Classifying protein sequences using hydropathy blocks

The annotation of proteins can be achieved by classifying the protein of interest into a certain known protein family to induce its functional and structural features. This paper presents a new method for classifying protein sequences based upon the hydropathy blocks occurring in protein sequences. First, a fixed-dimensional feature vector is generated for each protein sequence using the frequency of the hydropathy blocks occurring in the sequence. Then, the support vector machine (SVM) classifier is utilized to classify the protein sequences into the known protein families. The experimental results have shown that the proteins belonging to the same family or subfamily can be identified using features generated from the hydropathy blocks.     

利用初始残差和解耦操作的自适应深层图卷积

传统的图卷积网络(GCN)及其很多变体都是在浅层时达到最佳的效果,而没有充分利用图中节点的高阶邻居信息.随后产生的深层图卷积模型可以解决以上问题却又不可避免地产生了过平滑的问题,导致模型无法有效区分图中不同类别的节点.针对此问题,提出了一种利用初始残差和解耦操作的自适应深层图卷积模型ID-AGCN.首先,对节点的表示转...     

The clique-transversal set problem in claw-free graphs with degree at most 4

A clique of a graph G is defined as a complete subgraph maximal under inclusion and having at least two vertices. A clique-transversal set D of G is a subset of vertices of G such that D meets all cliques of G. The clique-transversal set problem is to find a minimum clique-transversal set of G. In this paper we present a polynomial time algorithm for the clique-transversal set problem on claw-free graphs with degree at most 4.     

Parameterizing cut sets in a graph by the number of their components

For a connected graph G=(V,E), a subset U⊆V is a disconnected cut if U disconnects G and the subgraph G[U] induced by U is disconnected as well. A cut U is a k-cut if G[U] contains exactly k(≥1) components. More specifically, a k-cut U is a (k,?)-cut if V?U induces a subgraph with exactly ?(≥2) components. The Disconnected Cut problem is to test whether a graph has a disconnected cut and is known to be NP-complete. The problems k-Cut and (k,?)-Cut are to test whether a graph has a k-cut or (k,?)-cut, respectively. By pinpointing a close relationship to graph contractibility problems we show that (k,?)-Cut is in P for k=1 and any fixed constant ?≥2, while it is NP-complete for any fixed pair k,?≥2. We then prove that k-Cut is in P for k=1 and NP-complete for any fixed k≥2. On the other hand, for every fixed integer g≥0, we present an FPT algorithm that solves (k,?)-Cut on graphs of Euler genus at most g when parameterized by k+?. By modifying this algorithm we can also show that k-Cut is in FPT for this graph class when parameterized by k. Finally, we show that Disconnected Cut is solvable in polynomial time for minor-closed classes of graphs excluding some apex graph.     

Automatic urban modeling using volumetric reconstruction with surface graph cuts

The demand for 3D city-scale models has been significantly increased due to the proliferation of urban planning, city navigation, and virtual reality applications. We present an approach to automatically reconstruct buildings densely spanning a large urban area. Our method takes as input calibrated aerial images and available GIS meta-data. Our computational pipeline computes a per-building 2.5D volumetric reconstruction by exploiting photo-consistency where it is highly sampled amongst the aerial images. Our building surface graph cut method overcomes errors of occlusion, geometry, and calibration in order to stitch together aerial images and yield a visually coherent texture-mapped result. Our comparisons show similar quality to the manually modeled buildings of Google Earth, and show improvements over naive texture mapping and over space-carving methods. We have tested our algorithms with a 12 sq km area of Boston, MA (USA), using 4667 images (i.e., 280 GB of raw image data) and producing 1785 buildings.     

RTG: a recursive realistic graph generator using random typing

We propose a new, recursive model to generate realistic graphs, evolving over time. Our model has the following properties: it is (a) flexible, capable of generating the cross product of weighted/unweighted, directed/undirected, uni/bipartite graphs; (b) realistic, giving graphs that obey eleven static and dynamic laws that real graphs follow (we formally prove that for several of the (power) laws and we estimate their exponents as a function of the model parameters); (c) parsimonious, requiring only four parameters. (d) fast, being linear on the number of edges; (e) simple, intuitively leading to the generation of macroscopic patterns. We empirically show that our model mimics two real-world graphs very well: Blognet (unipartite, undirected, unweighted) with 27 K nodes and 125 K edges; and Committee-to-Candidate campaign donations (bipartite, directed, weighted) with 23 K nodes and 880 K edges. We also show how to handle time so that edge/weight additions are bursty and self-similar.     

