Search results for: viterbi algorithm

Authors: Alessandro Evangelista, Vito M. Manghisi, Michele Gattullo, Enricoandrea Laviola

Abstract:

In this work, we propose a custom visualization technique for Out-Of-View-Objects in Virtual and Augmented Reality applications using Head Mounted Displays. In the last two decades, Augmented Reality (AR) and Virtual Reality (VR) technologies experienced a remarkable growth of applications for navigation, interaction, and collaboration in different types of environments, real or virtual. Both environments can be potentially very complex, as they can include many virtual objects located in different places. Given the natural limitation of the human Field of View (about 210° horizontal and 150° vertical), humans cannot perceive objects outside this angular range. Moreover, despite recent technological advances in AR e VR Head-Mounted Displays (HMDs), these devices still suffer from a limited Field of View, especially regarding Optical See-Through displays, thus greatly amplifying the challenge of visualizing out-of-view objects. This problem is not negligible when the user needs to be aware of the number and the position of the out-of-view objects in the environment. For instance, during a maintenance operation on a construction site where virtual objects serve to improve the dangers' awareness. Providing such information can enhance the comprehension of the scene, enable fast navigation and focused search, and improve users' safety. In our research, we investigated how to represent out-of-view-objects in HMD User Interfaces (UI). Inspired by commercial video games such as Call of Duty Modern Warfare, we designed a customized Compass. By exploiting the Unity 3D graphics engine, we implemented our custom solution that can be used both in AR and VR environments. The Compass Bar consists of a graduated bar (in degrees) at the top center of the UI. The values of the bar range from -180 (far left) to +180 (far right), the zero is placed in front of the user. Two vertical lines on the bar show the amplitude of the user's field of view. Every virtual object within the scene is represented onto the compass bar as a specific color-coded proxy icon (a circular ring with a colored dot at its center). To provide the user with information about the distance, we implemented a specific algorithm that increases the size of the inner dot as the user approaches the virtual object (i.e., when the user reaches the object, the dot fills the ring). This visualization technique for out-of-view objects has some advantages. It allows users to be quickly aware of the number and the position of the virtual objects in the environment. For instance, if the compass bar displays the proxy icon at about +90, users will immediately know that the virtual object is to their right and so on. Furthermore, by having qualitative information about the distance, users can optimize their speed, thus gaining effectiveness in their work. Given the small size and position of the Compass Bar, our solution also helps lessening the occlusion problem thus increasing user acceptance and engagement. As soon as the lockdown measures will allow, we will carry out user-tests comparing this solution with other state-of-the-art existing ones such as 3D Radar, SidebARs and EyeSee360.

Keywords: augmented reality, situation awareness, virtual reality, visualization design

Procedia PDF Downloads 126

Authors: Lucia Billeci, Gennaro Tartarisco, Maurizio Varanini

Abstract:

Fetal cardiac monitoring by fetal electrocardiogram (fECG) can provide significant clinical information about the healthy condition of the fetus. Despite this potentiality till now the use of fECG in clinical practice has been quite limited due to the difficulties in its measuring. The recovery of fECG from the signals acquired non-invasively by using electrodes placed on the maternal abdomen is a challenging task because abdominal signals are a mixture of several components and the fetal one is very weak. This paper presents an approach for fECG extraction from abdominal maternal recordings, which exploits the characteristics of pseudo-periodicity of fetal ECG. It consists of devising a quality index (fQI) for fECG and of finding the linear combinations of preprocessed abdominal signals, which maximize these fQI (quality index optimization - QIO). It aims at improving the performances of the most commonly adopted methods for fECG extraction, usually based on maternal ECG (mECG) estimating and canceling. The procedure for the fECG extraction and fetal QRS (fQRS) detection is completely unsupervised and based on the following steps: signal pre-processing; maternal ECG (mECG) extraction and maternal QRS detection; mECG component approximation and canceling by weighted principal component analysis; fECG extraction by fQI maximization and fetal QRS detection. The proposed method was compared with our previously developed procedure, which obtained the highest at the Physionet/Computing in Cardiology Challenge 2013. That procedure was based on removing the mECG from abdominal signals estimated by a principal component analysis (PCA) and applying the Independent component Analysis (ICA) on the residual signals. Both methods were developed and tuned using 69, 1 min long, abdominal measurements with fetal QRS annotation of the dataset A provided by PhysioNet/Computing in Cardiology Challenge 2013. The QIO-based and the ICA-based methods were compared in analyzing two databases of abdominal maternal ECG available on the Physionet site. The first is the Abdominal and Direct Fetal Electrocardiogram Database (ADdb) which contains the fetal QRS annotations thus allowing a quantitative performance comparison, the second is the Non-Invasive Fetal Electrocardiogram Database (NIdb), which does not contain the fetal QRS annotations so that the comparison between the two methods can be only qualitative. In particular, the comparison on NIdb was performed defining an index of quality for the fetal RR series. On the annotated database ADdb the QIO method, provided the performance indexes Sens=0.9988, PPA=0.9991, F1=0.9989 overcoming the ICA-based one, which provided Sens=0.9966, PPA=0.9972, F1=0.9969. The comparison on NIdb was performed defining an index of quality for the fetal RR series. The index of quality resulted higher for the QIO-based method compared to the ICA-based one in 35 records out 55 cases of the NIdb. The QIO-based method gave very high performances with both the databases. The results of this study foresees the application of the algorithm in a fully unsupervised way for the implementation in wearable devices for self-monitoring of fetal health.

Keywords: fetal electrocardiography, fetal QRS detection, independent component analysis (ICA), optimization, wearable

Procedia PDF Downloads 278

Authors: Sudipto Sarkar, Anamika Paul

Abstract:

Pseudoplastic (n<1, n is the power index) fluids have great importance in food, pharmaceutical and chemical process industries which require a lot of attention. Unfortunately, due to its complex flow behavior inadequate research works can be found even in laminar flow regime. A practical problem is solved in the present research work by numerical simulation where we tried to control the vortex shedding from a square cylinder using a horizontal splitter plate placed at the downstream flow region. The position of the plate is at the centerline of the cylinder with varying distance from the cylinder to calculate the critical gap-ratio. If the plate is placed inside this critical gap, the vortex shedding from the cylinder suppressed completely. The Reynolds number considered here is in unsteady laminar vortex shedding regime, Re = 100 (Re = U∞a/ν, where U∞ is the free-stream velocity of the flow, a is the side of the cylinder and ν is the maximum value of kinematic viscosity of the fluid). Flow behavior has been studied for three different gap-ratios (G/a = 2, 2.25 and 2.5, where G is the gap between cylinder and plate) and for a fluid with three different flow behavior indices (n =1, 0.8 and 0.5). The flow domain is constructed using Gambit 2.2.30 and this software is also used to generate the mesh and to impose the boundary conditions. For G/a = 2, the domain size is considered as 37.5a × 16a with 316 × 208 grid points in the streamwise and flow-normal directions respectively after a thorough grid independent study. Fine and equal grid spacing is used close to the geometry to capture the vortices shed from the cylinder and the boundary layer developed over the flat plate. Away from the geometry meshes are unequal in size and stretched out. For other gap-ratios, proportionate domain size and total grid points are used with similar kind of mesh distribution. Velocity inlet (u = U∞), pressure outlet (Neumann condition), symmetry (free-slip boundary condition) at upper and lower domain boundary conditions are used for the simulation. Wall boundary condition (u = v = 0) is considered both on the cylinder and the splitter plate surfaces. Discretized forms of fully conservative 2-D unsteady Navier Stokes equations are then solved by Ansys Fluent 14.5. SIMPLE algorithm written in finite volume method is selected for this purpose which is a default solver inculcate in Fluent. The results obtained for Newtonian fluid flow agree well with previous works supporting Fluent’s usefulness in academic research. A thorough analysis of instantaneous and time-averaged flow fields are depicted both for Newtonian and pseudoplastic fluid flow. It has been observed that as the value of n reduces the stretching of shear layers also reduce and these layers try to roll up before the plate. For flow with high pseudoplasticity (n = 0.5) the nature of vortex shedding changes and the value of critical gap-ratio reduces. These are the remarkable findings for laminar periodic vortex shedding regime in pseudoplastic flow environment.

