An application of near infra-red fibre bragg grating as dynamic sensor in SHM of thin composite laminates
- Authors: Zohari, Mohd , Kahandawa, Gayan , Epaarachchi, Jayantha , Lau, Alan , Cook, Kevin , Canning, John
- Date: 2013
- Type: Text , Conference paper
- Relation: Structural health monitoring 2013 : a roadmap to intelligent structures : proceedings of the 9th International Workshop on Structural Health Monitoring p. 267-275
- Full Text: false
- Reviewed:
- Description: Vibration testing is an essential component in Structural Health Monitoring (SHM). It can provide vital information regarding the integrity of critical structure; for instance, it can provide information on progressive failure monitoring of composites structure in the aerospace industry. Over the past decade, there have been many successful researches showing extraordinary ability of Fiber Bragg grating (FBG) sensors as a dynamic sensor. Ability of acquiring both static and dynamic strain measurements, make FBG sensor as a good alternative to replace the conventional vibration sensors. In addition the physical size of FBG sensor provides greater access to embed them in composite structures without affecting to any properties of the composite. However, in most applications to date, people have used only the FBG with wavelength 1550 nm. Moreover, FBG sensors with this wavelength are commonly use in industries such as telecommunications and medical industries. However, there is an option of using near infra-red (NIR) FBG range which comparably cheap in term of total system design. This paper details the use of near infra-red (NIR) FBGs as dynamic sensors; a part of SHM system for the monitoring of the damages in a thin glass fiber composite plates. Results reveal that the NIR FBG range gives good response to an impact and; also to applied high frequency vibrations.
NIR fibre bragg grating as dynamic sensor : An application of 1D digital wavelet analysis for signal denoising
- Authors: Zohari, Mohd , Kahandawa, Gayan , Epaarachchi, Jayantha , Lau, Alan , Canning, John , Cook, Kevin
- Date: 2013
- Type: Text , Conference paper
- Relation: Fourth International Conference on Smart Materials and Nanotechnology in Engineering
- Full Text: false
- Reviewed:
- Description: During the past decade, many successful studies have evidently shown remarkable capability of Fiber Bragg Gratings (FBG) sensor for dynamic sensing. Most of the research works utilized the 1550 nm wavelength range of FBG sensors. However near infra-red (NIR) FBG sensors can offer the lower cost of Structural health Monitoring (SHM) systems which uses cheaper silicon sources and detectors. Unfortunately, the excessive noise levels that experienced in NIR wavelengths have caused the rejection of sensor that operating in this range of wavelengths for SHM systems. However, with the appropriate use of signal processing tools, these noisy signals can be easily ‘cleaned’. Wavelet analysis is one of the powerful signal processing tools nowadays, not only for time-frequency analysis but also for signal denoising. This present study revealed that the NIR FBG range gave good response to impact signals. Furthermore, these ‘noisy’ signals’ response were successfully filtered using one dimensional wavelet analysis.
A study of hydrodynamic pressure in the A-pillar regions of idealised and production cars
- Authors: Zimmer, Gary , Alam, Firoz , Watkins, Simon
- Date: 2004
- Type: Text , Conference paper
- Relation: Paper presented at the 2nd BSME - ASME International Conference on Thermal Engineering, Dhaka, Bangladesh : 2nd January, 2004
- Full Text: false
- Reviewed:
- Description: E1
- Description: 2003000704
A study of the A-pillar vortex of a passenger car
- Authors: Zimmer, Gary , Alam, Firoz , Watkins, Simon
- Date: 2003
- Type: Text , Conference paper
- Relation: Paper presented at the International Conference on Mechanical Engineering 2003, Dhaka, Bangladesh : 26th December, 2003
- Full Text: false
- Reviewed:
- Description: E1
- Description: 2003000641
Discover multiple novel labels in multi-instance multi-label learning
- Authors: Zhu, Yue , Ting, Kaiming , Zhou, Zhi-Hua
- Date: 2017
- Type: Text , Conference paper
- Relation: Thirty-First AAAI Conference on Artificial Intelligence p. 2977-2984
- Full Text: false
- Reviewed:
- Description: Multi-instance multi-label learning (MIML) is a learning paradigm where an object is represented by a bag of instances and each bag is associated with multiple labels. Ordinary MIML setting assumes a fixed target label set. In real applications, multiple novel labels may exist outside this set, but hidden in the training data and unknown to the MIML learner. Existing MIML approaches are unable to discover the hidden novel labels, let alone predicting these labels in the previously unseen test data. In this paper, we propose the first approach to discover multiple novel labels in MIML problem using an efficient augmented lagrangian optimization, which has a bag-dependent loss term and a bag-independent clustering regularization term, enabling the known labels and multiple novel labels to be modeled simultaneously. The effectiveness of the proposed approach is validated in experiments.
