on new energy vehicles and traditional internal combustion engine vehicles are compared and analysed. On account of new problems caused by the combustion or explosion of new energy vehicles in tunnel, the difficulties of tunnel fire rescue, the applicability of fire extinguishing agent, the new challenges faced by firemen, and the rescue measures in tunnel are discussed. In the context of the increasing number of highway tunnels, the research results can provide a reference for the study of fire safety of new energy vehicle tunnels.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127125660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This investigation proposes a model of syngas creation from Refuse Derived Fuel (RDF) Pellet gasification with air in fixed bed reactor. The model (utilizing Aspen Plus process simulation software) is utilized to model the anticipated results of RDF gasification and to give some processes fundamentals concerning syngas generation from RDF gasification. The fixed bed reactors is an updraft fixed bed reactor which can be divided into 3 sections n (devolatilization, partial oxidation, and steam reforming). The model is based on a combination of modules that the Aspen Plus simulator provides, representing the three stages of gasification. Thermodynamics package used in the simulation comprised the Non- Random Two-Liquid (NRTL) model. The model works on the principle of Gibbs free energy minimization and was validated with experimental data of MSW gasification found in literature. The RYield module was combined with the RGibbs module to describe pyrolysis section, while the RGibbs module was used for the gasification section individually. Proximate and ultimate analysis of RDF pellets and operating conditions used in the model are discussed. The sensitivity analysis module of Aspen Plus was used to research the effect of air equivalence ratio ER and temperature value on the syngas composition, and carbon conversion The results indicate that higher temperature improves gasification as the composition of H2 and CO increase, as well as carbon conversion, until a temperature of 900°C, and higher air equivalence ratio increases the carbon conversion while decreasing syngas quality as there is an increase in CO2 and H. Results obtained are in good agreement of experimentally measured data in literature.
{"title":"Process Simulation of Municipal Solid Waste Derived Pellet Gasification for Fuel Production","authors":"A. Hlaba, A. Rabiu, O. A. Osibote","doi":"10.1145/3208854.3208869","DOIUrl":"https://doi.org/10.1145/3208854.3208869","url":null,"abstract":"This investigation proposes a model of syngas creation from Refuse Derived Fuel (RDF) Pellet gasification with air in fixed bed reactor. The model (utilizing Aspen Plus process simulation software) is utilized to model the anticipated results of RDF gasification and to give some processes fundamentals concerning syngas generation from RDF gasification. The fixed bed reactors is an updraft fixed bed reactor which can be divided into 3 sections n (devolatilization, partial oxidation, and steam reforming). The model is based on a combination of modules that the Aspen Plus simulator provides, representing the three stages of gasification. Thermodynamics package used in the simulation comprised the Non- Random Two-Liquid (NRTL) model. The model works on the principle of Gibbs free energy minimization and was validated with experimental data of MSW gasification found in literature. The RYield module was combined with the RGibbs module to describe pyrolysis section, while the RGibbs module was used for the gasification section individually. Proximate and ultimate analysis of RDF pellets and operating conditions used in the model are discussed. The sensitivity analysis module of Aspen Plus was used to research the effect of air equivalence ratio ER and temperature value on the syngas composition, and carbon conversion The results indicate that higher temperature improves gasification as the composition of H2 and CO increase, as well as carbon conversion, until a temperature of 900°C, and higher air equivalence ratio increases the carbon conversion while decreasing syngas quality as there is an increase in CO2 and H. Results obtained are in good agreement of experimentally measured data in literature.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127301491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Schuh, Marcel Schwartz, Dominik Kolz, P. Jussen, Timo Lütke Meyring
Electromobility provides the basis for a fundamental, worldwide paradigm shift concerning individual mobility. This change will entail an extensive shift in the market, affecting several industries and resulting in a complex and dynamic market environment. Given these circumstances, being prepared for different potential development trends is crucial for both individual and collective success in the electric mobility market. Therefore, the main objective of this paper is to generate one major scenario for the successful development of electromobility in Germany. This scenario points out a consistent combination of development trends for certain key factors, shaping electromobility. Current scientific work regarding the future of electromobility primarily focusses on technological aspects and, for the most part, neglects services as key for bridging the gap between technology and the customer. This desideratum for research is addressed by the present paper, which seeks to develop holistic scenarios that consider all key factors that are relevant in the context of electromobility. A fundamental finding of this study is that services can have a great impact on the success of electromobility, even in the absence of significant technological progress.
