The temporal relation or temporal links (denoted by the TLink tag) in Chinese electronic medical records includes temporal relations within a sentence (hereafter referred to as "within-sentence TLinks"), and between-sentence TLinks. Among them, within-sentence TLinks include event/event TLinks and event/time TLinks, and between-sentence TLinks include event/event TLinks. The recognition of temporal relation in Chinese electronic medical record was transformed into classification problem on entity pairs. Heuristic rules with high accuracy were developed and two different classifiers with basic features, phrase syntax, dependency features, and other features were trained to determine within-sentence TLinks. Apart from heuristic rules with high accuracy, basic features, phrase syntax, and other features were used to train the classifiers to determine between-sentence TLinks. The experimental results show that Support Vector Machine (SVM), SVM and Random Forest (RF) algorithms achieve the best performance of recognition on within-sentence event/event TLinks, within-sentence event/time TLinks and between-sentence event/event TLinks, with F ₁-scores of 84.0%, 85.6% and 63.5% respectively.

Current researches on the assessment of image aesthetic quality are based on visual content of images to give assessment results, ignoring the fact that aesthetics is a person's cognitive activity and not considering the user's understanding towards image semantic information during the evaluating process. In order to solve this problem, an approach to image aesthetic quality assessment based on semantic perception was proposed to apply both the object category information and scene category information of images to the aesthetic quality assessment. Using the transfer learning concept, a hybrid network integrating multiple features of the images was constructed. For each input image, the object category features, scene category features, and aesthetic features were extracted respectively by network, and the three features were combined to achieve better image aesthetic quality evaluation. The classification accuracy of the method on the AVA data set reached 89.5%, which was 19.9% higher than that of the traditional method, and the generalization performance on the CUKHPQ data set was greatly improved. The experimental results show that the proposed approach can achieve better classification performance on the aesthetic quality evaluation of images.

Since the hyponymy between symptoms has strong structural features, an automatic hyponymy extracting method based on symptom components was proposed. Firstly, it was found that symptoms can be divided into eight parts: atomic symptoms, adjunct words, and so on, and the composition of these parts satisfied certain constructed rules. Then, the lexical analysis system and Conditional Random Field (CRF) model were used to segment symptoms and label the parts of speech. Finally, the hyponymy extraction was considered as a classification problem. Symptom constitution features, dictionary features and general features were selected as the features of different classification algorithms to train the models. The relationship between symptoms were divided into hyponymy and non-hyponymy. The experimental results show that when these features are selected simultaneously, precision, recall and F1-measure of Support Vector Machine (SVM) are up to 82.68%, 82.13% and 82.40%, respectively. On this basis, by using the above hyponymy extracting algorithm, 20619 hyponymies were extracted, and the knowledge base of symptom hyponymy was built.

It is difficult to understand all the relations between firewall rules. Poorly-organized rules may cause the problem that firewall could not filter packets correctly. In order to solve this problem, an analysis method of inclusion relations between firewall rules based on set theory was proposed. Based on the inclusion relations in set theory, the proposed method analyzed and classified the relations between firewall rules without considering the actions of rules. The proposed method simplified the process of analysis relations between firewall rules, and it was implemented by using a functional programming language, Haskell. The whole Haskell codes were concise, which also were easy to maintain and expand. The experimental results show that, with regard to medium scale sets of rules, the proposed method can analyze the inclusion relations between firewall rules rapidly and effectively. The proposed method also provides an important basis for the succeeding rules conflict detection.

The base-band equivalent model between the transmitted signal and its corresponding received signals was established in this paper by analyzing the transceiver of radio proximity detector. Thus, with considering the multiple path loss of received signal, it could be used as one general echo simulation model for proximity detectors, and their different frequency signals could be simulated by this based-band approach. The echo signal obtained by this method could indicate the meeting process of targets and detectors, and its various version waveform for various detecting systems with various Doppler frequency varieties could also be simulated. Furthermore, it has the strong-points of low computation complexity and simple implementation. Finally, the proposed base-band echo simulation method was tested in one radio proximity detector working scenario. The numerical results show that the simulated time signal could reflect the meeting process of bomb targets with relative movements.

Taking into account the relatively poor versatility and effectiveness of the general robot visual navigation filtering algorithm, and taking advantage of the existing the median filter and multi-scale adaptive fusion filter, a combinatorial optimization filter based on the median and multi-scale was proposed. Firstly, the algorithm uses the median filter, and then uses the multi-scale filter. Finally the filtered results are fused according to smallest mean absolute error criterion(MAE). Experimental results show that the proposed algorithm can better filter out a variety of common noise for the robot road images, which enhances the versatility and effectiveness of the algorithm.

According to the characteristics of primary users’ service, this paper applied mixed Poisson distribution to primary users’ service modeling, evaluating the probability density of non-occupied duration of channel by using Expectation-Maximization (EM) algorithm to estimate the parameters of mixed Poisson distribution model and putting forward a multi-channel allocation algorithm based on channel estimation. The simulation results indicate that the proposed algorithm has excellent performance on conflict rate and throughput. Meanwhile, the proposed algorithm has lower implementation complexity for practical use.

This paper proposed a new non-parametric algorithm for clustering gene expression data. This algorithm combined the fuzzy clustering of multi-dimensional data with CTWC. Furthermore, it introduced the norm-based method to improve and prove reasonable. The colon tumor gene expression dataset was analyzed and the interesting combination of 8 genes is discovered, which could identify the colon tumor samples whih 90% accuracy as well as the subtypes of the colon tumor. Experiments were proved the feasibility of the method.