Abstract: E-learning platforms, such as Blackboard have two major shortcomings: limited data capture as a result of the limitations of SCORM (Shareable Content Object Reference Model), and lack of incorporation of Artificial Intelligence (AI) and machine learning algorithms which could lead to better course adaptations. With the recent development of Experience Application Programming Interface (xAPI), a large amount of additional types of data can be captured and that opens a window of possibilities from which online education can benefit. In a corporate setting, where companies invest billions on the learning and development of their employees, some learner behaviours can be troublesome for they can hinder the knowledge development of a learner. Behaviours that hinder the knowledge development also raise ambiguity about learner’s knowledge mastery, specifically those related to gaming the system. Furthermore, a company receives little benefit from their investment if employees are passing courses without possessing the required knowledge and potential compliance risks may arise. Using xAPI and rules derived from a state-of-the-art review, we identified three learner behaviours, primarily related to guessing, in a corporate compliance course. The identified behaviours are: trying each option for a question, specifically for multiple-choice questions; selecting a single option for all the questions on the test; and continuously repeating tests upon failing as opposed to going over the learning material. These behaviours were detected on learners who repeated the test at least 4 times before passing the course. These findings suggest that gauging the mastery of a learner from multiple-choice questions test scores alone is a naive approach. Thus, next steps will consider the incorporation of additional data points, knowledge estimation models to model knowledge mastery of a learner more accurately, and analysis of the data for correlations between knowledge development and identified learner behaviours. Additional work could explore how learner behaviours could be utilised to make changes to a course. For example, course content may require modifications (certain sections of learning material may be shown to not be helpful to many learners to master the learning outcomes aimed at) or course design (such as the type and duration of feedback).
Abstract: In this paper we present the design and the implementation of a target tracking system where the target is set to be a moving person in a video sequence. The system can be applied easily as a vision system for mobile robot. The system is composed of two major parts the first is the detection of the person in the video frame using the SVM learning machine based on the “HOG” descriptors. The second part is the tracking of a moving person it’s done by using a combination of the Kalman filter and a modified version of the Camshift tracking algorithm by adding the target motion feature to the color feature, the experimental results had shown that the new algorithm had overcame the traditional Camshift algorithm in robustness and in case of occlusion.
Abstract: This research aims to design and build a wet etching system, which is suitable for anisotropic wet etching, in order to reduce etching time, to reduce hillocks on the etched surface (to reduce roughness), and to create a 45-degree wall angle (micro-mirror). This study would start by designing a wet etching system. There are four main components in this system: an ultrasonic cleaning, a condenser, a motor and a substrate holder. After that, an ultrasonic machine was modified by applying a condenser to maintain the consistency of the solution concentration during the etching process and installing a motor for improving the roughness. This effect on the etch rate and the roughness showed that the etch rate increased and the roughness was reduced.
Abstract: A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.
Abstract: In the last decade, a new industrial revolution seems to be emerging, supported -once again- by the rapid advancements of Information Technology in the areas of Machine-to-Machine (M2M) communication permitting large numbers of intelligent devices, e.g. sensors to communicate with each other and take decisions without any or minimum indirect human intervention. The advent of these technologies have triggered the emergence of a new category of hybrid (cyber-physical) manufacturing systems, combining advanced manufacturing techniques with innovative M2M applications based on the Internet of Things (IoT), under the umbrella term Industry 4.0. Even though the topic of Industry 4.0 has attracted much attention during the last few years, the attempts of providing a systematic literature review of the subject are scarce. In this paper, we present the authors’ initial study of the field with a special focus on the use and applications of Industry 4.0 principles in material handling automations and in-house logistics. Research shows that despite the vivid discussion and attractiveness of the subject, there are still many challenges and issues that have to be addressed before Industry 4.0 becomes standardized and widely applicable.
Abstract: Data assets protection is a crucial issue in the
cybersecurity field. Companies use logical access control tools to
vault their information assets and protect them against external
threats, but they lack solutions to counter insider threats. Nowadays,
insider threats are the most significant concern of security analysts.
They are mainly individuals with legitimate access to companies
information systems, which use their rights with malicious intents.
In several fields, behavior anomaly detection is the method used by
cyber specialists to counter the threats of user malicious activities
effectively. In this paper, we present the step toward the construction
of a user and entity behavior analysis framework by proposing a
behavior anomaly detection model. This model combines machine
learning classification techniques and graph-based methods, relying
on linear algebra and parallel computing techniques. We show the
utility of an ensemble learning approach in this context. We present
some detection methods tests results on an representative access
control dataset. The use of some explored classifiers gives results
up to 99% of accuracy.
