Academic literature on the topic 'Feature Map Scaling'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Feature Map Scaling.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Feature Map Scaling"
1
Leem, Choon Seong, D. A. Dornfeld, and S. E. Dreyfus. "A Customized Neural Network for Sensor Fusion in On-Line Monitoring of Cutting Tool Wear." Journal of Engineering for Industry 117, no. 2 (May 1, 1995): 152–59. http://dx.doi.org/10.1115/1.2803289.
Full textAbstract:
A customized neural network for sensor fusion of acoustic emission and force in on-line detection of tool wear is developed. Based on two critical concerns regarding practical and reliable tool-wear monitoring systems, the maximal utilization of “unsupervised” sensor data and the avoidance of off-line feature analysis, the neural network is trained by unsupervised Kohonen’s Feature Map procedure followed by an Input Feature Scaling algorithm. After levels of tool wear are topologically ordered by Kohonen’s Feature Map, input features of AE and force sensor signals are transformed via Input Feature Scaling so that the resulting decision boundaries of the neural network approximate those of error-minimizing Bayes classifier. In a machining experiment, the customized neural network achieved high accuracy rates in the classification of levels of tool wear. Also, the neural network shows several practical and reliable properties for the implementation of the monitoring system in manufacturing industries.
2
Li, Mao Hai, and Li Ning Sun. "Monocular Vision Based Mobile Robot 3D Map Building." Applied Mechanics and Materials 43 (December 2010): 49–52. http://dx.doi.org/10.4028/www.scientific.net/amm.43.49.
Full textAbstract:
A robust dense 3D feature map is built only with monocular vision and odometry. Monocular vision mounted on the robot front-end tracks the 3D natural landmarks, which are structured with matching Scale Invariant Feature Transform (SIFT) feature matching pairs. SIFT features are highly distinctive and invariant to image scaling, rotation, and change in 3D viewpoints. A fast SIFT feature matching algorithm is implemented with the KD-Tree based nearest search approach in the time cost of O(log2N), and matches with large error are eliminated by epipolar line restriction. A map building algorithm based on 3D spatial SIFT landmarks is designed and implemented. Experiment results on Pioneer mobile robot in a real indoor environment show the superior performance of our proposed method.
3
El Chakik, Abdallah, Abdul Rahman El Sayed, Hassan Alabboud, and Amer Bakkach. "An invariant descriptor map for 3D objects matching." International Journal of Engineering & Technology 9, no. 1 (January 23, 2020): 59. http://dx.doi.org/10.14419/ijet.v9i1.29918.
Full textAbstract:
Meshes and point clouds are traditionally used to represent and match 3D shapes. The matching prob-lem can be formulated as finding the best one-to-one correspondence between featured regions of two shapes. This paper presents an efficient and robust 3D matching method using vertices descriptors de-tection to define feature regions and an optimization approach for regions matching. To do so, we compute an invariant shape descriptor map based on 3D surface patches calculated using Zernike coef-ficients. Then, we propose a multi-scale descriptor map to improve the measured descriptor map quali-ty and to deal with noise. In addition, we introduce a linear algorithm for feature regions segmentation according to the descriptor map. Finally, the matching problem is modelled as sub-graph isomorphism problem, which is a combinatorial optimization problem to match feature regions while preserving the geometric. Finally, we show the robustness and stability of our method through many experimental re-sults with respect to scaling, noise, rotation, and translation.
4
Ma, Ding, Zhigang Zhao, Ye Zheng, Renzhong Guo, and Wei Zhu. "PolySimp: A Tool for Polygon Simplification Based on the Underlying Scaling Hierarchy." ISPRS International Journal of Geo-Information 9, no. 10 (October 10, 2020): 594. http://dx.doi.org/10.3390/ijgi9100594.