Leakage diagnosis with a contamination mitigation control framework using a graph theory based model

This work proposes an operational management approach for water distribution networks (WDNs) that can detect and localize leakages while also mitigating contamination resulting from these leaks. The primary emphasis of this work is the development of a contamination mitigation control scheme. A leak typically leads to a drop in network pressure that increases the risk of contamination. A leakage localization algorithm is responsible for detecting and localizing the leakage in the WDN. When a leak is detected in the network the contamination mitigation control is activated. The flow and pressure settings of the pumps are regulated by the contamination mitigation control in an optimal manner to minimize the risk of contamination. The entire framework is tested on the Smart Water Infrastructure Laboratory situated at Aalborg University, Denmark and a large-scale benchmark water network, which is part of a city network, L-town.     

A graph coloring heuristic using partial solutions and a reactive tabu scheme

Most of the recent heuristics for the graph coloring problem start from an infeasible k-coloring (adjacent vertices may have the same color) and try to make the solution feasible through a sequence of color exchanges. In contrast, our approach (called FOO-PARTIALCOL), which is based on tabu search, considers feasible but partial solutions and tries to increase the size of the current partial solution. A solution consists of k disjoint stable sets (and, therefore, is a feasible, partial k-coloring) and a set of uncolored vertices. We introduce a reactive tabu tenure which substantially enhances the performance of both our heuristic as well as the classical tabu algorithm (called TABUCOL) proposed by Hertz and de Werra [Using tabu search techniques for graph coloring, Computing 1987;39:345–51]. We will report numerical results on different benchmark graphs and we will observe that FOO-PARTIALCOL, though very simple, outperforms TABUCOL on some instances, provides very competitive results on a set of benchmark graphs which are known to be difficult, and outperforms the best-known methods on the graph flat300_28_0. For this graph, FOO-PARTIALCOL finds an optimal coloring with 28 colors. The best coloring achieved to date uses 31 colors. Algorithms very close to TABUCOL are still used as intensification procedures in the best coloring methods, which are evolutionary heuristics. FOO-PARTIALCOL could then be a powerful alternative. In conclusion FOO-PARTIALCOL is one of the most efficient simple local search coloring methods yet available.     

Recovery of missing information in graph sequences by means of reference pattern matching and decision tree learning

Algorithms for the analysis of graph sequences are proposed in this paper. In particular, we study the problem of recovering missing information and predicting the occurrence of nodes and edges in time series of graphs. Two different recovery schemes are developed. The first scheme uses reference patterns that are extracted from a training set of graph sequences, while the second method is based on decision tree induction. Our work is motivated by applications in computer network analysis. However, the proposed recovery and prediction schemes are generic and can be applied in other domains as well.     

Solving time-dependent multimodal transport problems using a transfer graph model

In this paper we present an hybrid approach for solving the time-dependent multimodal transport problem. This approach has been tested on realistic instances of the problem providing an adequate balance between computation time and memory space. This solution can be applied to real transport networks in order to reduce the impact of traffic congestion on pollution, economy, and citizen’s welfare. A comparison with two previous approaches are given from theoretical point of view as well as experimental performance.     

