On-line Preprocessing Research Articles

Agnostic CH-DT Technique for SCADA Network High-Dimensional Data-Aware Intrusion Detection System

The pervasiveness in the industrial internet of things (IIoT) due to the application of supervisory control and data acquisition (SCADA) has led to the growth of heterogeneous sensor data, thereby increasing the risk of intrusions and attacks. The existence and effect of intruders and their innovative attack techniques are on the rise. Existing intrusion detection systems (IDS) tend to be computationally expensive with this form of data due to the presence of noise. In real-time domains, available methods lag, necessitating additional research into effective feature extraction schemes, which is fundamental in machine learning (ML) for time exigency. This study, in a comparative analysis of some feature selection techniques (FS), proposes a combination of an efficient ML classifier and an agnostic feature selection (FS) scheme for attack detection and classification in a real-time SCADA network. The flexibility and interoperability of the proposed approach resolve the computational complexity of vulnerability detection schemes while reducing false alarm rates (FAR) and overall model execution time. With the view of an online preprocessing, the proposed technique is phased thus: (i) data preparatory consisting of data cleansing and normalization followed by (ii) the combination of a pre-pruned decision tree (DT) algorithm and an agnostic Chi-square FS approach built to obtain an optimal subset of data features for efficient IDS. (iii) Evaluation of proposed agnostic DT-CH and other FS candidates for anomaly detection.

Online Prediction of Electric Vehicle Battery Failure Using LSTM Network

The electric vehicle industry is developing rapidly as part of the global energy structure transformation, which has increased the importance of overcoming power battery safety issues. In this paper, first, we study the relationship between different types of vehicle faults and battery data based on the actual vehicle operation data in the big data supervisory platform of new energy vehicles. Second, we propose a method to realize the online prediction of electric vehicle battery faults, based on a Long Short-Term Memory (LSTM). Third, we carry out prediction research for two kinds of faults: low State of Charge (SOC) alarm and insulation alarm. Last, we show via experimental results that the model based on the LSTM network can effectively predict battery faults with an accuracy of more than 85%. Through this research, it is possible to complete online pre-processing of vehicle operation data and fault prediction of power batteries, improve vehicle monitoring capabilities and ensure the safety of electric vehicle use.

An online identification approach for a nonlinear ship motion model based on a receding horizon

The ship motion system is a nonlinear control object, and its system parameters exhibit time-varying characteristics with the ship motion state, which increases the difficulty of control. Therefore, parameter identification has an important significance for the stability of ship motion control. Aiming at the real-time identification problem of the nonlinear and time-varying ship motion system during movement, this paper reconstructs the ship motion system with the propeller speed and rudder angle as control variables and designs an online identification algorithm with the sliding time window method based on the extended Kalman filter algorithm. In addition, to solve the problem of noise in ship motion data collected in real-time, a real-time wavelet filter is developed to perform online preprocessing of the input data of the identification algorithm. The applicability of the method is further demonstrated via a model-scale Korea Research Institute of Ships and Ocean Engineering container ship free-running experiments in a basin.

Real-time Raman spectroscopy for in vivo, online gastric cancer diagnosis during clinical endoscopic examination

Optical spectroscopic techniques including reflectance, fluorescence and Raman spectroscopy have shown promising potential for in vivo precancer and cancer diagnostics in a variety of organs. However, data-analysis has mostly been limited to post-processing and off-line algorithm development. In this work, we develop a fully automated on-line Raman spectral diagnostics framework integrated with a multimodal image-guided Raman technique for real-time in vivo cancer detection at endoscopy. A total of 2748 in vivo gastric tissue spectra (2465 normal and 283 cancer) were acquired from 305 patients recruited to construct a spectral database for diagnostic algorithms development. The novel diagnostic scheme developed implements on-line preprocessing, outlier detection based on principal component analysis statistics (i.e., Hotelling's T2 and Q-residuals) for tissue Raman spectra verification as well as for organ specific probabilistic diagnostics using different diagnostic algorithms. Free-running optical diagnosis and processing time of < 0.5 s can be achieved, which is critical to realizing real-time in vivo tissue diagnostics during clinical endoscopic examination. The optimized partial least squares-discriminant analysis (PLS-DA) models based on the randomly resampled training database (80% for learning and 20% for testing) provide the diagnostic accuracy of 85.6% [95% confidence interval (CI): 82.9% to 88.2%] [sensitivity of 80.5% (95% CI: 71.4% to 89.6%) and specificity of 86.2% (95% CI: 83.6% to 88.7%)] for the detection of gastric cancer. The PLS-DA algorithms are further applied prospectively on 10 gastric patients at gastroscopy, achieving the predictive accuracy of 80.0% (60/75) [sensitivity of 90.0% (27/30) and specificity of 73.3% (33/45)] for in vivo diagnosis of gastric cancer. The receiver operating characteristics curves further confirmed the efficacy of Raman endoscopy together with PLS-DA algorithms for in vivo prospective diagnosis of gastric cancer. This work successfully moves biomedical Raman spectroscopic technique into real-time, on-line clinical cancer diagnosis, especially in routine endoscopic diagnostic applications.

