Hybrid neural network

About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.

A Hybrid Neural Network Methodology for Cost Estimation

Abstract: This paper presents an integrated system approach, utilizing a hybrid methodology for the generation of practical cost and schedule baselines and for bid preparation under the prevailing competitive bidding environment. The system incorporates enhancements to the various functions that cover the quantitative aspects of estimate preparation, including: direct and indirect cost estimation, planning and scheduling, and resource utilization. For practicality, the system accounts for the qualitative aspects that strongly influence bid markup decision (e.g., competition, market conditions, and contractor keenness for the job). In order to provide a practical and efficient aid to such an experience-based decision, the system utilizes Neural Networks, an Al-based technique that emulates the human ability to learn from past experience and derive speedy solutions to new situations, based mainly on intuitive judgement (gut feeling) that is difficult to model by other AIbased techniques including expert systems. The paper emphasizes the conceptual and design stages of the system development, establishing a structured methodology for cost estimation and bid preparation in a competitive environment.

Hybrid Neural Network to Impute Missing Data for IoT Applications

Abstract: The new development of the Internet of Things (IoT) depends on reliable data delivery, where transferring data between devices should be accurate and fast to ensure high performance for IoT applications. IoT applications could suffer from low quality of data delivery due to several factors such as connection errors, sensor faults, or security attacks. Low quality of data delivery reduces the performance of IoT applications since if the collected data is incomplete it could eventually be useless. In this paper, we propose a hybrid neural network with genetic algorithm to impute the missing data for medical IoT applications. A deep learning neural network (Jordan network) is used as a model to predict the missing data, while the genetic algorithm is adopted to optimize the weights of the neural network. The obtained results show that the proposed algorithm is able to impute missing data with high classification value based on Area Under the Curve (AUC) and improve the final performance of IoT application by up tp 5%.

Hybrid modeling of inulinase bio-production process

Abstract: BACKGROUND: A potential application of inulinase in the food industry is the production of fructooligosaccharides (FOS) through transfructosilation of sucrose. Besides their ability to increase the shelf-life and flavor of many products, FOS have many interesting functional properties. The use of an industrial medium may represent a good, cost-effective alternative to produce inulinase, since the activity of the enzyme produced may be improved or at least remain the same compared with that obtained using a synthetic medium. Thus, inulinase production for use in FOS synthesis is of considerable scientific and technological appeal, as is the development of a reliable mathematical model of the process. This paper describes a hybrid neural network approach to model inulinase production in a batch bioreactor using agroindustrial residues as substrate. The hybrid modeling makes use of a series artificial neural network to estimate the kinetic parameters of the process and the mass balance as constitutive equations. RESULTS: The proposed model was shown to be capable of describing the complex behavior of inulinase production employing agroindustrial residues as substrate, so that the mathematical framework developed is a useful tool for simulation of this process. CONCLUSION: The hybrid neural network model developed was shown to be an interesting alternative to estimate model parameters since complete elucidation of the phenomena and mechanisms involved in the fermentation is not required owing to the black-box nature of the ANN used as parameter estimator. Copyright © 2010 Society of Chemical Industry

Network Intrusion Detection using Hybrid Neural Networks

Abstract: Intrusion detection is a critical process in network security. It is the task of detecting, preventing and possibly reacting to the attack and intrusions in a network based computer systems. This paper presents an intrusion detection system based on self-organizing maps (SOM) and back propagation network (BPN) for visualizing and classifying intrusion. The performance of the proposed hybrid neural network approach is tested using KDD cup' 99 data available in the UCI KDD archive. The proposed approach considers all kinds of attacks under major category (normal, DOS, probe,U2R, and R2L) which provides an insightful visualization for network intrusion and works well in detecting different attacks in the considered system

Hybrid Machine Learning for Scanning Near-field Optical Spectroscopy

Abstract: Author(s): Chen, X; Yao, Z; Xu, S; McLeod, AS; Gilbert Corder, SN; Zhao, Y; Tsuneto, M; Bechtel, HA; Martin, MC; Carr, GL; Fogler, MM; Stanciu, SG; Basov, DN; Liu, M | Abstract: The underlying physics behind an experimental observation often lacks a simple analytical description. This is especially the case for scanning probe microscopy techniques, where the interaction between the probe and the sample is nontrivial. Realistic modeling to include the exact details of the probe is widely acknowledged as a challenge. Due to various complexity constraints, the probe is often only approximated in a simplified geometry, leading to a source for modeling inconsistencies. On the other hand, a well-trained artificial neural network based on real data can grasp the hidden correlation between the signal and the sample properties, circumventing the explicit probe modeling process. In this work we show that, via a combination of model calculation and experimental data acquisition, a physics-infused hybrid neural network can predict the probe-sample interaction in the widely used scattering-type scanning near-field optical microscope. This hybrid network provides a long-sought solution for accurate extraction of material properties from tip-specific raw data. The methodology can be extended to other scanning probe microscopy techniques as well as other data-oriented physical problems in general.