{"title":"Scenarios for the Development of Electromobility","authors":"G. Schuh, Marcel Schwartz, Dominik Kolz, P. Jussen, Timo Lütke Meyring","doi":"10.1145/3208854.3208866","DOIUrl":"https://doi.org/10.1145/3208854.3208866","url":null,"abstract":"Electromobility provides the basis for a fundamental, worldwide paradigm shift concerning individual mobility. This change will entail an extensive shift in the market, affecting several industries and resulting in a complex and dynamic market environment. Given these circumstances, being prepared for different potential development trends is crucial for both individual and collective success in the electric mobility market. Therefore, the main objective of this paper is to generate one major scenario for the successful development of electromobility in Germany. This scenario points out a consistent combination of development trends for certain key factors, shaping electromobility. Current scientific work regarding the future of electromobility primarily focusses on technological aspects and, for the most part, neglects services as key for bridging the gap between technology and the customer. This desideratum for research is addressed by the present paper, which seeks to develop holistic scenarios that consider all key factors that are relevant in the context of electromobility. A fundamental finding of this study is that services can have a great impact on the success of electromobility, even in the absence of significant technological progress.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129464169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we based on the existing research results, the effects on dissolution rate (DR) of carbonate rock are analyzed for three factors: mineral and chemical component of carbonate rock, atmospheric temperature and rainfall. The formula is established on the relation between rainfall and DR. Considering mineral and chemical component of carbonate rock by the difference of research area. The results show that: Precipitation is positively correlated with carbonate dissolution, and the influence of temperature is of a stage. The DR of carbonate rocks in Guilin is calculated to be 79.65mm/ka, which is calculated from the mineral chemical composition of carbonate rocks in Yaoshan Scenic Area, Guilin. The average regional DR is 95.16mm/ka; the calculation formula of DR of carbonate rock proposed in this paper is suitable for the southwest of China.
{"title":"The Dissolution Rate of Carbonate Rock in Southwest of China Based on the Influence Factor Analysis","authors":"Bai Yang, Jianlin Ma, Z. Sun, Y. Fu, B. Liu","doi":"10.1145/3208854.3208882","DOIUrl":"https://doi.org/10.1145/3208854.3208882","url":null,"abstract":"In this paper, we based on the existing research results, the effects on dissolution rate (DR) of carbonate rock are analyzed for three factors: mineral and chemical component of carbonate rock, atmospheric temperature and rainfall. The formula is established on the relation between rainfall and DR. Considering mineral and chemical component of carbonate rock by the difference of research area. The results show that: Precipitation is positively correlated with carbonate dissolution, and the influence of temperature is of a stage. The DR of carbonate rocks in Guilin is calculated to be 79.65mm/ka, which is calculated from the mineral chemical composition of carbonate rocks in Yaoshan Scenic Area, Guilin. The average regional DR is 95.16mm/ka; the calculation formula of DR of carbonate rock proposed in this paper is suitable for the southwest of China.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130097614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Seismic data often contains different types of noise, and eliminating noise is one of the most important issues in seismic data processing. Noise on seismic data has influence on decline of SNR (signal to noise ratio) and resolution ratio of seismic data. Because of the reasons above, it is difficult to accurately obtain the geological structure by analyzing seismic signal. In view of limitation of selecting threshold value in the traditional wavelet analysis method, this paper proposes the multi-threshold wavelet packet method based on the frequency sequence. Through theoretical analysis and simulation of seismic signal, the de-noising processing is realized by using the multi-threshold wavelet packet de-noising method, the results show that the method can effectively filter out seismic noise and reserve the useful signal with the middle and high frequency. So the capability of noise reduction is superior to other traditional methods, which can effectively improve the resolution ratio of the seismic signal and establish the foundation for later inversion of geological structure.
{"title":"Multi-threshold Wavelet Packet-Based Method to Attenuate Noise from Seismic Signal","authors":"Hejun Chai, He Huang, Zongling Yan, Xiaosong Zhang, Yanyun Li, Ping Gan, Yangfan Huang","doi":"10.1145/3208854.3208876","DOIUrl":"https://doi.org/10.1145/3208854.3208876","url":null,"abstract":"Seismic data often contains different types of noise, and eliminating noise is one of the most important issues in seismic data processing. Noise on seismic data has influence on decline of SNR (signal to noise ratio) and resolution ratio of seismic data. Because of the reasons above, it is difficult to accurately obtain the geological structure by analyzing seismic signal. In view of limitation of selecting threshold value in the traditional wavelet analysis method, this paper proposes the multi-threshold wavelet packet method based on the frequency sequence. Through theoretical analysis and simulation of seismic signal, the de-noising processing is realized by using the multi-threshold wavelet packet de-noising method, the results show that the method can effectively filter out seismic noise and reserve the useful signal with the middle and high frequency. So the capability of noise reduction is superior to other traditional methods, which can effectively improve the resolution ratio of the seismic signal and establish the foundation for later inversion of geological structure.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"38 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123279551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To avoid being discovered by the defenders of a target, APT attackers are using encrypted communication to hide communication features, using code obfuscation and file-less technology to avoid malicious code being easily reversed and leaking out its internal working mechanism, and using misleading content to conceal their identities. And it is clearly ineffective to detect APT attacks by relying on one single technology. All of these tough situation make information security and privacy protection face increasingly serious threats. In this paper, through a deep study of Cyber Kill Chain behaviors, combining with intelligence analysis technology, we transform APT detecting problem to be a measurable mathematical problem through weighted Bayesian classification with correction factor so as to detect APTs and perceive threats. In the solution, we adopted intelligence acquisition technology from massive data, and TFIDF algorithm for calculate attack behavior's weight. Also we designed a correction factor to improve the Markov Weighted Bayesian Model with multiple behaviors being detected by modifying the value of the probability of APT attack.
