The Experts below are selected from a list of 174603 Experts worldwide ranked by ideXlab platform

Chaehan So - One of the best experts on this subject based on the ideXlab platform.

  • human in the loop design cycles a Process framework that integrates design sprints agile Processes and machine learning with humans
    arXiv: Human-Computer Interaction, 2020
    Co-Authors: Chaehan So
    Abstract:

    Demands on more transparency of the backbox nature of machine learning models have led to the recent rise of human-in-the-loop in machine learning, i.e. Processes that integrate humans in the training and application of machine learning models. The present work argues that this Process Requirement does not represent an obstacle but an opportunity to optimize the design Process. Hence, this work proposes a new Process framework, Human-in-the-learning-loop (HILL) Design Cycles - a design Process that integrates the structural elements of agile and design thinking Process, and controls the training of a machine learning model by the human in the loop. The HILL Design Cycles Process replaces the qualitative user testing by a quantitative psychometric measurement instrument for design perception. The generated user feedback serves to train a machine learning model and to instruct the subsequent design cycle along four design dimensions (novelty, energy, simplicity, tool). Mapping the four-dimensional user feedback into user stories and priorities, the design sprint thus transforms the user feedback directly into the implementation Process. The human in the loop is a quality engineer who scrutinizes the collected user feedback to prevents invalid data to enter machine learning model training.

Wenlong Jia - One of the best experts on this subject based on the ideXlab platform.

  • a multi hierarchy grey relational analysis model for natural gas pipeline operation schemes comprehensive evaluation
    International Journal of Industrial Engineering-theory Applications and Practice, 2012
    Co-Authors: Wenlong Jia, Enbin Liu
    Abstract:

    In the condition of satisfying Process Requirement, determining the optimum operation schemes of natural gas pipeline network is essential to improve the overall efficiency of network operation. According to the operation parameters of natural gas network, the multi-hierarchy comprehensive evaluation index system is illustrated, and the weights of each index are determined with an improved Analytic Hierarchy Process (AHP). This paper presents a multi-hierarchy grey relational analysis (GRA) method which is suitable for evaluating the multi-hierarchy index system with combining the AHP and grey relational analysis. Ultimately, the industrial application shows that multi hierarchy grey relational analysis is effective to evaluate the nature gas pipeline network operation schemes.

  • application of multi hierarchy grey relational analysis to evaluating natural gas pipeline operation schemes
    Computer Science and Information Engineering, 2011
    Co-Authors: Wenlong Jia
    Abstract:

    In the condition of satisfying Process Requirement, determining the optimum operation schemes of natural gas pipeline network is essential to improve the overall efficiency of network operation. According to the operation parameters of natural gas network, the multi-hierarchy comprehensive evaluation index system is illustrated. This paper presents a multi-hierarchy grey relational analysis method which is suitable for evaluating the multi-hierarchy index system with combining the AHP and grey relational analysis. The comprehensive evaluating mathematic model for natural gas network operation schemes is built based on the method. Ultimately, the practical application shows that multi hierarchy grey relational analysis is effective to evaluate the nature gas pipeline network operation schemes.

S Sahudin - One of the best experts on this subject based on the ideXlab platform.

  • design and development of manufacturing facilities for friction stir welding Process using conventional milling machine
    IOP Conference Series: Materials Science and Engineering, 2019
    Co-Authors: Salina Budin, N C Maideen, Koay Mei Hyie, S Sahudin
    Abstract:

    Friction stir welding (FSW) is a solid-state joining Process that has many advantages including the ability to join high strength alloy as well as dissimilar metals which are hard to be joined by conventional fusion techniques. This welding Process involves the penetration of rotating tool which consist of shoulder and prolonged by a pin into a metal plate. The Process is followed by advancing speed to weld the metal plate. However, it requires a specialized machine to perform the joining Process. A new FSW system including its tools may be costly and thus becomes the main barrier to the development of this FSW Process in industry. One of the possible solutions is by adapting the current conventional milling machine with additional rotating and feeding principles to suit the FSW Process Requirement. In this work, suitable tools, jigs and fixtures for FSW Process using conventional milling machine were designed. The design of the tool, jigs and fixtures were fabricated and tested by joining two similar plates of A6061 aluminium alloys. The investigation shows promising results with defect-free welds, good strength and smooth surface finish without gap creation between the welded plates.

Sahudin S. - One of the best experts on this subject based on the ideXlab platform.

  • Design and Development of Manufacturing Facilities for Friction Stir Welding Process using Conventional Milling Machine
    'IOP Publishing', 2019
    Co-Authors: Budin S., Maideen N.c., Hyie K.m., Sahudin S.
    Abstract:

    Friction stir welding (FSW) is a solid-state joining Process that has many advantages including the ability to join high strength alloy as well as dissimilar metals which are hard to be joined by conventional fusion techniques. This welding Process involves the penetration of rotating tool which consist of shoulder and prolonged by a pin into a metal plate. The Process is followed by advancing speed to weld the metal plate. However, it requires a specialized machine to perform the joining Process. A new FSW system including its tools may be costly and thus becomes the main barrier to the development of this FSW Process in industry. One of the possible solutions is by adapting the current conventional milling machine with additional rotating and feeding principles to suit the FSW Process Requirement. In this work, suitable tools, jigs and fixtures for FSW Process using conventional milling machine were designed. The design of the tool, jigs and fixtures were fabricated and tested by joining two similar plates of A6061 aluminium alloys. The investigation shows promising results with defect-free welds, good strength and smooth surface finish without gap creation between the welded plates. © Published under licence by IOP Publishing Ltd

So Chaehan - One of the best experts on this subject based on the ideXlab platform.

  • Human-in-the-Loop Design Cycles -- A Process Framework that Integrates Design Sprints, Agile Processes, and Machine Learning with Humans
    2020
    Co-Authors: So Chaehan
    Abstract:

    Demands on more transparency of the backbox nature of machine learning models have led to the recent rise of human-in-the-loop in machine learning, i.e. Processes that integrate humans in the training and application of machine learning models. The present work argues that this Process Requirement does not represent an obstacle but an opportunity to optimize the design Process. Hence, this work proposes a new Process framework, Human-in-the-learning-loop (HILL) Design Cycles - a design Process that integrates the structural elements of agile and design thinking Process, and controls the training of a machine learning model by the human in the loop. The HILL Design Cycles Process replaces the qualitative user testing by a quantitative psychometric measurement instrument for design perception. The generated user feedback serves to train a machine learning model and to instruct the subsequent design cycle along four design dimensions (novelty, energy, simplicity, tool). Mapping the four-dimensional user feedback into user stories and priorities, the design sprint thus transforms the user feedback directly into the implementation Process. The human in the loop is a quality engineer who scrutinizes the collected user feedback to prevents invalid data to enter machine learning model training.Comment: To be published in: Lecture Notes in Artificial Intelligence, 1st International Conference on Artificial Intelligence in HCI, AI-HCI, Held as Part of HCI International 2020, Kopenhagen, Denmark, July 19-24, Springe