The clustering-based case-based reasoning for imbalanced business failure prediction: a hybrid approach through integrating unsupervised process with supervised process

Case-based reasoning (CBR) is one of the main forecasting methods in business forecasting, which performs well in prediction and holds the ability of giving explanations for the results. In business failure prediction (BFP), the number of failed enterprises is relatively small, compared with the number of non-failed ones. However, the loss is huge when an enterprise fails. Therefore, it is necessary to develop methods (trained on imbalanced samples) which forecast well for this small proportion of failed enterprises and performs accurately on total accuracy meanwhile. Commonly used methods constructed on the assumption of balanced samples do not perform well in predicting minority samples on imbalanced samples consisting of the minority/failed enterprises and the majority/non-failed ones. This article develops a new method called clustering-based CBR (CBCBR), which integrates clustering analysis, an unsupervised process, with CBR, a supervised process, to enhance the efficiency of retrieving information from both minority and majority in CBR. In CBCBR, various case classes are firstly generated through hierarchical clustering inside stored experienced cases, and class centres are calculated out by integrating cases information in the same clustered class. When predicting the label of a target case, its nearest clustered case class is firstly retrieved by ranking similarities between the target case and each clustered case class centre. Then, nearest neighbours of the target case in the determined clustered case class are retrieved. Finally, labels of the nearest experienced cases are used in prediction. In the empirical experiment with two imbalanced samples from China, the performance of CBCBR was compared with the classical CBR, a support vector machine, a logistic regression and a multi-variant discriminate analysis. The results show that compared with the other four methods, CBCBR performed significantly better in terms of sensitivity for identifying the minority samples and generated high total accuracy meanwhile. The proposed approach makes CBR useful in imbalanced forecasting.     

Constructing and applying higher order textons: Estimating breast cancer risk

Texture analysis based on textons is extended by introducing a method for computing textons of arbitrary order. First-, second- and third-order textons are applied to classify screening mammograms as to indicate a low or high risk of breast cancer. First-order textons are found to provide better estimates of breast cancer risk than other orders on their own but the combination of first- and second-order textons outperforms first-order textons alone and other combinations of two orders. Combining all three orders of textons does not improve classification. This example indicates that including higher-order textons has the potential to improve classification performance.     

Coupling-and-decoupling: A hierarchical model for occlusion-free object detection

Handling occlusion is a very challenging problem in object detection. This paper presents a method of learning a hierarchical model for X-to-X occlusion-free object detection (e.g., car-to-car and person-to-person occlusions in our experiments). The proposed method is motivated by an intuitive coupling-and-decoupling strategy. In the learning stage, the pair of occluding X?s (e.g., car pairs or person pairs) is represented directly and jointly by a hierarchical And–Or directed acyclic graph (AOG) which accounts for the statistically significant co-occurrence (i.e., coupling). The structure and the parameters of the AOG are learned using the latent structural SVM (LSSVM) framework. In detection, a dynamic programming (DP) algorithm is utilized to find the best parse trees for all sliding windows with detection scores being greater than the learned threshold. Then, the two single X?s are decoupled from the declared detections of X-to-X occluding pairs together with some non-maximum suppression (NMS) post-processing. In experiments, our method is tested on both a roadside-car dataset collected by ourselves (which will be released with this paper) and two public person datasets, the MPII-2Person dataset and the TUD-Crossing dataset. Our method is compared with state-of-the-art deformable part-based methods, and obtains comparable or better detection performance.     

Robust passive autofocus system for mobile phone camera applications

A robust autofocus system is a ubiquitous function in today’s mobile phone camera applications. However, due to the power consumption and size requirements, it is difficult for the autofocus function to be implemented into the design of mobile phone cameras. This paper presents a passive autofocus system with low computational complexity. This system uses a novel contrast measurement to determine degree of image sharpness, which can better reflect the information about image discontinuities. In order to gauge the performance of this measurement, a modified peak search strategy is used in the experiments. The experimental results from several typical image sequences validate the effectiveness of the proposed method.     

Simulation of the smart grid communications: Challenges,techniques, and future trends

This paper gives an overview of available simulation techniques to support the analysis of smart grid communications. Intelligent power grids, known as smart grids, are required as the demand for energy continues to grow and more emphasis is being placed on the supply of renewable energy. The main ingredient of smart grid is the integration of information and communication technology into the grids to monitor and regulate power generation and the demand. The impact of the communication networks on the performance of power system dynamics can only be understood through numerical simulations. This paper provides an overview of available simulation techniques for smart grid communications with a particular focus on the co-simulation frameworks and their enabling technologies. Moreover, a case study with VPNET for analyzing agent based shipboard smart grid protections considering communication impacts is provided.     

Making sky lanterns from polygonal meshes

Releasing sky lanterns is a popular way of celebrating festivals and ceremonies in the Asian countries. This paper presents a computer-aided approach to help novice users to design flyable sky lantern with desired shape. Given a closed up-right 3D model with a user-specified cutting on the bottom, our system optimizes the shape by regularizing the boundary, smoothing the geometry and improving the volume-to-area ratio to make it feasible for flying. The optimized shape is then approximated by a set of developable patches. Next, through a physical analysis step that tests the flying condition and determines the optimal size, the approximated shape is flattened into 2D patches, which can be printed out and glued together to form the airbag. Finally, the user can attach the airbag to a bamboo frame and assemble the fuel cell. We successfully apply our prototype system to design and construct real sky lanterns.     

