1
|
Abd Ali DM, Chalob DF, Khudhair AB. Networks Data Transfer Classification Based On Neural Networks. WASIT JOURNAL OF COMPUTER AND MATHEMATICS SCIENCE 2022; 1:207-225. [DOI: 10.31185/wjcm.96] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/02/2023]
Abstract
Data transmission classification is an important issue in networks communications, since the data classification process has the ultimate impact in organizing and arranging it according to size and area to prepare it for transmission to minimize the transmission bandwidth and enhancing the bit rate. There are several methods and mechanisms for classifying the transmitted data according to the type of data and to the classification efficiency. One of the most recent classification methods is the classification of artificial neural networks (ANN). It is considered one of the most dynamic and up-to-date research in areas of application. ANN is a branch of artificial intelligence (AI). The neural network is trained by backpropagation algorithm. Various combinations of functions and their effect while utilizing ANN as a file, classifier was studied and the validity of these functions for different types of datasets was analyzed. Back propagation neural university (BPNN) supported with Levenberg Marqurdte (LM) activation function might be utilized with as a successful data classification tool with a suitable set of training and learning functions which operates, when the probability is maximum. Whenever the maximum likelihood method was compared with backpropagation neural network method, the BPNN supported with Levenberg Marqurdte (LM) activation function was further accurate than maximum likelihood method. A high predictive ability against stable and well-functioning BPNN is possible. Multilayer feed-forward neural network algorithm is also used for classification. However BPNN supported with Levenberg Marqurdte (LM) activation function proves to be more effective than other classification algorithms.
Collapse
|
2
|
Classification of Handwritten Text Signatures by Person and Gender: A Comparative Study of Transfer Learning Methods. ACTA INFORMATICA PRAGENSIA 2022. [DOI: 10.18267/j.aip.197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
|
3
|
Theiling BP, Chou L, Da Poian V, Battler M, Raimalwala K, Arevalo R, Neveu M, Ni Z, Graham H, Elsila J, Thompson B. Science Autonomy for Ocean Worlds Astrobiology: A Perspective. ASTROBIOLOGY 2022; 22:901-913. [PMID: 35507950 DOI: 10.1089/ast.2021.0062] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Astrobiology missions to ocean worlds in our solar system must overcome both scientific and technological challenges due to extreme temperature and radiation conditions, long communication times, and limited bandwidth. While such tools could not replace ground-based analysis by science and engineering teams, machine learning algorithms could enhance the science return of these missions through development of autonomous science capabilities. Examples of science autonomy include onboard data analysis and subsequent instrument optimization, data prioritization (for transmission), and real-time decision-making based on data analysis. Similar advances could be made to develop streamlined data processing software for rapid ground-based analyses. Here we discuss several ways machine learning and autonomy could be used for astrobiology missions, including landing site selection, prioritization and targeting of samples, classification of "features" (e.g., proposed biosignatures) and novelties (uncharacterized, "new" features, which may be of most interest to agnostic astrobiological investigations), and data transmission.
Collapse
Affiliation(s)
| | - Luoth Chou
- NASA Goddard Space Flight Center, Greenbelt, Maryland, USA
- Georgetown University, Washington, DC, USA
| | - Victoria Da Poian
- NASA Goddard Space Flight Center, Greenbelt, Maryland, USA
- Microtell LLC, Greenbelt, Maryland, USA
| | | | | | - Ricardo Arevalo
- Department of Geology, University of Maryland, College Park, Maryland, USA
| | - Marc Neveu
- NASA Goddard Space Flight Center, Greenbelt, Maryland, USA
- Center for Research and Exploration in Space Sciences and Technology II (CRESST II), USA
- Department of Astronomy, University of Maryland, College Park, Maryland, USA
| | - Ziqin Ni
- Department of Geology, University of Maryland, College Park, Maryland, USA
| | - Heather Graham
- NASA Goddard Space Flight Center, Greenbelt, Maryland, USA
| | - Jamie Elsila
- NASA Goddard Space Flight Center, Greenbelt, Maryland, USA
| | | |
Collapse
|
4
|
Abstract
Abstract
This paper introduces a new image-based handwritten historical digit dataset named Arkiv Digital Sweden (ARDIS). The images in ARDIS dataset are extracted from 15,000 Swedish church records which were written by different priests with various handwriting styles in the nineteenth and twentieth centuries. The constructed dataset consists of three single-digit datasets and one-digit string dataset. The digit string dataset includes 10,000 samples in red–green–blue color space, whereas the other datasets contain 7600 single-digit images in different color spaces. An extensive analysis of machine learning methods on several digit datasets is carried out. Additionally, correlation between ARDIS and existing digit datasets Modified National Institute of Standards and Technology (MNIST) and US Postal Service (USPS) is investigated. Experimental results show that machine learning algorithms, including deep learning methods, provide low recognition accuracy as they face difficulties when trained on existing datasets and tested on ARDIS dataset. Accordingly, convolutional neural network trained on MNIST and USPS and tested on ARDIS provide the highest accuracies $$58.80\%$$
58.80
%
and $$35.44\%$$
35.44
%
, respectively. Consequently, the results reveal that machine learning methods trained on existing datasets can have difficulties to recognize digits effectively on our dataset which proves that ARDIS dataset has unique characteristics. This dataset is publicly available for the research community to further advance handwritten digit recognition algorithms.
