Computation of Person Re-Identification using Self-Learning Anomaly Detection Framework in Deep-Learning

This paper proposes an application of a self-Learning anomaly detection framework in Deep-learning. In this application, both hybrid unsupervised and supervised machine learning schemes are used. Firstly, it takes metadata of the unsupervised data clustering module (DCM). Data clustering module (DCM) analyses the pattern of the monitoring data and enables the self-learning capability that eliminates the requirement of the prior knowledge of the abnormal network behaviors and also has the potential to detect the unforeseen anomalies. Next, we use the self-learning mechanism that transfer pattern learned by the DCM to a supervised data regression and classification module (DRCM) it’s Complexity is mainly related to scalability of supervised learning module. It is more measurable and less time consuming for online anomalies by avoiding excessively usage of the original dataset. It has a density-based clustering algorithm and deep learning, neural network structure-based DCM and DRCM. We are also using an anti-spoofing-based approach for presentation attack detection (PAD). In these approaches, we are mainly detecting a person reidentify and computing without having any false anomalies.

Download Full-text

Deep learning-based question answering system for intelligent humanoid robot

Journal Of Big Data ◽

10.1186/s40537-020-00341-6 ◽

2020 ◽

Vol 7 (1) ◽

Author(s):

Widodo Budiharto ◽

Vincent Andreas ◽

Alexander Agung Santoso Gunawan

Keyword(s):

Neural Network ◽

Deep Learning ◽

Knowledge Base ◽

Humanoid Robot ◽

Question Answering ◽

The Self ◽

Learning Approach ◽

Learning Capability ◽

Question Answering Systems ◽

Self Learning

Abstract Background The development of Intelligent Humanoid Robot focuses on question answering systems that can interact with people is very limited. In this research, we would like to propose an Intelligent Humanoid Robot with the self-learning capability for accepting and giving responses from people based on Deep Learning and Big Data knowledge base. This kind of robot can be used widely in hotels, universities, and public services. The Humanoid Robot should consider the style of questions and conclude the answer through conversation between robot and user. In our scenario, the robot will detect the user’s face and accept commands from the user to do an action. Findings The question from the user will be processed using deep learning, and the result will be compared to the knowledge base on the system. We proposed our Deep Learning approach, based on Recurrent Neural Network (RNN) encoder, Convolution Neural Network (CNN) encoder, with Bidirectional Attention Flow (BiDAF). Conclusions Our evaluation indicates that using RNN based encoder with BiDAF gives a higher score, than CNN encoder with the BiDAF. Based on our experiment, our model get 82.43% F1 score and the RNN based encoder will give a higher EM/F1 score than using the CNN encoder.

Download Full-text

Deep Learning-Based Question Answering System for Intelligent Humanoid Robot

10.21203/rs.3.rs-26510/v2 ◽

2020 ◽

Author(s):

Widodo Budiharto ◽

Vincent Andreas ◽

Alexander Agung Santoso Gunawan

Keyword(s):

Neural Network ◽

Deep Learning ◽

Knowledge Base ◽

Humanoid Robot ◽

Question Answering ◽

The Self ◽

Learning Approach ◽

Learning Capability ◽

Question Answering Systems ◽

Self Learning

Abstract Background- The development of Intelligent Humanoid Robot focuses on question answering systems that can interact with people is very limited. In this research, we would like to propose an Intelligent Humanoid Robot with the self-learning capability for accepting and giving responses from people based on Deep Learning and Big Data knowledge base. This kind of robot can be used widely in hotels, universities, and public services. The Humanoid Robot should consider the style of questions and conclude the answer through conversation between robot and user. In our scenario, the robot will detect the user’s face and accept commands from the user to do an action. Findings- The question from the user will be processed using deep learning, and the result will be compared to the knowledge base on the system. We proposed our Deep Learning approach, based on Recurrent Neural Network (RNN) encoder, Convolution Neural Network (CNN) encoder, with Bidirectional Attention Flow (BiDAF). Conclusions- Our evaluation indicates that using RNN based encoder with BiDAF gives a higher score, than CNN encoder with the BiDAF. Based on our experiment, our model get 82.43% F1 score and the RNN based encoder will give a higher EM / F1 score than using the CNN encoder.

Download Full-text

Deep Learning-Based Question Answering System for Intelligent Humanoid Robot

10.21203/rs.3.rs-26510/v1 ◽

2020 ◽

Author(s):

Widodo Budiharto ◽

Vincent Andreas ◽

Alexander Agung Santoso Gunawan

Keyword(s):

Big Data ◽

Deep Learning ◽

Humanoid Robot ◽

Question Answering ◽

Training Dataset ◽

Learning Approach ◽

Exact Match ◽

Learning Capability ◽

Question Answering Systems ◽

Self Learning

Abstract The development of intelligent Humanoid Robot focuses on question answering systems to be able to interact with people is very rare. In this research, we would like to propose a Humanoid Robot with the self-learning capability for accepting and giving a response from people based on Deep Learning and big data from the internet. This kind of robot can be used widely in hotels, universities and public services. The Humanoid Robot should consider the style of questions and conclude the answer through conversation between robot and user. In our scenario, the robot will detect the user’s face and accept commands from the user to do an action, where the question from the user will be processed using deep learning, and the result will be compared with knowledge on the system. We proposed our deep learning approach, based on use GRU/LSTM, CNN and BiDAF with big data SQuAD as training dataset. Our experiment indicates that using GRU/LSTM encoder with BiDAF gives higher Exact Match and F1 Score, than CNN with the BiDAF model.

