Image classification tasks in scientific research often struggle with limited data, particularly when few images are available per class, necessitating effective data augmentation strategies. For snakes and other string-shaped objects, traditional augmentation methods such as flipping, adding noise, or altering colour prove inadequate in enhancing classification accuracy. This paper introduces KGOT (Keypoint-Guided Ophidian Transformation), a novel image augmentation technique designed to generate realistic, non-linear transformations of string-shaped objects. KGOT first straightens the snake image, then warps it according to a reference curve defined by key points, effectively inverting the straightening process. By utilizing advanced curve interpolation, pixel mapping, and post-processing techniques, KGOT ensures smooth, biologically plausible deformations while preserving important individual-specific features. Our experiments demonstrate that KGOT-augmented data increase accuracy compared to the traditional augmentation method using geographic transformation techniques. Although some limitations persist in scenarios where snake bodies overlap, the success of KGOT augmentation provides valuable information on factors that improve classification performance. This approach holds promise not only for snake individual identification but also for a broader range of applications involving string-shaped object classification tasks.

The defect on the fabric surface is one of the important factors affecting the quality of fabrics. Defect detection becomes the core means of quality control. Current deep-Iearning-based defect detection methods present a significant challenge in detection accuracy due to the diversity of fabric patterns and the scarcity of defect samples. Inspired by the transfer-learning paradigm, this article proposes a novel YOLOv7-based fine-tuning method for fabric defect detection. Specifically, we first employ a well-trained object detection network (i.e. YOLOv7) as a benchmark model to locate and classify defect-picking points. Considering the fabrics are mostly occluded and shaded, we therefore introduce a multi-channel attention mechanism and design the corresponding loss function. Finally, we manually clean a fabric defect dataset and use it to fine-tune the YOLOv7. Extensive experiments tested on public datasets show that our fine-tuned YOLOv7 improves mAP by 3.5%, precision by 6.3%, and recall rate by 5.7% compared to the baseline model YOLOv7. Especially, our fine-tuning method leads to a 6 MB reduction in model size. Further ablation studies demonstrate the effectiveness and contribution of our designs toward the whole network model.

With the acceleration of urbanization, climate change, and population growth, the global electricity demand shows a significant upward trend. Accurate short-term load forecasting (STLF) plays a vital role in optimizing the operation of the electrical distribution system. Although recent deep learning-based short-term load forecasting models have shown significant advantages, achieving accurate load forecasting remains a daunting challenge as power load demand is affected by many external environmental factors and the inherent defects of traditional forecasting models such as recurrent neural networks (RNNs) and support vector machine (SVM). In order to tackle this challenge, this paper proposes a transformer-based short-term load forecasting model. It takes loads in distributed feeders as forecasting objects and makes full use of the self-attention mechanism to capture the long-term dependency and complex nonlinear characteristics of load data. Experimental results show that the model performs well in processing complex time-series data and load fluctuations in different seasons. It has strong generalization ability and provides a new solution for forecasting distribution feeder load.

Fault detection in mechatronic transmissions is particularly challenging due to the nonstationary nature of monitoring signals arising from complex operating conditions, coupled with the high-safety requirements that limit the availability of fault data. Sparse linear parameter varying autoregressive moving average (Spa LPV-ARMA) model is a powerful tool for dealing with nonstationary time series, and good fitting results can be achieved through the basis function expansion, where parameters of the model are associated with additional variables. However, current research on Spa LPV-ARMA model only considers single basis function, overlooking the potential complementarity of multiple basis functions. This article proposes a novel enhanced Spa LPV-ARMA model with ensemble basis for mechatronic transmission fault detection. The proposed model incorporates the concept of ensemble learning by combining models with different basis functions, and a stepwise approach is utilized to select the models to be combined. The rational choice of the combination scale allows the ensemble model to have fewer parameters with higher accuracy. Simulation and experimental studies in mechatronic transmission are conducted, verifying that the proposed ensemble basis Spa LPV-ARMA model exhibits higher modeling accuracy and fault detection performance.