Keywords: CFD, pseudoplastic fluid flow, wake-boundary layer interactions, critical gap-ratio

Procedia PDF Downloads 110

Authors: Nutcha Taneepanichskul, Helen C. Hailes, Mark Miodownik

Abstract:

Plastic waste has emerged as a critical global environmental challenge, primarily driven by the prevalent use of conventional plastics derived from petrochemical refining and manufacturing processes in modern packaging. While these plastics serve vital functions, their persistence in the environment post-disposal poses significant threats to ecosystems. Addressing this issue necessitates approaches, one of which involves the development of biodegradable plastics designed to degrade under controlled conditions, such as industrial composting facilities. It is imperative to note that compostable plastics are engineered for degradation within specific environments and are not suited for uncontrolled settings, including natural landscapes and aquatic ecosystems. The full benefits of compostable packaging are realized when subjected to industrial composting, preventing environmental contamination and waste stream pollution. Therefore, effective sorting technologies are essential to enhance composting rates for these materials and diminish the risk of contaminating recycling streams. In this study, it leverage hyperspectral imaging technology (HSI) coupled with advanced machine learning algorithms to accurately identify various types of plastics, encompassing conventional variants like Polyethylene terephthalate (PET), Polypropylene (PP), Low density polyethylene (LDPE), High density polyethylene (HDPE) and biodegradable alternatives such as Polybutylene adipate terephthalate (PBAT), Polylactic acid (PLA), and Polyhydroxyalkanoates (PHA). The dataset is partitioned into three subsets: a training dataset comprising uncontaminated conventional and biodegradable plastics, a validation dataset encompassing contaminated plastics of both types, and a testing dataset featuring real-world packaging items in both pristine and contaminated states. Five distinct machine learning algorithms, namely Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Logistic Regression, and Decision Tree Algorithm, were developed and evaluated for their classification performance. Remarkably, the Logistic Regression and CNN model exhibited the most promising outcomes, achieving a perfect accuracy rate of 100% for the training and validation datasets. Notably, the testing dataset yielded an accuracy exceeding 80%. The successful implementation of this sorting technology within recycling and composting facilities holds the potential to significantly elevate recycling and composting rates. As a result, the envisioned circular economy for plastics can be established, thereby offering a viable solution to mitigate plastic pollution.

Keywords: biodegradable plastics, sorting technology, hyperspectral imaging technology, machine learning algorithms

Procedia PDF Downloads 77

Authors: Mattias Bergstrom

Abstract:

Significance of the Study: This research will provide new insights into the risks with digital embedded infrastructure. Through this research, we will analyze each risk and its potential negation strategies, especially for AI and autonomous automation. Moreover, the analysis that is presented in this paper will convey valuable information for future research that can create more stable, secure, and efficient autonomous systems. To learn and understand the risks, a large IoT system was envisioned, and risks with hardware, tampering, and cyberattacks were collected, researched, and evaluated to create a comprehensive understanding of the potential risks. Potential solutions have then been evaluated on an open source IoT hardware setup. This list shows the identified passive and active risks evaluated in the research. Passive Risks: (1) Hardware failures- Critical Systems relying on high rate data and data quality are growing; SCADA systems for infrastructure are good examples of such systems. (2) Hardware delivers erroneous data- Sensors break, and when they do so, they don’t always go silent; they can keep going, just that the data they deliver is garbage, and if that data is not filtered out, it becomes disruptive noise in the system. (3) Bad Hardware injection- Erroneous generated sensor data can be pumped into a system by malicious actors with the intent to create disruptive noise in critical systems. (4) Data gravity- The weight of the data collected will affect Data-Mobility. (5) Cost inhibitors- Running services that need huge centralized computing is cost inhibiting. Large complex AI can be extremely expensive to run. Active Risks: Denial of Service- It is one of the most simple attacks, where an attacker just overloads the system with bogus requests so that valid requests disappear in the noise. Malware- Malware can be anything from simple viruses to complex botnets created with specific goals, where the creator is stealing computer power and bandwidth from you to attack someone else. Ransomware- It is a kind of malware, but it is so different in its implementation that it is worth its own mention. The goal with these pieces of software is to encrypt your system so that it can only be unlocked with a key that is held for ransom. DNS spoofing- By spoofing DNS calls, valid requests and data dumps can be sent to bad destinations, where the data can be extracted for extortion or to corrupt and re-inject into a running system creating a data echo noise loop. After testing multiple potential solutions. We found that the most prominent solution to these risks was to use a Peer 2 Peer consensus algorithm over a blockchain to validate the data and behavior of the devices (sensors, storage, and computing) in the system. By the devices autonomously policing themselves for deviant behavior, all risks listed above can be negated. In conclusion, an Internet middleware that provides these features would be an easy and secure solution to any future autonomous IoT deployments. As it provides separation from the open Internet, at the same time, it is accessible over the blockchain keys.

Keywords: IoT, security, infrastructure, SCADA, blockchain, AI

Procedia PDF Downloads 106

Authors: Almudena Espin Perez, Tyler Risom, Carl Pelz, Isabel English, Robert M. Angelo, Rosalie Sears, Andrew J. Gentles

Abstract:

Pancreatic ductal adenocarcinoma (PDAC) is one of the most deadly malignancies. The role of the tumor microenvironment (TME) is gaining significant attention in cancer research. Despite ongoing efforts, the nature of the interactions between tumors, immune cells, and stromal cells remains poorly understood. The cell-intrinsic properties that govern cell lineage plasticity in PDAC and extrinsic influences of immune populations require technically challenging approaches due to the inherently heterogeneous nature of PDAC. Understanding the cell lineage plasticity of PDAC will improve the development of novel strategies that could be translated to the clinic. Members of the team have demonstrated that the acquisition of ductal to neuroendocrine lineage plasticity in PDAC confers therapeutic resistance and is a biomarker of poor outcomes in patients. Our approach combines computational methods for deconvolving bulk transcriptomic cancer data using CIBERSORTx and high-throughput single-cell imaging using Multiplexed Ion Beam Imaging (MIBI) to study lineage plasticity in PDAC and its relationship to the infiltrating immune system. The CIBERSORTx algorithm uses signature matrices from immune cells and stroma from sorted and single-cell data in order to 1) infer the fractions of different immune cell types and stromal cells in bulked gene expression data and 2) impute a representative transcriptome profile for each cell type. We studied a unique set of 300 genomically well-characterized primary PDAC samples with rich clinical annotation. We deconvolved the PDAC transcriptome profiles using CIBERSORTx, leveraging publicly available single-cell RNA-seq data from normal pancreatic tissue and PDAC to estimate cell type proportions in PDAC, and digitally reconstruct cell-specific transcriptional profiles from our study dataset. We built signature matrices and optimized by simulations and comparison to ground truth data. We identified cell-type-specific transcriptional programs that contribute to cancer cell lineage plasticity, especially in the ductal compartment. We also studied cell differentiation hierarchies using CytoTRACE and predict cell lineage trajectories for acinar and ductal cells that we believe are pinpointing relevant information on PDAC progression. Collaborators (Angelo lab, Stanford University) has led the development of the Multiplexed Ion Beam Imaging (MIBI) platform for spatial proteomics. We will use in the very near future MIBI from tissue microarray of 40 PDAC samples to understand the spatial relationship between cancer cell lineage plasticity and stromal cells focused on infiltrating immune cells, using the relevant markers of PDAC plasticity identified from the RNA-seq analysis.

Keywords: deconvolution, imaging, microenvironment, PDAC

Procedia PDF Downloads 126

Authors: Qian Chen, Lin Xu, Ping Ju, Zhuoran Li, Yiping Yu, Yuqing Jin

Abstract:

The operation of power grid is becoming more and more complex and difficult due to its rapid development towards high voltage, long distance, and large capacity. For instance, many large-scale wind farms have connected to power grid, where their fluctuation and randomness is very likely to affect the stability and safety of the grid. Fortunately, many new-type equipments based on power electronics have been applied to power grid, such as UPFC (Unified Power Flow Controller), TCSC (Thyristor Controlled Series Compensation), STATCOM (Static Synchronous Compensator) and so on, which can help to deal with the problem above. Compared with traditional equipment such as generator, new-type controllable devices, represented by the FACTS (Flexible AC Transmission System), have more accurate control ability and respond faster. But they are too expensive to use widely. Therefore, on the basis of the comparison and analysis of the controlling characteristics between traditional control equipment and new-type controllable equipment in both time and space scale, a coordinated optimizing control method within mutil-time-space frame is proposed in this paper to bring both kinds of advantages into play, which can better both control ability and economical efficiency. Firstly, the coordination of different space sizes of grid is studied focused on the fluctuation caused by large-scale wind farms connected to power grid. With generator, FSC (Fixed Series Compensation) and TCSC, the coordination method on two-layer regional power grid vs. its sub grid is studied in detail. The coordination control model is built, the corresponding scheme is promoted, and the conclusion is verified by simulation. By analysis, interface power flow can be controlled by generator and the specific line power flow between two-layer regions can be adjusted by FSC and TCSC. The smaller the interface power flow adjusted by generator, the bigger the control margin of TCSC, instead, the total consumption of generator is much higher. Secondly, the coordination of different time sizes is studied to further the amount of the total consumption of generator and the control margin of TCSC, where the minimum control cost can be acquired. The coordination method on two-layer ultra short-term correction vs. AGC (Automatic Generation Control) is studied with generator, FSC and TCSC. The optimal control model is founded, genetic algorithm is selected to solve the problem, and the conclusion is verified by simulation. Finally, the aforementioned method within multi-time-space scale is analyzed with practical cases, and simulated on PSASP (Power System Analysis Software Package) platform. The correctness and effectiveness are verified by the simulation result. Moreover, this coordinated optimizing control method can contribute to the decrease of control cost and will provide reference to the following studies in this field.

