A New Treatment of Depression for Drainage Network Extraction Based on DEM

Depressions in landscapes function as buffers for water and sediment. A landscape with depressions has less runoff, less erosion and more sedimentation than that without depressions. Sinks in digital elevation models （DEMs） can be considered the real features that represent depressions in actual landscapes or spurious features that result from errors in DEM creation. In many hydrological and erosion models, all sinks are considered as spurious features and, as a result, these models do not deal with the sinks that represent real depressions. Consequently, the surface runoff and erosion are overestimated due to removing the depressions. Aiming at this problem, this paper presents a new method, which deal with the sinks that represent real depressions. The drainage network is extracted without changing the original DEM. The method includes four steps： detecting pits, detecting depressions, merging depressions, and extracting drainage network. Because the elevations of grid cells are not changed, the method can also avoid producing new fiat areas, which are always produced by the conventional filling methods. The proposed method was applied to the Xihanshui River basin, the upper reach of the Jialingjiang River basin, China, to automatically extract the drainage network based on DEM. The extracted drainage network agrees well with the reality and can be used for further hydrologic analysis and erosion estimation.

Road network extraction in classified SAR images using genetic algorithm

Due to the complicated background of objectives and speckle noise, it is almost impossible to extract roads directly from original synthetic aperture radar(SAR) images. A method is proposed for extraction of road network from high-resolution SAR image. Firstly, fuzzy C means is used to classify the filtered SAR image unsupervisedly, and the road pixels are isolated from the image to simplify the extraction of road network. Secondly, according to the features of roads and the membership of pixels to roads, a road model is constructed, which can reduce the extraction of road network to searching globally optimization continuous curves which pass some seed points. Finally, regarding the curves as individuals and coding a chromosome using integer code of variance relative to coordinates, the genetic operations are used to search global optimization roads. The experimental results show that the algorithm can effectively extract road network from high-resolution SAR images.

Line Patterns Segmentation in Blurred Images Using Contrast Enhancement and Local Entropy Thresholding

Finger vein extraction and recognition hold significance in various applications due to the unique and reliable nature of finger vein patterns. While recently finger vein recognition has gained popularity, there are still challenges associated with extracting and processing finger vein patterns related to image quality, positioning and alignment, skin conditions, security concerns and processing techniques applied. In this paper, a method for robust segmentation of line patterns in strongly blurred images is presented and evaluated in vessel network extraction from infrared images of human fingers. In a four-step process: local normalization of brightness, image enhancement, segmentation and cleaning were involved. A novel image enhancement method was used to re-establish the line patterns from the brightness sum of the independent close-form solutions of the adopted optimization criterion derived in small windows. In the proposed method, the computational resources were reduced significantly compared to the solution derived when the whole image was processed. In the enhanced image, where the concave structures have been sufficiently emphasized, accurate detection of line patterns was obtained by local entropy thresholding. Typical segmentation errors appearing in the binary image were removed using morphological dilation with a line structuring element and morphological filtering with a majority filter to eliminate isolated blobs. The proposed method performs accurate detection of the vessel network in human finger infrared images, as the experimental results show, applied both in real and artificial images and can readily be applied in many image enhancement and segmentation applications.

Determining Critical Support Discharge of a Riverhead and River Network Analysis： Case Studies of Lhasa River and Nyangqu River

A riverhead is the demarcation point of continuous water channel and seasonal channel, which is characterized by a criti- cal flow that can support a continuous water body. In this study, the critical support discharge （CSD） is defined as the critical steady flows required to form the origin of a stream. The CSD is used as the criterion to determine the beginning of the riverhead, which can be controlled by hydro-climate factors （e.g., annual precipitation, annual evaporation, or minimum stream flow in arid season）. The CSD has a close correlation with the critical support/source area （CSA） that largely affects the density of the river network and the division of sub-watersheds. In general, river density may vary with regional meteorological and hydrological conditions that have to be considered in the analysis. In this paper, a new model referring to the relationship of CSA and CSD is proposed, which is based on the physical mechanism for the origin of riverheads. The feasibility of the model was verified using two watersheds （Duilongqu Basin of the Lhasa River and Beishuiqu Basin of the Nyangqu River） in Tibet Autonomous Region to calculate the CSA and extract river networks. A series of CSAs based on different CSDs in derived equation were tested by comparing the extracted river networks with the reference network obtained from a digitized map of river network at large scales. Comparison results of river networks derived from digital elevation model with real ones indicate that the CSD （equal to criterion of flow quantity （Qc）） are 0.0028 m3/s in Duilongqu and 0.0085 m3/s in Beishuiqu. Results show that the Qc can vary with hydro-climate conditions. The Qc is high in humid region and low in arid region, and the optimal Qo of 0.0085 m3/s in Beishuiqu Basin （humid region） is higher than 0.0028 m3/s in Duilongqu Basin （semi-arid region）. The suggested method provides a new application approach that can be used to determine the Qo of a riverhead in complex geographical regions, which can also reflect the effect of hydro-climate change on rivers supply in different regions.