New class adaptation via instance generation in one-pass class incremental learning
- Authors: Zhu, Yue , Ting, Kaiming , Zhou, Zhi-Hua
- Date: 2017
- Type: Text , Conference paper
- Relation: 2017 IEEE International Conference on Data Mining (ICDM)
- Full Text: false
- Reviewed:
- Description: One pass learning updates a model with only a single scan of the dataset, without storing historical data. Previous studies focus on classification tasks with a fixed class set, and will perform poorly in an open dynamic environment when new classes emerge in a data stream. The performance degrades because the classifier needs to receive a sufficient number of instances from new classes to establish a good model. This can take a long period of time. In order to reduce this period to deal with any-time prediction task, we introduce a framework to handle emerging new classes called One-Pass Class Incremental Learning (OPCIL). The central issue in OPCIL is: how to effectively adapt a classifier of existing classes to incorporate emerging new classes. We call it the new class adaptation issue, and propose a new approach to address it, which requires only one new class instance. The key is to generate pseudo instances which are optimized to satisfy properties that produce a good discriminative classifier. We provide the necessary propertiesand optimization procedures required to address this issue. Experiments validate the effectiveness of this approach.
An enhancement to closed-form method for natural image matting
- Authors: Zhu, Jun , Zhang, Dengsheng , Lu, Guojun
- Date: 2010
- Type: Text , Conference paper
- Relation: Proceedings of the 2010 Digital Image Computing: Techniques and Applications p. 629-634
- Full Text: false
- Reviewed:
- Description: Natural image matting is a task to estimate fractional opacity of foreground layer from an image. Many matting methods have been proposed, and most of them are trimap-based. Among these methods, closed-form matting offers both trimap-based and scribble-based matting. However, the closed-form method causes significant errors at background-hole regions due to over-smoothing. In this paper, we identify the source of the problem and propose our solution to enhance the closed-form method. Experiments show that our enhanced method can improve the accuracy for trimap-based images and obtain similar result to the closed-form method for scribble-based matting.
Embedding-based neural network for investment return prediction
- Authors: Zhu, Jianlong , Xian, Dan , Fengxiao, , Nie, Yichen
- Date: 2022
- Type: Text , Conference paper
- Relation: 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022, Virtual online, 23-25 September 2022, 2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) p. 670-673
- Full Text: false
- Reviewed:
- Description: In addition to being familiar with policies, high investment returns also require extensive knowledge of relevant industry knowledge and news. In addition, it is necessary to leverage relevant theories for investment to make decisions, thereby amplifying investment returns. A effective investment return estimate can feedback the future rate of return of investment behavior. In recent years, deep learning are developing rapidly, and investment return prediction based on deep learning has become an emerging research topic. This paper proposes an embedding-based dual branch approach to predict an investment's return. This approach leverages embedding to encode the investment id into a low-dimensional dense vector, thereby mapping high-dimensional data to a low-dimensional manifold, so that high-dimensional features can be represented competitively. In addition, the dual branch model realizes the decoupling of features by separately encoding different information in the two branches. In addition, the swish activation function further improves the model performance. Our approach are validated on the Ubiquant Market Prediction dataset. The results demonstrate the superiority of our approach compared to Xgboost, Lightgbm and Catboost. © 2022 IEEE.
Model modification in scheduling of batch chemical processes
- Authors: Zhou, Xiaojun , Gao, David , Yang, Chunhua
- Date: 2015
- Type: Text , Conference paper
- Relation: 3rd World Congress on Global Optimization in Engineering and Science, WCGO 2013; Anhui, China; 8th-12th July 2013 Vol. 95, p. 89-97
- Full Text: false
- Reviewed:
- Description: This paper addresses the model modification in scheduling of batch chemical processes, which is widely used in current literatures. In the modified model, the capacity, storage constraints are modified and the allocation, sequence constraints are simplified. It is shown that the modified model can lead to fewer decision variables, fewer constraints, resulting in low computational complexity. Experimental results with two classical examples are given to demonstrate the effectiveness of the proposed formulation and approach. © Springer International Publishing Switzerland 2015.