Keywords: FACTS, multi-space-time frame, optimal control, TCSC

Procedia PDF Downloads 265

Authors: Sharon Hovav, Ilya Levner, Oren Nahum, Istvan Szabo

Abstract:

In modern large-scale logistic centers (e.g., big automated warehouses), complex logistic operations performed by human staff (pickers) need to be coordinated with the operations of automated facilities (robots, conveyors, cranes, lifts, flow racks, etc.). The efficiency of advanced logistic centers strongly depends on optimizing picking technologies in synch with the facility/product layout, as well as on optimal distribution of material flows (products) in the system. The challenge is to develop a mathematical operations research (OR) tool that will optimize system cost-effectiveness. In this work, we propose a model that describes an automatic logistic center consisting of a set of workstations located at several galleries (floors), with each station containing a known number of flow racks. The requirements of each product and the working capacity of stations served by a given set of workers (pickers) are assumed as predetermined. The goal of the model is to maximize system efficiency. The proposed model includes two echelons. The first is the setting of the (optimal) number of workstations needed to create the total processing/logistic system, subject to picker capacities. The second echelon deals with the assignment of the products to the workstations and flow racks, aimed to achieve maximal throughputs of picked products over the entire system given picker capacities and budget constraints. The solutions to the problems at the two echelons interact to balance the overall load in the flow racks and maximize overall efficiency. We have developed an operations research model within each echelon. In the first echelon, the problem of calculating the optimal number of workstations is formulated as a non-standard bin-packing problem with capacity constraints for each bin. The problem arising in the second echelon is presented as a constrained product-workstation-flow rack assignment problem with non-standard mini-max criteria in which the workload maximum is calculated across all workstations in the center and the exterior minimum is calculated across all possible product-workstation-flow rack assignments. The OR problems arising in each echelon are proved to be NP-hard. Consequently, we find and develop heuristic and approximation solution algorithms based on exploiting and improving local optimums. The LC model considered in this work is highly dynamic and is recalculated periodically based on updated demand forecasts that reflect market trends, technological changes, seasonality, and the introduction of new items. The suggested two-echelon approach and the min-max balancing scheme are shown to work effectively on illustrative examples and real-life logistic data.

Keywords: logistics center, product-workstation, assignment, maximum performance, load balancing, fast algorithm

Procedia PDF Downloads 226

Authors: Khethiwe Mtshali, Zamantungwa T. H. Khumalo, Stanford Kwenda, Ismail Arshad, Oriel M. M. Thekisoe

Abstract:

Ecologically, the gut, mammary glands and bloodstream consist of distinct microbial communities of commensals, mutualists and pathogens, forming a complex ecosystem of niches. The by-products derived from these body sites i.e. faeces, milk and blood, respectively, have many uses in rural communities where they aid in the facilitation of day-to-day household activities and occasional rituals. Thus, although livestock rearing plays a vital role in the sustenance of the livelihoods of rural communities, it may serve as a potent reservoir of different pathogenic organisms that could have devastating health and economic implications. This study aimed to simultaneously explore the microbial profiles of corresponding faecal, milk and blood samples from lactating cows using 16S rRNA metagenomic sequencing. Bacterial communities were inferred through the Divisive Amplicon Denoising Algorithm 2 (DADA2) pipeline coupled with SILVA database v138. All downstream analyses were performed in R v3.6.1. Alpha-diversity metrics showed significant differences between faeces and blood, faeces and milk, but did not vary significantly between blood and milk (Kruskal-Wallis, P < 0.05). Beta-diversity metrics on Principal Coordinate Analysis (PCoA) and Non-Metric Dimensional Scaling (NMDS) clustered samples by type, suggesting that microbial communities of the studied niches are significantly different (PERMANOVA, P < 0.05). A number of taxa were significantly differentially abundant (DA) between groups based on the Wald test implemented in the DESeq2 package (Padj < 0.01). The majority of the DA taxa were significantly enriched in faeces than in milk and blood, except for the genus Anaplasma, which was significantly enriched in blood and was, in turn, the most abundant taxon overall. A total of 30 phyla, 74 classes, 156 orders, 243 families and 408 genera were obtained from the overall analysis. The most abundant phyla obtained between the three body sites were Firmicutes, Bacteroidota, and Proteobacteria. A total of 58 genus-level taxa were simultaneously detected between the sample groups, while bacterial signatures of at least 8 of these occurred concurrently in corresponding faeces, milk and blood samples from the same group of animals constituting a pool. The important taxa identified in this study could be categorized into four potentially pathogenic clusters: i) arthropod-borne; ii) food-borne and zoonotic; iii) mastitogenic and; iv) metritic and abortigenic. This study provides insight into the microbial composition of bovine faeces, milk, and blood and its extent of overlapping. It further highlights the potential risk of disease occurrence and transmission between the animals and the inhabitants of the sampled rural community, pertaining to their unsanitary practices associated with the use of cattle by-products.

Keywords: microbial profiling, 16S rRNA, NGS, feces, milk, blood, lactating cows, small-scale farmers

Procedia PDF Downloads 109

Authors: Pei-Jyun Hsieh, Cheng-Hsuan Li, Bor-Chen Kuo

Abstract:

For hyperspectral image classification, feature reduction is an important pre-processing for avoiding the Hughes phenomena due to the difficulty for collecting training samples. Hence, lots of researches developed feature selection methods such as F-score, HSIC (Hilbert-Schmidt Independence Criterion), and etc., to improve hyperspectral image classification. However, most of them only consider the class separability in the original space, i.e., a linear class separability. In this study, we proposed a nonlinear class separability measure based on kernel trick for selecting an appropriate feature subset. The proposed nonlinear class separability was formed by a generalized RBF kernel with different bandwidths with respect to different features. Moreover, it considered the within-class separability and the between-class separability. A genetic algorithm was applied to tune these bandwidths such that the smallest with-class separability and the largest between-class separability simultaneously. This indicates the corresponding feature space is more suitable for classification. In addition, the corresponding nonlinear classification boundary can separate classes very well. These optimal bandwidths also show the importance of bands for hyperspectral image classification. The reciprocals of these bandwidths can be viewed as weights of bands. The smaller bandwidth, the larger weight of the band, and the more importance for classification. Hence, the descending order of the reciprocals of the bands gives an order for selecting the appropriate feature subsets. In the experiments, three hyperspectral image data sets, the Indian Pine Site data set, the PAVIA data set, and the Salinas A data set, were used to demonstrate the selected feature subsets by the proposed nonlinear feature selection method are more appropriate for hyperspectral image classification. Only ten percent of samples were randomly selected to form the training dataset. All non-background samples were used to form the testing dataset. The support vector machine was applied to classify these testing samples based on selected feature subsets. According to the experiments on the Indian Pine Site data set with 220 bands, the highest accuracies by applying the proposed method, F-score, and HSIC are 0.8795, 0.8795, and 0.87404, respectively. However, the proposed method selects 158 features. F-score and HSIC select 168 features and 217 features, respectively. Moreover, the classification accuracies increase dramatically only using first few features. The classification accuracies with respect to feature subsets of 10 features, 20 features, 50 features, and 110 features are 0.69587, 0.7348, 0.79217, and 0.84164, respectively. Furthermore, only using half selected features (110 features) of the proposed method, the corresponding classification accuracy (0.84168) is approximate to the highest classification accuracy, 0.8795. For other two hyperspectral image data sets, the PAVIA data set and Salinas A data set, we can obtain the similar results. These results illustrate our proposed method can efficiently find feature subsets to improve hyperspectral image classification. One can apply the proposed method to determine the suitable feature subset first according to specific purposes. Then researchers can only use the corresponding sensors to obtain the hyperspectral image and classify the samples. This can not only improve the classification performance but also reduce the cost for obtaining hyperspectral images.

Keywords: hyperspectral image classification, nonlinear feature selection, kernel trick, support vector machine

Procedia PDF Downloads 262

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 120

Authors: Jérôme de Reffye, Marc Antoni

Abstract:

Following the development of the ERTMS system, we think it is interesting to develop another software-based track circuit system which would fit secondary railway lines with an easy-to-work implementation and a low sensitivity to rail-wheel impedance variations. We called this track circuit 'Track Railway by Automatic Circuits.' To be internationally implemented, this system must not have any mechanical component and must be compatible with existing track circuit systems. For example, the system is independent from the French 'Joints Isolants Collés' that isolate track sections from one another, and it is equally independent from component used in Germany called 'Counting Axles,' in French 'compteur d’essieux.' This track circuit is fully interoperable. Such universality is obtained by replacing the train detection mechanical system with a space-time filtering of train position. The various track sections are defined by the frequency of a continuous signal. The set of frequencies related to the track sections is a set of orthogonal functions in a Hilbert Space. Thus the failure probability of track sections separation is precisely calculated on the basis of signal-to-noise ratio. SNR is a function of the level of traction current conducted by rails. This is the reason why we developed a very powerful algorithm to reject noise and jamming to obtain an SNR compatible with the precision required for the track circuit and SIL 4 level. The SIL 4 level is thus reachable by an adjustment of the set of orthogonal functions. Our major contributions to railway engineering signalling science are i) Train space localization is precisely defined by a calibration system. The operation bypasses the GSM-R radio system of the ERTMS system. Moreover, the track circuit is naturally protected against radio-type jammers. After the calibration operation, the track circuit is autonomous. ii) A mathematical topology adapted to train space localization by following the train through a linear time filtering of the received signal. Track sections are numerically defined and can be modified with a software update. The system was numerically simulated, and results were beyond our expectations. We achieved a precision of one meter. Rail-ground and rail-wheel impedance sensitivity analysis gave excellent results. Results are now complete and ready to be published. This work was initialised as a research project of the French Railways developed by the Pi-Ramses Company under SNCF contract and required five years to obtain the results. This track circuit is already at Level 3 of the ERTMS system, and it will be much cheaper to implement and to work. The traffic regulation is based on variable length track sections. As the traffic growths, the maximum speed is reduced, and the track section lengths are decreasing. It is possible if the elementary track section is correctly defined for the minimum speed and if every track section is able to emit with variable frequencies.

