Search results

Object detection models have gained considerable popularity as they aid in lot of applications, like monitoring, video surveillance, etc. Object detection through the video tracking faces lot of challenges, as most of the videos obtained as the real time stream are affected due to the environmental factors.

This research develops a system for crowd tracking and crowd behaviour recognition using hybrid tracking model. The input for the proposed crowd tracking system is high density crowd videos containing hundreds of people. The first step is to detect human through visual recognition algorithms. Here, a priori knowledge of location point is given as input to visual recognition algorithm. The visual recognition algorithm identifies the human through the constraints defined within Minimum Bounding Rectangle (MBR). Then, the spatial tracking model based tracks the path of the human object movement in the video frame, and the tracking is carried out by extraction of color histogram and texture features. Also, the temporal tracking model is applied based on NARX neural network model, which is effectively utilized to detect the location of moving objects. Once the path of the person is tracked, the behaviour of every human object is identified using the Optimal Support Vector Machine which is newly developed by combing SVM and optimization algorithm, namely MBSO. The proposed MBSO algorithm is developed through the integration of the existing techniques, like BSA and MBO.

The dataset for the object tracking is utilized from Tracking in high crowd density dataset. The proposed OSVM classifier has attained improved performance with the values of 0.95 for accuracy.

This paper presents a hybrid high density video tracking model, and the behaviour recognition model. The proposed hybrid tracking model tracks the path of the object in the video through the temporal tracking and spatial tracking. The features train the proposed OSVM classifier based on the weights selected by the proposed MBSO algorithm. The proposed MBSO algorithm can be regarded as the modified version of the BSO algorithm.

The purpose of this paper is to develop a generic framework for hybrid (integrated deployment of system dynamics and discrete event simulation) simulation which can be applied in the healthcare domain.

As hybrid simulation in an organisational context is a new topic with limited available data on deployment of hybrid simulation in organisational context, an inductive approach has been applied. On the basis of knowledge induced from literature, a generic conceptual framework for hybrid simulation has been developed. The proposed framework is demonstrated using an explanatory case study comprising an accident and emergency (A&E) department.

The framework provided detailed guidance for the development of a hybrid model of an A&E case study. Findings of this case study suggest that the hybrid model was more efficient in capturing behavioural impact on operational performances.

The framework is limited to only SD and DES; as agent‐based is another simulation method which is emerging as a promising tool for analysing problems such as spread of infectious diseases in healthcare context, inclusion of this into the framework will enhance the utility of the framework.

This framework will aid in the development of hybrid models capable of comprehending both detail as well as dynamic complexity, which will contribute towards a deeper understanding of the problems, resulting in more effective decision making.

It is expected that this research will encourage those engaged in simulation (e.g. researchers, practitioners, decision makers) to realise the potential of cross‐fertilisation of the two simulation paradigms.

Currently, there is no conceptual framework which provides guidance for developing hybrid models. In order to address this gap, this paper contributes by proposing a conceptual framework for hybrid simulation for the healthcare domain.

The purpose of this paper is to describe an innovative international management programme that has been developed across four countries for Master-level students. It first analyses the advantages and disadvantages of two of the most common forms of internationalisation in higher education; the student exchange and full-scale offshore campus model. It then shows how one programme at Grenoble Ecole de Management (GEM) has been designed to capture the best parts of both models in the creation of a hybrid, transcontinental programme. This has resulted in the creation of high quality international education for a large number of students whilst further developing a stronger alliance network between faculties and the business community.

The paper analyses the advantages and disadvantages of two forms of internationalisation. From there, it draws upon a case study of a hybrid programme based on discussions with faculty and students from four internationally accredited business schools in Vancouver, New York, Grenoble and Beijing. It is supplemented with research on the development of international higher education.

International exchange programmes and offshore international campuses can enrich the learning experience for students. However, there are limitations to both models. A hybrid model, though more complex to develop may have a much deeper impact on student learning and faculty development while also offering graduates a greater number of international employment opportunities. The paper outlines some best practices and preliminary learning outcomes.

The transcontinental project is relatively new being in its third year. Initial results are very positive, but the full implications will be understood in the coming years.

The paper outlines a framework for joint academic programmes overseas. It demonstrates that by assessing the pros and cons of different forms of international development, a third way can be designed to ensure a richer experience for students, faculty and the business community.

The programmes are designed to include a greater number of stakeholders and involve teaching, research and corporate participation. This contrasts with many international ventures in higher education institutions that may deal with only one aspect. The paper gives a clear framework for the creation of such programmes. It will be of value to academics, administrators and directors wishing to innovate in their international development for the benefit of their students and faculty.