Detecting logical relationships in mechanical,electrical, and plumbing (MEP) systems with BIM using graph matching

The increasingly complex design has gained difficulty in conducting the rule compliance checking for the Mechanical, Electrical and Plumbing (MEP) system in the design phase. Useful rule-checking systems could contribute to a quicker project delivery time. Currently, an efficient method for checking the logical relationship is still lacking. This study aims to propose an MEP rule checking framework using the subgraph matching technology. First, the MEP components in the BIM model are extracted by utilizing the application programming interface (API), and a graph database is established with point-based and curve-based instances being nodes and relationships, respectively. Second, the graph database is simplified to increase the speed of graph matching. Third, the rules, which regulate how the MEP components should be connected, are represented by a knowledge graph. Finally, rule checking is achieved by comparing the graph database against the knowledge graph, and the critical path in a sub-system is detected by calculating the betweenness centrality. A case study with a rail station is used to evaluate the approach where the overall model checking and rule checking are conducted on the original and simplified graph databases sequentially. The results show that the proposed approach could achieve the rule compliance checking at a high speed, and 6 unconnected instances along with 155 problematic pipe fittings have been found. Besides, the critical path for the selected ACS system is from the water-cooled chiller to the condenser water pump. The proposed framework could help in the overall model checking and rule checking process, improving the efficiency of BIM engineers. This research demonstrates that converting a BIM model into a graph database can benefit conventional BIM analysis methods by incorporating advanced technologies (e.g., artificial intelligence) to enable a more flexible and accurate MEP design process.     

Ultrasonic evaluation of fetal lung development using deep learning with graph

BackgroundThe neonatal respiratory morbidity that was primarily caused by the immaturity of the fetal lung is an important clinical issue in close relation to the morbidity and mortality of the fetus. In clinics, the amniocentesis has been used to evaluate the fetal lung maturity, which is time-consuming, costly and invasive. As a non-invasive means, ultrasonography has been explored to quantitatively examine the fetal lung in the past decades. However, existing studies required the contour of the fetal lung which was delineated manually. This may lead to significant inter- and intra-observer variations.MethodsWe proposed a deep learning model for automated fetal lung segmentation and measurement, which was constructed combined U-Net with Graph model and pre-trained Vgg-16 network. The graph connection would extract stable feature for final segmentation and pre-trained method could speed up convergence.The model was trained with 3500 datasets augmented from 250 ultrasound images with both the fetal lung and heart delineated manually, and tested on 50 ultrasound images. In addition, the correlation between the size of fetal lung/heart as delineated by the model with gestational age was analyzed.ResultsThe fetal lung and cardiac area were segmented automatically with the accuracy, average Intersection over Union(IoU), sensitivity and precision being 0.991, 0.818, 0.909 and 0.888, respectively. In addition, the size of fetal lung/heart was well correlated with the gestational age, demonstrating good potentials for assessing the fetal development.ConclusionsThis study proposed a new robust method for automatic fetal lung segmentation in ultrasound images using Vgg16-GCN-UNet. Our proposed method could be utilized potentially not only to improve existing research in quantitative analyzing the fetal lung using ultrasound imaging technology, but also to alleviate the labor of the clinicians in routine measurement of the fetal lung/cardiac.     

A new document representation using term frequency and vectorized graph connectionists with application to document retrieval

This paper presents a new document representation with vectorized multiple features including term frequency and term-connection-frequency. A document is represented by undirected and directed graph, respectively. Then terms and vectorized graph connectionists are extracted from the graphs by employing several feature extraction methods. This hybrid document feature representation more accurately reflects the underlying semantics that are difficult to achieve from the currently used term histograms, and it facilitates the matching of complex graph. In application level, we develop a document retrieval system based on self-organizing map (SOM) to speed up the retrieval process. We perform extensive experimental verification, and the results suggest that the proposed method is computationally efficient and accurate for document retrieval.     

符号序列多阶Markov分类

针对基于固定阶Markov链模型的方法不能充分利用不同阶次子序列结构特征的问题,提出一种基于多阶Markov模型的符号序列贝叶斯分类新方法。首先,建立了基于多阶次Markov模型的条件概率分布模型;其次,提出一种附后缀表的n-阶子序列后缀树结构和高效的树构造算法,该算法能够在扫描一遍序列集过程中建立多阶条件概率模型;最后,提出符号序列的贝叶斯分类器,其训练算法基于最大似然法学习不同阶次模型的权重,分类算法使用各阶次的加权条件概率进行贝叶斯分类预测。在三个应用领域实际序列集上进行了系列实验,结果表明：新分类器对模型阶数变化不敏感;与使用固定阶模型的支持向量机等现有方法相比,所提方法在基因序列与语音序列上可以取得40%以上的分类精度提升,且可输出符号序列Markov模型最优阶数参考值。     