{"title":"Information Protecting against APT Based on the Study of Cyber Kill Chain with Weighted Bayesian Classification with Correction Factor","authors":"Senhao Wen, Yu Rao, Hanbing Yan","doi":"10.1145/3208854.3208893","DOIUrl":"https://doi.org/10.1145/3208854.3208893","url":null,"abstract":"To avoid being discovered by the defenders of a target, APT attackers are using encrypted communication to hide communication features, using code obfuscation and file-less technology to avoid malicious code being easily reversed and leaking out its internal working mechanism, and using misleading content to conceal their identities. And it is clearly ineffective to detect APT attacks by relying on one single technology. All of these tough situation make information security and privacy protection face increasingly serious threats. In this paper, through a deep study of Cyber Kill Chain behaviors, combining with intelligence analysis technology, we transform APT detecting problem to be a measurable mathematical problem through weighted Bayesian classification with correction factor so as to detect APTs and perceive threats. In the solution, we adopted intelligence acquisition technology from massive data, and TFIDF algorithm for calculate attack behavior's weight. Also we designed a correction factor to improve the Markov Weighted Bayesian Model with multiple behaviors being detected by modifying the value of the probability of APT attack.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125051223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Inatda Srisampao, Peerapong Pornwongthong, S. Roddecha, Wawat Rodiahwati, M. Sriariyanun
In the biofuel production, an important step in biofuel production from lignocellulosic biomass is the transformation of cellulose into glucose by the function of cellulase. Pretreatment is a necessary process to promote the enzyme efficiency in hydrolysis. In this study, cholinium acetate ([Ch][OAc]), an ionic liquid (IL), was applied in pretreatment of rice straw. The [Ch][OAc] pretreatment conditions were optimized to maximize sugar release of rice straw using a response surface methodology (RSM) with three testing parameters, including loading mass ratio per IL, treatment time, and reaction temperature. The hydrolysis results demonstrated that the highest production of reducing sugars at 57.12 mg/0.1 g-rice straw was achieved at 130 °C for 304.27 min and using 13.79% loading mass ratio, which was 6.57 times higher than the untreated rice straw. Moreover, impacts of [Ch][OAc] pretreatment were analyzed using FTIR. The result showed that [Ch][OAc] removed crystallinity structure of cellulose and lignin content. These results suggested the potential of [Ch][OAc] pretreatment of biofuel production from lignocellulosic biomass.
{"title":"Pretreatment Optimization of Cholinium Ionic Liquid for Maximizing Sugar Release from Rice Straw","authors":"Inatda Srisampao, Peerapong Pornwongthong, S. Roddecha, Wawat Rodiahwati, M. Sriariyanun","doi":"10.1145/3208854.3208864","DOIUrl":"https://doi.org/10.1145/3208854.3208864","url":null,"abstract":"In the biofuel production, an important step in biofuel production from lignocellulosic biomass is the transformation of cellulose into glucose by the function of cellulase. Pretreatment is a necessary process to promote the enzyme efficiency in hydrolysis. In this study, cholinium acetate ([Ch][OAc]), an ionic liquid (IL), was applied in pretreatment of rice straw. The [Ch][OAc] pretreatment conditions were optimized to maximize sugar release of rice straw using a response surface methodology (RSM) with three testing parameters, including loading mass ratio per IL, treatment time, and reaction temperature. The hydrolysis results demonstrated that the highest production of reducing sugars at 57.12 mg/0.1 g-rice straw was achieved at 130 °C for 304.27 min and using 13.79% loading mass ratio, which was 6.57 times higher than the untreated rice straw. Moreover, impacts of [Ch][OAc] pretreatment were analyzed using FTIR. The result showed that [Ch][OAc] removed crystallinity structure of cellulose and lignin content. These results suggested the potential of [Ch][OAc] pretreatment of biofuel production from lignocellulosic biomass.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114610626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to solve the problem of how to make effective use of the natural ventilation in the shaft to assist the mechanical ventilation in the long tunnel and improve ventilation effect and save energy consumption, based on the construction ventilation of Guantian tunnel, the influence parameters of natural ventilation in shaft were carried out by theoretical analysis, numerical simulation and field test. The research results show that the natural ventilation of shaft has a certain effect on assisting mechanical ventilation under specific temperature conditions, the effect of strengthening the ventilation by changing the diameter of the shaft is limited. Within 250m of shaft depth, the ventilation effect of the shaft increases with the increase of the shaft depth, but the ventilation effect has no significant change with the depth increasing when the shaft depth is more than 250m. The greater the temperature difference, the better the natural ventilation effect of the shaft, and the natural ventilation effect of the shaft as outlet in winter is better than that of the shaft as inlet in summer. The introduction of fresh airflow into the main tunnel is the key to the implementation of the air intake scheme of the shaft. It is reasonable to set the fan away from the 5m position of the middle line of the shaft.
