No abstract

The increasing design documents created in the design process provide a useful source of process-oriented design information. Hence, the need for automated design information extraction using advanced text mining techniques is increasing. However, most of the existing text mining approaches have problems in mining design information in depth, which results in low efficiency in applying the discovered information to improve the design project. With the aim of extracting process-oriented design information from design documents in depth, this paper proposes a layered text mining approach that produces a hierarchical process model which captures the process behavior at the different level of details. Our approach consists of several interrelated algorithms, namely, a content-based document clustering algorithm, a hybrid named entity recognition (NER) algorithm and a frequency-based entity relationship detection method, which have been integrated into a system architecture for extracting design information from coarse-grained views to fine-grained specifications. To evaluate the performance of the proposed algorithms, experiments were conducted on an email archive that was collected from a real-life design project. The results showed an increase in the detection accuracy for the process-oriented information detection.

With the arrival of cyber physical world and an extensive support of advanced information technology (IT) infrastructure, nowadays it is possible to obtain the footprints of design activities through emails, design journals, change logs, and different forms of social data. In order to manage a more effective design process, it is essential to learn from the past by utilizing these valuable sources and understand, for example, what design tasks are actually carried out, their interactions, and how they impact each other. In this paper, a computational approach based on the deep belief nets (DBN) is proposed to automatically uncover design tasks and quantify their interactions from design document archives. First, a DBN topic model with real-valued units is developed to learn a set of intrinsic topic features from a simple word-frequency-based input representation. The trained DBN model is then utilized to discover design tasks by unfolding hidden units by sets of strongly connected words, followed by estimating the interactions among tasks on the basis of their co-occurrence frequency in a hidden topic space. Finally, the proposed approach is demonstrated through a real-life case study using a design email archive spanning for more than 2 yr.

With the arrival of cyber physical world and an extensive support of advanced IT infrastructure, nowadays it is possible to obtain the footprints of design activities through emails, design journals, change logs, and different forms of social data. In order to manage a more effective design process, it is essential to learn from the past and understand, for example, what design tasks are actually carried out, their interactions and how they impact each other. In this paper, a computational approach based on deep belief nets (DBN) is proposed to automatically uncover design tasks and quantify their interactions. A DBN topic modeling with real-valued units is to learn a set of intrinsic topic features from a simple word-frequency based input representation. Evaluated using a design email archive spanning for more than two years, the proposed approach has achieved a much higher accuracy in identifying design tasks compared to a prevailing approach.

Traffic wave, also known as stop wave or traffic shockwave, is travelling disturbance in the distribution of vehicles on the highways. In this paper, we attempt to study this problem using a simulation approach. Largely inspired by an interesting observation from ant chain movement, we explore how such a vivid pattern can be mathematically modeled and whether the similar way of behavior is helpful for dealing traffic wave issue in our highway systems. Therefore, a decentralized fast-adaptive clustering approach is proposed jointly with considerations for traffic optimization. To validate the proposed approach and to better understand its mechanism in lifting traffic flow, simulation study is carried out using real-world traffic data. Results have revealed the applicability and effectiveness of the proposed approach and have also indicated that both road configuration and traffic demand affect the effectiveness of the proposed model.