Fast PRISM: Branch and Bound Hough Transform for Object Class Detection

This paper addresses the task of efficient object class detection by means of the Hough transform. This approach has been made popular by the Implicit Shape Model (ISM) and has been adopted many times. Although ISM exhibits robust detection performance, its probabilistic formulation is unsatisfactory. The PRincipled Implicit Shape Model (PRISM) overcomes these problems by interpreting Hough voting as a dual implementation of linear sliding-window detection. It thereby gives a sound justification to the voting procedure and imposes minimal constraints. We demonstrate PRISM's flexibility by two complementary implementations: a generatively trained Gaussian Mixture Model as well as a discriminatively trained histogram approach. Both systems achieve state-of-the-art performance. Detections are found by gradient-based or branch and bound search, respectively. The latter greatly benefits from PRISM's feature-centric view. It thereby avoids the unfavourable memory trade-off and any on-line pre-processing of the original Efficient Subwindow Search (ESS). Moreover, our approach takes account of the features' scale value while ESS does not. Finally, we show how to avoid soft-matching and spatial pyramid descriptors during detection without losing their positive effect. This makes algorithms simpler and faster. Both are possible if the object model is properly regularised and we discuss a modification of SVMs which allows for doing so.

HANDWRITING RECOGNITION OF WHITEBOARD NOTES — STUDYING THE INFLUENCE OF TRAINING SET SIZE AND TYPE

This paper presents a system for the recognition of online whiteboard notes. Notes written on a whiteboard is a new modality in handwriting recognition research that has received relatively little attention in the past. For the recognition we use an offline HMM-recognizer, which is supplemented with methods for processing the online data and generating offline images. The system consists of six main modules: online preprocessing, transformation of online to offline data, offline preprocessing, feature extraction, classification and post-processing. The recognition rate of our basic recognizer in a writer independent experiment is 59.5%. By applying state-of-the-art methods, such as optimizing the number of states and Gaussian components, and by including a language model we could achieve a statistically significant increase of the recognition rate to 64.3%. To further improve the system performance we increased the size of the training set. For that we investigated two different strategies. First, we used another existing database of offline handwritten text. Second, we used a recently collected whiteboard database, called the IAM-OnDB. By means of these strategies the recognition rate could be further increased up to 68.5%.

Evaluation of data produced by optode arrays under flow injection analysis (FIA) conditions using a partial least squares method (PLS2)

Transient diffuse reflectance spectra in the visible wavelength region from an enzyme optode were evaluated to determine artificial mixtures consisting of penicillin and ampicillin simultaneously. In order to achieve a discrimination of the samples the optode operated at two different working pH values. Using an appropriate FIA modus a linear range in the increase and decrease of the time-dependent signal was registered which could be easily fitted by means of ordinary linear regression. In this way characteristic static and dynamic features of the enzyme catalyzed reaction could be extracted for the evaluation by partial least-squares (PLS). The pre-processed raw data were differently weighted and the optimal number of primary factors was each selected by full cross validation. The interpretation of the spectral loadings and the correlation matrix identifies redundant variables resulting in a model with an optimal number of variables. The results obtained with this model show that the straightforward linear regression can be a sufficient approach to avoid the introduction of systematic errors in on-line pre-processing of data.

Silicon drift detector readout and on-line data reduction using a fast VLSI dedicated fuzzy processor

A silicon drift detector front-end and a smart readout system different from a trivial zero-suppression is proposed. On-line preprocessing, using a fast VLSI dedicated fuzzy processor, reduces significantly acquisition data volume and hardware requirements.