Full textAbstract:
Map generalization is a process of reducing the contents of a map or data to properly show a geographic feature(s) at a smaller extent. Over the past few years, the fractal way of thinking has emerged as a new paradigm for map generalization. A geographic feature can be deemed as a fractal given the perspective of scaling, as its rough, irregular, and unsmooth shape inherently holds a striking scaling hierarchy of far more small elements than large ones. The pattern of far more small things than large ones is a de facto heavy tailed distribution. In this paper, we apply the scaling hierarchy for map generalization to polygonal features. To do this, we firstly revisit the scaling hierarchy of a classic fractal: the Koch Snowflake. We then review previous work that used the Douglas–Peuker algorithm, which identifies characteristic points on a line to derive three types of measures that are long-tailed distributed: the baseline length (d), the perpendicular distance to the baseline (x), and the area formed by x and d (area). More importantly, we extend the usage of the three measures to other most popular cartographical generalization methods; i.e., the bend simplify method, Visvalingam–Whyatt method, and hierarchical decomposition method, each of which decomposes any polygon into a set of bends, triangles, or convex hulls as basic geometric units for simplification. The different levels of details of the polygon can then be derived by recursively selecting the head part of geometric units and omitting the tail part using head/tail breaks, which is a new classification scheme for data with a heavy-tailed distribution. Since there are currently few tools with which to readily conduct the polygon simplification from such a fractal perspective, we have developed PolySimp, a tool that integrates the mentioned four algorithms for polygon simplification based on its underlying scaling hierarchy. The British coastline was selected to demonstrate the tool’s usefulness. The developed tool can be expected to showcase the applicability of fractal way of thinking and contribute to the development of map generalization.
5
Chang, Chin Chen, I. Ta Lee, Tsung Ta Ke, and Wen Kai Tai. "An Object-Based Image Reducing Approach." Advanced Materials Research 1044-1045 (October 2014): 1049–52. http://dx.doi.org/10.4028/www.scientific.net/amr.1044-1045.1049.
Full textAbstract:
Common methods for reducing image size include scaling and cropping. However, these two approaches have some quality problems for reduced images. In this paper, we propose an image reducing algorithm by separating the main objects and the background. First, we extract two feature maps, namely, an enhanced visual saliency map and an improved gradient map from an input image. After that, we integrate these two feature maps to an importance map. Finally, we generate the target image using the importance map. The proposed approach can obtain desired results for a wide range of images.
6
Li, James Xinzhi. "Visualization of High-Dimensional Data with Relational Perspective Map." Information Visualization 3, no. 1 (March 2004): 49–59. http://dx.doi.org/10.1057/palgrave.ivs.9500051.
Full textAbstract:
This paper introduces a method called relational perspective map (RPM) to visualize distance information in high-dimensional spaces. Like conventional multidimensional scaling, the RPM algorithm aims to produce proximity preserving 2-dimensional (2-D) maps. The main idea of the RPM algorithm is to simulate a multiparticle system on a closed surface: whereas the repulsive forces between the particles reflect the distance information, the closed surface holds the whole system in balance and prevents the resulting map from degeneracy. A special feature of RPM algorithm is its ability to partition a complex dataset into pieces and map them onto a 2-D space without overlapping. Compared to other multidimensional scaling methods, RPM is able to reveal more local details of complex datasets. This paper demonstrates the properties of RPM maps with four examples and provides extensive comparison to other multidimensional scaling methods, such as Sammon Mapping and Curvilinear Principle Analysis.
7
Ma, Liang, Jihua Zhu, Li Zhu, Shaoyi Du, and Jingru Cui. "Merging grid maps of different resolutions by scaling registration." Robotica 34, no. 11 (March 20, 2015): 2516–31. http://dx.doi.org/10.1017/s0263574715000168.
