Search

Accurate regulation of modern greenhouse requires fast and accurate acquisition of various key physiological indexes of greenhouse crops. Greenhouse environmental data and crop physiological data were used as input and output, and the Deep&Wide Neural Network (WDNN) model was established to predict the tomato net photosynthetic rate in greenhouse. Through the adoption of ADAM algorithm, the accuracy of WDNN has been improved. At the same time, compared with the traditional Deep Neural Network(DNN), WDNN has a better prediction effect. Mean Absolute Error (MAE), Mean Squard Error (MSE), Root Mean Squard Error (RMSE) of WDNN predicted value and real value were 0.7498, 1.7617, 1.3272, respectively, and determination coefficient of the model was 0.9764.

Mobile ad-hoc networks (MANET) has highly dynamic topology, open access of wireless channel and unpredictable behaviors; however, absence of effective security mechanism render MANET more vulnerable to positive attacks. Conventional assessments always require large sample data satisfy specific distribution and establish models through subjective recognition, thus lack common applicability, objectivity and reliability. To solve this problem and make accurate assessment, we propose RAPCA-PP model on basis of Projection Pursuit theory to realize both risk assessment and attributes analysis. Due to Projection Pursuit's theoretical merits, RAPCA-PP is thoroughly data-driven; it can be applied to conditions with small sample quantity, incomplete data and no-prior experience. Using RAGA for solution, RAPCA-PP shows well convergence. Compared with Grey Relations Projection, it demonstrates both better accuracy and higher discrimination. Moreover, our model can analysis attributes by importance and eliminate redundancy. Experiment shows that assessment with eliminated attributes can also correctly reflect each node's performance. RAPCA-PP proved to be suitable for real MANET working scenarios.

Conventional risk assessments in Ad-Hoc Networks always require sample satisfy specific distribution with large quantity and establish models through subjective judgment, these methods lack general applicability, objectivity and credibility. Moreover, some models only focus on single time point evaluation and failed to thoroughly reveal dynamic behavioral character. To solve these problems and make correct assessment, we propose RAPCA-PP model on the basis of Projection Pursuit theory to conduct both risk assessment and attribute analysis over dynamic time sequence. RAPCA-PP is completely data-driven and can be applied in small sample, incomplete data and no-prior experience. Compared with Grey Relations Projection, it boasts both better accuracy and higher discrimination. Since RAPCA-PP makes evaluation along time axis, it can reflect MANET’s node series behavioral features. Experiments demonstrate that assessment with eliminated attributes can also correctly reflect each node's performance and be utilized for IDS realization. RAPCA-PP proved to be suitable for real MANET working scenarios.

IPSec VPN is commonly used to implement secure communications between different branch intranets over public networks. Multi-link aggregate IPSec VPN can make better use of multiple physical links of corporation. On the basis of analysis on the insufficiency of packet-based scheduling, a session-based tunnel scheduling model for multi-link aggregate IPSec VPN is proposed. The new model can distribute IPSec traffics over multiple tunnels negotiated on different physical links in unit of session. A prototype system of the new model which adopts Netfilter mechanism is implemented on Linux platform. Analysis on the test result for the prototype system shows that the new model can work effectively, the cost of scheduling is controllable and the performance of model is acceptable.

Society has become so dependent on information systems that provide the information underpinnings for critical infrastructure applications. With the development of network technology, these systems continue to emerge and grow, and have become unbounded networked systems that are highly distributed. But traditional security technology is not sufficient to deal with the protection and survivability of highly distributed information systems operating in unbounded networks ?Survivability research is the key to resolve the problem. This paper organizes and summarizes the current literatures and presents an overview of survivability research by discussing the definition, the various techniques and the estimate models of survivability, and finally, presents a conclusion and future work.

The spread of spam made a lot of interference to Internet users, and wasted network bandwidth. Anti-spam technology has been developed to the third-generation technology, behavior recognition technology. Many studies have focused on the detection of abnormal behavior in the period of SMTP conversation. In this paper, user’s typical sending behavior mathematical model is concerned. To find the abnormal behavior different from the typical behavior, similarity is computed between behaviors of separate users, or between the same user’s behavior in long-time and short-time. Combing the common features of email messages, especially most of spam presence of hyperlink, the URL model is also built. Lastly, by Naiive Bayes model, several behavior recognizing models can cooperate to detect spam.

IPSec VPN is widely used to secure communications between different branch intranets over Internet, and its performance is becoming more and more important now. Traditional IPSec accelerating approaches are mostly based on hardware and have low cost performance. In this paper, we propose a software approach based on IPSec Thumbnail Protocol (ITP) to accelerate IPSec communication. By caching data segments of the original IP packet and constructing ITP Thumbnail packet to transfer, IPSec communication can be accelerated. We implement an ITP prototype system on Linux platform and evaluate it in our test environment. The experimental results show that the ITP protocol is effective and the overall IPSec communication performance is improved obviously.

In order to build a more compact, simple, mobile and reliable vision measurement system in plant physiological parameter measurement, we choose the smart camera and infrared light source as the principle components. The hardware architecture of smart camera and the software development process is described. An example of leaf area measurement algorithm is shown which include camera calibration section to establish the spatial relationship between leaf and camera. Special initialized a snake active contour is able to separate the leaf boundary from its petiole. With the extrinsic parameters and contour of leaf we can calculate the real area of leaf. Similarly, other useful plant physiological parameters such as the diameter of fruit, height of plant could be achieved with this system.

Internet has become the universal information communications infrastructure. VPN is commonly used to implement communications over different branch intranets. IPSec is a suit of protocols that adds security to communications at the IP layer, and it is a popular technology to implement VPN. On the basis of analysis on the insufficiency of traditional IPSec systems, a multi-link aggregate IPSec model is proposed. The new model can negotiate multiple groups of security policies on different physical links for same branch intranet pair, and distribute IPSec traffics over multiple links. A prototype system of the new model which is based on Netfilter mechanism is implemented on Linux platform. Analysis on the test result from the prototype system shows that the new model can work better under the environment of multi-link, and can enhance the capability and reliability of VPN application.