Control chartis one of the important statistical process control tools. Abnormal situations and the potential quality problems in the production process can be judged and revealed according tothe state of control char...
详细信息
Control chartis one of the important statistical process control tools. Abnormal situations and the potential quality problems in the production process can be judged and revealed according tothe state of control chart. Thus the recognition of control chartis of greatimportance. Toimprove patterns recognition performance of control chart, a new method based on improved sequential forward selection(ISFS) and extreme learning machine(ELM) was presented. Firstly the 13 time domain features were extracted from control chart;secondly, the improved sequential forward selection method was used toselect the features toreduce the relevance and redundancy between features and improve recognition rate;finally, ELM was adopted toidentify control chart. Experimental results show that the proposed method can achieve a significant classification performance with accuracy of 98.7%,providing a new method for the control chart recognition.
With the prevalence of web-based learning, the application of concept mapping, as a powerful diagnostic and instructional tool, has been widely exploited in both education and computer science. In recent years, severa...
详细信息
With the prevalence of web-based learning, the application of concept mapping, as a powerful diagnostic and instructional tool, has been widely exploited in both education and computer science. In recent years, several methods have been presented toautomatically construct concept map that achieved encouraging results, while ignoring some critical issues when applied in actual E-learning system. In this paper,we propose a practical approach for constructing concept map,which is adapted tothe dynamic character of a real ***, we apply fuzzy set theory and fuzzy reasoning basis on fuzzy rules for similarity degree between twoconcepts, tofind direct prerequisite relationship among concepts. It provides a useful way toimprove accuracy and reduce complexity of the concept map.
In the case of metrics-based software defect prediction, an intelligent selection of metrics is one of the key factors that affect the model performance. Tosolve the problem that only the correlation between software ...
详细信息
In the case of metrics-based software defect prediction, an intelligent selection of metrics is one of the key factors that affect the model performance. Tosolve the problem that only the correlation between software metrics is considered and the issue of redundance is tend tobe ignored in the current studies, a new algorithm which combines Relief F feature selection algorithm and correlation analysis is proposed. An experiment via 3 different classifiers over classic data sets from PROMISE repository is carried out, which is compared tothe other twowell-known feature selection algorithms. The ANOVA（Analysis of Variance） analysis shows that, a new method called Relief F-LC（a fusion algorithm based on Relief F and linear correlation analysis） feature selection algorithm can improve defect prediction performance.
As Wireless Sensor Networks have been employed to support critical monitoring applications, network availability has become a major design concern. In these networks, redundancy can be exploited to enhance the attaina...
详细信息
As Wireless Sensor Networks have been employed to support critical monitoring applications, network availability has become a major design concern. In these networks, redundancy can be exploited to enhance the attainable availability level, where redundant sensors can replace faulty nodes. When camera-enabled sensors are deployed to retrieve visual information, the perception of redundancy changes considerably, since the redundancy of visual sensors depends on the monitoring requirements of the applications. In such context, characteristics as deployment density, viewing angle and sensing range are relevant when planning wireless sensor network applications, directly impacting in the number of redundant nodes. We propose an algorithm to select redundant nodes in Wireless Visual Sensor Networks, according to the application requirements. Moreover, we discuss how parameters of the deployed network can influence on the number of redundant nodes.
In recent years, LBS(Location-Based Service) have been widely used. In order toattract more users, some location service providers may unite merchants togive rewards tousers whocheck in a place and evaluate for mercha...
详细信息
In recent years, LBS(Location-Based Service) have been widely used. In order toattract more users, some location service providers may unite merchants togive rewards tousers whocheck in a place and evaluate for merchant services, and this has led tolocation cheating attack, where some dishonest users provide false location information todefraud the location service provider. In this paper, we proposed a location authentication scheme based on adjacent nodes. When verifying the authenticity of location provided by a user, some adjacent nodes with higher credits are selected as witnesses. The location information provided by the witnesses is compared with that presented by the user toverify whether user's location is authentic or not. Through the security analysis, we prove that this scheme can effectively prevent location cheatin LBS.