Full textAbstract:
SUMMARYThis paper considers the problem of merging grid maps that have different resolutions. Because the goal of map merging is to find the optimal transformation between two partially overlapping grid maps, it can be viewed as a special image registration issue. To address this special issue, the solution considers the non-common areas and designs an objective function based on the trimmed mean-square error (MSE). The trimmed and scaling iterative closest point (TsICP) algorithm is then proposed to solve this well-designed objective function. As the TsICP algorithm can be proven to be locally convergent in theory, a good initial transformation should be provided. Accordingly, scale-invariant feature transform (SIFT) features are extracted for the maps to be potentially merged, and the random sample consensus (RANSAC) algorithm is employed to find the geometrically consistent feature matches that are used to estimate the initial transformation for the TsICP algorithm. In addition, this paper presents the rules for the fusion of the grid maps based on the estimated transformation. Experimental results carried out with publicly available datasets illustrate the superior performance of this approach at merging grid maps with respect to robustness and accuracy.
8
Li, Lin, Zheng Min Xia, Sheng Hong Li, Li Pan, and Zhi Hua Huang. "Detecting Overlapping Communities with MDS and Local Expansion FCM." Applied Mechanics and Materials 644-650 (September 2014): 3295–99. http://dx.doi.org/10.4028/www.scientific.net/amm.644-650.3295.
Full textAbstract:
Community structure is an important feature to understand structural and functional properties in various complex networks. In this paper, we use Multidimensional Scaling (MDS) to map nodes of network into Euclidean space to keep the distance information of nodes, and then we use topology feature of communities to propose the local expansion strategy to detect initial seeds for FCM. Finally, the FCM are used to uncover overlapping communities in the complex networks. The test results in real-world and artificial networks show that the proposed algorithm is efficient and robust in uncovering overlapping community structure.
9
Yang, Yang, and Hongmin Deng. "GC-YOLOv3: You Only Look Once with Global Context Block." Electronics 9, no. 8 (July 31, 2020): 1235. http://dx.doi.org/10.3390/electronics9081235.
Full textAbstract:
In order to make the classification and regression of single-stage detectors more accurate, an object detection algorithm named Global Context You-Only-Look-Once v3 (GC-YOLOv3) is proposed based on the You-Only-Look-Once (YOLO) in this paper. Firstly, a better cascading model with learnable semantic fusion between a feature extraction network and a feature pyramid network is designed to improve detection accuracy using a global context block. Secondly, the information to be retained is screened by combining three different scaling feature maps together. Finally, a global self-attention mechanism is used to highlight the useful information of feature maps while suppressing irrelevant information. Experiments show that our GC-YOLOv3 reaches a maximum of 55.5 object detection mean Average Precision (mAP)@0.5 on Common Objects in Context (COCO) 2017 test-dev and that the mAP is 5.1% higher than that of the YOLOv3 algorithm on Pascal Visual Object Classes (PASCAL VOC) 2007 test set. Therefore, experiments indicate that the proposed GC-YOLOv3 model exhibits optimal performance on the PASCAL VOC and COCO datasets.
10
Chen, Ying, Lei Zhang, and Xiao Juan Ji. "A New Robust Watermarking Algorithm for Small Vector Data Set." Applied Mechanics and Materials 263-266 (December 2012): 2999–3004. http://dx.doi.org/10.4028/www.scientific.net/amm.263-266.2999.
Full textAbstract:
Because less data can be hidden on the small vector data set , its copyright is very difficult to obtain protection, and the data is vulnerable to attack, so a new double watermarking algorithm was proposed in this paper. Its main features are: 1) it selected feature points from the sequence of Douglas, then embedded watermarking points on both sides of the feature point, and last embedded watermarking points by wavelet transform again; 2) Further more it increased the map graphic deformation control design. The algorithm was applied to experimental data, and the test results showed that the algorithm had good robustness on graphics, rotation, scaling and shifting geometric transformation of points in graph layers. However, due to the smaller vector data set, so the algorithm is robustness on deletion and cropping of points in graph layers.
Dissertations / Theses on the topic "Feature Map Scaling"
1
Lukáč, Peter. "Verifikace osob podle hlasu bez extrakce příznaků." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2021. http://www.nusl.cz/ntk/nusl-445531.
