Automatic Real Time Research Articles

Continuous Process Verification 4.0 application in upstream: adaptiveness implementation managed by AI in the hypoxic bioprocess of the Pichia pastoris cell factory.

The experimental approach developed in this research demonstrated how the cloud, the Internet of Things (IoT), edge computing, and Artificial Intelligence (AI), considered key technologies in Industry 4.0, provide the expected horizon for adaptive vision in Continued Process Verification (CPV), the final stage of Process Validation (PV). Pichia pastoris producing Candida rugosa lipase 1 under the regulation of the constitutive GAP promoter was selected as an experimental bioprocess. The bioprocess worked under hypoxic conditions in carbon-limited fed-batch cultures through a physiological control based on the respiratory quotient (RQ). In this novel bioprocess, a digital twin (DT) was built and successfully tested. The implementation of online sensors worked as a bridge between the microorganism and AI models, to provide predictions from the edge and the cloud. AI models emulated the metabolism of Pichia based on critical process parameters and actionable factors to achieve the expected quality attributes. This innovative AI-aided Adaptive-Proportional Control strategy (AI-APC) improved the reproducibility comparing to a Manual-Heuristic Control strategy (MHC), showing better performance than the Boolean-Logic-Controller (BLC) tested. The accuracy, indicated by the Mean Relative Error (MRE), was for the AI-APC lower than 4%, better than the obtained for MHC (10%) and BLC (5%). Moreover, in terms of precision, the same trend was observed when comparing the Root Mean Square Deviation (RMSD) values, becoming lower as the complexity of the controller increases. The successful automatic real time control of the bioprocess orchestrated by AI models proved the 4.0 capabilities brought by the adaptive concept and its validity in biopharmaceutical upstream operations.

Comparison of optimizers for model predictive thermal control of buildings

Considering recent developments in the energy sector, further reduction of electricity cost and flattening of the electric power demand curve are needed. We have focused on an autonomous electric heater control system that can easily be implemented in existing buildings without strict comfort requirements. Examples are winter heating of warehouses and vacation homes, and heat drying of buildings under construction. We have set up a system that typically reduces electricity cost by about 40% on the basis of automatic weather and real time pricing forecasts. The system uses the building as an energy reservoir over periods with high electricity cost. Using a model predictive control system, we compare use of a genetic algorithm, a particle swarm optimization, and a neural network for heater control, all working in a closed loop to reduce the influence of modeling errors. We have simulated the performance of the systems using realistic data and found that all three optimizers give about the same performance, varying only a few percent in efficiency. However, the computational and memory requirements of the neural network are much lower than for the other optimizers, so it is preferable for use with inexpensive microcontrollers. We carried out a full-scale experiment at a residential house and found agreement with simulation results.

IOT Assisted ECG Monitoring Framework with Secure Data Transmission Application

The growing Internet of Things (IoT) frame work enables us to create tiny devices that are capable of sensing processing and communicating, enabling sensors, embedding devices and other' things 'to be created which will help to understand the environment. In this paper, the IoT assisted electrocardiogram (ECG) monitoring framework with secure data transmission has been proposed in this research. With the proposed IoT assisted ECG monitoring system, the development and implementation of a light weight ECG Signal Strength Analysis has been proposed for automatic classification and real time implementation, using ECG sensors, Arduino, Android phones, Bluetooth and cloud servers. The Light weight Secure IoT (LS-IoT) and Light weight Access Control (LAC) have been introduced for asecuredatatypetransmission.Real-timeanalysisandverificationareperformedontheECGsignalsobtainedfromtheMIT-BI Hand Physio Net Challenges databases as well as the ECG signals for various physical activities. The potential for determining the clinical acceptability of ECG signals to increase the effectiveness, accuracy, and dependability of an unsupervised diagnostic system is significant in the proposed IoT assisted ECG monitoring framework.