Typhoon eye extraction with an automatic SAR image segmentation method

Spaceborne microwave synthetic aperture radar (SAR), with its high spatial resolution (10–100 m), large area coverage, and day/night imaging capability, has been used as an important tool for typhoon monitoring. Since the microwave signal can penetrate through clouds, SAR images reveal typhoon morphology at the sea surface. Within the region of a typhoon eye, wind speed and the associated sea surface roughness are usually low. Therefore, the typhoon eye can be well distinguished as dark areas in SAR images. However, automatic typhoon eye extraction from SAR images is hampered by SAR image speckle noise and other false-alarm dark features contained in an image. In this study, we propose an image processing approach to extract typhoon eyes from SAR images. The three-step image processing includes: (1) applying an extended non-local means image denoizing algorithm to reduce image speckle noise; (2) applying a top-hat transform to denoized imagery to enhance the contrast; and (3) using a labelled watershed to segment the typhoon eye. Experimental results from analysing three Environmental Satellite SAR typhoon images show that our approach provides fast and efficient SAR image segmentation for typhoon eye extraction. Typhoon eyes are segmented correctly, and their edges are well detected. Our experimental results are comparable to manually extracted typhoon eye information. Fine-tuning of this approach will provide an automatic tool for typhoon eye information extraction from SAR images.     

A New Indole Synthesis Promoted by Metal Triflates

A new synthesis of 4- and 7-carbon-substituted indoles is described. The overall sequence involves the addition of a nitrile oxide to 1 carboethoxy-2-(or 3-) allylpyrrole, hydrogenation of the intermediate isoxazoline to β-hydroxy ketone and cyclization of the ketol using magnesium or zinc triflate to the substituted indole. This new indole-forming strategy can also accommodate the introduction of oxygen functionality into the indole 6-position. Possible mechanistic aspects of the reaction are detailed.     

Prelaunch calibration and primary results from in-orbit calibration of the atmospheric correction microwave radiometer (ACMR) on the HY-2A satellite of China

The atmospheric correction microwave radiometer (ACMR) is one of the main payloads for correcting atmospheric path delay in the radar altimeter on the Haiyang-2A (HY-2A) satellite. The ACMR is a three-band microwave radiometer operating at 18.7, 23.8, and 37.0 GHz. Calibration of the ACMR is important for applying its measurements to correct for atmospheric effects on the HY-2A altimeter signal transmission in the air. Therefore, a detailed introduction to the principles and specifications of the ACMR system is given first. The thermal vacuum calibration method of the ACMR is discussed and analysed, and the microwave transfer functions and related coefficients are given, especially the nonlinear coefficients derived from a test for correcting nonlinear responses between the input of antenna temperature and the output of voltage at each channel of the ACMR. Furthermore, antenna pattern correction algorithms for removing the effects of side lobe and cross-polarization are derived and their coefficients are used for in-orbit data processing. Primary calibration results are given by comparing with the similar spaceborne Jason microwave radiometer (JMR) on the Jason-1 satellite and with the advanced microwave radiometer (AMR) on Jason-2. The results of this comparison show that the data from the ACMR match well to those from the JMR and AMR.     

Recent climate variability and its impact on precipitation,temperature, and vegetation dynamics in the Lancang River headwater area of China

The alpine ecosystem is one of the most fragile ecosystems threatened by global climate change. The impact of climate variability on the vegetation dynamics of alpine ecosystems has become important in global change studies. In this study, spatially explicit gridded data, including the Moderate Resolution Imaging Spectroradiometer (MODIS) land-surface temperature (LST) product (MOD11A1/A2), the Tropical Rainfall Measuring Mission (TRMM) rainfall product (3B43), and MODIS net primary productivity (NPP) product (MOD17A3), together with meteorological observation data, were used to explore the spatio-temporal pattern of climate variability and its impact on vegetation dynamics from 2000 to 2012 in the Lancang River headwater area. We found that the variation patterns of LST, precipitation, and NPP in the study area showed remarkable spatial differences. From the northwest to the southeast the spatial variation of average annual LST exhibited a decreasing–increasing–decreasing–increasing pattern. At the same time, most of the study area exhibited an increasing LST during the growing season. The annual precipitation increased in the semi-arid northern part, whereas it decreased in the semi-humid southern part. The precipitation variability during the growing season has a pattern similar to the annual precipitation variability. Although the majority of the regions have seen an NPP increase from 2000 to 2012, the responses of the vegetation to the varied climate factors were spatially heterogeneous. The alpine–subalpine meadows in the high-altitude areas were more sensitive to climate variability in the growing season. It is argued that satellite remote-sensing products have great potential in investigating the impact of climate variability on vegetation dynamics at the finer scale, especially for the Lancang River headwater area with complex surface heterogeneity.