Industrial asset management (IAM) is crucial for the sustainability and efficiency of industries that depend on significant infrastructure, especially pipelines. Pipelines are vital assets in the global energy supply chain, transporting oil, natural gas, and chemical products, and their maintenance is essential to prevent severe environmental and economic consequences. However, current methods such as manual visual inspections are limited by their invasiveness, the requirement for periodic shutdowns, and a lack of real-time accuracy. These limitations present substantial challenges to effective IAM. This paper introduces an innovative digital twin ecosystem integrated with information and communication technology to enhance IAM for pipelines. This ecosystem creates a dynamic, interactive digital twin that accurately reflects the physical state of pipelines, bolstered by real-time data transmission from sensors. The ecosystem comprises physical pipelines equipped with sensors, a comprehensive data knowledge library that records and updates damage information, a virtual pipeline twin, and an interactive platform that facilitates detailed visualization and interaction. Through a detailed case study of pipeline damage detection on cracks and corrosion using visual imaging techniques, this paper demonstrates enhanced results and visualizations compared to existing methods. The observed damage features sharper contrasts, higher resolution, and clearer boundaries in affected areas, significantly improving the accuracy of damage localization. Additionally, the relative accuracy of the calculated damage stress intensity factor by the virtual twin model reaches 95%. In summary, the capabilities for real-time, remote interaction and comprehensive visualization within the digital twin ecosystem significantly enhance the management efficiency of digital and intelligent pipeline IAM.

Recently the machine learning-enabled modeling technology has become a powerful tool to develop data-driven models for explaining, predicting, and describing system behaviors. In particular, it has become a key tool for developing data-driven models for emerging digital twin development which demands the living models for simulating system behaviors. However, such data-driven models carry a fatal deficiency: once the operational environments changed, the model may hardly work well or even becomes useless. This paper attempts to address this issue by proposing to apply transfer learning techniques to develop lifetime robust models for real-world applications. After laying out problems and the reasons of model performance degradation, this paper presents a framework for developing lifetime predictive models for digital twin. A show case from our on-going research project along with the preliminary results demonstrates the feasibility and usefulness of the proposed predictive modeling methods.

Modeling system behavior plays a vital role in controlling systems and in monitoring systems health. Recently the machine learning-enabled modeling technology has become a powerful technique and tool for developing models for explaining, predicting, and describing system behaviors. In particular, the machine learning-enabled predictive modeling methods have been widely applied to develop the data-driven models from the “big” data in different applications such as system prognostics, system control, and system health management. Over last decade, we have worked on a research program, machine learning-enabled modeling technologies, focusing on the application of machine learning to real-world problems such as control, prognostics, and fault diagnostics. The developed modeling methodologies can help building the machine lerning0vased models form large-sized operational historic data for various domain applications. This paper attempts to summarize the challenge issues facing us and the solutions for addressing these issues. On the same time, the paper also discusses some remaining challenges and future directions.

Fault detection, diagnostics, and prognostics (FDD&P) ensure the operation efficiency and safety of engineering systems. In the building domain, they can help significantly reduce energy consumption and improve occupant comfort. Specifically, prognostics are becoming increasingly important as a pro-active fault prevention strategy through continuously monitoring the health of energy systems. In this article, we develop a machine learning-based method for building systems. The proposed method can help develop predictive models from historical operation and maintenance data. After the detailed description of the proposed machine learning-based prognostic method, a case study involving prognostics on central heating and cooling plant (CHCP) equipment is provided. To this end, a year's worth of sensor and actuator data from four boilers and five chillers of a CHCP in Ottawa, Canada are collected. The plant operators are interviewed to understand how they handle failure events, and their logbooks are reviewed to extract the date and time of the recorded failure events. The sensor and actuator data up to two weeks prior to each of these failure events are used to develop regression tree models that predict time to failure (TTF). The results indicate that about half of the modeled failure events could be accurately predicted by looking at the data available in the distributed control system. Finally, the future work is outlined.