Artificial Intelligence (AI) versus POCUS Expert: A Validation Study of Three Automatic AI-Based, Real-Time, Hemodynamic Echocardiographic Assessment Tools

Point Of Care Ultra-Sound (POCUS) is an operator dependent modality. POCUS examinations usually include 'Eyeballing' the inspected anatomical structure without conducting accurate measurements due to complexity and insufficient time. Automatic real time measuring tools can make accurate measurements fast and simple and dramatically increase examination reliability while saving the operator much time and effort. In this study we aim to assess three automatic tools which are integrated into the Venue™ device by GE: the automatic ejection fraction, velocity time integral, and inferior vena cava tools in comparison to the gold standard-an examination by a POCUS expert. A separate study was conducted for each of the three automatic tools. In each study, cardiac views were acquired by a POCUS expert. Relevant measurements were taken by both an auto tool and a POCUS expert who was blinded to the auto tool's measurement. The agreement between the POCUS expert and the auto tool was measured for both the measurements and the image quality using a Cohen's Kappa test. All three tools have shown good agreement with the POCUS expert for high quality views: auto LVEF (0.498; p < 0.001), auto IVC (0.536; p = 0.009), and the auto VTI (0.655; p = 0.024). Auto VTI has also shown a good agreement for medium quality clips (0.914; p < 0.001). Image quality agreement was significant for the auto EF and auto IVC tools. The Venue™ show a high agreement with a POCUS expert for high quality views. This shows that auto tools can provide reliable real time assistance in performing accurate measurements, but do not reduce the need of a good image acquisition technique.

OCT Risk Factors for Development of Atrophy in Eyes with Intermediate Age-Related Macular Degeneration

To determine the frequency of multiple OCT biomarkers of intermediate age-related macular degeneration (iAMD) and their relationship with the development of complete retinal pigment epithelium and outer retinal atrophy (cRORA) after 2 years. Retrospective cohort study. This retrospective analysis included 330 eyes of 330 consecutive patients with iAMD in ≥ 1 eye who had 24 months of follow-up data. Spectralis OCT volume scans (49 B-scans over 6× 6 mm, automatic real time = 6, fovea-centered) at baseline were evaluated for the previously described iAMD biomarkers, including a high-central drusen volume (DV; ≥ 0.03 mm3), intraretinal hyper-reflective foci (IHRF), subretinal drusenoid deposits (SDDs), hypo-reflective drusen cores (hDCs), and a thin or thick (multilayered) double-layer sign (DLS). The age-related macular degeneration (AMD) status in the fellow eye was also assessed and classified as normal or early AMD, iAMD, exudative macular neovascularization, or cRORA. Incidence of cRORA, odds ratio for demographics, and OCT features. At month 24, 16.36% (54/330) of the iAMD eyes developed cRORA. Several baseline features, including high-central DV, IHRF, SDD, hDC, thin DLS, and cRORA in the fellow eye, were associated with a significantly greater risk for development of cRORA at 2 years. The odds ratio, 95% confidence interval, P value, and baseline frequencies of these biomarkers were DV (6.510, 2.467-17.176, P < 0.001, 49.1%), IHRF (12.763, 4.763-34.202, P < 0.001, 38.8%), SDD (2.307, 1.003-5.304, P= 0.049, 34.2%), hDC (3.012, 1.152-7.873, P= 0.024, 13.0%), thin DLS (4.517, 1.555-13.126, P= 0.006, 11.8%), and cRORA in the fellow eye (7.184, 1.938-26.623, P= 0.003, 8.2%). In addition to the 4 previously reported factors that are present in a significant proportion of iAMD (DV, IHRF, hDC, and SDD), a thin DLS and cRORA in the fellow eye were associated with an increased risk of progression to cRORA over 2 years. These biomarkers may aid in prognostication, risk stratification, and selection of patients for clinical trials.