Keywords: track section, track circuits, space-time crossing, adaptive track section, automatic railway signalling

Procedia PDF Downloads 331

Authors: Georges Ghazi, Magali Gelhaye, Ruxandra Botez

Abstract:

Over the years, the Flight Management System (FMS) has experienced a continuous improvement of its many features, to the point of becoming the pilot’s primary interface for flight planning operation on the airplane. With the assistance of the FMS, the concept of distance and time has been completely revolutionized, providing the crew members with the determination of the optimized route (or flight plan) from the departure airport to the arrival airport. To accomplish this function, the FMS needs an accurate Aircraft Performance Model (APM) of the aircraft. In general, APMs that equipped most modern FMSs are established before the entry into service of an individual aircraft, and results from the combination of a set of ordinary differential equations and a set of performance databases. Unfortunately, an aircraft in service is constantly exposed to dynamic loads that degrade its flight characteristics. These degradations endow two main origins: airframe deterioration (control surfaces rigging, seals missing or damaged, etc.) and engine performance degradation (fuel consumption increase for a given thrust). Thus, after several years of service, the performance databases and the APM associated to a specific aircraft are no longer representative enough of the actual aircraft performance. It is important to monitor the trend of the performance deterioration and correct the uncertainties of the aircraft model in order to improve the accuracy the flight management system predictions. The basis of this research lies in the new ability to continuously update an Aircraft Performance Model (APM) during flight using an adaptive lookup table technique. This methodology was developed and applied to the well-known Cessna Citation X business aircraft. For the purpose of this study, a level D Research Aircraft Flight Simulator (RAFS) was used as a test aircraft. According to Federal Aviation Administration the level D is the highest certification level for the flight dynamics modeling. Basically, using data available in the Flight Crew Operating Manual (FCOM), a first APM describing the variation of the engine fan speed and aircraft fuel flow w.r.t flight conditions was derived. This model was next improved using the proposed methodology. To do that, several cruise flights were performed using the RAFS. An algorithm was developed to frequently sample the aircraft sensors measurements during the flight and compare the model prediction with the actual measurements. Based on these comparisons, a correction was performed on the actual APM in order to minimize the error between the predicted data and the measured data. In this way, as the aircraft flies, the APM will be continuously enhanced, making the FMS more and more precise and the prediction of trajectories more realistic and more reliable. The results obtained are very encouraging. Indeed, using the tables initialized with the FCOM data, only a few iterations were needed to reduce the fuel flow prediction error from an average relative error of 12% to 0.3%. Similarly, the FCOM prediction regarding the engine fan speed was reduced from a maximum error deviation of 5.0% to 0.2% after only ten flights.

Keywords: aircraft performance, cruise, trajectory optimization, adaptive lookup tables, Cessna Citation X

Procedia PDF Downloads 263

Authors: Joana Almeida, Kendall Reid, Jonas Bengtsson

Abstract:

Pallets are devices that are used for moving and storing freight and are nearly omnipresent in supply chains. The market is dominated by timber pallets, with plastic being a common alternative. Either option underpins the use of important resources (oil, land, timber), the emission of greenhouse gases and additional waste generation in most supply chains. This study uses a dynamic approach to the life cycle assessment (LCA) of pallets. It demonstrates that what ultimately defines the environmental burden of pallets in the supply chain is how often the length of its lifespan, which depends on the durability of the material and on how pallets are utilized. This study proposes a life cycle assessment (LCA) of pallets in supply chains supported by an algorithm that estimates pallet durability in function of material resilience and of logistics. The LCA runs from cradle-to-grave, including raw material provision, manufacture, transport and end of life. The scope is representative of timber and plastic pallets in the Australian and South-East Asia markets. The materials included in this analysis are: -tropical mixed hardwood, unsustainably harvested in SE Asia; -certified softwood, sustainably harvested; -conventional plastic, a mix of virgin and scrap plastic; -recycled plastic pallets, 100% mixed plastic scrap, which are being pioneered by Re > Pal. The logistical model purports that more complex supply chains and rougher handling subject pallets to higher stress loads. More stress shortens the lifespan of pallets in function of their composition. Timber pallets can be repaired, extending their lifespan, while plastic pallets cannot. At the factory gate, softwood pallets have the lowest carbon footprint. Re > pal follows closely due to its burden-free feedstock. Tropical mixed hardwood and plastic pallets have the highest footprints. Harvesting tropical mixed hardwood in SE Asia often leads to deforestation, leading to emissions from land use change. The higher footprint of plastic pallets is due to the production of virgin plastic. Our findings show that manufacture alone does not determine the sustainability of pallets. Even though certified softwood pallets have lower carbon footprint and their lifespan can be extended by repair, the need for re-supply of materials and disposal of waste timber offsets this advantage. It also leads to most waste being generated among all pallets. In a supply chain context, Re > Pal pallets have the lowest footprint due to lower replacement and disposal needs. In addition, Re > Pal are nearly ‘waste neutral’, because the waste that is generated throughout their life cycle is almost totally offset by the scrap uptake for production. The absolute results of this study can be confirmed by progressing the logistics model, improving data quality, expanding the range of materials and utilization practices. Still, this LCA demonstrates that considering logistics, raw materials and material durability is central for sustainable decision-making on pallet purchasing, management and disposal.

Keywords: carbon footprint, life cycle assessment, recycled plastic, waste

Procedia PDF Downloads 221

Authors: Harpal Singh, Sakshi Batra

Abstract:

The widespread and easy accesses to multimedia contents and possibility to make numerous copies without loss of significant fidelity have roused the requirement of digital rights management. Thus this problem can be effectively solved by Digital watermarking technology. This is a concept of embedding some sort of data or special pattern (watermark) in the multimedia content; this information will later prove ownership in case of a dispute, trace the marked document’s dissemination, identify a misappropriating person or simply inform user about the rights-holder. The primary motive of digital watermarking is to embed the data imperceptibly and robustly in the host information. Extensive counts of watermarking techniques have been developed to embed copyright marks or data in digital images, video, audio and other multimedia objects. With the development of digital video-based innovations, copyright dilemma for the multimedia industry increases. Video watermarking had been proposed in recent years to serve the issue of illicit copying and allocation of videos. It is the process of embedding copyright information in video bit streams. Practically video watermarking schemes have to address some serious challenges as compared to image watermarking schemes like real-time requirements in the video broadcasting, large volume of inherently redundant data between frames, the unbalance between the motion and motionless regions etc. and they are particularly vulnerable to attacks, for example, frame swapping, statistical analysis, rotation, noise, median and crop attacks. In this paper, an effective, robust and imperceptible video watermarking algorithm is proposed based on hybridization of powerful mathematical transforms; Fractional Fourier Transform (FrFT), Discrete Wavelet transforms (DWT) and Singular Value Decomposition (SVD) using redundant wavelet. This scheme utilizes various transforms for embedding watermarks on different layers by using Hybrid systems. For this purpose, the video frames are portioned into layers (RGB) and the watermark is being embedded in two forms in the video frames using SVD portioning of the watermark, and DWT sub-band decomposition of host video, to facilitate copyright safeguard as well as reliability. The FrFT orders are used as the encryption key that allows the watermarking method to be more robust against various attacks. The fidelity of the scheme is enhanced by introducing key generation and wavelet based key embedding watermarking scheme. Thus, for watermark embedding and extraction, same key is required. Therefore the key must be shared between the owner and the verifier via some safe network. This paper demonstrates the performance by considering different qualitative metrics namely Peak Signal to Noise ratio, Structure similarity index and correlation values and also apply some attacks to prove the robustness. The Experimental results are presented to demonstrate that the proposed scheme can withstand a variety of video processing attacks as well as imperceptibility.