Download Full-text

Improved K-means Clustering Algorithm and its Applications

Recent Patents on Engineering ◽

10.2174/1872212113666181203110611 ◽

2019 ◽

Vol 13 (4) ◽

pp. 403-409

Author(s):

Hui Qi ◽

Jinqing Li ◽

Xiaoqiang Di ◽

Weiwu Ren ◽

Fengrong Zhang

Keyword(s):

Data Clustering ◽

Large Scale ◽

Clustering Algorithm ◽

Principal Component ◽

Mean Value ◽

Attack Detection ◽

Cluster Center ◽

Network Attack ◽

Initial Cluster ◽

Low Dimensional

Background: K-means algorithm is implemented through two steps: initialization and subsequent iterations. Initialization is to select the initial cluster center, while subsequent iterations are to continuously change the cluster center until it won't change any more or the number of iterations reaches its maximum. K-means algorithm is so sensitive to the cluster center selected during initialization that the selection of a different initial cluster center will influence the algorithm performance. Therefore, improving the initialization process has become an important means of K-means performance improvement. Methods: This paper uses a new strategy to select the initial cluster center. It first calculates the minimum and maximum values of the data in a certain index (For lower-dimensional data, such as twodimensional data, features with larger variance, or the distance to the origin can be selected; for higher-dimensional data, PCA can be used to select the principal component with the largest variance), and then divides the range into equally-sized sub-ranges. Next adjust the sub-ranges based on the data distribution so that each sub-range contains as much data as possible. Finally, the mean value of the data in each sub-range is calculated and used as the initial clustering center. Results: The theoretical analysis shows that although the time complexity of the initialization process is linear, the algorithm has the characteristics of the superlinear initialization method. This algorithm is applied to two-dimensional GPS data analysis and high-dimensional network attack detection. Experimental results show that this algorithm achieves high clustering performance and clustering speed. Conclusion: This paper reduces the subsequent iterations of K-means algorithm without compromising the clustering performance, which makes it suitable for large-scale data clustering. This algorithm can not only be applied to low-dimensional data clustering, but also suitable for highdimensional data.

Download Full-text

A Deep Learning Ensemble for Network Anomaly and Cyber-Attack Detection

Sensors ◽

10.3390/s20164583 ◽

2020 ◽

Vol 20 (16) ◽

pp. 4583 ◽

Cited By ~ 2

Author(s):

Vibekananda Dutta ◽

Michał Choraś ◽

Marek Pawlicki ◽

Rafał Kozik

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Anomaly Detection ◽

Statistical Significance ◽

Attack Detection ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Second Phase ◽

Network Intrusion ◽

Network Anomaly Detection

Currently, expert systems and applied machine learning algorithms are widely used to automate network intrusion detection. In critical infrastructure applications of communication technologies, the interaction among various industrial control systems and the Internet environment intrinsic to the IoT technology makes them susceptible to cyber-attacks. Given the existence of the enormous network traffic in critical Cyber-Physical Systems (CPSs), traditional methods of machine learning implemented in network anomaly detection are inefficient. Therefore, recently developed machine learning techniques, with the emphasis on deep learning, are finding their successful implementations in the detection and classification of anomalies at both the network and host levels. This paper presents an ensemble method that leverages deep models such as the Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and a meta-classifier (i.e., logistic regression) following the principle of stacked generalization. To enhance the capabilities of the proposed approach, the method utilizes a two-step process for the apprehension of network anomalies. In the first stage, data pre-processing, a Deep Sparse AutoEncoder (DSAE) is employed for the feature engineering problem. In the second phase, a stacking ensemble learning approach is utilized for classification. The efficiency of the method disclosed in this work is tested on heterogeneous datasets, including data gathered in the IoT environment, namely IoT-23, LITNET-2020, and NetML-2020. The results of the evaluation of the proposed approach are discussed. Statistical significance is tested and compared to the state-of-the-art approaches in network anomaly detection.

Download Full-text

Cross Breed Clustering Algorithm for High Dimensional Data

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.a5313.119119 ◽

2019 ◽

Vol 9 (1) ◽

pp. 5049-5052

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Data Clustering ◽

Clustering Algorithm ◽

Clustering Algorithms ◽

High Dimensional Data ◽

High Dimensional ◽

Growing Domain ◽

Present World

Clustering plays a major role in machine learning and also in data mining. Deep learning is fast growing domain in present world. Improving the quality of the clustering results by adopting the deep learning algorithms. Many clustering algorithm process various datasets to get the better results. But for the high dimensional data clustering is still an issue to process and get the quality clustering results with the existing clustering algorithms. In this paper, the cross breed clustering algorithm for high dimensional data is utilized. Various datasets are used to get the results.

Download Full-text