A multiobjective state transition algorithm for single machine scheduling
- Authors: Zhou, Xiaojun , Hanoun, Samer , Gao, David , Nahavandi, Saeid
- Date: 2015
- Type: Text , Conference paper
- Relation: 3rd World Congress on Global Optimization in Engineering and Science, WCGO 2013; Anhui, China; 8th-12th July 2013 Vol. 95, p. 79-88
- Full Text: false
- Reviewed:
- Description: In this paper, a discrete state transition algorithm is introduced to solve a multiobjective single machine job shop scheduling problem. In the proposed approach, a non-dominated sort technique is used to select the best from a candidate state set, and a Pareto archived strategy is adopted to keep all the non-dominated solutions. Compared with the enumeration and other heuristics, experimental results have demonstrated the effectiveness of the multiobjective state transition algorithm. © Springer International Publishing Switzerland 2015.
Extracting road centrelines from binary road images by optimizing geodesic lines
- Authors: Zhou, Shaoguang , Lu, Guojun , Teng, Shyh , Zhang, Dengsheng
- Date: 2016
- Type: Text , Conference proceedings , Conference paper
- Relation: 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015; Auckland, New Zealand; 23rd-24th November 2015 Vol. 2016-November, p. 1-6
- Full Text: false
- Reviewed:
- Description: Binary road images can be obtained from remotely sensed images with the aid of classification and segmentation techniques. Extracting road centrelines from these binary images are crucial to update a Geographic Information System (GIS) database. A current state of art method of centreline extraction needs to remove road junctions and depends on the accuracy of the endpoints, leading to three main limitations: (1) causing small gaps in the roads, (2) wrongly treating short non-road segments as roads, and (3) producing centrelines of low accuracy around the road end regions. To overcome these limitations, we propose to use an iteratively searching scheme to obtain the longest geodesic line in the preprocessed road skeleton images. Several image pixels at each end of the geodesic lines were removed to avoid noise, and the remaining parts were optimized using a dynamic programming snake model. The proposed method is applied to three types of binary road images and compared with the state of art method. It shows that the proposed method is less affected by the end regions of the roads, and is effective in filling the gaps in the roads. It also has an advantage on processing short non-road segments. © 2015 IEEE.
- Description: International Conference Image and Vision Computing New Zealand
Shrinkage properties of fibre-enzyme reinforced clay
- Authors: Zhou, Limin , Xie, Yuekai , Costa, Susanga , Kandra, Harpreet
- Date: 2017
- Type: Text , Conference paper
- Relation: International Conference On Sustainable Civil Engineering Practices
- Full Text: false
- Reviewed:
- Description: Shrinkage of clay soils during drying can impose significant unfavourable effects on engineering applications. Researchers have attempted to amend drying shrinkage by mixing soil with various additives such as nanomaterials, fibre, geo-polymer etc. This paper discusses the shrinkage characteristics of an expansive clay mixed with nylon fibre and an organic enzyme. As clay is mostly used in compacted form in civil engineering applications, the study was focused on the shrinkage behaviour of compacted clay. Different percentages of nylon fibre, ranging from 0 to 1.2 percent by weight, were mixed with soil. The amount of enzyme added to each mixture was kept fixed at 0.35 g of enzyme per kg of dry soil. Compacted soil blocks were made using standard compaction procedures and cut in to rectangular specimens of size 80 x 60 x 40 mm.Compaction test results indicated that addition of fibre and enzyme can slightly improve the dry density of soil. Rectangular block specimens were allowed to dry without restraints under room temperature. Change in moisture content, linear and volumetric shrinkage and change in void ratio were investigated. Image analysis techniques were used to measure the changes in dimensions.