Full textAbstract:
Verifikácia osôb je oblasť, ktorá sa stále modernizuje, zlepšuje a snaží sa vyhovieť požiadavkám, ktoré sa na ňu kladú vo oblastiach využitia ako sú autorizačné systmémy, forenzné analýzy, atď. Vylepšenia sa uskutočňujú vďaka pokrom v hlbokom učení, tvorením nových trénovacích a testovacích dátovych sad a rôznych súťaží vo verifikácií osôb a workshopov. V tejto práci preskúmame modely pre verifikáciu osôb bez extrakcie príznakov. Používanie nespracovaných zvukových stôp ako vstupy modelov zjednodušuje spracovávanie vstpu a teda znižujú sa výpočetné a pamäťové požiadavky a redukuje sa počet hyperparametrov potrebných pre tvorbu príznakov z nahrávok, ktoré ovplivňujú výsledky. Momentálne modely bez extrakcie príznakov nedosahujú výsledky modelov s extrakciou príznakov. Na základných modeloch budeme experimentovať s modernými technikamy a budeme sa snažiť zlepšiť presnosť modelov. Experimenty s modernými technikamy značne zlepšili výsledky základných modelov ale stále sme nedosiahli výsledky vylepšeného modelu s extrakciou príznakov. Zlepšenie je ale dostatočné nato aby sme vytovrili fúziu so s týmto modelom. Záverom diskutujeme dosiahnuté výsledky a navrhujeme zlepšenia na základe týchto výsledkov.
2
Lin, Yue. "A Comparison Study on Head/tail Breaks and Topfer’s Method for Model-based Map Generalization on Geographic Features in Country and City Levels." Thesis, Högskolan i Gävle, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-20453.
Full textAbstract:
Map generalization is a traditional cartographical issue which should be particularly considered in today’sinformation age. The aim of this study is to find some characteristics about head/tail breaks which worksas generalization method compared with the well known Topfer’s method. A questionnaire survey wasconducted to let 30 users choose either of the series maps of both methods and the reason(s) for thatchoice. Also to test their understanding of the series maps histograms were added for them to match.Afterwards the sample results were analyzed using both univariate and bivariate analysis approaches. Itshows that the head/tail breaks method was selected by 58%, compared with 38.7% of Topfer’s method,because of its simplicity. By checking the correctness of histogram question it also shows that those whowell understood answers choose the head/tail breaks rather than the Topfer’s method. However in somecases, where the amount of geographical features is relatively small, Topfer’s method is more selectedbecause of its informative characteristic and similar structure to the original map. It was also found that inthe comparison the head/tail breaks is more advantageous in line feature type generalization than in arealfeature type. This is probably because Topfer’s method changes its minority selection rule to half selectionin line feature type, whereas the head/tail breaks keeps the scaling property. Any difference between thetwo tested scales, Finland level and Helsinki level, is not found in this comparison study. However, futurework should explore more regarding this and other issues.
Book chapters on the topic "Feature Map Scaling"
1
Tidke, Sonali. "MonogDB." In Privacy and Security Policies in Big Data, 64–91. IGI Global, 2017. http://dx.doi.org/10.4018/978-1-5225-2486-1.ch004.
Full textAbstract:
MongoDB is a NoSQL type of database management system which does not adhere to the commonly used relational database management model. MongoDB is used for horizontal scaling across a large number of servers which may have tens, hundreds or even thousands of servers. This horizontal scaling is performed using sharding. Sharding is a database partitioning technique which partitions large database into smaller parts which are easy to manage and faster to access. There are hundreds of NoSQL databases available in the market. But each NoSQL product is different in terms of features, implementations and behavior. NoSQL and RDBMS solve different set of problems and have different requirements. MongoDB has a powerful query language which extends SQL to JSON enabling developers to take benefit of power of SQL and flexibility of JSON. Along with support for select/from/where type of queries, MongoDB supports aggregation, sorting, joins as well as nested array and collections. To improve query performance, indexes and many more features are also available.
2
Clark, Robin D., and Cynthia J. Curry. "Skin." In Genetic Consultations in the Newborn, edited by Robin D. Clark and Cynthia J. Curry, 257–60. Oxford University Press, 2019. http://dx.doi.org/10.1093/med/9780199990993.003.0038.