MOCAM: A 4k × 4k CCD Mosaic for the Canada-France-Hawaii Telescope Prime Focus

MOCAM is a wide field CCD camera, currently nearing completion, which will be offered to the Canada-France-Hawaii Telescope (CFHT) user community in 1995. The project is a collaboration between the CFHT, the Dominion Astronomical Observatory (DAO, Canada), the Institut des Sciences de l'Univers (INSU, France), Laboratoire d'Astrophysique de Toulouse (LAT, France) and the University of Hawaii (UH). In the interests of producing a reliable and effective camera in the shortest time, it was decided to use existing technologies rather than innovative ones. Two-edge buttable 2048 × 2048 15 μm pixel CCDs were obtained from the LORAL aerospace foundry, based on a mask designed by J. Geary at Smithsonian Astrophysical Observatory (SAO). They are mounted in a dewar designed by G. Luppino (UH); the focal plane mounting keeps the mosaic flat to within two pixels and the CCDs are aligned to within two pixels. A mechanical interface designed and fabricated by the DAO holds a 150 mm shutter and a filter wheel which has a positioning repeatability better than five μm.The four CCDs are operated in parallel by a San Diego GenIII controller adapted by LAT. The mosaic is read out in seven minutes and a single 33 Mb FITS file is generated to enable convenient on-line preprocessing. The user will control the system through a single CFHT Pegasus environment session. The camera field is 14′ × 14′ with a 0.″2 pixel sampling and the readout noise is less than seven electrons. The scientific goals of the initiators of the project are studies of distant clusters, deep galaxy counts and quasars surveys.

The Parallel Processing Compute Server

The Parallel Processing Compute Server (PPCS) is a distributed-memory multiprocessing system consisting of System/370 microprocessors (33 at present) interconnected through a matrix switch. This paper describes the hardware configuration, the extensions to the System/370 instruction set that are provided to support the distributed memory and interprocessor signalling, the modification to the VM/SP operating system that allow it to run effectively on many closely coupled processors (most of which have no disks), and the application-support layer, which permits FORTRAN programs to take advantage of the highly parallel environment. A PPCS with 32 satellite processors, Parallel VM, and CS/X has been installed at the European Organization for Nuclear Research (CERN) and is running applications used by the high-energy physics (HEP) community. At CERN, on-line data acquisition and preprocessing of experimental data is a major computing task. High-energy physics experiments can generate streams of data at a rate of several gigabytes per second. Once filtered and recorded, data are subject to further analysis off-line. Both on-line and off-line processing are numerically intensive computing jobs. The PPCS is primarily intended for the off-line processing, but it can be used for on-line work as well.

An innovation in flow cytometry data collection and analysis producing a correlated multiple sample analysis in a single file

The problems associated with rapid analysis and interpretation of data from multicolor immunofluorescence panels have been a formidable barrier to their routine use. Using present flow cytometry concepts, a panel of 11 tubes each containing multiple phenotypic markers or controls requires postdata acquisition manipulation of many multiparameter histogram and listmode files. We have developed a method that compresses all of the information from such a panel into a single listmode data file during run time. A single data file is used to record the entire phenotypic analysis for a particular patient or series within an experiment. This is accomplished by the incorporation of a tube identifier parameter (TIP) as well as the fluorescence and light scatter parameters normally collected. The TIP can then be used for gating discrimination of any tube or set of tubes within a panel. When the TIP is correlated with the PRISM parameter the entire patient phenotypic image can be represented within a single two-parameter histogram we have called a phenogram. This phenogram can be generated in real time, providing on-line preprocessing of a complex multicolor experiment. By examining the image created by the phenogram it is possible to rapidly flag abnormalities such as incorrect gating. This procedure was carried out on an EPICS Elite flow cytometer in its standard configuration with the addition of hardware to provide an input for the TIP.

Microcomputer-based system for 24-hour recording of oesophageal motility and pH profile with automated analysis.

A system developed for long-term simultaneous recording of oesophageal motility and pH in the ambulant patient is described. The system consists of a microprocessor based data-acquisition and preprocessing device, a personal computer for postprocessing, report generation and data storage, a miniature two-sensor pressure catheter and a pH electrode. Identification and classification of oesophageal contractions are performed in separate steps, using online preprocessing software for identification and offline postprocessing software for categorisation, classification and report generation. Contractions are categorised as peristaltic, simultaneous or nontransmitte and classified according to their amplitude, duration and propagation velocity. The method described reduces the amount of data from 870 kbyte to approximately 40 kbyte per 24 hours in a multiparameter recording device, and offers the opportunity for offline postprocessing with different sets of criteria. The system has been found to be accurate and reliable in 24-hour studies in both healthy volunteers and patients with non-cardiac chest pain.