Enhanced multizone single-trip sand-control system successfully treats six zones in offshore Indonesia well
- Authors: Zhou, Leon , Gunawan, Indra , Jannise, Ricki , Suire, Casey , Eiman, Tyson
- Date: 2014
- Type: Text , Conference paper
- Relation: Offshore Technology Conference Asia: Meeting the Challenges for Asia's Growth, OTC ASIA 2014 p. 1799-1808
- Full Text:
- Reviewed:
- Description: Although multiple-zone, downhole sand-control tool systems have been in use since the early 1990s, these systems had been designed for jobs that only required low-pump-rates with low-pressure differentials. Multiple-zone systems capable of high fracturing pump rates and the associated differentials only recently have been introduced to the oilfield. Although these jobs are becoming more common, most of the completions have been limited to four or five treated zones. This paper presents a case history from Indonesia in which six discrete zones in an offshore deployment were treated successfully in a single trip. The challenges for this completion were numerous. Manufacturing lead time was very short, and the system would have to be adapted to the unique requirements of the completion design and the use of new components. Since the proppant and pump rating for these systems was based on five zones, rigorous analysis was necessary to ensure that a high pump rate, high differential pressure-rated single-trip, multiple-zone sand-control tool system was capable of treating six zones and that the crossover tool would survive the erosive effects of these extreme conditions. To provide assurance of the elastomeric seal integrity of the service tool, a testing program was executed for treatments to provide tracking and verification of conditions. Procedures were prepared, and equipment was retained on hand to replace the service tools, if any leaks were evident. Since system installation experience was limited in this area, gathering sufficient knowledge and experience for system deployment had to be addressed quickly. This would require sharing of lessons learned, use of experienced personnel from previous installations, and conducting of detailed training discussions between subject matter experts and service personnel. Deployment challenges and solutions, successes experienced at the well site, and the actual performance of the operations are discussed in this paper.
Metric learning-based few-shot malicious node detection for IoT backhaul/fronthaul networks
- Authors: Zhou, Ke , Lin, Xi , Wu, Jun , Bashir, Ali , Li, Jianhua , Imran, Muhammad
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE Global Communications Conference, GLOBECOM 2022, Virtual, online, 4-8 December 2022, 2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings p. 5777-5782
- Full Text: false
- Reviewed:
- Description: The development of backhaul/fronthaul networks can enable low latency and high reliability, but nodes in future networks like Internet of Things (IoT) can conduct malicious activities like flooding attack and DDoS attack, which can decrease QoS of smart backhaul/fronthaul network. Timely detection of malicious nodes in future networks is significant for low-latency backhaul/fronthaul networks. However, conventional supervised learning-based detection models require abundant malicious training samples, while capturing adequate malicious samples can not meet the requirement of timely detection. In this paper, we propose a novel few-shot malicious node detection system for improving QoS of IoT backhaul/fronthaul network, which can detect malicious nodes with unknown malicious activities through a limited number of network traffic samples. In our proposed system, we first design a fresh IoT traffic sample processing approach, which integrates normal activity samples and known malicious activity samples to generate training pairs. Then, we design a metric learning-based malicious node detection model training method, which employs a contrastive loss over distance metric to distinguish between similar and dissimilar pairs of samples. Besides, the trained model can detect nodes with unknown malicious activities by comparing real-time samples with few-shot samples of malicious nodes. Finally, the proposed system is evaluated on a real-world IoT network dataset named N-BaIoT. The exhaustive experiment results show that our model can achieve an average accuracy around 97.67 % when detecting malicious nodes with unknown malicious activities, which is comparable to state-of-the-art supervised learning models while our model only needs 5-shot samples of malicious node. © 2022 IEEE.
Video driven traffic modelling in paramics
- Authors: Zhou, Hailing , Creighton, Douglas , Lim, Cheepeng , Wei, Lei , Gao, David
- Date: 2013
- Type: Text , Conference paper
- Relation: Proceedings - UKSim 15th International Conference on Computer Modelling and Simulation, UKSim 2013 p. 525-530
- Full Text: false
- Reviewed:
- Description: With urbanization and vehicle availability, there exist many traffic problems including congestion, environmental impact and safety. In order to address these problems, we propose a video driven traffic modelling system in this paper. The system can simulate real-world traffic activities in a computer, based on traffic data recorded in videos. Video processing is employed to estimate metrics such as traffic volumes. These metrics are used to update the traffic system model, which is then simulated using the ParamicsTM traffic simulation platform. Video driven traffic modelling has widespread potential application in traffic systems, due to the convenience and reduced costs of model development and maintenance. Experiments are conducted in this paper to demonstrate the effectiveness of the proposed system. © 2013 IEEE.