Abstract: This paper presents a Machine Learning (ML) approach to support Meningitis diagnosis in patients at a children’s hospital in Sao Paulo, Brazil. The aim is to use ML techniques to reduce the use of invasive procedures, such as cerebrospinal fluid (CSF) collection, as much as possible. In this study, we focus on predicting the probability of Meningitis given the results of a blood and urine laboratory tests, together with the analysis of pain or other complaints from the patient. We tested a number of different ML algorithms, including: Adaptative Boosting (AdaBoost), Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Random Forest and Support Vector Machines (SVM). Decision Tree algorithm performed best, with 94.56% and 96.18% accuracy for training and testing data, respectively. These results represent a significant aid to doctors in diagnosing Meningitis as early as possible and in preventing expensive and painful procedures on some children.
Abstract: This paper provides a comprehensive study pertaining to diagnosis of intermittent high vibrations on an industrial gas turbine using detailed vibrations analysis, followed by its rectification. Engro Polymer & Chemicals Limited, a Chlor-Vinyl complex located in Pakistan has a captive combined cycle power plant having two 28 MW gas turbines (make Hitachi) & one 15 MW steam turbine. In 2018, the organization faced an issue of high vibrations on one of the gas turbines. These high vibration peaks appeared intermittently on both compressor’s drive end (DE) & turbine’s non-drive end (NDE) bearing. The amplitude of high vibration peaks was between 150-170% on the DE bearing & 200-300% on the NDE bearing from baseline values. In one of these episodes, the gas turbine got tripped on “High Vibrations Trip” logic actuated at 155µm. Limited instrumentation is available on the machine, which is monitored with GE Bently Nevada 3300 system having two proximity probes installed at Turbine NDE, Compressor DE &at Generator DE & NDE bearings. Machine’s transient ramp-up & steady state data was collected using ADRE SXP & DSPI 408. Since only 01 key phasor is installed at Turbine high speed shaft, a derived drive key phasor was configured in ADRE to obtain low speed shaft rpm required for data analysis. By analyzing the Bode plots, Shaft center line plot, Polar plot & orbit plots; rubbing was evident on Turbine’s NDE along with increased bearing clearance of Turbine’s NDE radial bearing. The subject bearing was then inspected & heavy deposition of carbonized coke was found on the labyrinth seals of bearing housing with clear rubbing marks on shaft & housing covering at 20-25 degrees on the inner radius of labyrinth seals. The collected coke sample was tested in laboratory & found to be the residue of lube oil in the bearing housing. After detailed inspection & cleaning of shaft journal area & bearing housing, new radial bearing was installed. Before assembling the bearing housing, cleaning of bearing cooling & sealing air lines was also carried out as inadequate flow of cooling & sealing air can accelerate coke formation in bearing housing. The machine was then taken back online & data was collected again using ADRE SXP & DSPI 408 for health analysis. The vibrations were found in acceptable zone as per ISO standard 7919-3 while all other parameters were also within vendor defined range. As a learning from subject case, revised operating & maintenance regime has also been proposed to enhance machine’s reliability.
Abstract: Chip formation characteristics are investigated during surface finishing of high density polyethylene (HDPE) samples using a shaper machine. Both the cutting speed and depth of cut are varied continually to enable observations under various machining conditions. The generated chips are analyzed in terms of their shape, size, and deformation. Their physical appearances are also observed using digital camera and optical microscope. The investigation shows that continuous chips are obtained for all the cutting conditions. It is observed that cutting speed is more influential than depth of cut to cause dimensional changes of chips. Chips curl radius is also found to increase gradually with the increase of cutting speed. The length of continuous chips remains always smaller than the job length, and the corresponding discrepancies are found to be more prominent at lower cutting speed. Microstructures of the chips reveal that cracks are formed at higher cutting speeds and depth of cuts, which is not that significant at low depth of cut.