Towards an effective application of parameter estimation and uncertainty analysis to mathematical groundwater models

Groundwater models serve as support tools to among others: assess water resources, evaluate management strategies, design remediation systems and optimize monitoring networks. Thus, the assimilation of information from observations into models is crucial to improve forecasts and reduce uncertainty of their results. As more information is collected routinely due to the use of automatic sensors, data loggers and real time transmission systems; groundwater modelers are becoming increasingly aware of the importance of using sophisticated tools to perform model calibration in combination with sensitivity and uncertainty analysis. Despite their usefulness, available approaches to perform this kind of analyses still present some challenges such as non-unique solution for the parameter estimation problem, high computational burden and a need of a deep understanding of the theoretical basis for the correct interpretation and use of their results, in particular the ones related to uncertainty analysis. We present a brief derivation of the main equations that serve as basis for this kind of analysis. We demonstrate how to use them to estimate parameters, assess the sensitivity and quantify the uncertainty of the model results using an example inspired by a real world setting. We analyze some of the main pitfalls that can occur when performing such kind of analyses and comment on practical approaches to overcome them. We also demonstrate that including groundwater flow estimations, although helpful in constraining the solution of the inverse problem as shown previously, may be difficult to apply in practice and, in some cases, may not provide enough information to significantly constrain the set of potential solutions. Therefore, this article can serve as a practitioner-oriented introduction for the application of parameter estimation and uncertainty analysis to groundwater models.

Technology-Based Compensation Assessment and Detection of Upper Extremity Activities of Stroke Survivors: Systematic Review.

BackgroundUpper extremity (UE) impairment affects up to 80% of stroke survivors and accounts for most of the rehabilitation after discharge from the hospital release. Compensation, commonly used by stroke survivors during UE rehabilitation, is applied to adapt to the loss of motor function and may impede the rehabilitation process in the long term and lead to new orthopedic problems. Intensive monitoring of compensatory movements is critical for improving the functional outcomes during rehabilitation.ObjectiveThis review analyzes how technology-based methods have been applied to assess and detect compensation during stroke UE rehabilitation.MethodsWe conducted a wide database search. All studies were independently screened by 2 reviewers (XW and YF), with a third reviewer (BY) involved in resolving discrepancies. The final included studies were rated according to their level of clinical evidence based on their correlation with clinical scales (with the same tasks or the same evaluation criteria). One reviewer (XW) extracted data on publication, demographic information, compensation types, sensors used for compensation assessment, compensation measurements, and statistical or artificial intelligence methods. Accuracy was checked by another reviewer (YF). Four research questions were presented. For each question, the data were synthesized and tabulated, and a descriptive summary of the findings was provided. The data were synthesized and tabulated based on each research question.ResultsA total of 72 studies were included in this review. In all, 2 types of compensation were identified: disuse of the affected upper limb and awkward use of the affected upper limb to adjust for limited strength, mobility, and motor control. Various models and quantitative measurements have been proposed to characterize compensation. Body-worn technology (25/72, 35% studies) was the most used sensor technology to assess compensation, followed by marker-based motion capture system (24/72, 33% studies) and marker-free vision sensor technology (16/72, 22% studies). Most studies (56/72, 78% studies) used statistical methods for compensation assessment, whereas heterogeneous machine learning algorithms (15/72, 21% studies) were also applied for automatic detection of compensatory movements and postures.ConclusionsThis systematic review provides insights for future research on technology-based compensation assessment and detection in stroke UE rehabilitation. Technology-based compensation assessment and detection have the capacity to augment rehabilitation independent of the constant care of therapists. The drawbacks of each sensor in compensation assessment and detection are discussed, and future research could focus on methods to overcome these disadvantages. It is advised that open data together with multilabel classification algorithms or deep learning algorithms could benefit from automatic real time compensation detection. It is also recommended that technology-based compensation predictions be explored.

Intellectual system for automated determination of the quality of natural stones surfaces processing

This automation of determination of the quality of natural stone surfaces processing is a relevant problem. It provides an intellectual system for automated determination of the quality of processing surfaces of natural stones (ISADQSS), which allows rapid assessment of the quality of stone surfaces, including roughness, with high accuracy and quick action in automatic mode and real time. The measurement result is independent of the humidity and cleanliness of the outer surface. The root mean square error of the proposed ISADQSS does not exceed 5%, the time to determine the value of the roughness is not over 2 s. ISADQSS is based on the principles of synergetic integration of various technical automation devices with different properties – artificial neural networks (ANN) (in the case of their implementation in the form of neuroprocessors), as well as the so-called registrar of main drive currents (RMDC), which is used as a sensor sensitive to changes in the rubbing force of the stone-cutting tool depending on changes in the roughness value of the machined surface. The proposed ISADQSS is an innovative and promising development that combines such advantages as high accuracy and speed, versatility and ease of use.