Full textAbstract:
This chapter reviews the various types of congenital ectodermal dysplasias (ED). These present variably with involvement of skin, teeth, sweat glands, hair, and nails. In the newborn period ED can resemble ichthyosis with erythema and scaling. X-lLinked hypohidrotic ectodermal dysplasia is the most common form and may affect girls as well as boys. This can cause infant overheating with serious sequelae. Long term dental management is needed for this disorder as well as for most of the other ED’s. Several ED syndromes involve immunodeficiency. Several allelic rare multiple anomaly ED syndromes are caused by pathogenic variants in TP63. The clinical case presentation features an infant with autosomal recessive hypohidrotic ectodermal dysplasia.
3
Andreasen, Troels, Henrik Bulskov, and Jørgen Fischer Nilsson. "A Natural Logic System for Large Knowledge Bases." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2020. http://dx.doi.org/10.3233/faia200824.
Full textAbstract:
This paper describes principles and structure for a software system that implements a dialect of natural logic for knowledge bases. Natural logics are formal logics that resemble stylized natural language fragments, and whose reasoning rules reflect common-sense reasoning. Natural logics may be seen as forms of extended syllogistic logic. The paper proposes and describes realization of deductive querying functionalities using a previously specified natural logic dialect called Natura-Log. In focus here is the engineering of an inference engine employing as a key feature relational database operations. Thereby the inference steps are subjected to computation in bulk for scaling-up to large knowledge bases. Accordingly, the system eventually is to be realized as a general-purpose database application package with the database being turned logical knowledge base.
4
Lopez, Kyra Mikaela M., and Ma Sheila A. Magboo. "A Clinical Decision Support Tool to Detect Invasive Ductal Carcinoma in Histopathological Images Using Support Vector Machines, Naïve-Bayes, and K-Nearest Neighbor Classifiers." In Machine Learning and Artificial Intelligence. IOS Press, 2020. http://dx.doi.org/10.3233/faia200765.
Full textAbstract:
This study aims to describe a model that will apply image processing and traditional machine learning techniques specifically Support Vector Machines, Naïve-Bayes, and k-Nearest Neighbors to identify whether or not a given breast histopathological image has Invasive Ductal Carcinoma (IDC). The dataset consisted of 54,811 breast cancer image patches of size 50px x 50px, consisting of 39,148 IDC negative and 15,663 IDC positive. Feature extraction was accomplished using Oriented FAST and Rotated BRIEF (ORB) descriptors. Feature scaling was performed using Min-Max Normalization while K-Means Clustering on the ORB descriptors was used to generate the visual codebook. Automatic hyperparameter tuning using Grid Search Cross Validation was implemented although it can also accept user supplied hyperparameter values for SVM, Naïve Bayes, and K-NN models should the user want to do experimentation. Aside from computing for accuracy, the AUPRC and MCC metrics were used to address the dataset imbalance. The results showed that SVM has the best overall performance, obtaining accuracy = 0.7490, AUPRC = 0.5536, and MCC = 0.2924.
5
Lovejoy, Shaun. "The weather: Nothing but turbulence . . . and don’t mind the gap." In Weather, Macroweather, and the Climate. Oxford University Press, 2019. http://dx.doi.org/10.1093/oso/9780190864217.003.0008.