Abstract: The contra-rotating axial machine is a promising solution for several applications, where high pressure and efficiencies are needed. Also, they allow reducing the speed of rotation, the radial spacing and a better flexibility of use. However, this requires a better understanding of their operation, including the influence of second rotor on the overall aerodynamic performances. This work consisted of both experimental and numerical studies to characterize this counter-rotating fan, especially the analysis of the effects of the blades stagger angle and the inter-distance between the rotors. The experimental study served to validate the computational fluid dynamics model (CFD) used in the simulations. The numerical study permitted to cover a wider range of parameter and deeper investigation on flow structures details, including the effects of blade stagger angle and inter-distance, associated with the interaction between the rotors. As a result, there is a clear improvement in aerodynamic performance compared with a conventional machine.
Abstract: The neural network quantization is highly desired
procedure to perform before running neural networks on mobile
devices. Quantization without fine-tuning leads to accuracy drop of
the model, whereas commonly used training with quantization is done
on the full set of the labeled data and therefore is both time- and
resource-consuming. Real life applications require simplification and
acceleration of quantization procedure that will maintain accuracy of
full-precision neural network, especially for modern mobile neural
network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with
quantization procedure by introducing the trained scale factors for
discretization thresholds that are separate for each filter. Using the
proposed technique, we quantize the modern mobile architectures of
neural networks with the set of train data of only ∼ 10% of the
total ImageNet 2012 sample. Such reduction of train dataset size and
small number of trainable parameters allow to fine-tune the network
for several hours while maintaining the high accuracy of quantized
model (accuracy drop was less than 0.5%). Ready-for-use models and
code are available in the GitHub repository.
Abstract: High cycle fatigue comprising up to 107 load cycles has been the subject of many studies, and the behavior of many materials was recorded adequately in this regime. However, many applications involve larger numbers of load cycles during the lifetime of machine components. In this ultra-high cycle regime, other failure mechanisms play, and the concept of a fatigue endurance limit (assumed for materials such as steel) is often an oversimplification of reality. When machine component design demands a high geometrical complexity, cast iron grades become interesting candidate materials. Grey cast iron is known for its low cost, high compressive strength, and good damping properties. However, the ultra-high cycle fatigue behavior of cast iron is poorly documented. The current work focuses on the ultra-high cycle fatigue behavior of EN-GJL-250 (GG25) grey cast iron by developing an ultrasonic (20 kHz) fatigue testing system. Moreover, the testing machine is instrumented to measure the temperature and the displacement of the specimen, and to control the temperature. The high resonance frequency allowed to assess the behavior of the cast iron of interest within a matter of days for ultra-high numbers of cycles, and repeat the tests to quantify the natural scatter in fatigue resistance.
Abstract: During the recent years, much interest has been devoted to fractional order control that has appeared as a very eligible control approach for the systems experiencing parametric uncertainty and outer disturbances. The main purpose of this paper is to design and evaluate the performance of a fractional order proportional integral (FOPI) controller applied to control prototype variable speed wind generation system (WGS) that uses a doubly fed induction generator (DFIG). In this paper, the DFIG-machine is controlled according to the stator field-oriented control (FOC) strategy, which makes it possible to regulate separately the reactive and active powers exchanged between the WGS and the grid. The considered system is modeled and simulated using MATLAB-Simulink, and the performance of FOPI controller applied to the back-to-back power converter control of DFIG based grid connected variable speed wind turbine are evaluated and compared to the ones obtained with a conventional PI controller.
Abstract: 2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.
Abstract: Industry 4.0 is the fourth industrial revolution that focuses on interconnectivity of machine to machine, human to machine and human to human via Internet of Things (IoT). Technologies of industry 4.0 facilitate communication between human and machine through IoT and forms Cyber-Physical Production System (CPPS). In CPPS, multiple shop floors sensor data are connected through IoT and displayed through sensor dashboard to the operator. These sensor dashboards have enormous amount of information to be presented which becomes complex for operators to perform monitoring, controlling and interpretation tasks. Designing handheld sensor dashboards for supervision task will become a challenge for the interface designers. This paper reports emerging technologies of industry 4.0, changing context of increasing information complexity in consecutive industrial revolutions and upcoming design challenges for interface designers in context of Industry 4.0. Authors conclude that information complexity of sensor dashboards design has increased with consecutive industrial revolutions and designs of sensor dashboard causes cognitive load on users. Designing such complex dashboards interfaces in Industry 4.0 context will become main challenges for the interface designers.