This paper presents a novel case-based reasoning (CBR) application to crowd-scale deliberation. We propose a CBR approach to facilitating online discussion for crowd-scale deliberation. The objective is to smooth the discussion by avoiding flaming and to efficiently achieve a consensus. Accordingly, several challenging issues are addressed, including case definition and its structure, case creation, and implementation by incorporating with COLLAGREE, a crowd-scale deliberation platform supporting online discussion with the help of facilitators. After introducing an overview of the crowd-scale deliberation and the COLLAGREE, the paper presents the details of the proposed CBR approach for facilitation of online discussion along with some preliminary results. The feasibility of CBR-based facilitation support for crowd-scale deliberations is demonstrated.

Fault Detection, Diagnostics and Prognostics (FDD&P) is attracting a lot of attention from building operators and researchers because it can help greatly improve the performance of building operations by reducing energy consumption for heating, ventilation and air-conditioning (HVAC) while improving occupant comfort at the same time. However, FDD&P for building operations remains with many challenges due to special operation environments of HVAC systems. These challenges include `tolerance or ignorance' of failures in long-haul operations, lack of operation regulations, and even lack of documents for HVAC failure mode and effect analysis (FMEA), which is a systematic method of identifying and preventing system, product and process problems. To address some of these challenges, we propose to develop a FMEA for HVAC by exploring work orders generated by building energy management systems (BEMS) using a data mining approach. With the developed HVAC FMEA, it is possible to conduct pre-FDD&P procedures to improve HVAC maintenance and to select the high impact failures in order to acquire the operation data for selected failures and develop machine learning-based predictive models to predict a failure before it occurs and isolate the root component of a given failure. In this paper we report some preliminary results in developing an HVAC FMEA tool from a large number of work orders obtained from a BEMS in routine operations. The developed HVAC FMEA will be used as a guidance tool for data gathering and developing data-driven models for building HVAC FDD&P.

It is a great pleasure to welcome you to the 2016 IEEE 20thInternational Conference on Computer Supported Cooperative Work in Design (CSCWD 2016), which takes place at Qianhu Hotel, Nanchang, China, from May 4thto 6th, 2016.

A grade crossing is defined as an intersection between a roadway and a railway at the same elevation or grade. Multiple new prevention measures have been implemented to reduce the number of train-vehicle collisions; however, crossing safety is still a major issue as accidents still frequently occur. The push for data-driven models to evaluate risks at grade crossings has also increased to keep up with the changing technologies. There are many different protection types (gates with bells, cross-buck, stop-sign, mirrors and etc.) that serve to warn or stop oncoming traffic. Many attributes have an inherent impact on accident frequency; including the protection type, train speed, traffic volume and e.t.c. To address which factors are most important, we propose a data-driven modeling method to effectively analyze the impact of multiple factors that affect crossing safety and subsequently provide scientific insight for key factors for enhancing crossing safety. In this work, the Canadian crossing accident database for the years of 2004 – 2013 was used with additional generated features to enhance the scope of the study. These include features that were computed using GIS and sightline measurements. Data-driven modeling using RandomForests were used to rank and analyze 21 attributes for each protection type. From the analysis results it is possible to identify which key factors have the highest influence on improving safety and collision prediction at grade crossings.

The need for higher equipment availability and lower maintenance cost is driving the development and integration of prognostic and health management (PHM) systems. Taking advantage of advances in sensor technologies, PHM systems enable a predictive maintenance strategy through continuously monitoring the health of complex systems. The core of PHM technology is prognostic which is able to estimate time to failure (TTF) for the monitored components or systems using the built-in predictive models. In this paper, the state of the art of TTF estimation will be first reviewed. After introduction of traditional methods of TTF estimation, we will present the developed approaches for estimating TTF, including classification, regression, on-demand regression, Particle Filtering (PF)-based method, and so on. The main purpose of this paper is to summarize the work on TTF estimation technologies developed in the past decade.

