Data processing model and performance analysis of cognitive computing based on machine learning in Internet environment
- 16 Downloads
To solve the problem that the rapid growth of data scale in the Internet environment makes it more difficult to extract meaningful information from massive data, a cognitive computing model is proposed, and the data processing technology that the model can use and the task scheduling algorithm under distributed background conditions are explored. In addition, aiming at the decision-making problem of the availability of massive information in the Internet, a cognitive decision algorithm based on deep confidence network and linear perceptron is proposed. According to the result of deep confidence network training, a cognitive decision model with error control function is established, and the decision result of whether the information is effective or not is given by considering the information itself and context information comprehensively. The experimental results show that the cognitive decision model based on deep belief network and linear perceptron performs well in the late training period. In addition, according to the experimental results, the most suitable operating parameters are selected. The accuracy of the algorithm is much higher than that of the deep belief network and the multilayer perceptron, indicating that this algorithm has some improvement in cognitive decision accuracy.
KeywordsInternet environment Cognitive computing Machine learning Data processing
This study was not funded by any other parties. Author Hu Jin does not have received any research grants from any other companies.
Compliance with ethical standards
Conflict of interest
Author Hu Jin declares that he has no conflict of interest.
Human and animal rights
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. This article does not contain any studies with animals performed by any of the authors.
Informed consent was obtained from all individual participants included in the study.
- Andreou AG, Dykman AA, Fischl KD et al (2016) IEEE international symposium on Real-time sensory information processing using the TrueNorth neurosynaptic system//circuits and systems (ISCAS). IEEE, pp 2911–2911Google Scholar
- Gottlieb J, Lopes M, Oudeyer PY (2016) Motivated cognition: neural and computational mechanisms of curiosity, attention, and intrinsic motivation. In: Recent developments in neuroscience research on human motivation. Emerald Group Publishing Limited, Bingley, pp 149–172Google Scholar
- Itaya K, Takahashi K, Nakamura M et al (2016) BriCA: a modular software platform for whole brain architecture. In: International conference on neural information processing. Springer, Cham, pp 334–341Google Scholar
- Lempel R (2017) Personalization is a two-way street//proceedings of the eleventh ACM conference on recommender systems. ACM, pp 3–3Google Scholar
- Zheng J, Guo S, Gao L et al (2018) Inferring Gender of Micro-Blog Users based on Multi-Classifiers Fusion. Int J Perform Eng 14(2):349Google Scholar