Off-line Machine Research Articles

The Industry Internet of Things (IIoT) as a Methodology for Autonomous Diagnostics in Aerospace Structural Health Monitoring

Structural Health Monitoring (SHM), defined as the process that involves sensing, computing, and decision making to assess the integrity of infrastructure, has been plagued by data management challenges. The Industrial Internet of Things (IIoT), a subset of Internet of Things (IoT), provides a way to decisively address SHM’s big data problem and provide a framework for autonomous processing. The key focus of IIoT is operational efficiency and cost optimization. The purpose, therefore, of the IIoT approach in this investigation is to develop a framework that connects nondestructive evaluation sensor data with real-time processing algorithms on an IoT hardware/software system to provide diagnostic capabilities for efficient data processing related to SHM. Specifically, the proposed IIoT approach is comprised of three components: the Cloud, the Fog, and the Edge. The Cloud is used to store historical data as well as to perform demanding computations such as off-line machine learning. The Fog is the hardware that performs real-time diagnostics using information received both from sensing and the Cloud. The Edge is the bottom level hardware that records data at the sensor level. In this investigation, an application of this approach to evaluate the state of health of an aerospace grade composite material at laboratory conditions is presented. The key link that limits human intervention in data processing is the implemented database management approach which is the particular focus of this manuscript. Specifically, a NoSQL database is implemented to provide live data transfer from the Edge to both the Fog and Cloud. Through this database, the algorithms used are capable to execute filtering by classification at the Fog level, as live data is recorded. The processed data is automatically sent to the Cloud for further operations such as visualization. The system integration with three layers provides an opportunity to create a paradigm for intelligent real-time data quality management.

A Review Towards Hyperspectral Imaging for Real-Time Quality Control of Food Products with an Illustrative Case Study of Milk Powder Production

Hyperspectral imaging (HSI) is a relatively fast analytical method that is being used for quality testing of natural foods (e.g. fruits and vegetables). This method has been proposed to replace existing manual off-line sensory quality tests of processed foods (e.g. milk powder). This article reviews the current status of HSI for monitoring natural and processed food product quality and identifies key knowledge gaps in recent literature that may be responsible for the limited success of HSI, especially for processed foods (e.g. milk powder) quality testing at the lab and industrial scales. Furthermore, various strategies to cope with challenges associated with limited HSI success are discussed. From the current literature, HSI has been used primarily as an off-line machine vision technique for quality testing to replace existing manual sensory tests. However, HSI lacks scenarios of testing and controlling product quality in real time, especially for processed foods. Little has been reported to date on generalising suitable design choices for the ‘successful’ implementation of HSI. To address this deficiency, the potential of HSI to achieve real-time quality control was examined using the milk powder production process as a case study.

Neural Networks Pipeline for Offline Machine Printed Arabic OCR

In the context of Arabic optical characters recognition, Arabic poses more challenges because of its cursive nature. We purpose a system for recognizing a document containing Arabic text, using a p...

Neural Networks Pipeline for Offline Machine Printed Arabic OCR

In the context of Arabic optical characters recognition, Arabic poses more challenges because of its cursive nature. We purpose a system for recognizing a document containing Arabic text, using a pipeline of three neural networks. The first network model predicts the font size of an Arabic word, then the word is normalized to an 18pt font size that will be used to train the next two models. The second model is used to segment a word into characters. The problem of words segmentation in the Arabic language, as in many similar cursive languages, presents a challenge to the OCR systems. This paper presents a multichannel neural network to solve the offline segmentation of machine-printed Arabic documents. The segmented characters are then fed as an input to a convolutional neural network for Arabic characters recognition. The font size prediction model produced a test accuracy of 99.1%. The accuracy of the segmentation model using one font is 98.9%, while four-font model showed 95.5% accuracy. The whole pipeline showed an accuracy of 94.38% on Arabic Transparent font of size 18pt from APTI data set.

