Multiple IoT based Network Attacks Discrimination by Multilayer Feedforward Neural Networks

In this paper a new neural model for detection of multiple network IoT-based attacks, such as DDoS TCP, UDP, and HHTP flood, is presented. It consists of feedforward multilayer network with back propagation. A general algorithm for its optimization during training is proposed, leading to proper number of neurons in the hidden layers. The Scaled Gradient Descent algorithm and the Adam optimization are studied with better classification results, obtained by the developed classifiers, using the latter. Tangent hyperbolic function appears to be proper selection for the hidden neurons. Two sets of features, gathered from aggregated records of the network traffic, are tested, containing 8 and 10 components. While more accurate results are obtained for the 10-feature set, the 8-feature set offers twice lower training time and seems applicable for real-world applications. The detection rate for 7 of 10 different network attacks, primarily various types of floods, is higher than 90% and for 3 of them – mainly reconnaissance and keylogging activities with low intensity of the generated traffic, deviates between 57% and 68%. The classifier is considered applicable for industrial implementation.

Exploiting User Friendship Networks for User Identification across Social Networks

Identifying offline entities corresponding to multiple virtual accounts of users across social networks is crucial for the development of related fields, such as user recommendation system, network security, and user behavior pattern analysis. The data generated by users on multiple social networks has similarities. Thus, the concept of symmetry can be used to analyze user-generated information for user identification. In this paper, we propose a friendship networks-based user identification across social networks algorithm (FNUI), which performs the similarity of multi-hop neighbor nodes of a user to characterize the information redundancy in the friend networks fully. Subsequently, a gradient descent algorithm is used to optimize the contribution of the user’s multi-hop nodes in the user identification process. Ultimately, user identification is achieved in conjunction with the Gale–Shapley matching algorithm. Experimental results show that compared with baselines, such as friend relationship-based user identification (FRUI) and friendship learning-based user identification (FBI): (1) The contribution of single-hop neighbor nodes in the user identification process is higher than other multi-hop neighbor nodes; (2) The redundancy of information contained in multi-hop neighbor nodes has a more significant impact on user identification; (3) The precision rate, recall rate, comprehensive evaluation index (F1), and area under curve (AUC) of user identification have been improved.

College English Online Teaching Model Based on Deep Learning

In today’s era, online teaching plays an important part in the college English teaching. Deep learning, famous for its ability of imitating the learning process of human brains and obtaining the internal essential features or rules of voice, videos, images, and other data, can be applied to assist and improve the college English online teaching which involves a wide use of those data. Based on the combination of the multilayer neural network model and the k-means clustering algorithm, this paper designs a kind of deep learning method that can be used to assist and improve the college English online teaching. Experiments were designed to test the reliability of this deep learning method. The results show that the optimization algorithm designed in this paper, which can adjust the learning rate, will improve the common probability gradient descent algorithm. Besides, it is proved that the deep learning’s efficiency of the CNN model is significantly higher than that of the MLP model. With the help of this deep learning method, it becomes feasible to apply the technologies related to the artificial intelligence to help teachers deeply analyze and diagnose students’ English learning behavior, replace the teachers in part to answer students’ questions in time, and automatically grade assignments in the process of the college English online teaching. Surveys and exams were then conducted to evaluate the effect of the application of the college English online teaching model based on deep learning on the students’ learning cognition and their academic performance. The results show that the college English online teaching model based on deep learning can stimulate students’ learning motivation and improve their academic performance.

Process Monitoring of Quality-Related Variables in Wastewater Treatment Using Kalman-Elman Neural Network-Based Soft-Sensor Modeling

Proper monitoring of quality-related but hard-to-measure effluent variables in wastewater plants is imperative. Soft sensors, such as dynamic neural network, are widely used to predict and monitor these variables and then to optimize plant operations. However, the traditional training methods of dynamic neural network may lead to poor local optima and low learning rates, resulting in inaccurate estimations of parameters and deviation of predictions. This study introduces a general Kalman-Elman method to monitor the effluent qualities, such as biochemical oxygen demand (BOD), chemical oxygen demand (COD), and total nitrogen (TN). The method couples an Elman neural network with the square-root unscented Kalman filter (SR-UKF) to build a soft-sensor model. In the proposed methodology, adaptive noise estimation and weight constraining are introduced to estimate the unknown noise and constrain the parameter values. The main merits of the proposed approach include the following: First, improving the mapping accuracy of the model and overcoming the underprediction phenomena in data-driven process monitoring; second, implementing the parameter constraint and avoid large weight values; and finally, providing a new way to update the parameters online. The proposed method is verified from a dataset of the University of California database (UCI database). The obtained results show that the proposed soft-sensor model achieved better prediction performance with root mean square error (RMSE) being at least 50% better than the Elman network based on back propagation through the time algorithm (Elman-BPTT), Elman network based on momentum gradient descent algorithm (Elman-GDM), and Elman network based on Levenberg-Marquardt algorithm (Elman-LM). This method can give satisfying prediction of quality-related effluent variables with the largest correlation coefficient (R) for approximately 0.85 in output suspended solids (SS-S) and 0.95 in BOD and COD.

