A Novel Hybrid Model for Predicting Traffic Flow via Improved Ensemble Learning Combined with Deep Belief Networks

The intelligent transportation system (ITS) plays an irreplaceable role in alleviating urban traffic congestion and realizing sustainable urban development. Accurate and efficient short-term traffic state forecasting is a significant issue in ITS. This study proposes a novel hybrid model (ELM-IBF) to predict the traffic state on urban expressways by taking advantage of both deep learning models and ensemble learning framework. First, a developed bagging framework is introduced to combine several deep belief networks (DBNs) that are utilized to capture the complicated temporal characteristic of traffic flow. Then, a novel combination method named improved Bayesian fusion (IBF) is proposed to replace the averaging method in the bagging framework since it can better fuse the prediction results of the component DBNs by assigning the reasonable weights to DBNs at each prediction time interval. Finally, the proposed hybrid model is validated with ground-truth traffic flow data captured by the remote traffic microwave sensors installed on the multiple road sections of 2nd Ring Road in Beijing. The experimental results illustrate that the ELM-IBF method can effectively capture sharp fluctuations in the traffic flow. Compared with several benchmark models (e.g., artificial neural network, long short-term memory neural network, and DBN), the ELM-IBF model reveals better performance in forecasting single-step-ahead traffic volume and speed. Additionally, it is proved that the ELM-IBF model is capable of providing stable and high-quality results in multistep-ahead traffic flow prediction.

Iot Device Classification in Cloud Organizations Using Deep Belief Networks

With the rapid increase in the usage of IoT devices, the cyber threats are increasing among the communication between the IoT devices. The challenges related to security surmounts with increasing number of IoT devices due to its functionality and heterogeneity. In recent times, deep learning algorithms are offered to resolve the constraints associated with detection of malicious devices among the networks. In this paper, we utilize deep belief network (DBN) to resolve the problems associated with identification, detection of anomaly IoT devices. Several features are extracted initially to find the malicious devices in the IoT device network that includes storage, computational resources and high dimensional features. These features extracted from the network traffic assists in achieving the classification of devices by DBN. The simulation is performed to test the accuracy and detection rate of the proposed deep learning classifier. The results show that the proposed method is effective in implementing the detection of malicious nodes in the network than existing methods.

Face Recognition Based on Fractal Code and Deep Belief Networks

An enhanced algorithm to recognize the human face using bi-dimensional fractal codes and deep belief networks is presented in this work. The proposed method is experimentally robust against variations in the appearance of human face images, despite different disturbances affecting the measurements and the acquisition process such as occlusion, changes in lighting, pose, and expression or the presence or absence of structural components. That is mainly based on fractal codes (IFS) and bi-dimensional subspaces for features extraction and space reduction, combined with a deep belief network (DBN) classifier. The evaluation is performed through comparisons using probabilistic neural network (PNN) and nearest neighbours (KNN) approaches on three well-known databases (FERET, ORL, and FEI). The results suggest the effectiveness and robustness of the proposed approach.

Mitigation of Malware Effect using Cyber Threat Analysis using Ensemble Deep Belief Networks

Cybersecurity is a technique that entails security models development techniques to the illegal access, modification, or destruction of computing resources, networks, program, and data. Due to tremendous developments in information and communication technologies, new dangers to cyber security have arisen and are rapidly changing. The creation of a Deep Learning system requires a substantial number of input samples and it can take a great deal of time and resources to gather and process the samples. Building and maintaining the basic system requires a huge number of resources, including memory, data and computational power. In this paper, we develop an Ensemble Deep Belief Networks to classify the cybersecurity threats in large scale network. An extensive simulation is conducted to test the efficacy of model under different security attacks. The results show that the proposed method achieves higher level of security than the other methods.