Binary and Multi-Class Learning Based Low Complexity Optimization for HEVC Encoding

High Efficiency Video Coding (HEVC) improves the compression efficiency at the cost of high computational complexity by using the quad-tree coding unit (CU) structure and variable prediction unit (PU) modes. To minimize the HEVC encoding complexity while maintaining its compression efficiency, a binary and multi-class support vector machine (SVM)-based fast HEVC encoding algorithm is presented in this paper. First, the processes of recursive CU decision and PU selection in HEVC are modeled as hierarchical binary classification and multi-class classification structures. Second, according to the two classification structures, the CU decision and PU selection are optimized by binary and multi-class SVM, i.e., the CU and PU can be predicted directly via classifiers without intensive rate distortion (RD) cost calculation. In particular, to achieve better prediction performance, a learning method is proposed to combine the off-line machine learning (ML) mode and on-line ML mode for classifiers based on a multiple reviewers system. Additionally, the optimal parameters determination scheme is adopted for flexible complexity allocation under a given RD constraint. Experimental results show that the proposed method can achieve 68.3%, 67.3%, and 65.6% time saving on average while the values of Bjontegaard delta peak signal-to-noise ratio are −0.093dB, −0.091dB, and −0.094dB and the values of Bjontegaard delta bit rate are 4.191%, 3.842%, and 3.665% under low delay $P$ main, low delay main, and random access configurations, respectively, when compared with the HEVC test model version HM 16.5. Meanwhile, the proposed method outperforms the state-of-the-art fast coding algorithms in terms of complexity reduction and RD performance.

Hybrid ensemble learning for triggering of GPS in long-term tracking applications

Long-term tracking is an expanding field with applications in logistics, ecology and wearable computing. The main challenge for longevity of tracking applications is the high energy consumption of GPS, which has been addressed by using low power sensors to trigger GPS activation upon detecting events of interest. While triggering can reduce power consumption, static thresholds can under-perform in the long-term as context changes. This paper presents a comparison between a dynamic adaptive threshold algorithm and off-line machine learning techniques. We test the algorithms on empirical data from flying foxes to show that off-line machine learning techniques improve the hit rate when compared to the dynamic adaptive threshold algorithm. We then combine the models into an on/off-line hybrid ensemble learning model to improve both hit rate and false alarm rate when compared to the dynamic adaptive threshold algorithm. The hybrid model also has lower false alarm rate and precision when compared to the stand alone machine learning algorithms. We also test the off-line machine learning techniques on unknown data to show that the hit and false alarm rates vary from node to node. This indicates that more consistent performance might be found through the development of on-line machine learning algorithms.

SVM-DSmT COMBINATION FOR THE SIMULTANEOUS VERIFICATION OF OFF-LINE AND ON-LINE HANDWRITTEN SIGNATURES

A combination handwritten signature verification system is proposed for managing conflicts provided from each individual off-line and on-line support vector machine (SVM), respectively. Basically, the system is divided into three parts: (i) Off-line verification system, (ii) on-line verification system and (iii) combination module using belief function theory. The proposed framework allows combining the normalized SVM outputs and uses an estimation technique based on the dissonant model of Appriou to compute the belief assignments. Combination is performed using belief models such as Dempster-Shafer (DS) rule and proportional conflict redistribution (PCR) rule followed by the likelihood ratio-based decision making. Experiments are conducted on the well-known NISDCC signature collection using false rejection and false acceptance criteria. The obtained results show that the proposed combination framework using Dezert-Smarandache (DSm) theory yields the best verification accuracy even when individual off-line and on-line classifications provide conflicting results.

Evaluation of Nicotiana Tabacum (FCV) Quality Using Off-Line Machine Vision

A number of techniques have been proposed in the past for automatic quality evaluations of pre–processed tobacco using image processing. Although some studies have aimed to evaluate the quality of processed tobacco. There is no automatic system that is capable of evaluating the processed tobacco. This paper proposes a new method for counting the number of normal FCV tobacco (Nicotiana tabacum) as well as foreign elements using machine vision. By proposed method a quality evaluation of processed FCV tobacco can be done which would be very beneficial for the purpose of its quality which is ready to be eat product.