Keywords: discrete wavelet transform, robustness, video watermarking, watermark

Procedia PDF Downloads 223

Authors: Dinara F. Gaynutdinova, Vladimir Ya Modorsky, Nikolay A. Shevelev

Abstract:

The problem under research is that of unpredictable modes occurring in two-stage centrifugal hydraulic pump as a result of hydraulic processes caused by vibrations of structural components. Numerical, analytical and experimental approaches are considered. A hypothesis was developed that the problem of unpredictable pressure decrease at the second stage of centrifugal pumps is caused by cavitation effects occurring upon vibration. The problem has been studied experimentally and theoretically as of today. The theoretical study was conducted numerically and analytically. Hydroelastic processes in dynamic “liquid – deformed structure” system were numerically modelled and analysed. Using ANSYS CFX program engineering analysis complex and computing capacity of a supercomputer the cavitation parameters were established to depend on vibration parameters. An influence domain of amplitudes and vibration frequencies on concentration of cavitation bubbles was formulated. The obtained numerical solution was verified using CFM program package developed in PNRPU. The package is based on a differential equation system in hyperbolic and elliptic partial derivatives. The system is solved by using one of finite-difference method options – the particle-in-cell method. The method defines the problem solution algorithm. The obtained numerical solution was verified analytically by model problem calculations with the use of known analytical solutions of in-pipe piston movement and cantilever rod end face impact. An infrastructure consisting of an experimental fast hydro-dynamic processes research installation and a supercomputer connected by a high-speed network, was created to verify the obtained numerical solutions. Physical experiments included measurement, record, processing and analysis of data for fast processes research by using National Instrument signals measurement system and Lab View software. The model chamber end face oscillated during physical experiments and, thus, loaded the hydraulic volume. The loading frequency varied from 0 to 5 kHz. The length of the operating chamber varied from 0.4 to 1.0 m. Additional loads weighed from 2 to 10 kg. The liquid column varied from 0.4 to 1 m high. Liquid pressure history was registered. The experiment showed dependence of forced system oscillation amplitude on loading frequency at various values: operating chamber geometrical dimensions, liquid column height and structure weight. Maximum pressure oscillation (in the basic variant) amplitudes were discovered at loading frequencies of approximately 1,5 kHz. These results match the analytical and numerical solutions in ANSYS and CFM.

Keywords: computing experiment, hydroelasticity, physical experiment, vibration

Procedia PDF Downloads 243

Authors: Bashar Mahmoud, Lee Mortimer, Michael Fairweather

Abstract:

New methods have recently been introduced to improve the thermal property values of molten nitrate salts (a binary mixture of NaNO3:KNO3in 60:40 wt. %), by doping them with minute concentration of nanoparticles in the range of 0.5 to 1.5 wt. % to form the so-called: Nano-heat-transfer-fluid, apt for thermal energy transfer and storage applications. The present study aims to assess the stability of these nanofluids using the advanced computational modelling technique, Lagrangian particle tracking. A multi-phase solid-liquid model is used, where the motion of embedded nanoparticles in the suspended fluid is treated by an Euler-Lagrange hybrid scheme with fixed time stepping. This technique enables measurements of various multi-scale forces whose characteristic (length and timescales) are quite different. Two systems are considered, both consisting of 50 nm Al2O3 ceramic nanoparticles suspended in fluids of different density ratios. This includes both water (5 to 95 °C) and molten nitrate salt (220 to 500 °C) at various volume fractions ranging between 1% to 5%. Dynamic properties of both phases are coupled to the ambient temperature of the fluid suspension. The three-dimensional computational region consists of a 1μm cube and particles are homogeneously distributed across the domain. Periodic boundary conditions are enforced. The particle equations of motion are integrated using the fourth order Runge-Kutta algorithm with a very small time-step, Δts, set at 10-11 s. The implemented technique demonstrates the key dynamics of aggregated nanoparticles and this involves: Brownian motion, soft-sphere particle-particle collisions, and Derjaguin, Landau, Vervey, and Overbeek (DLVO) forces. These mechanisms are responsible for the predictive model of aggregation of nano-suspensions. An energy transport-based method of predicting the thermal conductivity of the nanofluids is also used to determine thermal properties of the suspension. The simulation results confirms the effectiveness of the technique. The values are in excellent agreement with the theoretical and experimental data obtained from similar studies. The predictions indicates the role of Brownian motion and DLVO force (represented by both the repulsive electric double layer and an attractive Van der Waals) and its influence in the level of nanoparticles agglomeration. As to the nano-aggregates formed that was found to play a key role in governing the thermal behavior of nanofluids at various particle concentration. The presentation will include a quantitative assessment of these forces and mechanisms, which would lead to conclusions about nanofluids, heat transfer performance and thermal characteristics and its potential application in solar thermal energy plants.

Keywords: thermal energy storage, molten salt, nano-fluids, multi-scale computational modelling

Procedia PDF Downloads 190

Authors: A. Arshad, M. Lehtonen. M. Humayun

Abstract:

With the increasing Distributed Generation (DG) penetration, distribution systems are advancing towards the smart grid technology for least latency in tackling voltage control problem in a distributed manner. This paper proposes a Multi-agent based distributed voltage level control. In this method a flat architecture of agents is used and agents involved in the whole controlling procedure are On Load Tap Changer Agent (OLTCA), Static VAR Compensator Agent (SVCA), and the agents associated with DGs and loads at their locations. The objectives of the proposed voltage control model are to minimize network losses and DG curtailments while maintaining voltage value within statutory limits as close as possible to the nominal. The total loss cost is the sum of network losses cost, DG curtailment costs, and voltage damage cost (which is based on penalty function implementation). The total cost is iteratively calculated for various stricter limits by plotting voltage damage cost and losses cost against varying voltage limit band. The method provides the optimal limits closer to nominal value with minimum total loss cost. In order to achieve the objective of voltage control, the whole network is divided into multiple control regions; downstream from the controlling device. The OLTCA behaves as a supervisory agent and performs all the optimizations. At first, a token is generated by OLTCA on each time step and it transfers from node to node until the node with voltage violation is detected. Upon detection of such a node, the token grants permission to Load Agent (LA) for initiation of possible remedial actions. LA will contact the respective controlling devices dependent on the vicinity of the violated node. If the violated node does not lie in the vicinity of the controller or the controlling capabilities of all the downstream control devices are at their limits then OLTC is considered as a last resort. For a realistic study, simulations are performed for a typical Finnish residential medium-voltage distribution system using Matlab ®. These simulations are executed for two cases; simple Distributed Voltage Control (DVC) and DVC with optimized loss cost (DVC + Penalty Function). A sensitivity analysis is performed based on DG penetration. The results indicate that costs of losses and DG curtailments are directly proportional to the DG penetration, while in case 2 there is a significant reduction in total loss. For lower DG penetration, losses are reduced more or less 50%, while for higher DG penetration, loss reduction is not very significant. Another observation is that the newer stricter limits calculated by cost optimization moves towards the statutory limits of ±10% of the nominal with the increasing DG penetration as for 25, 45 and 65% limits calculated are ±5, ±6.25 and 8.75% respectively. Observed results conclude that the novel voltage control algorithm proposed in case 1 is able to deal with the voltage control problem instantly but with higher losses. In contrast, case 2 make sure to reduce the network losses through proposed iterative method of loss cost optimization by OLTCA, slowly with time.

Keywords: distributed voltage control, distribution system, multi-agent systems, smart grids

Procedia PDF Downloads 310

Authors: Maxwell Henderson, Tristan Cook, Justin Chan Jin Le, Mark Hodson, YoungJung Chang, John Novak, Daniel Padilha, Nishan Kulatilaka, Ansu Bagchi, Sanjoy Ray, John Kelly

Abstract:

We present a method of using adiabatic quantum optimization (AQO) to solve a mixed integer nonlinear programming (MINLP) problem instance. The MINLP problem is a general form of a set of NP-hard optimization problems that are critical to many business applications. It requires optimizing a set of discrete and continuous variables with nonlinear and potentially nonconvex constraints. Obtaining an exact, optimal solution for MINLP problem instances of non-trivial size using classical computation methods is currently intractable. Current leading algorithms leverage heuristic and divide-and-conquer methods to determine approximate solutions. Creating more accurate and efficient algorithms is an active area of research. Quantum computing (QC) has several theoretical benefits compared to classical computing, through which QC algorithms could obtain MINLP solutions that are superior to current algorithms. AQO is a particular form of QC that could offer more near-term benefits compared to other forms of QC, as hardware development is in a more mature state and devices are currently commercially available from D-Wave Systems Inc. It is also designed for optimization problems: it uses an effect called quantum tunneling to explore all lowest points of an energy landscape where classical approaches could become stuck in local minima. Our work used a novel algorithm formulated for AQO to solve a special type of MINLP problem. The research focused on determining: 1) if the problem is possible to solve using AQO, 2) if it can be solved by current hardware, 3) what the currently achievable performance is, 4) what the performance will be on projected future hardware, and 5) when AQO is likely to provide a benefit over classical computing methods. Two different methods, integer range and 1-hot encoding, were investigated for transforming the MINLP problem instance constraints into a mathematical structure that can be embedded directly onto the current D-Wave architecture. For testing and validation a D-Wave 2X device was used, as well as QxBranch’s QxLib software library, which includes a QC simulator based on simulated annealing. Our results indicate that it is mathematically possible to formulate the MINLP problem for AQO, but that currently available hardware is unable to solve problems of useful size. Classical general-purpose simulated annealing is currently able to solve larger problem sizes, but does not scale well and such methods would likely be outperformed in the future by improved AQO hardware with higher qubit connectivity and lower temperatures. If larger AQO devices are able to show improvements that trend in this direction, commercially viable solutions to the MINLP for particular applications could be implemented on hardware projected to be available in 5-10 years. Continued investigation into optimal AQO hardware architectures and novel methods for embedding MINLP problem constraints on to those architectures is needed to realize those commercial benefits.