Collapse
|
5
|
Optimal approximation of piecewise smooth functions using deep ReLU neural networks. Neural Netw 2018; 108:296-330. [DOI: 10.1016/j.neunet.2018.08.019] [Citation(s) in RCA: 164] [Impact Index Per Article: 27.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2017] [Revised: 05/17/2018] [Accepted: 08/21/2018] [Indexed: 01/04/2023]
|
6
|
Using complexity measures to determine the structure of directed acyclic graphs in multiclass classification. Appl Soft Comput 2018. [DOI: 10.1016/j.asoc.2018.01.013] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
7
|
Bhalla V, Chaudhury S, Jain A. A Novel Hybrid CNN-AIS Visual Pattern Recognition Engine. LECTURE NOTES IN COMPUTER SCIENCE 2015:215-224. [DOI: 10.1007/978-3-319-19941-2_21] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/19/2023]
|
8
|
Vié R, Johannet A, Azéma N. Settling of mineral aqueous suspensions. Classification and stability prediction by neural networks. Colloids Surf A Physicochem Eng Asp 2014. [DOI: 10.1016/j.colsurfa.2014.07.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
9
|
Paisitkriangkrai S, van den Hengel A. A scalable stagewise approach to large-margin multiclass loss-based boosting. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2014; 25:1002-1013. [PMID: 24808045 DOI: 10.1109/tnnls.2013.2282369] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
We present a scalable and effective classification model to train multiclass boosting for multiclass classification problems. A direct formulation of multiclass boosting had been introduced in the past in the sense that it directly maximized the multiclass margin. The major problem of that approach is its high computational complexity during training, which hampers its application to real-world problems. In this paper, we propose a scalable and simple stagewise multiclass boosting method which also directly maximizes the multiclass margin. Our approach offers the following advantages: 1) it is simple and computationally efficient to train. The approach can speed up the training time by more than two orders of magnitude without sacrificing the classification accuracy and 2) like traditional AdaBoost, it is less sensitive to the choice of parameters and empirically demonstrates excellent generalization performance. Experimental results on challenging multiclass machine learning and vision tasks demonstrate that the proposed approach substantially improves the convergence rate and accuracy of the final visual detector at no additional computational cost compared to existing multiclass boosting.
Collapse
|
10
|
Analyzing the presence of noise in multi-class problems: alleviating its influence with the One-vs-One decomposition. Knowl Inf Syst 2012. [DOI: 10.1007/s10115-012-0570-1] [Citation(s) in RCA: 46] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
11
|
Bermak A, Martinez D. A compact 3D VLSI classifier using bagging threshold network ensembles. ACTA ACUST UNITED AC 2012; 14:1097-109. [PMID: 18244563 DOI: 10.1109/tnn.2003.816362] [Citation(s) in RCA: 42] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
A bagging ensemble consists of a set of classifiers trained independently and combined by a majority vote. Such a combination improves generalization performance but can require large amounts of memory and computation, a serious drawback for addressing portable real-time pattern recognition applications. We report here a compact three-dimensional (3D) multiprecision very large-scale integration (VLSI) implementation of a bagging ensemble. In our circuit, individual classifiers are decision trees implemented as threshold networks - one layer of threshold logic units (TLUs) followed by combinatorial logic functions. The hardware was fabricated using 0.7-/spl mu/m CMOS technology and packaged using MCM-V micro-packaging technology. The 3D chip implements up to 192 TLUs operating at a speed of up to 48 GCPPS and implemented in a volume of (/spl omega/ /spl times/ L /spl times/ h) = (2 /spl times/ 2 /spl times/ 0.7) cm/sup 3/. The 3D circuit features a high level of programmability and flexibility offering the possibility to make an efficient use of the hardware resources in order to reduce the power consumption. Successful operation of the 3D chip for various precisions and ensemble sizes is demonstrated through an electronic nose application.