Social cyber-criminal, towards automatic real time recognition of malicious posts on Twitter

Easy access to the internet throughout the world has fully reformed the usage of social communication such as Facebook, Twitter, Linked In which are becoming a part of our life. Accordingly, cybercrime has become a vital problem, especially in developing countries. The dissemination of information with no risk of being discovered and fetched leads to an increase in cyber-criminal. Meanwhile, the huge amount of data continuously produced from Twitter made the discovery process of cyber-criminals is a tough assignment. This research will contribute in determined on the build the comparable vectors for (positive and negative classes) and then the classify incoming tweets to predicate his class (positive or negative). The proposed routines staring with the construct super comparable vectors (SCV) (positive and negative vectors), and the construct vector for the incoming tweet, and then calculate similarities with both SCV and compare calculated similarities to predicate class of incoming tweet. In this research, we used some common techniques for calculating the weight of terms in tweets to construct SCV. To ensure the successful operation of the proposed system, we performed a pilot analysis on a real example of an examination. Research Improves precision, recall, and F1 values by 87%, 59%, 69.99%, respectively.

A validation study of a continuous automatic measurement of the mechanical power in ARDS patients.

Our aim was to investigate the repeatability and the accuracy of the measured MP at different PEEP values and tidal volume compared with the calculated MP. MP was measured and calculated in sedated and paralyzed ARDS patients at low and high tidal volume, at 5-10-15 cmH2O of PEEP both in volume and pressure-controlled ventilation. The same measurements were performed twice. Fifty ARDS patients were enrolled. MP was measured and calculated for a total of 300 measurements. The bias and limits of agreement were 0.38 from -1.31 to 2.0J/min. The measured and calculated MP were similar in each ventilatory condition. The mechanical power measured by a new automatic real time system implemented in a mechanical ventilator was repeatable and accurate compared with the computed one.

Automatic Real Time Platoon Formation Using the Road Graph

Automatic Real Time Platoon Formation Using the Road Graph

Automatic Real Time Platoon Formation Using the Road Graph

Automatic Real Time Platoon Formation Using the Road Graph

Wearable Device for Residential Elbow Joint Rehabilitation with Voice Prompts and Tracking Feedback APP

In this paper, we propose a wearable device for residential elbow joint rehabilitation with voice prompts and a tracking feedback app (WDRTFAPP). We have developed the app as well as the Arduino embedded system, which we have integrated together. In this research, the patients were simulated by our team not real patients. By using this wearable device, the elbow joint rehabilitation could be executed at home for the simulated patients with mild and moderately mild elbow joint symptoms. During the rehabilitation, data captured by the wearable device were sent to the tracking feedback APP, using automatic real time via Bluetooth transmission. After TFAPP received the rehabilitation data from the wearable device, the rehabilitation data was sent to the cloud database by Wi-Fi or 5G communication automatically in real time. When the performance of the elbow joint rehabilitation was incorrect the patients received a voice prompt by TFAPP. The simulated patients could query their rehabilitation data using different search strategies, namely by date or TFAPP, at any time or location. In the experimental results, it showed that the correct detecting rate of elbow joint rehabilitation could be up to 90% by WDRTFAPP. The medical staff also could track the rehabilitation status of each simulated patient by the tracking feedback APP (TFAPP) with remote accessing, such as the Internet. Moreover, the rehabilitation appointments could be set up by the clinical staff with TFAPP, using the Internet. Furthermore, the medical staff could track the rehabilitation status of each simulated patient and give feedback at any time and location. The costs of the rehabilitation could be reduced (in terms of time and money spent by the simulated patients) and the manpower required by the hospital.

