Context awareness in process monitoring of additive manufacturing using a digital twin

Wire Arc Additive Manufacturing allows the cost-effective manufacturing of customized, large-scale metal parts. As the post-process quality assurance of large parts is costly and time-consuming, process monitoring is inevitable. In the present study, a context-aware monitoring solution was investigated by integrating machine, temporal, and spatial context in the data analysis. By analyzing the voltage patterns of each cycle in the oscillating cold metal transfer process with a deep neural network, temporal context was included. Spatial context awareness was enabled by building a digital twin of the manufactured part using an Octree as spatial indexing data structure. By means of the spatial context awareness, two quality metrics—the defect expansion and the local anomaly density—were introduced. The defect expansion was tracked in-process by assigning detected defects to the same defect cluster in case of spatial correlation. The local anomaly density was derived by defining a spherical region of interest which enabled the detection of aggregations of anomalies. By means of the context aware monitoring system, defects were detected in-process with a higher sensitivity as common defect detectors for welding applications, showing less false-positives and false-negatives. A quantitative evaluation of defect expansion and densities of various defect types such as pore nests was enabled.

Understanding the Moderating Impact of Context-Awareness and Ubiquity on Mobile Government Services Adoption

The factors of context-awareness and mobile ubiquity are major components in the development and diffusion of any mobile technology-driven applications and services. Principally in the m-government development space, the issues of context-awareness and ubiquity are crucial if m-government initiatives are to be successful. The moderating effect of context-awareness and ubiquity on mobile government adoption is examined for 409 students from a Chinese University based on the Technology Acceptance Model. Using the Structural Equation Modeling technique, the results indicate that perceived ease of use (PEOU) was significantly related to intention to use, but perceived usefulness (PU) did not have a significant effect on mobile government adoption. The moderating analysis indicated that context-awareness significantly moderated the impact of PU but had no moderating effect on PEOU. Also, it was discovered that ubiquity was significant in moderating both the PEOU and PU on mobile government adoption. Policy implications and directions for future research are presented.

Unobtrusive Pedestrian Identification by Leveraging Footstep Sounds with Replay Resistance

The ability to identify pedestrians unobtrusively is essential for smart buildings to provide customized environments, energy saving, health monitoring and security-enhanced services. In this paper, we present an unobtrusive pedestrian identification system by passively listening to people's walking sounds. The proposed acoustic system can be easily integrated with the widely deployed voice assistant devices while providing the context awareness ability. This work focuses on two major tasks. Firstly, we address the challenge of recognizing footstep sounds in complex indoor scenarios by exploiting deep learning and the advanced stereo recording technology that is available on most voice assistant devices. We develop a Convolutional Neural Network-based algorithm and the footstep sound-oriented signal processing schemes to identify users by their footstep sounds accurately. Secondly, we design a "live" footstep detection approach to defend against replay attacks. By deriving the novel inter-footstep and intra-footstep characteristics, we distinguish live footstep sounds from the machine speaker's replay sounds based on their spatial variances. The system is evaluated under normal scenarios, traditional replay attacks and the advanced replays, which are designed to forge footstep sounds both acoustically and spatially. Extensive experiments show that our system identifies people with up to 94.9% accuracy in one footstep and shields 100% traditional replay attacks and up to 99% advanced replay attacks.

No Need of Data Pre-processing

Device-free context awareness is important to many applications. There are two broadly used approaches for device-free context awareness, i.e., video-based and radio-based. Video-based approaches can deliver good performance, but privacy is a serious concern. Radio-based context awareness applications have drawn researchers' attention instead, because it does not violate privacy and radio signal can penetrate obstacles. The existing works design explicit methods for each radio-based application. Furthermore, they use one additional step to extract features before conducting classification and exploit deep learning as a classification tool. Although this feature extraction step helps explore patterns of raw signals, it generates unnecessary noise and information loss. The use of raw CSI signal without initial data processing was, however, considered as no usable patterns. In this article, we are the first to propose an innovative deep learning–based general framework for both signal processing and classification. The key novelty of this article is that the framework can be generalised for all the radio-based context awareness applications with the use of raw CSI. We also eliminate the extra work to extract features from raw radio signals. We conduct extensive evaluations to show the superior performance of our proposed method and its generalisation.

