Identifying important features from high-dimensional complex industrial data is crucial for production process anomaly monitoring. Aiming at the problem that the existing feature selection algorithms are difficult to model the complex intrinsic structure of data in the face of noise disturbance， a Multi-view Consistency-driven Robust feature selection method （MCR） was proposed. Firstly， a consistency-guided denoising mechanism with structure preservation was designed， in which multi-view collaborative modeling and inconsistency region detection were used to eliminate local noise disturbance while improving structural fidelity and integrity of the raw data. Then， a joint discriminative and consistency-driven feature fusion module was constructed， where high-quality multi-view embedding representations and a feature weight matrix were learned simultaneously， thereby enhancing the ability to perceive key feature dimensions. Finally， a cooperative sparse regularization-based feature selection strategy was introduced， so as to select the most discriminative and structurally consistent subset of features from the fused embedding space. Without relying on labeled information， this method achieves perception and selection of key feature dimensions through multi-view collaborative modeling and consistency-driven optimization. Extensive experimental results on several public benchmark datasets and a real-world cigarette production dataset demonstrate that MCR outperforms the existing mainstream feature selection methods such as Binary Horse herd Optimization Algorithm （BinHOA） and Improved Binary DJaya Algorithm （IBJA）， achieving classification accuracy improvements of 0.23 to 12.15 percentage points on public datasets and 2.22 to 5.00 percentage points on real industrial dataset， validating its robustness and effectiveness in complex scenarios.

Considering the data sharing difficulties and the risk of privacy disclosure in grid cloud server based on blockchain, a Data Sharing model based on Double Consortium Blockchains in smart grid(DSDCB) was proposed. Firstly, the data of electricity was stored under-chain by Inter Planetary File System(IPFS), the IPFS file fingerprints were stored on-chain, and the electricity data was shared to other consortium blockchain based on the multi-signature notary technology. Secondly, with ensuring privacy from leakage, proxy re-encryption and secure multi-party computing were combined to share single-node or multi-node security data. Finally, fully homomorphic encryption algorithm was used to integrate ciphertext data reasonably without decrypting the electricity data. The 51% attack, sybil attack, replay attack and man-in-the-middle attacks were resisted by the single-node cross-chain data sharing model of DSDCB. It was verified that the security and privacy of data were guaranteed by the secure multi-party cross-chain data sharing model of DSDCB when the number of malicious participants was less than k and the number of honest participants was more than 1. The simulation comparison shows that the computational cost of the DSDCB model is lower than those of Proxy Broadcast Re-Encryption(PBRE) and Data Sharing scheme based on Conditional PBRE(CPBRE-DS), and the model is more feasible than the Fully Homomorphic Non-interactive Verifiable Secret Sharing(FHNVSS) scheme.

Aiming at the problem of poor pedestrian detection effect in complex scenes, a pedestrian detection algorithm based on improved Mask R-CNN framework was proposed with the use of the leading research results in deep learning-based object detection. Firstly, K-means algorithm was used to cluster the object frames of the pedestrian datasets to obtain the appropriate aspect ratio. By adding the set of aspect ratio (2:5), 12 anchors were able to be adapted to the size of the pedestrian in the image. Secondly, combined with the technology of fine-grained image recognition, the high accuracy of pedestrian positioning was realized. Thirdly, the foreground object was segmented by the Full Convolutional Network (FCN), and pixel prediction was performed to obtain the local mask (upper body, lower body) of the pedestrian, so as to achieve the fine-grained detection of pedestrians. Finally, the overall mask of the pedestrian was obtained by learning the local features of the pedestrian. In order to verify the effectiveness of the improved algorithm, the proposed algorithm was compared with the current representative object detection methods (such as Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv2 and R-FCN (Region-based Fully Convolutional Network)) on the same dataset. The experimental results show that the improved algorithm increases the speed and accuracy of pedestrian detection and reduces the false positive rate.

Urban function areas can be differentiated either by their external physical characteristics or by inherent social functions. And, they have been keeping in dynamic process over time. Remote sensing, as a typical traditional method in urban function area classification, has its critical defects such as high time cost and helpless in their social functions. In order to solve the problem, a new urban functional area identification method based on Call Detail Record (CDR) data was proposed. The application of this new data source in urban land use classification was verified as follow steps. First, communication station cells were labeled with five categories (residence area, office area, commercial area, college area, scenic-spot area). Second, call duration distribution features and move-frequency features, extracted from these five urban function areas were compared and analyzed. Finally, a weighted decision algorithm based on the Gaussian Mixture Model (GMM) was designed, and the simulation on the training set was conducted. The experimental results prove that the CDR data is capable of delivering useful information between different urban function areas. There are corresponding relationships between the nature of urban functional areas and the behavior characteristics of mobile phone users. When decision weight is 0.6, the weighted decision algorithm achieves 51.08% recall rate in current datasets. Combined with the error analysis, this work indicates the feasibility of CDR data in solving the problem of urban functional area identification.