Visual-attention-model(VAM) is a kind of model with good robustness of bionic vision. For ground object sensed on UAV(Unmanned Aerial Vehicle) platform, in this paper object detection and tracking algorithm based on V...
详细信息
Visual-attention-model(VAM) is a kind of model with good robustness of bionic vision. For ground object sensed on UAV(Unmanned Aerial Vehicle) platform, in this paper object detection and tracking algorithm based on VAM and extended Kalman filter(EKF) is proposed, and applied tothe ground surroundings for object detection and tracking. In order toquickly extract the ground objects in aerial images, visual saliency map was calculated. Based on the robust detection of ground objects and EKF optima estimation, the proposed algorithm based on VAM and EKF could robustly detect and track object for UAV. Experimental results show that the algorithm in this paper is capable tobe adapting tocomplex ground surroundings for object detection and tracking, the designed visual saliency map is not only de-noise images effectively but alsocan help reserve original information as possible. In addition, calculation of the proposed algorithm is pretty simple, and sosuitable for engineering application.
In this Paper, an enhanced agglomerative fuzzy KMeans clustering algorithm with the MapR educe implementation is proposed. In this algorithm, an initial center selection method is introduced toimprove the accuracy and...
详细信息
In this Paper, an enhanced agglomerative fuzzy KMeans clustering algorithm with the MapR educe implementation is proposed. In this algorithm, an initial center selection method is introduced toimprove the accuracy and increase the convergence speed of the agglomerative fuzzy k-means algorithm. Then, a MapR educe implementation based on Apache Hadoop is presented toincrease the scalability for large scale datasets. Experiments were respectively conducted on a synthetic data set, the WINE dataset from UCI Repository and a randomly generated large dataset. The experimental results show that the proposed algorithm can identify true cluster number and produce accurate result with good scalability on large dataset.
According tothe modern control and optimal estimation theory, a mathematical model of the pilot attention resource allocation is developed. This model analyzes the inherent characteristics of pilotinput and output lin...
详细信息
According tothe modern control and optimal estimation theory, a mathematical model of the pilot attention resource allocation is developed. This model analyzes the inherent characteristics of pilotinput and output links in the pilot-vehicle closed-loop system, and the optimal control model of pilotis established by simplification and mathematical modeling. The control task chosen in this paper concerns the longitudinal motion of a hovering aircraft. Tosolve the pilot optimal attention allocation problem in the instrument-monitoring task of the pilot-vehicle closedloop system an objective function is set up based on flight control system state equation. In the process of solving optimization problem, the constrained optimization problem is converted intoan unconstrained problem, and is solved effectively with the method of steepest descent algorithm in the MATLAB.
With the increasingly widespread application of computer network, it has become a critical task todetect anomalous behaviors in the field of network security. In this paper we develop an entropy-based statistical appr...
详细信息
With the increasingly widespread application of computer network, it has become a critical task todetect anomalous behaviors in the field of network security. In this paper we develop an entropy-based statistical approach that determines and reports entropy contents for variables in the Management Information Base. The change of the entropy value indicates that a massive network event or an anomaly may occur. We give the analysis on a real data set provided by a large-size network company. Both our theoretical analysis and experimental results demonstrate that the method is effective and efficient for network anomaly detection.
In this paper we proposed a high accuracy automatic timing method for photofinish systems, as manual detection is subjective and time-consuming. Athlete objects are detected and extracted automatically, effective inte...
详细信息
In this paper we proposed a high accuracy automatic timing method for photofinish systems, as manual detection is subjective and time-consuming. Athlete objects are detected and extracted automatically, effective interferences elimination algorithm is proposed for torsolocating and finish line detection. The effectiveness of this method is verified by 2511 samples from 390 track events' original image data, and it achieved the accuracy of 82.07% within a tolerance of 2 ms time error. The experiment results show the objectivity and accuracy.
暂无评论