Context Awareness and Intelligence in Cognitive Radio Networks: Design and Applications

<p>CR technology, which is the next-generation wireless communication system, improves the utilization of the overall radio spectrum through dynamic adaptation to local spectrum availability. In CR networks, unlicensed or Secondary Users (SUs) may operate in underutilized spectrum (called white spaces) owned by the licensed or Primary Users (PUs) conditional upon PUs encountering acceptably low interference levels. Ideally, the PUs are oblivious to the presence of the SUs. Context awareness enables an SU to sense and observe its operating environment, which is complex and dynamic in nature; while intelligence enables the SU to learn knowledge, which can be acquired through observing the consequences of its prior action, about its operating environment so that it carries out the appropriate action to achieve optimum network performance in an efficient manner without following a strict and static predefined set of policies. Traditionally, without the application of intelligence, each wireless host adheres to a strict and static predefined set of policies, which may not be optimum in many kinds of operating environment. With the application of intelligence, the knowledge changes in line with the dynamic operating environment. This thesis investigates the application of an artificial intelligence approach called reinforcement learning to achieve context awareness and intelligence in order to enable the SUs to sense and utilize the high quality white spaces. To date, the research focus of the CR research community has been primarily on the physical layer of the open system interconnection model. The research into the data link layer is still in its infancy, and our research work focusing on this layer has been pioneering in this field and has attacted considerable international interest. There are four major outcomes in this thesis. Firstly, various types of multi-channel medium access control protocols are reviewed, followed by discussion of their merits and demerits. The purpose is to show the additional functionalities and challenges that each multi-channel medium access control protocol has to offer and address in order to operate in CR networks. Secondly, a novel cross-layer based quality of service architecture called C2net for CR networks is proposed to provide service prioritization and tackle the issues associated with CR networks. Thirdly, reinforcement learning is applied to pursue context awareness and intelligence in both centralized and distributed CR networks. Analysis and simulation results show that reinforcement learning is a promising mechanism to achieve context awareness and intelligence. Fourthly, the versatile reinforcement learning approach is applied in various schemes for performance enhancement in CR networks.</p>

Context Awareness and Intelligence in Cognitive Radio Networks: Design and Applications

<p>CR technology, which is the next-generation wireless communication system, improves the utilization of the overall radio spectrum through dynamic adaptation to local spectrum availability. In CR networks, unlicensed or Secondary Users (SUs) may operate in underutilized spectrum (called white spaces) owned by the licensed or Primary Users (PUs) conditional upon PUs encountering acceptably low interference levels. Ideally, the PUs are oblivious to the presence of the SUs. Context awareness enables an SU to sense and observe its operating environment, which is complex and dynamic in nature; while intelligence enables the SU to learn knowledge, which can be acquired through observing the consequences of its prior action, about its operating environment so that it carries out the appropriate action to achieve optimum network performance in an efficient manner without following a strict and static predefined set of policies. Traditionally, without the application of intelligence, each wireless host adheres to a strict and static predefined set of policies, which may not be optimum in many kinds of operating environment. With the application of intelligence, the knowledge changes in line with the dynamic operating environment. This thesis investigates the application of an artificial intelligence approach called reinforcement learning to achieve context awareness and intelligence in order to enable the SUs to sense and utilize the high quality white spaces. To date, the research focus of the CR research community has been primarily on the physical layer of the open system interconnection model. The research into the data link layer is still in its infancy, and our research work focusing on this layer has been pioneering in this field and has attacted considerable international interest. There are four major outcomes in this thesis. Firstly, various types of multi-channel medium access control protocols are reviewed, followed by discussion of their merits and demerits. The purpose is to show the additional functionalities and challenges that each multi-channel medium access control protocol has to offer and address in order to operate in CR networks. Secondly, a novel cross-layer based quality of service architecture called C2net for CR networks is proposed to provide service prioritization and tackle the issues associated with CR networks. Thirdly, reinforcement learning is applied to pursue context awareness and intelligence in both centralized and distributed CR networks. Analysis and simulation results show that reinforcement learning is a promising mechanism to achieve context awareness and intelligence. Fourthly, the versatile reinforcement learning approach is applied in various schemes for performance enhancement in CR networks.</p>