An Illegal Dumping Detection System Based on Image Processing in OpenALPR

Tipping or depositing large waste onto land using unauthorized and unlicensed methods are considered as illegal dumping. The increasing rate of illegal dumping becomes a crucial nation issue because this activity causes negative impacts to social, economy and environment. Thus, study on detecting the dumping activities is conducted to control the illegal dumping activities in Malaysia. Raspberry Pi with Python language is used as the microprocessor and a Raspberry Pi camera module with a microwave radar sensor are interfaced to it to capture the image of any vehicles entering the illegal dumping site. The image is captured to recognize the license plate of the vehicle. The method in this study is by using Open Automatic License Plate Recognition (ALPR), Open Computer Vision (CV) libraries and Optical Character Recognition (OCR) to detect the character of the plate registration number. The outcome of the study consists of recognition of Malaysia vehicles’ plate number and the automatic real time email notification on the illegal dumping case. The detection system can be used for case monitoring since the plate number recognition is done in real time. The system can be upgraded to ensure its sustainability in the harsh and isolated environment.

Classification of bottled mineral waters using solution cathode glow discharge optical emission spectroscopy and chemometrics methods

Water is the most important substance for daily life and contains minerals which play an important role in nutrition. In this study, seven kinds of bottled water in Chinese market were analysed and identified by the solution-cathode glow discharge optical emission spectroscopy (SCGD-OES) combined with chemometrics methods. The score matrix was obtained by principal component analysis (PCA), and the back propagation artificial neural network (BP-ANN) model was established to identify the kind of the brands of the bottled water based on their spectral properties. The average classification accuracy based on BP-ANN is 99.74%, support vector machine (SVM) model and linear discrimination analysis (LDA) model were also employed to classify the kind of the brands of the bottled water based on the PCA analysis results, and the correct identification rate based on SVM model and LDA model are 99.50% and 98.00%, respectively. It is confirmed that SCGD-OES combined with chemometrics methods is promising for automatic real time, reliable and robust measurement, and can be integrated into a simplified form for non-specialist users.

Smartband/Smartphone-based Automatic Smoking Detection and Real Time Mindfulness Intervention

Smartband/Smartphone-based Automatic Smoking Detection and Real Time Mindfulness Intervention

CLASSIFICATION AND QUANTITATIVE ANALYSIS OF GEOGRAPHIC ATROPHY JUNCTIONAL ZONE USING SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY.