Full textAbstract:
“This afternoon, the sky will start to clear, with cloud shreds, runners, and thin bars followed by flocks.” If Jean- Baptiste Lamarck (1744–1829) had had his way, this might have been an uplifting early- morning weather forecast announcing the coming of a sunny day. Unfortunately for poetry, in 1803, several months after Lamarck proposed this first cloud classification, the “namer of clouds,” Luke Howard (1772–1864), introduced his own staid Latin nomenclature that is still with us today and includes terms such as “cumulus,” “stratus,” and “cirrus.” Howard not only had a more scientific-sounding jargon, but was soon given publicity in the form of a poem by Goethe; Lamarck’s names didn’t stand a chance. For a long time, human- scale observation of clouds was the primary source of scientific knowledge of atmospheric morphologies and dynamics. This didn’t change until the appearance of the first weather maps based on meager collections of ground station measurements around 1850. This was the beginning of the field of “synoptic” (literally “map- scale”) meteorology. Under the leadership of Wilhelm Bjerknes (1862–1951), it spawned the Norwegian school of meteorology that focused notably on airmasses, the often sharp gradients between them called “fronts,” and the stability of the airmass interfaces. This was the dominant view when, in the mid 1920s, Richardson proposed his scaling 4/ 3 diffusion law. The spatial resolution of these “synoptic- scale” maps was so low that features smaller than 1,000 kilometers or so could not be discerned. Between these and the kilometric human “microscales,” virtually nothing was known. Richardson’s claim that a single scaling law might hold from thousands of kilometers down to millimeters didn’t seem so daring. Not only was it compatible with the scale- free equations that he had elaborated, but also there were no scalebound paradigms to contradict it. By the late 1940s and ʼ50s, the development of radar finally opened a window onto the intermediate range.
Conference papers on the topic "Feature Map Scaling"
1
Jung, Jee-weon, Seung-bin Kim, Hye-jin Shim, Ju-ho Kim, and Ha-Jin Yu. "Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms." In Interspeech 2020. ISCA: ISCA, 2020. http://dx.doi.org/10.21437/interspeech.2020-1011.
Full text
2
Song, Yu, Joris S. M. Vergeest, and Tjamme Wiegers. "Identifying Feature Handles of Freeform Shapes." In ASME 2008 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. ASMEDC, 2008. http://dx.doi.org/10.1115/detc2008-49438.
Full textAbstract:
Trends, ergonomics and engineering analysis post more challenges than ever to product shape designs, especially in the freeform area. In this paper, freeform feature handles are proposed for easing of difficulties in modifying an existing freeform shape. Considering the variations of curvature as the footprint of a freeform feature(s), curvature analysis is applied to find manipulators, e.g. handles, of a freeform feature(s) in the shape. For these, a Laplacian based pre-processing tool is proposed first to eliminate background noise of the shape. Then least square conformal mapping is applied to map the 3D geometry to a 2D polygon mesh with the minimum distortions of angle deformation and non-uniform scaling. By mapping the curvature of each vertex in the 3D shape to the 2D polygon mesh, a curvature raster image is created. With image processing tools, different levels of curvature changing are identified and marked as feature point(s) / line(s) / area(s) in the freeform shape. Following the definitions, the handles for those intrinsic freeform features are established by the user based on those feature items. Experiments were conducted on different types of shapes to verify the rightness of the proposed method. Different effects caused by different parameters are discussed as well.
3
Kang, Y., R. Sibold, M. Homer, L. Gladwin, R. Claus, W. Ng, and H. Ruan. "Semiconductor Nano and Micro Membrane Based Pressure Sensors for Wide Bandwidth Measurements." In ASME Turbo Expo 2019: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/gt2019-91681.
Full textAbstract:
Abstract Semiconductor nanoµ membranes (NMMs) are gaining acceptance in the semiconductor industry as the benefits they provide become key enablers in scaling and performance enhancements of electronic devices. These tailored-modulus conformal NMM sensor skins with integrated interconnect elements and electronic devices can be applied to new or existing wind tunnel models for full spectrum pressure monitoring. The material is resistant to normal fluids and solvents, can potentially operate over a wide temperature range, and is capable of withstanding erosion. Experimental data presented in this paper demonstrates that: 1) silicon NMMs may be used as single pressure sensor transducers and elements in sensor arrays, and 2) the arrays may be instrumented to map pressure over the surfaces of test articles over a range of Reynolds numbers, temperature and other environmental conditions. Of most importance, we have 1) shown that the small-feature-size sensor elements are highly sensitive to pressure (frequency response from DC up to 5MHz), 2) developed several types of sensor packages for the demonstration of pressure sensing with a miniature probe tip, and 3) confirmed operation in wind tunnel and shock tube tests over 100 times up to Mach 4.2 on several test articles.
