In real-life freeway transportation system, a few number of incident observation （very rare event） is available while there are large numbers of normal condition dataset. Most of researches on freeway incident detec...In real-life freeway transportation system, a few number of incident observation （very rare event） is available while there are large numbers of normal condition dataset. Most of researches on freeway incident detection have considered the incident detection problem as classification one. However, because of insufficiency of incident events, most of previous researches have utilized simulated incident events to develop freeway incident detection models. In order to overcome this drawback, this paper proposes a wavelet-based Hotelling 7a control chart for freeway incident detection, which integrates a wavelet transform into an abnormal detection method. Firstly, wavelet transform extracts useful features from noisy original traffic observations, leading to reduce the dimensionality of input vectors. Then, a Hotelling T2 control chart describes a decision boundary with only normal traffic observations with the selected features in the wavelet domain. Unlike the existing incident detection algorithms, which require lots of incident observations to construct incident detection models, the proposed approach can decide a decision boundary given only normal training observations. The proposed method is evaluated in comparison with California algorithm, Minnesota algorithm and conventional neural networks. The experimental results present that the proposed algorithm in this paper is a promising alternative for freeway automatic incident detections.展开更多
This paper presents the development process relating to the conceptual design of glass/renewable natural fibrereinforced polymer hybrid composite motorcycle side cover.Motorcycle side cover is a component frequently m...This paper presents the development process relating to the conceptual design of glass/renewable natural fibrereinforced polymer hybrid composite motorcycle side cover.Motorcycle side cover is a component frequently made from plastic or steel that functions on covering the motorcycle parts,components and systems such as frame,battery,electrical systems and mechanical systems.Function Analysis Systems Techniques(FAST)is used to identify the functions of motorcycle side cover.The right-side cover of motorcycle model SYM E-Bonus 110 has been physically studied to identify the competitive benchmarking criteria.The functions and competitive benchmarking criteria are then compiled and integrated with the environmental requirements to identify the Product Design Specifications(PDS).The coir fibre has been selected from six identified dominant renewable natural fibre used for automotive component through integration of Ranking Method and Quality Based Selection(QBS).Then the polypropylene matrix is selected after shortlisting the existing thermoplastic that is used with coir fibre and has high suitability for injection moulding manufacturing.The polypropylene matrix is then evaluated using Weighted Evaluation Matrix(WEM)by comparing to benchmark material which is Acrylonitrile Butadiene Styrene(ABS).After that,the conceptual design development of glass/renewable coir fibre-reinforced polypropylene motorcycle side cover is carried out using an integrated Theory of Inventive Problem Solving(TRIZ)and Morphological Chart,followed by final conceptual design selection using integration of Pugh Scoring Method and QBS.The conceptual design development intended on improving the biodegradability to reduce pollution to the environment.However,the usage of glass/coir fibre-reinforced polypropylene hybrid composite may increase the weight due to higher density.Four innovative design concepts have been developed and the selected final concept design has the most minimum number of ribs and minimum thickness with the same ratio of glass展开更多
为了提高SPC(Statistical Process Control)控制图的识别效果,提出了一种采用改进序列前向选择法(ISFS)和极限学习机(ELM)相结合的方法来进行控制图模式识别。首先,对控制图进行特征提取;然后,采用改进的序列前向选择法对特征进行选择,...为了提高SPC(Statistical Process Control)控制图的识别效果,提出了一种采用改进序列前向选择法(ISFS)和极限学习机(ELM)相结合的方法来进行控制图模式识别。首先,对控制图进行特征提取;然后,采用改进的序列前向选择法对特征进行选择,减少了特征间的相关性和冗余性;最后,利用极限学习机来进行模式识别。仿真结果显示,改进方法的识别率可达到98.7%,从而为控制图提供了一种有效的识别方法。展开更多
文摘In real-life freeway transportation system, a few number of incident observation （very rare event） is available while there are large numbers of normal condition dataset. Most of researches on freeway incident detection have considered the incident detection problem as classification one. However, because of insufficiency of incident events, most of previous researches have utilized simulated incident events to develop freeway incident detection models. In order to overcome this drawback, this paper proposes a wavelet-based Hotelling 7a control chart for freeway incident detection, which integrates a wavelet transform into an abnormal detection method. Firstly, wavelet transform extracts useful features from noisy original traffic observations, leading to reduce the dimensionality of input vectors. Then, a Hotelling T2 control chart describes a decision boundary with only normal traffic observations with the selected features in the wavelet domain. Unlike the existing incident detection algorithms, which require lots of incident observations to construct incident detection models, the proposed approach can decide a decision boundary given only normal training observations. The proposed method is evaluated in comparison with California algorithm, Minnesota algorithm and conventional neural networks. The experimental results present that the proposed algorithm in this paper is a promising alternative for freeway automatic incident detections.
文摘This paper presents the development process relating to the conceptual design of glass/renewable natural fibrereinforced polymer hybrid composite motorcycle side cover.Motorcycle side cover is a component frequently made from plastic or steel that functions on covering the motorcycle parts,components and systems such as frame,battery,electrical systems and mechanical systems.Function Analysis Systems Techniques(FAST)is used to identify the functions of motorcycle side cover.The right-side cover of motorcycle model SYM E-Bonus 110 has been physically studied to identify the competitive benchmarking criteria.The functions and competitive benchmarking criteria are then compiled and integrated with the environmental requirements to identify the Product Design Specifications(PDS).The coir fibre has been selected from six identified dominant renewable natural fibre used for automotive component through integration of Ranking Method and Quality Based Selection(QBS).Then the polypropylene matrix is selected after shortlisting the existing thermoplastic that is used with coir fibre and has high suitability for injection moulding manufacturing.The polypropylene matrix is then evaluated using Weighted Evaluation Matrix(WEM)by comparing to benchmark material which is Acrylonitrile Butadiene Styrene(ABS).After that,the conceptual design development of glass/renewable coir fibre-reinforced polypropylene motorcycle side cover is carried out using an integrated Theory of Inventive Problem Solving(TRIZ)and Morphological Chart,followed by final conceptual design selection using integration of Pugh Scoring Method and QBS.The conceptual design development intended on improving the biodegradability to reduce pollution to the environment.However,the usage of glass/coir fibre-reinforced polypropylene hybrid composite may increase the weight due to higher density.Four innovative design concepts have been developed and the selected final concept design has the most minimum number of ribs and minimum thickness with the same ratio of glass
文摘为了提高SPC(Statistical Process Control)控制图的识别效果,提出了一种采用改进序列前向选择法(ISFS)和极限学习机(ELM)相结合的方法来进行控制图模式识别。首先,对控制图进行特征提取;然后,采用改进的序列前向选择法对特征进行选择,减少了特征间的相关性和冗余性;最后,利用极限学习机来进行模式识别。仿真结果显示,改进方法的识别率可达到98.7%,从而为控制图提供了一种有效的识别方法。