Keywords: adiabatic quantum optimization, mixed integer nonlinear programming, quantum computing, NP-hard

Procedia PDF Downloads 524

Authors: Gerhard Gritsch, Ana Skupch, Manfred Hartmann, Wolfgang Frühwirt, Hannes Perko, Dieter Grossegger, Tilmann Kluge

Abstract:

Rehabilitation of stroke patients is dominated by classical physiotherapy. Nowadays, a field of research is the application of neurofeedback techniques in order to help stroke patients to get rid of their motor impairments. Especially, if a certain limb is completely paralyzed, neurofeedback is often the last option to cure the patient. Certain exercises, like the imagination of the impaired motor function, have to be performed to stimulate the neuroplasticity of the brain, such that in the neighboring parts of the injured cortex the corresponding activity takes place. During the exercises, it is very important to keep the motivation of the patient at a high level. For this reason, the missing natural feedback due to a movement of the effected limb may be replaced by a synthetic feedback based on the motor-related brain function. To generate such a synthetic feedback a system is needed which measures, detects, localizes and visualizes the motor related µ-rhythm. Fast therapeutic success can only be achieved if the feedback features high specificity, comes in real-time and without large delay. We describe such an approach that offers a 3D visualization of µ-rhythms in real time with a delay of 500ms. This is accomplished by combining smart EEG preprocessing in the frequency domain with source localization techniques. The algorithm first selects the EEG channel featuring the most prominent rhythm in the alpha frequency band from a so-called motor channel set (C4, CZ, C3; CP6, CP4, CP2, CP1, CP3, CP5). If the amplitude in the alpha frequency band of this certain electrode exceeds a threshold, a µ-rhythm is detected. To prevent detection of a mixture of posterior alpha activity and µ-activity, the amplitudes in the alpha band outside the motor channel set are not allowed to be in the same range as the main channel. The EEG signal of the main channel is used as template for calculating the spatial distribution of the µ - rhythm over all electrodes. This spatial distribution is the input for a inverse method which provides the 3D distribution of the µ - activity within the brain which is visualized in 3D as color coded activity map. This approach mitigates the influence of lid artifacts on the localization performance. The first results of several healthy subjects show that the system is capable of detecting and localizing the rarely appearing µ-rhythm. In most cases the results match with findings from visual EEG analysis. Frequent eye-lid artifacts have no influence on the system performance. Furthermore, the system will be able to run in real-time. Due to the design of the frequency transformation the processing delay is 500ms. First results are promising and we plan to extend the test data set to further evaluate the performance of the system. The relevance of the system with respect to the therapy of stroke patients has to be shown in studies with real patients after CE certification of the system. This work was performed within the project ‘LiveSolo’ funded by the Austrian Research Promotion Agency (FFG) (project number: 853263).

Keywords: real-time EEG neuroimaging, neurofeedback, stroke, EEG–signal processing, rehabilitation

Procedia PDF Downloads 385

Authors: Ben Morrow, Patrick O'Hara, Natalie Ban, Tunai Marques, Molly Fraser, Christopher Bone

Abstract:

Relative to commercial fisheries, recreational fisheries are often poorly understood and pose various challenges for monitoring frameworks. In British Columbia (BC), Canada, Pacific salmon are heavily targeted by recreational fishers while also being a key source of nutrient flow and crucial prey for a variety of marine and terrestrial fauna, including endangered Southern Resident killer whales (Orcinus orca). Although commercial fisheries were historically responsible for the majority of salmon retention, recreational fishing now comprises both greater effort and retention. The current monitoring scheme for recreational salmon fisheries involves aerial-roving creel surveys. However, this method has been identified as costly and having low predictive power as it is often limited to sampling fragments of fluid and temporally dynamic fisheries. This study used imagery from two shore-based autonomous cameras in a highly active recreational fishery around Sooke, BC, and evaluated their efficacy in supplementing existing aerial-roving surveys for monitoring a recreational salmon fishery. This study involved continuous monitoring and high temporal resolution (over one million images analyzed in a single fishing season), using a deep learning-based vessel detection algorithm and a custom image annotation tool to efficiently thin datasets. This allowed for the quantification of peak-season effort from a busy harbour, species-specific retention estimates, high levels of detected fishing events at a nearby popular fishing location, as well as the proportion of the fishery management area represented by cameras. Then, this study demonstrated how it could substantially enhance the temporal resolution of a fishery through diel activity pattern analyses, scaled monthly to visualize clusters of activity. This work also highlighted considerable off-season fishing detection, currently unaccounted for in the existing monitoring framework. These results demonstrate several distinct applications of autonomous cameras for providing enhanced detail currently unavailable in the current monitoring framework, each of which has important considerations for the managerial allocation of resources. Further, the approach and methodology can benefit other studies that apply shore-based camera monitoring, supplement aerial-roving creel surveys to improve fine-scale temporal understanding, inform the optimal timing of creel surveys, and improve the predictive power of recreational stock assessments to preserve important and endangered fish species.

Keywords: cameras, monitoring, recreational fishing, stock assessment

Procedia PDF Downloads 122

Authors: Yael Neumann

Abstract:

Attention deficits are common in people with aphasia (PWA). Two treatment approaches address these deficits: domain-general methods like Play Attention, which focus on cognitive functioning, and domain-specific methods like Language-Specific Attention Treatment (L-SAT), which use linguistically based tasks. Research indicates that L-SAT can improve both attentional deficits and functional language skills, while Play Attention has shown success in enhancing attentional capabilities among school-aged children with attention issues compared to standard cognitive training. This study employed a randomized controlled cross-over single-subject design to evaluate the effectiveness of these two attention treatments over 25 weeks. Four PWA participated, undergoing a battery of eight standardized tests measuring language and cognitive skills. The treatments were counterbalanced. Play Attention used EEG sensors to detect brainwaves, enabling participants to manipulate items in a computer game while learning to suppress theta activity and increase beta activity. An algorithm tracked changes in the theta-to-beta ratio, allowing points to be earned during the games. L-SAT, on the other hand, involved hierarchical language tasks that increased in complexity, requiring greater attention from participants. Results showed that for language tests, Participant 1 (moderate aphasia) aligned with existing literature, showing L-SAT was more effective than Play Attention. However, Participants 2 (very severe) and 3 and 4 (mild) did not conform to this pattern; both treatments yielded similar outcomes. This may be due to the extremes of aphasia severity: the very severe participant faced significant overall deficits, making both approaches equally challenging, while the mild participant performed well initially, leaving limited room for improvement. In attention tests, Participants 1 and 4 exhibited results consistent with prior research, indicating Play Attention was superior to L-SAT. Participant 2, however, showed no significant improvement with either program, although L-SAT had a slight edge on the Visual Elevator task, measuring switching and mental flexibility. This advantage was not sustained at the one-month follow-up, likely due to the participant’s struggles with complex attention tasks. Participant 3's results similarly did not align with prior studies, revealing no difference between the two treatments, possibly due to the challenging nature of the attention measures used. Regarding participation and ecological tests, all participants showed similar mild improvements with both treatments. This limited progress could stem from the short study duration, with only five weeks allocated for each treatment, which may not have been enough time to achieve meaningful changes affecting life participation. In conclusion, the performance of participants appeared influenced by their level of aphasia severity. The moderate PWA’s results were most aligned with existing literature, indicating better attention improvement from the domain-general approach (Play Attention) and better language improvement from the domain-specific approach (L-SAT).

Keywords: attention, language, cognitive rehabilitation, neurofeedback

Procedia PDF Downloads 14

Authors: Farhan A. Alenizi

Abstract:

Digital watermarking has evolved in the past years as an important means for data authentication and ownership protection. The images and video watermarking was well known in the field of multimedia processing; however, 3D objects' watermarking techniques have emerged as an important means for the same purposes, as 3D mesh models are in increasing use in different areas of scientific, industrial, and medical applications. Like the image watermarking techniques, 3D watermarking can take place in either space or transform domains. Unlike images and video watermarking, where the frames have regular structures in both space and temporal domains, 3D objects are represented in different ways as meshes that are basically irregular samplings of surfaces; moreover, meshes can undergo a large variety of alterations which may be hard to tackle. This makes the watermarking process more challenging. While the transform domain watermarking is preferable in images and videos, they are still difficult to implement in 3d meshes due to the huge number of vertices involved and the complicated topology and geometry, and hence the difficulty to perform the spectral decomposition, even though significant work was done in the field. Spatial domain watermarking has attracted significant attention in the past years; they can either act on the topology or on the geometry of the model. Exploiting the statistical characteristics in the 3D mesh models from both geometrical and topological aspects was useful in hiding data. However, doing that with minimal surface distortions to the mesh attracted significant research in the field. A 3D mesh blind watermarking technique is proposed in this research. The watermarking method depends on modifying the vertices' positions with respect to the center of the object. An optimal method will be developed to reduce the errors, minimizing the distortions that the 3d object may experience due to the watermarking process, and reducing the computational complexity due to the iterations and other factors. The technique relies on the displacement process of the vertices' locations depending on the modification of the variances of the vertices’ norms. Statistical analyses were performed to establish the proper distributions that best fit each mesh, and hence establishing the bins sizes. Several optimizing approaches were introduced in the realms of mesh local roughness, the statistical distributions of the norms, and the displacements in the mesh centers. To evaluate the algorithm's robustness against other common geometry and connectivity attacks, the watermarked objects were subjected to uniform noise, Laplacian smoothing, vertices quantization, simplification, and cropping. Experimental results showed that the approach is robust in terms of both perceptual and quantitative qualities. It was also robust against both geometry and connectivity attacks. Moreover, the probability of true positive detection versus the probability of false-positive detection was evaluated. To validate the accuracy of the test cases, the receiver operating characteristics (ROC) curves were drawn, and they’ve shown robustness from this aspect. 3D watermarking is still a new field but still a promising one.