4
Xu, Jinglin, Feiping Nie, and Junwei Han. "Feature Selection via Scaling Factor Integrated Multi-Class Support Vector Machines." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/442.
Full textAbstract:
In data mining, we often encounter high dimensional and noisy features, which may not only increase the load of computational resources but also result in the problem of model overfitting. Feature selection is often adopted to address this issue. In this paper, we propose a novel feature selection method based on multi-class SVM, which introduces the scaling factor with a flexible parameter to renewedly adjust the distribution of feature weights and select the most discriminative features. Concretely, the proposed method designs a scaling factor with p/2 power to control the distribution of weights adaptively and search optimal sparsity of weighting matrix. In addition, to solve the proposed model, we provide an alternative and iterative optimization method. It not only makes solutions of weighting matrix and scaling factor independently, but also provides a better way to address the problem of solving L2,0-norm. Comprehensive experiments are conducted on six datasets to demonstrate that this work can obtain better performance compared with a number of existing state-of-the-art multi-class feature selection methods.
5
Jiang, Y., A. V. Murray, P. T. Ireland, and L. di Mare. "Coolant Jets Interaction in Effusion Cooling System: Experimental and Numerical Study." In ASME Turbo Expo 2019: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/gt2019-90156.
Full textAbstract:
Abstract The interaction of coolant jets is significant in effusion settings as a result of the short streamwise and spanwise distance between films. This complicates the design of effusion cooling devices because computing the interaction between numerous, closely spaced rows of films is a challenging task. A flat plate effusion cooling model is investigated at both low and high blowing ratios. Pressure sensitive paint (PSP) is used to measure film effectiveness. Computational fluid dynamics (CFD) calculations are performed to examine the cooling flow features in detail. The mesh sensitivity is studied to demonstrate the effect of mesh size on film effectiveness. The solution obtained by coarse mesh may not capture the correct trend with blowing ratio variation. Results of the computational work by fine mesh demonstrate good agreement with the measured effectiveness. Coolant jets interaction is also investigated. The profile of quantities such as velocity, temperature, kinetic energy and Reynolds stress at several locations in the flow field is compared. The boundary layer profiles are scaled by the thermal boundary layer thickness to study the feature of heat transfer. It is observed that profiles of the flow quantities are self-similar. Two distinct scalings are found: an outer scaling based on boundary layer thickness which collapses the upper part of the profiles; an inner scaling which collapses the profiles at distances from the wall comparable to the penetration depth of a single jet. The latter scaling is based on the distance from the wall to the minimum temperature profile. This distance identifies the location of the coolant leaving the effusion cooling device.
6
Basak, Suryoday, and Manfred Huber. "Evolutionary Feature Scaling in K-Nearest Neighbors Based on Label Dispersion Minimization." In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 2020. http://dx.doi.org/10.1109/smc42975.2020.9282834.
Full text
7
Geekiyanage, Suranga C. H., Adrian Ambrus, and Dan Sui. "Feature Selection for Kick Detection With Machine Learning Using Laboratory Data." In ASME 2019 38th International Conference on Ocean, Offshore and Arctic Engineering. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/omae2019-95496.
Full textAbstract:
Abstract Conventional kick detection methods mainly include monitoring pit gains, surface flow data (flow in and flow out), surface and down-hole pressure variations, and outputs from physics-based models. Kick detection times depend on a driller’s individual ability to interpret these drilling measurements, symptoms and model predictions. Furthermore, testing a novel data-driven solution in a full-scale operation may induce non-productive time, safety risks and crew fatigue adding to false alarms that inevitably occur during testing. Therefore, the development of better, faster and less human intervention-dependent kick detection on a laboratory scale system is a valuable step before full-scale testing. We have generated a dataset containing seven typical drilling measurements and a sequence of gas kicks from experiments conducted in the laboratory scale. First, we employ data analysis tools following data pre-processing steps, data scaling, outlier detection, and natural feature selection. Next, we consider additional “engineered features” and apply different feature combinations to logistic regression with an ensemble method (boosting) for developing kick detection algorithms. In our data analysis, ‘Delta flow’ (difference between flow in and flow out of the well) and ‘Rate of change of delta flow’ designed features, combined with logistic regression and boosting, give promising results in detecting kicks. Finally, we propose an intelligent algorithm and alarm architecture for a complete kick alarm system, which draws from both data analysis and machine learning models developed in this work.