基于词性标注序列特征提取的微博情感分类

传统的n-gram文本特征提取方法会产生高维度的特征向量,高维数据不但增大了分类的难度,同时也会增加分类的时间。针对这一问题,提出了一种基于词性（POS）标注序列的特征提取方法,根据词性序列能够代表一类文本的这一个特点,利用词性序列组作为文本的特征以达到降低特征维度的效果。在实验中,词性序列特征提取方法比n-gram特征提取方法至少提高了9%的分类精度,降低4816个维度。实验结果表明,该方法能够适用于微博情感分类。     

A corporate credit rating model using multi-class support vector machines with an ordinal pairwise partitioning approach

Predicting corporate credit-rating using statistical and artificial intelligence (AI) techniques has received considerable research attention in the literature. In recent years, multi-class support vector machines (MSVMs) have become a very appealing machine-learning approach due to their good performance. Until now, researchers have proposed a variety of techniques for adapting support vector machines (SVMs) to multi-class classification, since SVMs were originally devised for binary classification. However, most of them have only focused on classifying samples into nominal categories; thus, the unique characteristic of credit-rating - ordinality - seldom has been considered in the proposed approaches. This study proposes a new type of MSVM classifier (named OMSVM) that is designed to extend the binary SVMs by applying an ordinal pairwise partitioning (OPP) strategy. Our model can efficiently and effectively handle multiple ordinal classes. To validate OMSVM, we applied it to a real-world case of bond rating. We compared the results of our model with those of conventional MSVM approaches and other AI techniques including MDA, MLOGIT, CBR, and ANNs. The results showed that our proposed model improves the performance of classification in comparison to other typical multi-class classification techniques and uses fewer computational resources.     

A graph coloring model for a feasibility problem in monthly crew scheduling with preferential bidding

We consider a monthly crew scheduling problem with preferential bidding in the airline industry. We propose a new methodology based on a graph coloring model and a tabu search algorithm for determining if the problem contains at least one feasible solution. We then show how to combine the proposed approach with a heuristic sequential scheduling method that uses column generation and branch-and-bound techniques.     

Chaotic mixing using periodic and aperiodic sequences of mixing protocols in a micromixer

We conducted a numerical study on mixing in a barrier embedded micromixer with an emphasis on the effect of periodic and aperiodic sequences of mixing protocols on mixing performance. A mapping method was employed to investigate mixing in various sequences, enabling us to qualitatively observe the progress of mixing and also to quantify both the rate and the final state of mixing. First, we introduce the design concept of the four mixing protocols and the route to achieve chaotic mixing of the mixer. Then, several periodic sequences consisting of the four mixing protocols are used to investigate the mixing performance depending on the sequence. Chaotic mixing was observed, but with different mixing rates and different final mixing states significantly influenced by the specific sequence of mixing protocols and inertia. As for the effect of inertia, the higher the Reynolds number the larger the rotational motion of the fluid leading to faster mixing. We found that a sequence showing the best mixing performance at a certain Reynolds number is not always superior to other sequences in a different Reynolds number regime. A properly chosen aperiodic sequence results in faster and more uniform mixing than periodic sequences.     

Crew pairing optimization by a genetic algorithm with unexpressed genes

We propose a genetic algorithm to solve the pairing optimization problem for subway crew scheduling. Our genetic algorithm employs new crossover and mutation operators specially designed to work with the chromosomes of set-oriented representation. To enhance the efficiency of the search with the newly designed genetic operators, we let a chromosome consist of an expressed part and an unexpressed part. While the genes in both parts evolve, only the genes in the expressed part are used when an individual is evaluated. The purpose of the unexpressed part is to preserve information susceptible to be lost by the application of genetic operators, and thus to maintain the diversity of the search. Experiments with real-world data have shown that our genetic algorithm outperforms other local search methods such as simulated annealing and tabu search. Received: June 2005/Accepted: December 2005