Brain tumor segmentation and classification is the interesting area for differentiating the tumorous and the non-tumorous cells in the brain and classifies the tumorous cells for identifying its level. The methods developed so far lack the automatic classification, consuming considerable time for the classification. In this work, a novel brain tumor classification approach, namely, harmony cuckoo search-based deep belief network (HCS-DBN) has been proposed. Here, the images present in the database are segmented based on the newly developed hybrid active contour (HAC) segmentation model, which is the integration of the Bayesian fuzzy clustering (BFC) and the active contour model. The proposed HCS-DBN algorithm is trained with the features obtained from the segmented images. Finally, the classifier provides the information about the tumor class in each slice available in the database. Experimentation of the proposed HAC and the HCS-DBN algorithm is done using the MRI image available in the BRATS database, and results are observed. The simulation results prove that the proposed HAC and the HCS-DBN algorithm have an overall better performance with the values of 0.945, 0.9695 and 0.99348 for accuracy, sensitivity and specificity, respectively.

The proposed HAC segmentation approach integrates the properties of the AC model and BFC. Initially, the brain image with different modalities is subjected to segmentation with the BFC and AC models. Then, the Laplacian correction is applied to fuse the segmented outputs from each model. Finally, the proposed HAC segmentation provides the error-free segments of the brain tumor regions prevailing in the MRI image. The next step is to extract the useful features, based on scattering transform, wavelet transform and local Gabor binary pattern, from the segmented brain image. Finally, the extracted features from each segment are provided to the DBN for the training, and the HCS algorithm chooses the optimal weights for DBN training.

The experimentation of the proposed HAC with the HCS-DBN algorithm is analyzed with the standard BRATS database, and its performance is evaluated based on metrics such as accuracy, sensitivity and specificity. The simulation results of the proposed HAC with the HCS-DBN algorithm are compared against existing works such as k-NN, NN, multi-SVM and multi-SVNN. The results achieved by the proposed HAC with the HCS-DBN algorithm are eventually higher than the existing works with the values of 0.945, 0.9695 and 0.99348 for accuracy, sensitivity and specificity, respectively.

This work presents the brain tumor segmentation and the classification scheme by introducing the HAC-based segmentation model. The proposed HAC model combines the BFC and the active contour model through a fusion process, using the Laplacian correction probability for segmenting the slices in the database.

The purpose of this paper is to investigate the market readiness to adopt the Cloud as the future ERP platform, by using the analytic hierarchy process (AHP) decision support methodology.

Interviewing is conducted on the convenient sample, of enterprises from various industries. The interview is conducted through expert telephone interview and self-administered questionnaire. Results are then used as a basis for forming the weight factors necessary for the AHP decision model. Data are analyzed and synthesized using AHP and Expert Choice.

Results demonstrate a huge interest for TCO reduction, but also a concern for data privacy and availability. Large enterprises want their data on local servers, while smaller companies tend to act as “first adopters”, mainly because of the cost benefits that Cloud offers. Finally, vendors see the hybrid solutions as the most suitable approach for the overall market, at least while current Cloud obstacles exist.

This research does not aim to answer the question what is the best solution for a particular industry. Instead, it assumes the general approach, which answers the question what would in general be the adequate solution for the SME and how much are SMEs ready to adopt the ERP in the Cloud. A further research is necessary to validate these results in practice. That research should be industry specific, i.e. narrowed to one industry only. Then, it would be possible to answer the question what is the best solution for high-tech SMEs.

This paper summarizes Cloud pros and cons useful for decision makers to establish a starting point for IT reorganization. Additionally, AHP results provide some indications of the market's perception regarding Cloud and ERP, while vendors' statements about ERP-Cloud solutions provide an interesting glimpse of the ERP market in the next few years.

Market demands constant flexibility and cost effectiveness, forcing companies to adapt faster than ever. Therefore, there is a significant risk for first adopters and their business if they adopt an inadequate solution. This paper offers a high-level overview of the SME's market understanding and willingness to adopt ERP in the Cloud idea, and it demonstrates how the AHP decision support methodology can be used to assess the readiness of enterprises to adopt the Cloud-ERP solution.

Rolling element bearings (REBs) are commonly used in rotating machinery such as pumps, motors, fans and other machineries. The REBs deteriorate over life cycle time. To know the amount of deteriorate at any time, this paper aims to present a prognostics approach based on integrating optimize health indicator (OHI) and machine learning algorithm.

Proposed optimum prediction model would be used to evaluate the remaining useful life (RUL) of REBs. Initially, signal raw data are preprocessing through mother wavelet transform; after that, the primary fault features are extracted. Further, these features process to elevate the clarity of features using the random forest algorithm. Based on variable importance of features, the best representation of fault features is selected. Optimize the selected feature by adjusting weight vector using optimization techniques such as genetic algorithm (GA), sequential quadratic optimization (SQO) and multiobjective optimization (MOO). New OHIs are determined and apply to train the network. Finally, optimum predictive models are developed by integrating OHI and artificial neural network (ANN), K-mean clustering (KMC) (i.e. OHI–GA–ANN, OHI–SQO–ANN, OHI–MOO–ANN, OHI–GA–KMC, OHI–SQO–KMC and OHI–MOO–KMC).