{"title":"Energy Saving Construction Ventilation Effect by Using Natural Wind of Shaft in Super-Long Highway Tunnel","authors":"Heng Zhang, Jianchun Sun, Fen Xiang","doi":"10.1145/3208854.3208871","DOIUrl":"https://doi.org/10.1145/3208854.3208871","url":null,"abstract":"In order to solve the problem of how to make effective use of the natural ventilation in the shaft to assist the mechanical ventilation in the long tunnel and improve ventilation effect and save energy consumption, based on the construction ventilation of Guantian tunnel, the influence parameters of natural ventilation in shaft were carried out by theoretical analysis, numerical simulation and field test. The research results show that the natural ventilation of shaft has a certain effect on assisting mechanical ventilation under specific temperature conditions, the effect of strengthening the ventilation by changing the diameter of the shaft is limited. Within 250m of shaft depth, the ventilation effect of the shaft increases with the increase of the shaft depth, but the ventilation effect has no significant change with the depth increasing when the shaft depth is more than 250m. The greater the temperature difference, the better the natural ventilation effect of the shaft, and the natural ventilation effect of the shaft as outlet in winter is better than that of the shaft as inlet in summer. The introduction of fresh airflow into the main tunnel is the key to the implementation of the air intake scheme of the shaft. It is reasonable to set the fan away from the 5m position of the middle line of the shaft.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"1 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130550613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Convolutional neural network (CNN) has proven itself as a promising methodology for various computer vision tasks due to its efficient hierarchical feature learning of input data. However, the pre-trained CNN model always has a limited ability to be spatially invariant to the image as the convolutional layers are not invariant to general affine transformations, such as rotation and scale. This scenario will extremely affect the generalization ability of the trained CNNs. In this work, we address this problem by leveraging recent advances in spatial transform network (STN) and XGBoost. Specifically, we propose a framework which consists of an embedded STN and XGBoost for learning the geometric invariance features and discrimination representation of the image data. We firstly establish a CNN embedding a STN to effectively extract the geometric invariance features of input image; then instead of employing the conventional softmax unit as the classifier, we adopt the high-efficient and faster XGBoost as the discrimination representation of the learned features. We conduct a series of experiments based on benchmark dataset Fashion MNIST to verify the effectiveness of our framework. The results demonstrate that our method can not only learn the geometric invariance features of input images, but also have a superior performance for the discriminate representation of the learned features, compared with recent several representative methods.
{"title":"Learning Geometric Invariance Features and Discrimination Representation for Image Classification via Spatial Transform Network and XGBoost Modeling","authors":"Liye Mei, Xiaopeng Guo, Wang Yin","doi":"10.1145/3208854.3208886","DOIUrl":"https://doi.org/10.1145/3208854.3208886","url":null,"abstract":"Convolutional neural network (CNN) has proven itself as a promising methodology for various computer vision tasks due to its efficient hierarchical feature learning of input data. However, the pre-trained CNN model always has a limited ability to be spatially invariant to the image as the convolutional layers are not invariant to general affine transformations, such as rotation and scale. This scenario will extremely affect the generalization ability of the trained CNNs. In this work, we address this problem by leveraging recent advances in spatial transform network (STN) and XGBoost. Specifically, we propose a framework which consists of an embedded STN and XGBoost for learning the geometric invariance features and discrimination representation of the image data. We firstly establish a CNN embedding a STN to effectively extract the geometric invariance features of input image; then instead of employing the conventional softmax unit as the classifier, we adopt the high-efficient and faster XGBoost as the discrimination representation of the learned features. We conduct a series of experiments based on benchmark dataset Fashion MNIST to verify the effectiveness of our framework. The results demonstrate that our method can not only learn the geometric invariance features of input images, but also have a superior performance for the discriminate representation of the learned features, compared with recent several representative methods.","PeriodicalId":365707,"journal":{"name":"IEEA '18","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130959774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：