Journal of Computer Networks and Communications

Convolutional neural network (CNN) is a very important method in deep learning, which solves many complex pattern recognition problems. Fruitful results have been achieved in image recognition, speech recognition, and natural language processing. Compared with traditional neural network, convolutional weight sharing, sparse connection, and pooling operations in convolutional neural network greatly reduce the number of training parameters, reduce size of feature map, simplify network model, and improve training efficiency. Based on convolution operation, pooling operation, softmax classifier, and network optimization algorithm in improved convolutional neural network of LeNet-5, this paper conducts image recognition experiments on handwritten digits and face datasets, respectively. A method combining local binary pattern and convolutional neural network is proposed for face recognition research. Through experiments, it is found that adding LBP image information to improved convolutional neural network of LeNet-5 can improve accuracy of face recognition to 99.8%, which has important theoretical and practical significance.

As the “new oil of the future,” big data is becoming the leading industry of the new economy, the core asset of the country and enterprises, the “new blue ocean” to be pursued, and the national strategy to be developed by all countries. The development of big data and its related technology supports and promotes a new round of technological innovation, making a new generation of information security technology reform and innovation, bringing opportunities and challenges to optimize, and consolidating national information security. In the era of big data, what kind of challenges and impacts will information security face? and is it crucial to explore the response strategies? At present, China has risen to become the world’s largest number of Internet users and the largest number of people using smartphones, but because China’s information security is the initial stage, involving information security, especially national information security laws and regulations are not much, the national social supervision and monitoring mechanisms are not much, the application level of science and technology content is relatively backward, the core technology has a patent technology not much, resulting in the flood of network data nowadays. Therefore, the underground illegal “data industry chain” activities are rampant. Therefore, this paper proposes a security-aware model based on the combination of distributed data analysis technology and data features. The model uses data features to dynamically generate a library of situational anomalies, effectively solving the problem of analyzing and processing rapidly and dynamically generated data streams, increasing the detection rate to more than 98%, effectively reducing the possibility of false detection, and having good results on large-scale datasets.

Wireless Sensor Networks (WSNS) have become an indispensable tool in this epoch of technological advancements, particularly for progress made in the Internet of things. Wireless sensor nodes are deployed to collect and transmit vital data from the environment to a base station for analysis. Nevertheless, the limited battery power of the sensor nodes is rapidly drained when they stay awake for an extended period. Research has shown that significant sources of energy dissipation of sensor nodes are idle listening, packet collision, control overhead, and overhearing. One optimal solution is employing a low duty cycle mac protocol, particularly the sensor mac (SMAC) protocol. It is essential to have a detailed knowledge of the challenges identified in SMAC and solutions suggested to mitigate these challenges and the future directions. In this paper, we review techniques in SMAC protocols implemented in WSNS. In particular, we provide highlights of recent developments in the schemes used in SMAC for mitigating the challenges in SMAC and present research gaps in SMAC protocol. Finally, we discuss open issues that need to be addressed to advance the design and implementation of SMAC in WSN applications.

Oceans cover more than 75% of the planet’s land surface, making it the most water-rich place on the Earth. We know very little about oceans because of the extraordinary activities that take place in the depths. Underwater wireless sensors are devices that are able to monitor and record the physical and environmental parameters of their surroundings, as well as transmit these data in a continuous manner to one of the source sensors. The network that is formed by the collection of these underwater wireless sensors is referred to as an underwater wireless sensor network (UWSN). The analysis of performance parameters is thought to be most effectively done with this particular technology. In this paper, we will investigate various performance parameters in a random waypoint mobility model by shifting the maximum speed of a node and altering the number of nodes in the model. These parameters include average transmission delay, average jitter, average pathloss, percentage of utilization, and energy consumed in transmit, receive, and idle modes. The QualNet 7.1 simulator is utilized in order to conduct analyses and performance studies.

In modern times, with the development of industrialized society and the invention of clocks and watches, people have become more and more concerned about institutionalization, and higher education time and space have also shown the characteristics of institutionalization. In modern times, educational informatization has brought challenges and opportunities for educational reform and development. The vigorous development of education informatization has also produced changes in higher education spatiotemporally. For example, the rise of catechism and online learning, the importance of fragmented time, the development of space toward virtualization, and the expansion of interactive space for interpersonal interactions. In addition, the enrichment and sharing of educational materials, the informatization, and big data of educational management also contribute to the improvement of time efficiency and optimization of time structure in higher education. With the background of education under the new normal, this paper briefly analyzes the current situation of education informatization construction in colleges and universities from the perspective of education managers, and addresses the current situation and problems of teaching management informatization construction, such as organizational structure dominated by pyramidal functional departments, inefficiency, inability to connect work, difficulty in work gap, difficulty in horizontal coordination, and closed information. A work breakdown structure (WBS) based project management theory and work structure decomposition method are proposed. This paper finds that the improved association rule mining algorithm can improve the efficiency of teaching management practice in colleges and universities by more than 14.58%, which is an important reference value for college management informatization.

In the Internet of things, many data transfer protocols are used for various tasks. In this article, we consider the application layer protocols that are the main ones for transmitting messages in the IoT. The main problems are unpredictability, lack of stability of data transmission delays, and non-determinism, which are also important for real-time systems. The purpose of this study is to determine the most appropriate middleware and data transfer protocol for systems with high data transfer requirements, including real-time systems. Therefore, MQTT, RTPS, JMS, and AMQP protocols were analyzed in order to find out what tasks these protocols should be used for and whether they can be used in robotic and autonomous systems where high data transmission requirements are imposed. To evaluate the protocols, the standards were analyzed to determine the pros and cons, and the software implementations of each of them were selected. To assess the characteristics of data transmission, we have developed our own test scenarios that simulate complex situations. The behavior of software solutions is analyzed and a comparative analysis is made based on the obtained data. Together, the theoretical analysis of protocols and the study of software solutions allow us to conclude on the applicability of a particular protocol in real-time systems. As a result of the study, we can conclude that RTPS is the best solution for real-time systems with different traffic and MQTT performs well when transmitting short messages. But none of the protocols under consideration guarantees the determinism of data transmission, so it is better to use specialized link-layer protocols to obtain guarantees.