Collapse
Affiliation(s)
- A Bermak
- Electr. and Electron. Eng. Dept., Hong Kong Univ. of Sci. and Technol., Kowloon, China
| | | |
Collapse
|
12
|
Vial J, Pezous B, Thiébaut D, Sassiat P, Teillet B, Cahours X, Rivals I. The discriminant pixel approach: a new tool for the rational interpretation of GCxGC-MS chromatograms. Talanta 2011; 83:1295-301. [PMID: 21215866 DOI: 10.1016/j.talanta.2010.07.059] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2010] [Revised: 07/19/2010] [Accepted: 07/24/2010] [Indexed: 11/16/2022]
Abstract
GCxGC is now recognized as the most suited analytical technique for the characterization of complex mixtures of volatile compounds; it is implemented worldwide in academic and industrial laboratories. However, in the frame of comprehensive analysis of non-target analytes, going beyond the visual examination of the color plots remains challenging for most users. We propose a strategy that aims at classifying chromatograms according to the chemical composition of the samples while determining the origin of the discrimination between different classes of samples: the discriminant pixel approach. After data pre-processing and time-alignment, the discriminatory power of each chromatogram pixel for a given class was defined as its correlation with the membership to this class. Using a peak finding algorithm, the most discriminant pixels were then linked to chromatographic peaks. Finally, crosschecking with mass spectrometry data enabled to establish relationships with compounds that could consequently be considered as candidate class markers. This strategy was applied to a large experimental data set of 145 GCxGC-MS chromatograms of tobacco extracts corresponding to three distinct classes of tobacco.
Collapse
Affiliation(s)
- Jérôme Vial
- Laboratoire des Sciences Analytiques, Bioanalytiques et Miniaturisation (LSABM), UMR CNRS UPMC PECSA, ESPCI ParisTech, 10 rue Vauquelin, 75005 Paris, France.
| | | | | | | | | | | | | |
Collapse
|
13
|
|
14
|
|
15
|
|
16
|
Lézoray O, Cardot H. Comparing Combination Rules of Pairwise Neural Networks Classifiers. Neural Process Lett 2007. [DOI: 10.1007/s11063-007-9058-5] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/03/2023]
|
17
|
Sulzmann JN, Fürnkranz J, Hüllermeier E. On Pairwise Naive Bayes Classifiers. MACHINE LEARNING: ECML 2007 2007. [DOI: 10.1007/978-3-540-74958-5_35] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
|
18
|
Fernandes AM, Utkin AB, Lavrov AV, Vilar RM. Design of committee machines for classification of single-wavelength lidar signals applied to early forest fire detection. Pattern Recognit Lett 2005. [DOI: 10.1016/j.patrec.2004.09.012] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
19
|
|
20
|
Mańdziuk J, Shastri L. Incremental class learning approach and its application to handwritten digit recognition. Inf Sci (N Y) 2002. [DOI: 10.1016/s0020-0255(02)00170-6] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
21
|
Bajaj R, Dey L, Chaudhury S. Devnagari numeral recognition by combining decision of multiple connectionist classifiers. SADHANA 2002; 27:59-72. [DOI: 10.1007/bf02703312] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/19/2023]
|
22
|
Fürnkranz J. Pairwise Classification as an Ensemble Technique. LECTURE NOTES IN COMPUTER SCIENCE 2002. [DOI: 10.1007/3-540-36755-1_9] [Citation(s) in RCA: 15] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/11/2023]
|
23
|
Abstract
We describe a system of thousands of binary perceptrons with coarse-oriented edges as input that is able to recognize shapes, even in a context with hundreds of classes. The perceptrons have randomized feedforward connections from the input layer and form a recurrent network among themselves. Each class is represented by a prelearned attractor (serving as an associative hook) in the recurrent net corresponding to a randomly selected subpopulation of the perceptrons. In training, first the attractor of the correct class is activated among the perceptrons; then the visual stimulus is presented at the input layer. The feedforward connections are modified using field-dependent Hebbian learning with positive synapses, which we show to be stable with respect to large variations in feature statistics and coding levels and allows the use of the same threshold on all perceptrons. Recognition is based on only the visual stimuli. These activate the recurrent network, which is then driven by the dynamics to a sustained attractor state, concentrated in the correct class subset and providing a form of working memory. We believe this architecture is more transparent than standard feedforward two-layer networks and has stronger biological analogies.
