Aiming at the problems of inaccurate feature extraction and high complexity of traditional ElectroCardioGram (ECG) detection algorithms based on morphological features, an improved Long Short-Term Memory (LSTM) neural network was proposed. Based on the advantage of traditional LSTM model in time series data processing, the proposed model added reverse and depth calculations which avoids extraction of waveform features artificially and strengthens learning ability of the network. And supervised learning was performed in the model according to the given heart beat sequences and category labels, realizing the arrhythmia detection of unknown heart beats. The experimental results on the arrhythmia datasets in MIT-BIH database show that the overall accuracy of the proposed method reaches 98.34%. Compared with support vector machine, the accuracy and F1 value of the model are both improved.

In order to solve the contradiction between the estimation precision and the complexity of the existing tag number estimation algorithm, a Radio Frequency IDentification (RFID) tag number estimation algorithm based on sequential linear Bayes was proposed by the analysis and comparison of the existing algorithms. Firstly, a linear model for estimating the number of tags was established based on linear Bayesian theory. This model made full use of the amount and correlation of idle, successful and collision time slots. Then, the closed form expression of the tag number estimation was derived, and the sequential solution method of the statistics was given. Finally, the computational complexity of the sequential Bayesian algorithm was analyzed and compared. The simulation results show that the proposed algorithm improves the estimation accuracy and recognition efficiency by the sequential Bayesian method. The error is only 4% when the number of time slots is half of the frame length. The algorithm updates the estimated value of the number of tags in a linear analytic form to avoid the exhaustive search. Compared with the maximum posterior probability and Mahalanobis distance algorithm with high precision, the computational complexity is reduced from O( n ²) and O( n) to O( 1). Through theoretical analysis and simulation, the RFID tag number estimation algorithm based on sequential linear Bayes has both high precision and low complexity, and can meet the actual estimation requirements with hardware resource constraints.

Aiming at the shortcomings such as low prediction accuracy and low efficiency of model training in alarm prediction of communication networks, a communication network alarm forecasting scheme based on Canonical-order tree (Can-tree) weighted incremental association rule mining algorithm was proposed. Firstly, the alarm data was preprocessed to determine the alarm data weight and compressed into the Can-tree structure. Secondly, the Can-tree was mined by using the incremental association rule mining algorithm to generate alarm association rules. Finally, a pattern matching method was used to predict real-time alarm information, and the results were optimized. The experimental results show that the proposed method is efficient, and the previously mined results can improve the mining efficiency. The alarm weight assigning scheme can reasonably distinguish the importance of alarm data, help mine the alarm association rules with high importance, speed up the elimination of outdated alarm association rules, and improve the accuracy and precision of the prediction.

To alleviate the congestion of traditional data center network, the flow scheduling cost based congestion control routing algorithm on Software Defined Network (SDN) architecture was proposed. Firstly, the maximum flows and minimum flows on congestion links were differentiated. Secondly, the cost of each equivalent route for maximum flows was calculated, and the routes with minimum cost were selected as available scheduling routes for maximum flows. Then, the flow scheduling cost of each available scheduling route was defined by considering the cost change of rerouting operation and the occupancy ratio of bandwidth together. Finally, the maximum flows with minimum scheduling cost were scheduled to related available scheduling routes. The experimental results show that, the proposed algorithm is qualified to reduce the load of congestion links when network congestion occurs. Moreover, compared with the previous congestion control algorithm which taking into account the flow route selection only, the proposed algorithm improves the link utilization and reduces the transmission time of flow, which make the network link resources to be better used.

To solve the problem that high dimension of descriptor decreases the matching speed of Scale Invariant Feature Transform (SIFT) algorithm, an improved SIFT algorithm was proposed. The feature point was acted as the center, the circular rotation invariance structure was used to construct feature descriptor in the approximate size circular feature points' neighborhood, which was divided into several sub-rings. In each sub-ring, the pixel information was to maintain a relatively constant and positions changed only. The accumulated value of the gradient within each ring element was sorted to generate the feature vector descriptor when the image was rotated. The dimensions and complexity of the algorithm was reduced and the dimensions of feature descriptor were reduced from 128 to 48. The experimental results show that, the improved algorithm can improve rotating registration repetition rate to more than 85%. Compared with the SIFT algorithm, the average matching registration rate increases by 5%, the average time of image registration reduces by about 30% in the image rotation, zoom and illumination change cases. The improved SIFT algorithm is effective.