- Description: 2003011214
Video driven traffic modelling
- Authors: Zhou, Hailing , Creighton, Douglas , Wei, Lei , Gao, David , Nahavandi, Saeid
- Date: 2013
- Type: Text , Conference paper
- Relation: 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013 p. 506-511
- Full Text: false
- Reviewed:
- Description: We propose Video Driven Traffic Modelling (VDTM) for accurate simulation of real-world traffic behaviours with detailed information and low-cost model development and maintenance. Computer vision techniques are employed to estimate traffic parameters. These parameters are used to build and update a traffic system model. The model is simulated using the Paramics traffic simulation platform. Based on the simulation techniques, effects of traffic interventions can be evaluated in order to achieve better decision makings for traffic management authorities. In this paper, traffic parameters such as vehicle types, times of starting trips and corresponding origin-destinations are extracted from a video. A road network is manually defined according to the traffic composition in the video, and individual vehicles associated with extracted properties are modelled and simulated within the defined road network using Paramics. VDTM has widespread potential applications in supporting traffic decision-makings. To demonstrate the effectiveness, we apply it in optimizing a traffic signal control system, which adaptively adjusts green times of signals at an intersection to reduce traffic congestion.
- Description: E1
Relevance feature mapping for content-based image retrieval
- Authors: Zhou, Guang , Ting, Kaiming , Liu, Fei , Yin, Yilong
- Date: 2010
- Type: Text , Conference paper
- Relation: 16th ACM SIGKDD Workshop on Multimedia Data Mining p. 1-10
- Full Text: false
- Reviewed:
Understanding online frequency response signatures for transformer winding deformation: Axial displacement simulation
- Authors: Zhao, Zhongyong , Islam, Syed , Hashemnia, Naser , Hu, Di , Yao, Chenguo
- Date: 2016
- Type: Text , Conference proceedings , Conference paper
- Relation: 2016 International Conference on Condition Monitoring and Diagnosis, CMD 2016; Xi'an, China; 25th-28th September 2016 p. 404-407
- Full Text: false
- Reviewed:
- Description: The power transformer is considered as the most critical and expensive device in substation, however, the irreversible transformer winding mechanical deformation can eventually develop into catastrophic failure if no further steps are taken in a proper way, which would cause the outage of transformer and the significant economic losses. Online frequency response analysis (FRA) has been proven to be a promising tool for condition monitoring and diagnosing of winding deformation. Online FRA relies on graphic comparison of signatures, but up to now, there is no standard and practical interpretation code for signatures classification and quantification. This paper particularly studies the characteristic of online FRA signatures under the winding axial displacement mode, in which the 3D finite element electromagnetic analysis and online transformer equivalent high frequency electrical model are established as auxiliary tools to precisely emulate winding axial displacement. Results of this simulation will provide guidance on understanding online frequency response signatures.
Overview of business hyper-automation
- Authors: Zhao, Xiaohui , Oseni, Taiwo , Medishetty, Bhanu
- Date: 2022
- Type: Text , Conference paper
- Relation: 18th IEEE International Conference on e-Business Engineering, ICEBE 2022, Bournemouth, UK, 14-16 October 2022, Proceedings - 2022 IEEE International Conference on e-Business Engineering, ICEBE 2022 p. 100-105
- Full Text: false
- Reviewed:
- Description: Business hyper-Automation has emerged as a new topic with the advancement of AI, machine learning, process automation, sensing technology, blockchain, etc. It starts attracting industry interest as well, as many IT giants are establishing the market of business hyper-Automation. By organically combining these technologies, business hyper-Automation promises us flexible service delivery, intelligent business scheduling, resilience to unexpected changes, and significant reduction of workforce need. Around this novel concept, we are to discuss the motivation of business hyper-Automation and typical technologies employed by it. An outlook to related research topics and the future of hyper-Automation is conducted in the end. © 2022 IEEE.
Integrating Real-Time Analytics and Situational Awareness into Business Process Management
- Authors: Zhao, Xiaohui
- Date: 2021
- Type: Text , Conference paper
- Relation: 17th IEEE International Conference on e-Business Engineering, ICEBE 2021, Guangzhou, China, 12-14 November 2021, Proceedings - 2021 IEEE International Conference on e-Business Engineering, ICEBE 2021 p. 21-26
- Full Text:
- Reviewed:
- Description: The integration of real-Time business intelligence into business process navigation is expected to boost business process management to a highly intelligent and flexible level. This advance comes with many appealing features, such as operational business intelligence, adaptive process evolution, situational awareness, etc. With such capabilities, businesses can effectively improve their customer relationships, increase revenue and maximise operational efficiency. Despite the strong demand from industry, little work has been done in attempting this integration. With the aim of filling this gap, this paper discusses the requirements for realising data-driven, context-Aware business process management with real-Time intelligence. A system architecture is proposed to illustrate this integration, and a real-Time recommendation approach is also introduced to best adapt a business process to perceived changes. © 2021 IEEE.