Keywords: watermarking, mesh objects, local roughness, Laplacian Smoothing

Procedia PDF Downloads 159

Authors: Brayden Mi

Abstract:

Reverse time migration has been widely used in the Petroleum exploration industry to reveal subsurface images and to detect rock and fluid properties since the early 1980s. The seismic technology involves the construction of a velocity model through interpretive model construction, seismic tomography, or full waveform inversion, and the application of the reverse-time propagation of acquired seismic data and the original wavelet used in the acquisition. The methodology has matured from 2D, simple media to present-day to handle full 3D imaging challenges in extremely complex geological conditions. Conventional Ultrasound computed tomography (USCT) utilize travel-time-inversion to reconstruct the velocity structure of an organ. With the velocity structure, USCT data can be migrated with the “bend-ray” method, also known as migration. Its seismic application counterpart is called Kirchhoff depth migration, in which the source of reflective energy is traced by ray-tracing and summed to produce a subsurface image. It is well known that ray-tracing-based migration has severe limitations in strongly heterogeneous media and irregular acquisition geometries. Reverse time migration (RTM), on the other hand, fully accounts for the wave phenomena, including multiple arrives and turning rays due to complex velocity structure. It has the capability to fully reconstruct the image detectable in its acquisition aperture. The RTM algorithms typically require a rather accurate velocity model and demand high computing powers, and may not be applicable to real-time imaging as normally required in day-to-day medical operations. However, with the improvement of computing technology, such a computational bottleneck may not present a challenge in the near future. The present-day (RTM) algorithms are typically implemented from a flat datum for the seismic industry. It can be modified to accommodate any acquisition geometry and aperture, as long as sufficient illumination is provided. Such flexibility of RTM can be conveniently implemented for the application in USCT imaging if the spatial coordinates of the transmitters and receivers are known and enough data is collected to provide full illumination. This paper proposes an implementation of a full 3D RTM algorithm for USCT imaging to produce an accurate 3D acoustic image based on the Phase-shift-plus-interpolation (PSPI) method for wavefield extrapolation. In this method, each acquired data set (shot) is propagated back in time, and a known ultrasound wavelet is propagated forward in time, with PSPI wavefield extrapolation and a piece-wise constant velocity model of the organ (breast). The imaging condition is then applied to produce a partial image. Although each image is subject to the limitation of its own illumination aperture, the stack of multiple partial images will produce a full image of the organ, with a much-reduced noise level if compared with individual partial images.

Keywords: illumination, reverse time migration (RTM), ultrasound computed tomography (USCT), wavefield extrapolation

Procedia PDF Downloads 73

Authors: İsmail Kavdır, M. Burak Büyükcan, Ferhat Kurtulmuş

Abstract:

Table olive is a valuable product especially in Mediterranean countries. It is usually consumed after some fermentation process. Defects happened naturally or as a result of an impact while olives are still fresh may become more distinct after processing period. Defected olives are not desired both in table olive and olive oil industries as it will affect the final product quality and reduce market prices considerably. Therefore it is critical to sort table olives before processing or even after processing according to their quality and surface defects. However, doing manual sorting has many drawbacks such as high expenses, subjectivity, tediousness and inconsistency. Quality criterions for green olives were accepted as color and free of mechanical defects, wrinkling, surface blemishes and rotting. In this study, it was aimed to classify fresh table olives using different classifiers and NIR spectroscopy readings and also to compare the classifiers. For this purpose, green (Ayvalik variety) olives were classified based on their surface feature properties such as defect-free, with bruised defect and with fly defect using FT-NIR spectroscopy and classification algorithms such as artificial neural networks, ident and cluster. Bruker multi-purpose analyzer (MPA) FT-NIR spectrometer (Bruker Optik, GmbH, Ettlingen Germany) was used for spectral measurements. The spectrometer was equipped with InGaAs detectors (TE-InGaAs internal for reflectance and RT-InGaAs external for transmittance) and a 20-watt high intensity tungsten–halogen NIR light source. Reflectance measurements were performed with a fiber optic probe (type IN 261) which covered the wavelengths between 780–2500 nm, while transmittance measurements were performed between 800 and 1725 nm. Thirty-two scans were acquired for each reflectance spectrum in about 15.32 s while 128 scans were obtained for transmittance in about 62 s. Resolution was 8 cm⁻¹ for both spectral measurement modes. Instrument control was done using OPUS software (Bruker Optik, GmbH, Ettlingen Germany). Classification applications were performed using three classifiers; Backpropagation Neural Networks, ident and cluster classification algorithms. For these classification applications, Neural Network tool box in Matlab, ident and cluster modules in OPUS software were used. Classifications were performed considering different scenarios; two quality conditions at once (good vs bruised, good vs fly defect) and three quality conditions at once (good, bruised and fly defect). Two spectrometer readings were used in classification applications; reflectance and transmittance. Classification results obtained using artificial neural networks algorithm in discriminating good olives from bruised olives, from olives with fly defect and from the olive group including both bruised and fly defected olives with success rates respectively changing between 97 and 99%, 61 and 94% and between 58.67 and 92%. On the other hand, classification results obtained for discriminating good olives from bruised ones and also for discriminating good olives from fly defected olives using the ident method ranged between 75-97.5% and 32.5-57.5%, respectfully; results obtained for the same classification applications using the cluster method ranged between 52.5-97.5% and between 22.5-57.5%.

Keywords: artificial neural networks, statistical classifiers, NIR spectroscopy, reflectance, transmittance

Procedia PDF Downloads 244

Authors: Korbinian Schmidtner, Rudolf Sailer, Perry Bartelt, Wolfgang Fellin, Jan-Thomas Fischer, Matthias Granig

Abstract:

This study focuses on the evaluation of snow avalanche simulations, based on a survey that has been carried out among avalanche experts. In the last decades, the application of avalanche simulation tools has gained recognition within the realm of hazard management. Traditionally, avalanche runout models were used to predict extreme avalanche runout and prepare avalanche maps. This has changed rather dramatically with the application of numerical models. For safety regulations such as road safety simulation tools are now being coupled with real-time meteorological measurements to predict frequent avalanche hazard. That places new demands on model accuracy and requires the simulation of physical processes that previously could be ignored. These simulation tools are based on a deterministic description of the avalanche movement allowing to predict certain quantities (e.g. pressure, velocities, flow heights, runout lengths etc.) of the avalanche flow. Because of the highly variable regimes of the flowing snow, no uniform rheological law describing the motion of an avalanche is known. Therefore, analogies to fluid dynamical laws of other materials are stated. To transfer these constitutional laws to snow flows, certain assumptions and adjustments have to be imposed. Besides these limitations, there exist high uncertainties regarding the initial and boundary conditions. Further challenges arise when implementing the underlying flow model equations into an algorithm executable by a computer. This implementation is constrained by the choice of adequate numerical methods and their computational feasibility. Hence, the model development is compelled to introduce further simplifications and the related uncertainties. In the light of these issues many questions arise on avalanche simulations, on their assets and drawbacks, on potentials for improvements as well as their application in practice. To address these questions a survey among experts in the field of avalanche science (e.g. researchers, practitioners, engineers) from various countries has been conducted. In the questionnaire, special attention is drawn on the expert’s opinion regarding the influence of certain variables on the simulation result, their uncertainty and the reliability of the results. Furthermore, it was tested to which degree a simulation result influences the decision making for a hazard assessment. A discrepancy could be found between a large uncertainty of the simulation input parameters as compared to a relatively high reliability of the results. This contradiction can be explained taking into account how the experts employ the simulations. The credibility of the simulations is the result of a rather thoroughly simulation study, where different assumptions are tested, comparing the results of different flow models along with the use of supplemental data such as chronicles, field observation, silent witnesses i.a. which are regarded as essential for the hazard assessment and for sanctioning simulation results. As the importance of avalanche simulations grows within the hazard management along with their further development studies focusing on the modeling fashion could contribute to a better understanding how knowledge of the avalanche process can be gained by running simulations.