Extracting Campus’Road Network from Walking GPS Trajectories

Road network extraction is vital to both vehicle navigation and road planning.Existing approaches focus on mining urban trunk roads from GPS trajectories of floating cars.However,path extraction,which plays an important role in earthquake relief and village tour,is always ignored.Addressing this issue,we propose a novel approach of extracting campus’road network from walking GPS trajectories.It consists of data preprocessing and road centerline generation.The patrolling GPS trajectories,collected at Hunan University of Science and Technology,were used as the experimental data.The experimental evaluation results show that our approach is able to effectively and accurately extract both campus’trunk roads and paths.The coverage rate is 96.21%while the error rate is 3.26%.

DDoS Attack Detection via Multi-Scale Convolutional Neural Network

Distributed Denial-of-Service(DDoS)has caused great damage to the network in the big data environment.Existing methods are characterized by low computational efficiency,high false alarm rate and high false alarm rate.In this paper,we propose a DDoS attack detection method based on network flow grayscale matrix feature via multi-scale convolutional neural network(CNN).According to the different characteristics of the attack flow and the normal flow in the IP protocol,the seven-tuple is defined to describe the network flow characteristics and converted into a grayscale feature by binary.Based on the network flow grayscale matrix feature(GMF),the convolution kernel of different spatial scales is used to improve the accuracy of feature segmentation,global features and local features of the network flow are extracted.A DDoS attack classifier based on multi-scale convolution neural network is constructed.Experiments show that compared with correlation methods,this method can improve the robustness of the classifier,reduce the false alarm rate and the missing alarm rate.

Simulation of the Surface Hydrology of Dalinghe Watershed Automatically Based on SRTM DEM

[Objective] The aim was to simulate the surface water flow of Dalinghe watershed based on SRTM DEM.[Method] By using ArcGIS ModelBuilder,and SRTM DEM data of Dalinghe watershed as input data,the model to simulate the water flow of Dalinghe watershed was set up.[Result] The model realized automatic division of Dalinghe watershed area and extraction of stream network.In the meantime,it also made the choice of threshold during filling DEM and extracting stream network much easier.The division of the Dalinghe watershed was precise and the extraction result of Dalinghe and its corresponding level Ⅰ tributary river was close to actual stream network.However,the extraction of the smaller stream was less accurate.[Conclusion] The study provided scientific reference for the simulation of surface water network in future.

Multistage analysis method for detection of effective herb prescription from clinical data

Determining effective traditional Chinese medicine （TCM） treatments for specific disease conditions or particular patient groups is a difficult issue that necessitates investigation because of the complicated personalized manifestations in real-world patients and the individualized combination therapies prescribed in clinical settings. In this study, a multistage analysis method that integrates propensity case matching, complex network analysis, and herb set enrichment analysis was proposed to identify effective herb prescriptions for particular diseases （e.g., insomnia）. First, propensity case matching was applied to match clinical cases. Then, core network extraction and herb set enrichment were combined to detect core effective herb prescriptions. Effectiveness-based mutual information was used to detect strong herb symptom relationships. This method was applied on a TCM clinical data set with 955 patients collected from well-designed observational studies. Results revealed that groups of herb prescriptions with higher effectiveness rates （76.9% vs. 42.8% for matched samples; 94.2% vs. 84.9% for all samples） compared with the original prescriptions were found. Particular patient groups with symptom manifestations were also identified to help investigate the indications of the effective herb prescriptions.

Multi-Level Cross-Lingual Attentive Neural Architecture for Low Resource Name Tagging

Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to have lower performance, in comparison to the English language. In this paper, we tackle this challenging issue by incorporating multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance. Specifically, we regard entity type distribution as language independent and use bilingual lexicons to bridge cross-lingual semantic mapping. Then, we jointly apply word-level cross-lingual mutual influence and entity-type level monolingual word distributions to enhance low resource name tagging. Experiments on three languages demonstrate the effectiveness of this neural architecture： for Chinese,Uzbek, and Turkish, we are able to yield significant improvements in name tagging over all previous baselines.