Since recent studies on users' mobility based on Call Detail Record (CDR) mainly use metrics in one-dimensional space, such as the travel distance and the radius of gyration which can not exactly describe the scope of users' mobility, the Area of the Convex Hull Covering a user's daily Trajectory (ACHCT) was applied to investigate users' mobility scale in two-dimensional space, and the mobility vector was introduced to study the mobility of the crowd. Firstly, a method was designed to set up two-dimensional Cartesian coordinates based on latitude and longitude coordinates. The method applied the Mercator projection and the haversine formula to calculate the bearing and distance between scattering points, based on which the coordinates of points in the plane coordinates were determined. Then, based on the coordinates, the convex hulls covering users' daily trajectories were calculated and the distribution of the areas of all convex hulls was analyzed. Finally, the mobility vectors of agglomerated de-identified callers were accumulated respectively in different time segments and the changes in a day were analyzed. The experimental results show that, within the scale of 180 km, the average deviations of bearing angle and distance calculated with the new coordinates are 0.037° and 0.102%, compared with those calculated with Mercator projection and haversine formula. The new coordinates can maintain the distance and bearing between points well. ACHCT follows a power-law distribution and has a strong correlation with the travel distance. The changes of the crowd's mobility vector, show the tidal phenomenon of the crowd's travel and give a new sight to discover the correlation between areas where users reside and those nearby.

Large iterations and errors may be caused by using the Cyclic Redundancy Check (CRC) criterion in decoding when channel condition gets worse. Thus, an iterative stopping algorithm based on reliability and a retransmission algorithm were proposed. First, the reliability of the intermediate result was calculated after each iteration, and it was used to achieve early stop of iteration by reaching a threshold. Second, the intermediate result corresponding to the maximum reliability was saved and used as the final result of decoding. Finally, after each decoding, the maximum reliability was used to determine whether to retransmit by being under a threshold of retransmission or not, and the best result of decoding was calculated by using results of no more than three transmissions. Simulations show that, when signal to noise ratio is less than 1.2 dB, in comparison with the CRC criterion, bit errors can be reduced by one or two on the basis of not increasing iterations by using this stopping algorithm, and bit errors can be further reduced by at least two by using the retransmission algorithm. The algorithm based on reliability can achieve less number of bit errors and iterations.

Concerning the problem of excessive interaction flow, single point failure and low detection efficiency in existing Distributed Intrusion Detection System (DIDS), a new distributed intrusion detection model based on artificial immune theory was proposed. The new distributed intrusion detection model presented a central detector configuration and method of use and combined misuse detection and anomaly detection. The simulation model was designed based on OMNeT+〖KG-*3〗+ network simulation platform and experiments were run. According to the simulation results, the model overcomes excessive interaction flow problem of the fully distributed system, solves the problem of single point failure and improves the detection efficiency effectively. The simulation results verify the validity and effectiveness of the improved model.

This paper proposed a new best viewpoints selection approach that was capable of selecting best viewpoints for 3D models based on a feature points detection process. First, a new saliency measure was defined to compute the saliency of 3D meshes vertices, which assumed that the saliency of a given vertex on a 3D model could be described by its average difference of distances within a local space. Then, the effective feature points were promisingly able to be extracted based on vertices saliency. Finally, a simple selection strategy was adopted to determine the best viewpoints for 3D mesh models. The quality of viewpoints was a combination of the geometirc distribution and the saliency of visible feature points. The experimental results validate the effectiveness of the proposed approach, which can measure viewpoint quality objectively and obtain the best viewpoints of good visual effect.

To solve the problem of poor self-adaptive ability in the robot obstacle avoidance, combined with evolution thought of Genetic Algorithm (GA), an Evolutionary Operant Behavior Learning Model (EOBLM) was proposed for the mobile robot learning obstacle avoidance in unknown environment, which was based on Operant Conditioning (OC) and Adaptive Heuristic Critic (AHC) learning. The proposed model was a modified version of the AHC learning architecture. Adaptive Critic Element (ACE) network was composed of a multi-layer feedforward network and the learning was enhanced by TD(λ) algorithm and gradient descent algorithm. A tropism mechanism was designed in this stage as intrinsic motivation and it could direct the orientation of the Agent learning. Adaptive Selection Element (ASE) network was used to optimize operant behavior to achieve the best mapping from state to actor. The optimizing process has two stages. At the first stage, the information entropy got by OC learning algorithm was used as individual fitness to search the optimal individual with executing the GA learning. At the second stage, the OC learning selected the optimal operation behavior within the optimal individual and got new information entropy. The results of experiments on obstacle avoidance show that the method endows the mobile robot with the capabilities of learning obstacle avoidance actively for path planning through interaction with the environment constantly. The results were compared with the traditional AHC learning algorithm, and the proposed model had better performance on self-learning and self-adaptive abilities.

In order to obtain the SAR images which include the typical target of interest, a new method of SAR images screening based on bit-plane characteristics was proposed according to the imaging characteristic of target. Based on the suitable gray pretreatment to the images, the target’s prior knowledge was analyzed, the significant bit-plane image was paid attention by the measurement of bit-plane complexity, run length and frequency spectrum. And then SAR images were screened combined with the gray histogram features. Around the airport SAR images, experiment shows that the method can screen the images rapidly. Besides, the airport target is extracted successfully, which can satisfy the requirements.

To decrease the storage space and improve the search velocity of CRL(Certificate Revocation List),a bit pointer was used to shorten the certificate number of it.And a new certificate recocation tree was proposed,which could keep the good properties of CRT(Certificate Revocation Tree) that is easy to check or prove whether a certificate is revoked or not,the check only need the related path values but not the whole CRT values.The new tree also could overcome the disadvantage of CRT that any update will cause the whole CRT to be computed,so it accelerate the speed of the CRT update.