Keywords: expert interview, hazard management, modeling, simulation, snow avalanche

Procedia PDF Downloads 324

Authors: Ramesh P., Aby Joseph

Abstract:

Micro Inverters provide Module Embedded Solution for harvesting energy from small-scale solar photovoltaic (PV) panels. In addition to higher modularity & reliability (25 years of life), the MicroInverter has inherent advantages such as avoidance of long DC cables, eliminates module mismatch losses, minimizes partial shading effect, improves safety and flexibility in installations etc. Due to the above-stated benefits, the renewable energy technology with Solar Photovoltaic (PV) Micro Inverter becomes more widespread in Village Nano Grid application ensuring grid independence for rural communities and areas without access to electricity. While the primary objective of this paper is to discuss the problems related to rural electrification, this concept can also be extended to urban installation with grid connectivity. This work presents a comprehensive analysis of the power circuit design, control methodologies and prototyping of 300Wₚ Single Phase PV Micro Inverter. This paper investigates two different topologies for PV Micro Inverters, based on the first hand on Single Stage Flyback/ Forward PV Micro-Inverter configuration and the other hand on the Double stage configuration including DC-DC converter, H bridge DC-AC Inverter. This work covers Power Decoupling techniques to reduce the input filter capacitor size to buffer double line (100 Hz) ripple energy and eliminates the use of electrolytic capacitors. The propagation of the double line oscillation reflected back to PV module will affect the Maximum Power Point Tracking (MPPT) performance. Also, the grid current will be distorted. To mitigate this issue, an independent MPPT control algorithm is developed in this work to reject the propagation of this double line ripple oscillation to PV side to improve the MPPT performance and grid side to improve current quality. Here, the power hardware topology accepts wide input voltage variation and consists of suitably rated MOSFET switches, Galvanically Isolated gate drivers, high-frequency magnetics and Film capacitors with a long lifespan. The digital controller hardware platform inbuilt with the external peripheral interface is developed using floating point microcontroller TMS320F2806x from Texas Instruments. The firmware governing the operation of the PV Micro Inverter is written in C language and was developed using code composer studio Integrated Development Environment (IDE). In this work, the prototype hardware for the Single Phase Photovoltaic Micro Inverter with Double stage configuration was developed and the comparative analysis between the above mentioned configurations with experimental results will be presented.

Keywords: double line oscillation, micro inverter, MPPT, nano grid, power decoupling

Procedia PDF Downloads 133

Authors: Svetlana Petrikova, Alexander Yu Kostinskiy

Abstract:

Management of research evaluation in the Higher School of Economics (HSE) originates from the HSE Academic Fund created in 2004 to facilitate and support academic research and presents its results to international academic community. As the means to inspire the applicants, science projects went through competitive selection process evaluated by the group of experts. Drastic development of HSE, quantity of applied projects for each Academic Fund competition and the need to coordinate the conduct of expert evaluation resulted in founding of the Office for Research Evaluation in 2013. The Office’s primary objective is management of research evaluation of science projects. The standards to conduct the evaluation are defined as follows: - The exercise of the process approach, the unification of the functioning of department. - The uniformity of regulatory, organizational and methodological framework. - The development of proper on-line evaluation system. - The broad involvement of external Russian and international experts, the renouncement of the usage of own employees. - The development of an algorithm to make a correspondence between experts and science projects. - The methodical usage of opened/closed international and Russian databases to extend the expert database. - The transparency of evaluation results – free access to assessment while keeping experts confidentiality. The management of research evaluation of projects is based on the sole standard, organization and financing. The standard way of conducting research evaluation at HSE is based upon Regulations on basic principles for research evaluation at HSE. These Regulations have been developed from the moment of establishment of the Office for Research Evaluation and are based on conventional corporate standards for regulatory document management. The management system of research evaluation is implemented on the process approach basis. Process approach means deployment of work as a process, which is the aggregation of interrelated and interacting activities processing inputs into outputs. Inputs are firstly client asking for the assessment to be conducted, defining the conditions for organizing and carrying of the assessment and secondly the applicant with proper for the competition application; output is assessment given to the client. While exercising process approach to clarify interrelation and interacting main parties or subjects of the assessment are determined and the way for interaction between them forms up. Parties to expert assessment are: - Ordering Party – The department of the university taking the decision to subject a project to expert assessment; - Providing Party – The department of the university authorized to provide such assessment by the Ordering Party; - Performing Party – The legal and natural entities that have expertise in the area of research evaluation. Experts assess projects in accordance with criteria and states of expert opinions approved by the Ordering Party. Objects of assessment generally are applications or HSE competition project reports. Mainly assessments are deployed for internal needs, i.e. the most ordering parties are HSE branches and departments, but assessment can also be conducted for external clients. The financing of research evaluation at HSE is based on the established corporate culture and traditions of HSE.

Keywords: expert assessment, management of research evaluation, process approach, research evaluation

Procedia PDF Downloads 253

Authors: Andrey Cherdantsev, Mikhail Cherdantsev, Sergey Isaenkov, Dmitriy Markovich

Abstract:

In annular gas-liquid flow, liquid flows as a film along pipe walls sheared by high-velocity gas stream. Film surface is covered by large-scale disturbance waves which affect pressure drop and heat transfer in the system and are necessary for entrainment of liquid droplets from film surface into the core of gas stream. Disturbance waves are a highly complex and their properties are affected by numerous parameters. One of such aspects is flow development, i.e., change of flow properties with the distance from the inlet. In the present work, this question is studied using brightness-based laser-induced fluorescence (BBLIF) technique. This method enables one to perform simultaneous measurements of local film thickness in large number of points with high sampling frequency. In the present experiments first 50 cm of upward and downward annular flow in a vertical pipe of 11.7 mm i.d. is studied with temporal resolution of 10 kHz and spatial resolution of 0.5 mm. Thus, spatiotemporal evolution of film surface can be investigated, including scenarios of formation, acceleration and coalescence of disturbance waves. The behaviour of disturbance waves' velocity depending on phases flow rates and downstream distance was investigated. Besides measuring the waves properties, the goal of the work was to investigate the interrelation between disturbance waves properties and integral characteristics of the flow such as interfacial shear stress and flow rate of dispersed phase. In particular, it was shown that the initial acceleration of disturbance waves, defined by the value of shear stress, linearly decays with downstream distance. This lack of acceleration which may even lead to deceleration is related to liquid entrainment. Flow rate of disperse phase linearly grows with downstream distance. During entrainment events, liquid is extracted directly from disturbance waves, reducing their mass, area of interaction to the gas shear and, hence, velocity. Passing frequency of disturbance waves at each downstream position was measured automatically with a new algorithm of identification of characteristic lines of individual disturbance waves. Scenarios of coalescence of individual disturbance waves were identified. Transition from initial high-frequency Kelvin-Helmholtz waves appearing at the inlet to highly nonlinear disturbance waves with lower frequency was studied near the inlet using 3D realisation of BBLIF method in the same cylindrical channel and in a rectangular duct with cross-section of 5 mm by 50 mm. It was shown that the initial waves are generally two-dimensional but are promptly broken into localised three-dimensional wavelets. Coalescence of these wavelets leads to formation of quasi two-dimensional disturbance waves. Using cross-correlation analysis, loss and restoration of two-dimensionality of film surface with downstream distance were studied quantitatively. It was shown that all the processes occur closer to the inlet at higher gas velocities.

Keywords: annular flow, disturbance waves, entrainment, flow development

Procedia PDF Downloads 249

Authors: Sachin Jain, Daniel Perez-Astudillo, Dunia A. Bachour, Antonio P. Sanfilippo

Abstract:

The future of solar energy in Qatar is evolving steadily. Hence, high-quality spatial solar radiation data is of the uttermost requirement for any planning and commissioning of solar technology. Generally, two types of solar radiation data are available: satellite data and ground observations. Satellite solar radiation data is developed by the physical and statistical model. Ground data is collected by solar radiation measurement stations. The ground data is of high quality. However, they are limited to distributed point locations with the high cost of installation and maintenance for the ground stations. On the other hand, satellite solar radiation data is continuous and available throughout geographical locations, but they are relatively less accurate than ground data. To utilize the advantage of both data, a product has been developed here which provides spatial continuity and higher accuracy than any of the data alone. The popular satellite databases: National Solar radiation Data Base, NSRDB (PSM V3 model, spatial resolution: 4 km) is chosen here for merging with ground-measured solar radiation measurement in Qatar. The spatial distribution of ground solar radiation measurement stations is comprehensive in Qatar, with a network of 13 ground stations. The monthly average of the daily total Global Horizontal Irradiation (GHI) component from ground and satellite data is used for error analysis. The normalized root means square error (NRMSE) values of 3.31%, 6.53%, and 6.63% for October, November, and December 2019 were observed respectively when comparing in-situ and NSRDB data. The method is based on the Empirical Bayesian Kriging Regression Prediction model available in ArcGIS, ESRI. The workflow of the algorithm is based on the combination of regression and kriging methods. A regression model (OLS, ordinary least square) is fitted between the ground and NSBRD data points. A semi-variogram is fitted into the experimental semi-variogram obtained from the residuals. The kriging residuals obtained after fitting the semi-variogram model were added to NSRBD data predicted values obtained from the regression model to obtain the final predicted values. The NRMSE values obtained after merging are respectively 1.84%, 1.28%, and 1.81% for October, November, and December 2019. One more explanatory variable, that is the ground elevation, has been incorporated in the regression and kriging methods to reduce the error and to provide higher spatial resolution (30 m). The final GHI maps have been created after merging, and NRMSE values of 1.24%, 1.28%, and 1.28% have been observed for October, November, and December 2019, respectively. The proposed merging method has proven as a highly accurate method. An additional method is also proposed here to generate calibrated maps by using regression and kriging model and further to use the calibrated model to generate solar radiation maps from the explanatory variable only when not enough historical ground data is available for long-term analysis. The NRMSE values obtained after the comparison of the calibrated maps with ground data are 5.60% and 5.31% for November and December 2019 month respectively.

Keywords: global horizontal irradiation, GIS, empirical bayesian kriging regression prediction, NSRDB

Procedia PDF Downloads 88