The junctional zone at the border of areas of geographic atrophy (GA) in eyes with nonneovascular age-related macular degeneration is an important target region for future therapeutic strategies. The goal of this study was to perform a detailed classification and quantitative characterization of the junctional zone using spectral domain optical coherence tomography. Spectral domain optical coherence tomography volume cube scans (Spectralis OCT, 1024 × 37, Automatic Real Time > 9) were obtained from 15 eyes of 11 patients with GA because of nonneovascular age-related macular degeneration. Volume optical coherence tomography data were imported into previously described validated grading software (3D-OCTOR), and manual segmentation of the retinal pigment epithelium (RPE) and photoreceptor layers was performed on all B-scans (total of 555). Retinal pigment epithelium and photoreceptor defect maps were produced for each case. The borders of the photoreceptor defect area and RPE defect area were delineated individually on separate annotation layers. The two outlines were then superimposed to compare the areas of overlap and nonoverlap. The perimeter of the RPE defect area was calculated by the software in pixels. The superimposed outline of the photoreceptor defect area and the RPE defect area was scrutinized to classify the overlap configuration of the junctional zone into one of three categories: Type 0, exact correspondence between the edge of the RPE defect and photoreceptor defect; Type 1, loss of photoreceptors outside and beyond the edge of the RPE defect; Type 2, preservation of photoreceptors beyond the edge of the RPE defect. The relative proportion of the various border configurations was expressed as a percentage of the perimeter of the RPE defect. Each configuration was then classified into four subgroups according to irregularity of the RPE band and the presence of debris. Fifteen eyes of 11 patients (mean age: 79.3 ± 4.3 years; range: 79-94 years) were included in this study. Seventeen GA lesions were analyzed. Two hundred and thirty-two B-scans were found to pass through the GA lesions, yielding 612 individual GA borders which were separately analyzed and classified. The mean area of the RPE defect was 4.0 ± 4.4 mm, which was significantly smaller than that of the photoreceptor defect which measured 4.4 ± 4.1 mm (paired t test, P = 0.037). On average, 18.0 ± 9.6% (range, 2.3-36.6%) of the junctional zone was of the Type 0 configuration, 57.3 ± 19.0% (range, 21.3-96.8%) was Type 1, and 24.7 ± 18.0% (range, 0.9-64.4%) was Type 2. Type 1 was more prevalent than Type 0 and 2 (analysis of variance, P = 0.000). Debris was present at the margin of the defect in 24.3% (149 of 612) of all assessed junctional zones; 20.0% (14 of 70) of Type 0 junctions, 28.7% (120 of 418) of Type 1, and 12.1% (15 of 124) of Type 2. Debris was more common in Type 1 than Type 2 junctions (P < 0.001). Retinal pigment epithelial irregularity was present at the margin of the defect in 34.8% (213 of 612) of all assessed junctional zones; 52.9% (37 of 70) of Type 0 junctions, 38.0% (159 of 418) of Type 1, and 13.7% (17 of 124) of Type 2. Retinal pigment epithelial irregularity was present more often at Type 0 and Type 1 than at Type 2 junctions (P < 0.001 for both). The size of the optical coherence tomography-visible RPE and photoreceptor defect in GA lesions differ significantly. There were significant areas where the photoreceptor outer segments were preserved despite the absence of visible RPE cells, and also areas of photoreceptor outer segment loss despite apparent RPE preservation. These findings have implications for development of therapeutic strategies, particularly cell-replacement approaches.

OPEN PIT MINE 3D MAPPING BY TLS AND DIGITAL PHOTOGRAMMETRY: 3D MODEL UPDATE THANKS TO A SLAM BASED APPROACH

Abstract. The state of the art of 3D surveying technologies, if correctly applied, allows to obtain 3D coloured models of large open pit mines using different technologies as terrestrial laser scanner (TLS), with images, combined with UAV based digital photogrammetry. GNSS and/or total station are also currently used to geo reference the model. The University of Brescia has been realised a project to map in 3D an open pit mine located in Botticino, a famous location of marble extraction close to Brescia in North Italy. Terrestrial Laser Scanner 3D point clouds combined with RGB images and digital photogrammetry from UAV have been used to map a large part of the cave. By rigorous and well know procedures a 3D point cloud and mesh model have been obtained using an easy and rigorous approach. After the description of the combined mapping process, the paper describes the innovative process proposed for the daily/weekly update of the model itself. To realize this task a SLAM technology approach is described, using an innovative approach based on an innovative instrument capable to run an automatic localization process and real time on the field change detection analysis.

Automatic Real Time System for Traffic Security and Violation Detection

Automatic Real Time System for Traffic Security and Violation Detection

Boosting Based Implementationof Biometric Authentication in IoT

In security and control application the biometric authentication played a specific and important role to identify the person. Analysis of face recognization is the prerequisite process for the entire authentication. This paper focuses an automatic real-time implementation of face recognization system by highlevel description language such as python. Comparing the biometrics where still images are used, video based biometric holds ample information than a single image. It provides the innovative solution for automatic real time face recognition from the video by the following algorithms like Adaboost, Haar cascade classifier and local binary pattern Histogram (LBPH). From the video stream, the input images are trained by adaboost algorithm which is implemented in cascade classifier. AdaBoost is called as adaptive boosting algorithm. It is a learning algorithm which has been combined with a weak classifier in order to form a strong classifier. Here, the real time testing image is compared with the 627 frames of trained images which are obtained from 47.7 MB (56088648 bytes) video. The hardware implementation of face recognization is obtained and the result can be stored and viewed in http://169.254.108.24. Thus by the above said procedures are authenticated by the combinational performance of Adaboost and Cascade classifier.