Optimum prediction models performance are recorded and compared with the actual value. Finally, based on error term values best optimum prediction model is proposed for evaluation of RUL of REBs.

Proposed OHI–GA–KMC model is compared in terms of error values with previously published work. RUL predicted by OHI–GA–KMC model is smaller, giving the advantage of this method.

Based on the inverse kinematics and task space dynamic model, this paper aims to design a high-precision trajectory tracking controller for a 2-DoF translational parallel manipulator (TPM) driven by linear motors.

The task space dynamic model of a 2-DoF TPM is derived using Lagrangian equation of the first type. A task space dynamic model-based feedforward controller (MFC) is designed, which is combined with a cascade PID/PI controller and velocity feedforward controller (VFC) to construct a hybrid PID/PI+VFC/MFC controller. The hybrid controller is implemented in MATLAB/dSPACE real-time control platform. Experiment results are given to validate the effectiveness and industrial applicability of the hybrid controller.

The MFC can compensate for the nonlinear dynamic characteristics of a 2-DoF TPM and achieve better tracking performance than the conventional acceleration feedforward controller (AFC).

The task space dynamic model-based hybrid PID/PI+VFC/MFC controller is proposed for a 2-DoF linear-motor-driven TPM, which reduces the tracking error by at least 15 percent compared with conventional hybrid PID/PI+VFC/AFC controller. This control scheme can be extended to high-speed and high-precision trajectory tracking control of other parallel manipulators by reprogramming the feedforward signals of traditional cascade PID/PI controller.

This paper aims to solve the problems of the synchronization between branches and the uncertainties such as joint friction, load variation and external interference of a hybrid mechanism. The controller is used to improve the synchronization and robustness of the hybrid mechanism system and achieve both finite time convergence and chattering-free sliding mode.

First, the dynamic model of hybrid mechanism containing lumped uncertainties is formulated by the Lagrange method, and a composite error based on coupling synchronization error and the end-effector tracking error is set up in the task space. Then, by combining the finite time super twisting sliding mode control algorithm, a composite error-based finite time super twisting sliding mode synchronous control law is designed to make the end-effector tracking error and coupling synchronization error achieve better tracking performance and convergence performance. Finally, the Lyapunov stability of the control law and the finite-time convergence of the composite error are proved theoretically.

To verify the effectiveness of the proposed control method, simulations and experiments for the prototype system of the hybrid mechanism are conducted. The results show that the proposed control method can achieve better tracking performance and convergence performance.

This is a new innovation for a hybrid mechanism containing lumped uncertainties to improve the robustness, convergence performance, tracking performance and synchronization of the system.

This paper aims to propose and implement an integrated augmented-reality (AR)-aided assembly environment to incorporate the interaction between real and virtual components, so that users can obtain a more immersive experience of the assembly simulation in real time and achieve better assembly design.

A component contact handling strategy is proposed to model all the possible movements of virtual components when they interact with real components. A novel assembly information management approach is proposed to access and modify the information instances dynamically corresponding to user manipulation. To support the interaction between real and virtual components, a hybrid marker-less tracking method is implemented.

A prototype system has been developed, and a case study of an automobile alternator assembly is presented. A set of tests is implemented to validate the feasibility, efficiency, accuracy and intuitiveness of the system.

The prototype system allows the users to manipulate and assemble the designed virtual components to the real components, so that the users can check for possible design errors and modify the original design in the context of their final use and in the real-world scale.

This paper proposes an integrated AR simulation and planning platform based on hybrid-tracking and ontology-based assembly information management. Component contact handling strategy based on collision detection and assembly feature surfaces mating reasoning is proposed to solve component degree of freedom.

During flight, a small-size autonomous helicopter will suffer external disturbance that is wind gust. Moreover, the small-size helicopter can carries limited payload or battery. Therefore control system of an autonomous helicopter should be able to eliminate external disturbance and optimize energy consumption. The purpose of this paper is to propose a hybrid controller structure to control a small-size autonomous helicopter capable to eliminate external disturbance and optimize energy consumption. The proposed control strategy comprise of two components, a linear component to stabilize the nominal linear system and a discontinuous component to guarantee the robustness. An integral control is included in the system to eliminate steady state error and tracking reference input.

This research started with derived mathematic model of the small-size helicopter that will be controlled. Based on the obtained mathematic model, then design of a hybrid controller to control the autonomous helicopter. The hybrid controller was designed based on optimal controller and sliding mode controller. The optimal controller as main controller is used to stabilize the nominal linear system and a discontinuous component based on sliding mode controller to guarantee the robustness.

Performance of the proposed controller was tested in simulation. The hybrid controller performance was compared with optimal controller performance. The hybrid controller has better performance compared with optimal controller. Results of the simulation shows that the proposed controller has good performance and robust against external disturbances. The proposed controller has better performance in rise time, settling time and overshoot compared with optimal controller response both for step input response and tracking capability.

Hybrid controller to control small-size helicopter has not reported yet. In this research new hybrid controller structure for a small size autonomous helicopter was proposed.