Abstract: Artificial Intelligence (AI) has the potential to transform
manufacturing by improving shop floor processes such as production,
maintenance and quality. However, industrial datasets are notoriously
difficult to extract in a real-time, streaming fashion thus, negating
potential AI benefits. The main example is some specialized industrial
controllers that are operated by custom software which complicates
the process of connecting them to an Information Technology (IT)
based data acquisition network. Security concerns may also limit
direct physical access to these controllers for data acquisition.
To connect the Operational Technology (OT) data stored in these
controllers to an AI application in a secure, reliable and available
way, we propose a novel Industrial IoT (IIoT) solution in this paper.
In this solution, we demonstrate how video cameras can be installed
in a factory shop floor to continuously obtain images of the controller
HMIs. We propose image pre-processing to segment the HMI into
regions of streaming data and regions of fixed meta-data. We then
evaluate the performance of multiple Optical Character Recognition
(OCR) technologies such as Tesseract and Google vision to recognize
the streaming data and test it for typical factory HMIs and realistic
lighting conditions. Finally, we use the meta-data to match the OCR
output with the temporal, domain-dependent context of the data to
improve the accuracy of the output. Our IIoT solution enables reliable
and efficient data extraction which will improve the performance of
subsequent AI applications.
Abstract: This paper reviews the comparison of Resin Rich (RR) and Vacuum Pressure Impregnation (VPI) insulation system qualities for stator bar of rotating electrical machines. Voltage endurance and tangent delta are two diagnostic tests to determine the quality of insulation systems. The paper describes the trend of dissipation factor while performing voltage endurance test for different stator bar samples made with RR and VPI insulation system methods. Some samples were made with the same strands and insulation thickness but with different main wall material to prove the influence of insulation system methods on stator bar quality. Also, some of the samples were subjected to voltage at the temperature of their insulation class, and their dissipation factor changes were measured and studied.
Abstract: Deep learning structure is a branch of machine learning science and greet achievement in research and applications. Cellular neural networks are regarded as array of nonlinear analog processors called cells connected in a way allowing parallel computations. The paper discusses how to use deep learning structure for representing neural cellular automata model. The proposed learning technique in cellular automata model will be examined from structure of deep learning. A deep automata neural cellular system modifies each neuron based on the behavior of the individual and its decision as a result of multi-level deep structure learning. The paper will present the architecture of the model and the results of simulation of approach are given. Results from the implementation enrich deep neural cellular automata system and shed a light on concept formulation of the model and the learning in it.
Abstract: This study presented hybrid pre-processing approach along with a conceptual model to enhance the accuracy of river discharge prediction. In order to achieve this goal, Ensemble Empirical Mode Decomposition algorithm (EEMD), Discrete Wavelet Transform (DWT) and Mutual Information (MI) were employed as a hybrid pre-processing approach conjugated to Least Square Support Vector Machine (LSSVM). A conceptual strategy namely multi-station model was developed to forecast the Souris River discharge more accurately. The strategy used herein was capable of covering uncertainties and complexities of river discharge modeling. DWT and EEMD was coupled, and the feature selection was performed for decomposed sub-series using MI to be employed in multi-station model. In the proposed feature selection method, some useless sub-series were omitted to achieve better performance. Results approved efficiency of the proposed DWT-EEMD-MI approach to improve accuracy of multi-station modeling strategies.
Abstract: Objective of this research is to study effect of coffee grounds on physical and heating value properties of sugarcane bagasse pellets. The coffee grounds were tested as an additive for pelletizing process of bagasse pellets. Pelletizing was performed using a Flat–die pellet mill machine. Moisture content of raw materials was controlled at 10-13%. Die temperature range during the process was 75-80 oC. Physical characteristics (bulk density and durability) of the bagasse pellet and pellets with 1-5% coffee ground were determined following the standard assigned by the Pellet Fuel Institute (PFI). The results revealed increasing values of 648±3.4, 659 ± 3.1, 679 ± 3.3 and 685 ± 3.1 kg/m3 (for pellet bulk density); and 98.7 ± 0.11, 99.2 ± 0.26, 99.3 ± 0.19 and 99.4 ± 0.07% (for pellet durability), respectively. In addition, the heating values of the coffee ground supplemented pellets (15.9 ± 1.16, 17.0 ± 1.23 and 18.8 ± 1.34 MJ/kg) were improved comparing to the non-supplemented control (14.9 ± 1.14 MJ/kg), respectively. The results indicated that both the bulk density and durability values of the bagasse pellets were increased with the increasing proportion of the coffee ground additive.