Efficient Iterative Timing Recovery of Low-Density Parity-Check Decoding Metrics Using the Steepest Descent Algorithm for Satellite Communications at Low SNRs

An efficient iterative timing recovery via steepest descent of low-density parity-check (LDPC) decoding metrics is presented. In the proposed algorithm, a more accurate symbol timing synchronization is achieved at a low signal-to-noise (SNR) without any pilot symbol by maximizing the sum of the square of all soft metrics in LDPC decoding. The principle of the above-proposed algorithm is analyzed theoretically with the evolution trend of the probability mean of the soft LDPC decoding metrics by the Gaussian approximation. In addition, an efficiently approximate gradient descent algorithm is adopted to obtain excellent timing recovery with rather low complexity and global convergence. Finally, a complete timing recovery is accomplished where the proposed scheme performs fine timing capture, followed by a traditional Mueller–Müller (M&M) timing recovery, which acquires timing track. Using the proposed iterative timing recovery method, the simulation results indicate that the performance of the LDPC coded binary phase shift keying (BPSK) scheme with rather large timing errors is just within 0.1 dB of the ideal code performance at the cost of some rational computation and storage. Therefore, the proposed iterative timing recovery can be efficiently applied on occasions of the weak signal timing synchronization in satellite communications and so on.

Pseudo-188D: Phage Protein Prediction Based on a Model of Pseudo-188D

Phages have seriously affected the biochemical systems of the world, and not only are phages related to our health, but medical treatments for many cancers and skin infections are related to phages; therefore, this paper sought to identify phage proteins. In this paper, a Pseudo-188D model was established. The digital features of the phage were extracted by PseudoKNC, an appropriate vector was selected by the AdaBoost tool, and features were extracted by 188D. Then, the extracted digital features were combined together, and finally, the viral proteins of the phage were predicted by a stochastic gradient descent algorithm. Our model effect reached 93.4853%. To verify the stability of our model, we randomly selected 80% of the downloaded data to train the model and used the remaining 20% of the data to verify the robustness of our model.

Long-term Strategy Optimization of Scale Squeeze Treatment in a Carbonate Reservoir Under CO2-WAG Water-Alternating-Gas Injection

The objective of this study is to design a series of squeeze treatments for 20 years of production of a Brazilian pre-salt carbonate reservoir analogue, minimizing the cost of scale inhibition strategy. CO2-WAG (Water-Alternating-Gas) injection is implemented in the reservoir to increase oil recovery, but it may also increase the risk of scale deposition. Dissolution of CaCO3 as a consequence of pH decrease during the CO2 injection may result in a higher risk of calcium carbonate precipitation in the production system. The deposits may occur at any location from production bottom-hole to surface facilities. Squeeze treatment is thought to be the most efficient technique to prevent CaCO3 deposition in this reservoir. Therefore, the optimum WAG design for a quarter 5-spot model, with the maximum Net Present Value (NPV) and CO2 storage volume identified from a reservoir optimization process, was considered as the basis for optimizing the squeeze treatment strategy, and the results were compared with those for a base-case waterflooding scenario. Gradient Descent algorithm was used to identify the optimum squeeze lifetime duration for the total lifecycle. The main objective of squeeze strategy optimization is to identify the frequency and lifetime of treatments, resulting in the lowest possible expenditure to achieve water protection over the well's lifecycle. The simulation results for the WAG case showed that the scale window elongates over the last 10 years of production after water breakthrough in the production well. Different squeeze target lifetimes, ranging from 0.5 to 6 million bbl of produced water were considered to optimize the lifetime duration. The optimum squeeze lifetime was identified as being 2 million bbl of protected water, which was implemented for the subsequent squeeze treatments. Based on the water production rate and saturation ratio over time, the optimum chemical deployment plan was calculated. The optimization results showed that seven squeeze treatments were needed to protect the production well in the WAG scenario, while ten treatments were necessary in the waterflooding case, due to the higher water rate in the production window. The novelty of this approach is the ability to optimize a series of squeeze treatment designs for a long-term production period. It adds valuable information at the Front-End Engineering and Design (FEED) stage in a field, where scale control may have a significant impact on the field's economic viability.