Stereo vision is an active research topic in computer vision. Point Grey®Bumblebee®and digital single-lens reflex camera (DSLR) are normally found in the stereo vision research, they are robust but expensive. Open source electronic prototyping platforms such as Arduino and Raspberry Pi are interesting products, which allows students or researchers to custom made inexpensive experimental equipment for their research projects. This paper describes the intelligent stereo camera mobile platform developed in our research using Pi and camera modules and presents the concept of using inexpensive open source parts for robotic stereo vision research work in details.

What operation instruments interact with are human tissues and organs in virtual surgery. Because its impedance is nonlinear and unpredictable, the haptic interaction is difficult to be stable, especially when interacting with rigid tissues such as bone. To solve this difficult problem, this paper presents a sliding mode control algorithm based on Lyapunov theory to realize stable operation for virtual surgery which is never seen in previous research. The simulation results show that 1) the haptic interaction can remain stable when interacting with both soft tissues and large impedance tissues such as bone; 2) the haptic interaction can remain stable even when operation instruments interact with nonlinear impedance tissues.

Unexpected failures of complex equipment such as trains or aircraft introduce superfluous costs, disrupt operation, have an effect on consumer's satisfaction, and potentially decrease safety in practice. One of the objectives of prognostics and health management (PHM) systems is to help reduce the number of unexpected failures by continuously monitoring the components of interest and predicting their failures sufficiently in advance to allow for proper planning. In other words, PHM systems may help turn unexpected failures into expected ones. Recent research has demonstrated the usefulness of data mining to help build prognostic models for PHM but also has identified the need for new model evaluation methods that take into account the specificities of prognostic applications. This paper investigates this problem. First, it reviews classical and recent methods to evaluate data mining models and it explains their deficiencies with respect to prognostic applications. The paper then proposes a novel approach that overcomes these deficiencies. This approach integrates the various costs and benefits involved in prognostics to quantify the cost saving expected from a given prognostic model. From the end user's perspective, the formula is practical as it is easy to understand and requires realistic inputs. The paper illustrates the usefulness of the methods through a real-world case study involving data-mining prognostic models and realistic costs/benefits information. The results show the feasibility of the approach and its applicability to various prognostic applications.

E-commerce is a kind of commercial activities characterizing doing business via network. Along with the rapid advancement of wireless network, e-commerce witnessed a surprising flourish. Its applications appeared in a quite extensive range, and almost everything connected to internet could be transacted by means of e-commerce. In the near future, e-commerce in china tends to develop toward specialization, individuation, internationalization, inosculation and regionalization. Meantime, problems of credit, standardized commercial environment and supportability of network may possibly put hurdles on the march of our e-commerce.

This paper presents an approach to designing and developing knowledge bases in e-Learning systems. We explore the use of Protégé 2000 as a knowledge editor for course material, with the addition of Web Service interfaces on top of it to facilitate retrieval of the content. Protégé 2000 provides an extensible infrastructure and allows the easy construction of domain ontologies, customized data entry forms, and provides an API that can easily be extended by Web Services for the purpose of dynamic course material creation. The use of ontology and Web Services makes the knowledge bases for e-Learning sharable, reusable, and interoperable with other technologies, such as .Net, which have standard Web Service implementations.

This paper describes a successful but challenging application of data mining in the railway industry. The objective is to optimize maintenance and operation of trains through prognostics of wheel failures. In addition to reducing maintenance costs, the proposed technology will help improve railway safety and augment throughput. Building on established techniques from data mining and machine learning, we present a methodology to learn models to predict train wheel failures from readily available operational and maintenance data. This methodology addresses various data mining tasks such as automatic labeling, feature extraction, model building, model fusion, and evaluation. After a detailed description of the methodology, we report results from large-scale experiments. These results clearly show the great potential of this innovative application of data mining in the railway industry.