Collapse
Affiliation(s)
- Y Amit
- Department of Statistics, University of Chicago, Chicago, IL 60637, USA
| | | |
Collapse
|
24
|
|
25
|
|
26
|
Chim YC, Kassim AA, Ibrahim Y. Dual classifier system for handprinted alphanumeric character recognition. Pattern Anal Appl 1998. [DOI: 10.1007/bf01259365] [Citation(s) in RCA: 17] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
27
|
Abstract
We explore a new approach to shape recognition based on a virtually infinite family of binary features (queries) of the image data, designed to accommodate prior information about shape invariance and regularity. Each query corresponds to a spatial arrangement of several local topographic codes (or tags), which are in themselves too primitive and common to be informative about shape. All the discriminating power derives from relative angles and distances among the tags. The important attributes of the queries are a natural partial ordering corresponding to increasing structure and complexity; semi-invariance, meaning that most shapes of a given class will answer the same way to two queries that are successive in the ordering; and stability, since the queries are not based on distinguished points and substructures. No classifier based on the full feature set can be evaluated, and it is impossible to determine a priori which arrangements are informative. Our approach is to select informative features and build tree classifiers at the same time by inductive learning. In effect, each tree provides an approximation to the full posterior where the features chosen depend on the branch that is traversed. Due to the number and nature of the queries, standard decision tree construction based on a fixed-length feature vector is not feasible. Instead we entertain only a small random sample of queries at each node, constrain their complexity to increase with tree depth, and grow multiple trees. The terminal nodes are labeled by estimates of the corresponding posterior distribution over shape classes. An image is classified by sending it down every tree and aggregating the resulting distributions. The method is applied to classifying handwritten digits and synthetic linear and nonlinear deformations of three hundred [Formula: see text] symbols. State-of-the-art error rates are achieved on the National Institute of Standards and Technology database of digits. The principal goal of the experiments on [Formula: see text] symbols is to analyze invariance, generalization error and related issues, and a comparison with artificial neural networks methods is presented in this context. [Figure: see text]
Collapse
Affiliation(s)
- Yali Amit
- Department of Statistics, University of Chicago, Chicago, IL, 60637, U.S.A
| | - Donald Geman
- Department of Mathematics and Statistics, University of Massachusetts, Amherst, MA 01003, U.S.A
| |
Collapse
|
28
|
Sung-Bae Cho. Neural-network classifiers for recognizing totally unconstrained handwritten numerals. ACTA ACUST UNITED AC 1997; 8:43-53. [DOI: 10.1109/72.554190] [Citation(s) in RCA: 91] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
29
|
Lee SW, Song HH. A new recurrent neural-network architecture for visual pattern recognition. IEEE TRANSACTIONS ON NEURAL NETWORKS 1997; 8:331-340. [PMID: 18255636 DOI: 10.1109/72.557671] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
We propose a new type of recurrent neural-network architecture, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units. The proposed recurrent neural network differs from Jordan's and Elman's recurrent neural networks with respect to function and architecture, because it has been originally extended from being a mere multilayer feedforward neural network, to improve discrimination and generalization powers. We also prove the convergence properties of the learning algorithm in the proposed recurrent neural network, and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeric database of Concordia University, Montreal, Canada. Experimental results have confirmed that the proposed recurrent neural network improves discrimination and generalization powers in the recognition of visual patterns.
Collapse
Affiliation(s)
- S W Lee
- Dept. of Comput. Sci. and Eng., Korea Univ., Seoul
| | | |
Collapse
|
30
|
A new neural network: Hybrid location-content addressable memory. Neurocomputing 1996. [DOI: 10.1016/0925-2312(94)00078-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
31
|
Gioiello GAM, Tarantino A, Sorbello F, Vassallo G. Simple Techniques for an Efficient Recognition of Handwritten Characters Using Α MLP. JOURNAL OF INTELLIGENT SYSTEMS 1996. [DOI: 10.1515/jisys.1996.6.3-4.199] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
|
32
|
Lee SW. Multilayer cluster neural network for totally unconstrained handwritten numeral recognition. Neural Netw 1995. [DOI: 10.1016/0893-6080(95)00020-z] [Citation(s) in RCA: 16] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
|