Browsing by Subject "task analysis"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Agent-based Three Layer Framework of Assembly-Oriented Planning and Scheduling for Discrete Manufacturing Enterprises
    (IEEE, 2018-06) Fan, Yinghui; Anwar, Sohel; Wang, Litao; Mechanical and Energy Engineering, School of Engineering and Technology
    To solve the cost burden caused by delivery tardiness for small and medium sized packaging machinery enterprises, the assembly-oriented planning and scheduling is studied based on the multi-agent technology. Taking into account the due date, the planning and scheduling are optimized iteratively with the rule-based algorithms complying with the machining and assembling process constraints. To make the realistic large-scale production planning scheme tailored to fit the optimization algorithms, a multi-agent system is utilized to conceptually construct a three-layer framework corresponding to three planning horizons of different task level. These planning horizons are quarter/month of product/subassembly level, week of part level, and day of operation level. With the strategy of combining top-down task decomposition and bottom-up plan update (where the quarterly orders are decomposed into the monthly, weekly, and daily tasks according to the product processing structure while the resulting plans of every layer are updated iteratively based on the bottom layer optimization), the proposed framework not only addresses the planning but also the periodic and event-driven scheduling of the processes. In this paper, a gravure printing machine is considered as a test case for evaluating the proposed framework. The simulation results with the historical data of the orders for this machine demonstrate the effectiveness of the proposed scheme on the control of the distribution of idle-time. It can also provide a resolution to tardiness penalty for small and medium sized enterprises.
  • Thumbnail Image
    Item
    Attribute-aware Semantic Segmentation of Road Scenes for Understanding Pedestrian Orientations
    (IEEE, 2018-11) Sulistiyo, M. D.; Kawanishi, Y.; Deguchi, D.; Hirayama, T.; Ide, I.; Zheng, J. Y.; Murase, H.; Computer and Information Science, School of Science
    Semantic segmentation is an interesting task for many deep learning researchers for scene understanding. However, recognizing details about objects' attributes can be more informative and also helpful for a better scene understanding in intelligent vehicle use cases. This paper introduces a method for simultaneous semantic segmentation and pedestrian attributes recognition. A modified dataset built on top of the Cityscapes dataset is created by adding attribute classes corresponding to pedestrian orientation attributes. The proposed method extends the SegNet model and is trained by using both the original and the attribute-enriched datasets. Based on an experiment, the proposed attribute-aware semantic segmentation approach shows the ability to slightly improve the performance on the Cityscapes dataset, which is capable of expanding its classes in this case through additional data training.