8
Reitz, Gerald, Andreas Kellersmann, and Jens Friedrichs. "Full High Pressure Compressor Investigations to Determine Aerodynamic Changes due to Deterioration." In ASME Turbo Expo 2018: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2018. http://dx.doi.org/10.1115/gt2018-76644.
Full textAbstract:
The Institute of Jet Propulsion and Turbomachinery of the TU Braunschweig owns a jet engine of the type V2500-A1 from the International Aero Engines AG. To conduct research on the jet engine and its components, computer models are necessary. In this paper, the reverse engineering process of the high pressure compressor (HPC) regarding its aerodynamics is presented. Thereby, the reverse engineering process starts from digitizing newly manufactured airfoils, followed by FEM-calculations to enforce the operating forces on the geometries. A computational fluid dynamics (CFD) model using these geometries is set up, considering all relevant geometric and aerodynamic features such as bleed ports and the variable stator vane (VSV) system. Using this CFD-model, the compressor map is calculated and afterwards validated by available manufacturing data [18] and by the institute’s jet engine’s test cell data. Because this jet engine is a highly operated and deteriorated one, a map scaling is necessary before comparing the CFD-model with the test cell data. Nevertheless, an adequate agreement of the operating behavior between scaled compressor map and test cell data is shown. To estimate the deterioration level of the jet engine’s compressor and to evaluate the used scaling factors, the tip gaps inside the CFD-model were doubled and the compressor behavior was simulated. The observed effect of reduced compressor capacity and efficiency is in accordance with literature but is not able to explain the amount of the scaling factors completely.
9
Montazery, Mojtaba, and Nic Wilson. "Rescale-Invariant SVM for Binary Classification." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/348.
Full textAbstract:
Support Vector Machines (SVM) are among the most well-known machine learning methods, with broad use in different scientific areas. However, one necessary pre-processing phase for SVM is normalization (scaling) of features, since SVM is not invariant to the scales of the features’ spaces, i.e., different ways of scaling may lead to different results. We define a more robust decision-making approach for binary classification, in which one sample strongly belongs to a class if it belongs to that class for all possible rescalings of features. We derive a way of characterising the approach for binary SVM that allows determining when an instance strongly belongs to a class and when the classification is invariant to rescaling. The characterisation leads to a computation method to determine whether one sample is strongly positive, strongly negative or neither. Our experimental results back up the intuition that being strongly positive suggests stronger confidence that an instance really is positive.
10
Chen, Hua. "Size and Reynolds Number Effects on Compressor Performance and Scaling." In ASME Turbo Expo 2020: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/gt2020-14019.
Full textAbstract:
Abstract Performance of small turbocharger compressors is greatly affected by their size and size related Reynolds number. Although the effect of Reynolds number on compressors’ efficiency is well known, the effects of Reynolds number have on other performance and design parameters of these compressors are little recognized in open literature. This paper reports the effects of Reynolds number and size on peak efficiency and surge flow of turbocharger compressors, studies the influences of Reynolds number on optimum compressor blade count. Test results show that when a compressor is scaled up (Reynolds number increases), its stability is generally reduced, and vice versa when scaled down. How this feature can be utilised in compressor design is discussed, and an example is given to show how compressor efficiency and flow range may be improved when scaling down by employing a more stable vaneless diffuser and reducing impeller blade number. Finally, the effect of Reynolds number on blade number selection for different sizes of a compressor is studied through CFD and test, and based on these experiences and the theory of flow on flat plate, a design guide line is proposed for the optimum blade numbers in compressor scaling for both impellers with and without splitter.