Measuring Log Length using Computer Stereo Vision in Harvester Head

AbstractSales of harvested wood is based on harvester head measurements. Therefore, an accurate length measurement is important when a log is being processed on a forest harvester. A stereo camera pair was mounted to the harvester head and the motions of the harvester head and the log were estimated using off-line machine vision algorihms. Preliminary tests with seven different logs had a maximum error of 12 mm where the mean absolute error between measured and estimated log lengths was 0.09%.

Incorporating dynamism in traditional machine loading problem: an AI-based optimisation approach

Machine breakdowns have been recognised in flexible manufacturing systems (FMS) as the most undesirable characteristic adversely affecting the overall efficiency. In order to ameliorate product quality and productivity of FMS, it is necessary to analyse, as well as to minimise the effect of breakdowns on the objective measures of various decision problems. This paper addresses the machine loading problem of FMS with a view to maximise the throughput and minimise the system unbalance and makespan. Moreover, insufficient work has been done in the domain of machine loading problem that considers effect of breakdowns. This motivation resulted in a potential model in this paper that minimises the effect of breakdowns so that profitability can be augmented. The present work employs an on-line machine monitoring scheme and an off-line machine monitoring scheme in conjunction with reloading of part types to cope with the breakdowns. The proposed model bears similarity with the dynamic environment of FMS, hence, termed as the dynamic machine loading problem. Furthermore, to examine the effectiveness of the proposed model, results for throughput, system unbalance and makespan on different dataset from previous literature has been investigated with application of intelligence techniques such as genetic algorithms (GA), simulated annealing (SA) and artificial immune systems (AIS). The results incurred under breakdowns validate the robustness of the developed model for dynamic ambient of FMS.

Integrated Plasma Control in DIII-D

The integrated plasma control approach provides a systematic method for designing plasma control algorithms with high reliability and for confirming their performance off-line prior to experimental implementation. This approach includes construction of plasma and system response models, validation of models against operating experiments, design of integrated controllers that operate in concert with one another as well as with supervisory modules, simulation of control action against off-line and actual machine control platforms, and iteration of the design-test loop to optimize performance. Using this approach, required levels of robustness to model uncertainties and off-normal events can be quantified and incorporated in the design process. The DIII-D digital plasma control system (PCS) enables application of this method by providing a flexible programming environment and an architecture for real-time parallel operation of a set of computers that executes the large set of control algorithms needed for exploration of the advanced tokamak regime. The present work describes the DIII-D PCS and the approach, benefits, and progress made in integrated plasma control as applied to the DIII-D tokamak, with implications for the International Thermonuclear Experimental Reactor design and other next-generation tokamaks.

Methods and theory for off-line machine learning

Many problems in machine learning can be abstracted to the sequential design task of finding the minimum of an unknown erratic and possibly discontinuous function on the basis of noisy measurements. In the present work, it is presumed that there is no penalty for bad choices during the experimental stage, and at some time, not known to the decision maker, or under his control, the experimentation will be terminated, and the decision maker will need to specify the point considered best, on the basis of the experimentation. In this paper, we seek the best trade-off between: i) acquiring new test points, and ii) retesting at points previously selected so as to improve the estimates of relative performance. The algorithm is shown to achieve a performance standard described herein. This decision setting would seem natural for function minimization in a simulation contest or for tuning up a production process prior to putting it into service. >

A note on off-line machines with ‘brownian’ input heads

An off-line machine is a Turing machine with a separate read-only input tape. Such a machine is said to have a ‘Brownian’ input head if it has no control over and cannot observe the moves of the read-only head scanning the input tape. It is shown in this note that the binary languages (i.e., languages over a two-symbol alphabet) recognized by such machines are all regular. The proof is not constructive and relies heavily on the so-called ‘finite sequences theorem’ in the theory of well-partial-ordering.