Real-Time Acquisition and Preprocessing of Kinetic and Spectroscopic Data in Laser Flash Photolysis

An automatic flash photolysis system for the measurement of absorption decays and transient difference spectra is described. The apparatus performs a digital measurement of the light transmitted by the sample and a few on-line preprocessing operations on the measured data, such as the digital averaging of the signal and the computation of the change in absorbance. A boxcar averager, used as a gated integrator, constitutes the sampling head of the apparatus. A microprocessor-based acquisition and control unit performs a digital conversion of the value sampled by the boxcar, provides an on-line preprocessing of the data, and supervises every operation required by the measurement process. This unit is interfaced to a personal computer which allows a friendly interaction with the operator as well as the on-line display of the data. The electronic instrumentation features a time resolution of a few nanoseconds, with a boxcar averager as input head, and of a few hundreds of picoseconds, with a sampling oscilloscope as input head.

Multi-Frame Data Acquisition for PET Camera Using an On-Line Microprocessor-Based System

Multi-frame studies using cameras with fine spatial sampling and many possible coincidence lines create large memory requirements. To reduce these requirements and enable the PENN-PET scanner to perform gated cardiac studies, a microprocessor-based system for on-line preprocessing of raw data into sinograms was designed, built and evaluated.

A hierarchical architecture with independent professors for real-time systems

Real-Time Systems have characteristics such that they represent the limits of present-day designing capabilities. For this reason, it is necessary to devise system architectures that are specifically designed for real-time applications. To meet the design constraints imposed effectively, it is necessary to use a design method and to carry out a careful analysis of the manufacturing technology employed. The architecture proposed here is based on the use of several processors, which make it possible to perform independent functions of the system concurrently. In order to define this architecture, reference was made to the local environment model. The system therefore consists of independent processors that communicate through the exchange of messages. Control on the operation of the whole system is performed by a supervisor, and is based on microprogramming principles. The architecture described has numerous advantages, both in terms of performance and in terms of flexibility, modularity and diagnosability. The paper includes an application of this architecture to the design of an instrument for the acquisition and on-line pre-processing of data. Lastly, a performance evaluation study was carried out that made it possible to measure both effectiveness and efficiency of the system designed.

CHIL - A Comprehensive Histogramming Language

A high level language, CHIL, has been developed for use in processing event-by-event experimental data at the Holifield Heavy Ion Research Facility (HHIRF) using PERKIN-ELMER 3230 computers. CHIL has been fully integrated into all software which supports on-line and off-line histogramming and off-line preprocessing. CHIL supports simple gates, free-form-gates (2-D regions of arbitrary shape), condition test and branch statements, bit-tests, loops, calls to up to three user supplied subroutines and histogram generating statements. Any combination of 1, 2, 3 or 4-D histograms (32 megachannels max) may be recorded at 16 or 32 bits/channel. User routines may intercept the data being processed and modify it as desired. The CPU-intensive part of the processing utilizes microcoded routines which enhance performance by about a factor of two.

Data Acquisition Aspects of Super-PETT

Incorporation of differential time-of-flight (TOF) information in positron emission tomography offers significant performance improvement at the cost of increasing the quantity of data to be processed. A tomographic unit utilizing TOF data, called Super-PETT, is currently nearing the final stage of construction. Design and implementation aspects of the data acquisition system are described with an emphasis on instrument operation in an on-line preprocessing mode.

Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movement

A method of accurate storage and on-line preprocessing of an EEG signal, preceding and following a trigger signal, elicited by button pressing, is described. The method was used to study the changes occurring in the power of the rhythmic activity within the alpha band in central areas, during voluntary, self-paced movement in 10 normal humans. A short-lasting decrease or phasic event-related desynchronization (ERD) of alpha power, representing mu activity, was observed in all 10 subjects. During the 2 sec period preceding movement the phasic ERD was mostly bilateral, but larger prior to right than to left thumb movement. At onset and during the first second of execution of movement, the phasic ERD was mostly bilateral but predominant in ipsilateral areas. Preceding or during movement, maximum ERD was observed in most cases in central-vertex regions.

ATS-6 Preliminary Results from the 13/18-GHz COMSAT Propagation Experiment

The 13/18-GHz COMSAT Propagation Experiment (CPE) is reviewed, the data acquisition and processing are discussed, and samples of preliminary results are presented. The need for measurements of both hydrometeor-induced attenuation statistics and diversity effectiveness is brought out The facilitation of the experiment-CPE dual frequency and diversity site location, the CPE ground transmit terminals, the CPE transponder on Applications Technology Satellite-6 (ATS-6), and the CPE receive and data acquisition system-is briefly examined. The on-line preprocessing of the received signal is reviewed, followed by a discussion of the off-line processing of this database to remove signal fluctuations not due to hydrometeors. Finally, samples of the results of first-level analysis of the resultant data for the 18-GHz diversity site near Boston, Mass., and for the dual frequency 13/18-GHz site near Detroit, Mich., are presented and discussed.