Attentional sequence-based recognition: Markovian and evidential reasoning

Biological vision systems explore their environment via allocating their visual resources to only the interesting parts of a scene. This is achieved by a selective attention mechanism that controls eye movements. The data thus generated is a sequence of subimages of different locations and thus a sequence of features extracted from those images - referred to as attentional sequence. In higher level visual processing leading to scene cognition, it is hypothesized that the information contained in attentional sequences are combined and utilized by special mechanisms - although still poorly understood. However, developing models of such mechanisms prove out to be crucial - if we are to understand and mimic this behavior in robotic systems. In this paper, we consider the recognition problem and present two approaches to using attentional sequences for recognition: Markovian and evidential reasoning. Experimental results with our mobile robot APES reveal that simple shapes can be modeled and recognized by these methods - using as few as ten fixations and very simple features. For more complex scenes, longer attentional sequences or more sophisticated features may be required for cognition.     

Efficient mining of frequent episodes from complex sequences

Discovering patterns with great significance is an important problem in data mining discipline. An episode is defined to be a partially ordered set of events for consecutive and fixed-time intervals in a sequence. Most of previous studies on episodes consider only frequent episodes in a sequence of events (called simple sequence). In real world, we may find a set of events at each time slot in terms of various intervals (hours, days, weeks, etc.). We refer to such sequences as complex sequences. Mining frequent episodes in complex sequences has more extensive applications than that in simple sequences. In this paper, we discuss the problem on mining frequent episodes in a complex sequence. We extend previous algorithm MINEPI to MINEPI+$\mathrm{MINEPI}+$ for episode mining from complex sequences. Furthermore, a memory-anchored algorithm called EMMA is introduced for the mining task. Experimental evaluation on both real-world and synthetic data sets shows that EMMA is more efficient than MINEPI+$\mathrm{MINEPI}+$.     

A program for template matching of protein sequences

The matching of a template to a protein sequence is simplified by treating it as a special case of sequence alignment. Restriction of the distances between motifs in the template controls against spurious matches within very long sequences. The program using this algorithm is fast enough to be used in scanning large databases for sequences matching a complex template.     

Fast Fourier transform-based correlation of DNA sequences using complex plane encoding

The detection of similarities between DNA sequences can be accomplished using the signal-processing technique of cross-correlation. An early method used the fast Fourier transform (FFT) to perform correlations on DNA sequences in O(n log n) time for any length sequence. However, this method requires many FFTs (nine), runs no faster if one sequence is much shorter than the other, and measures only global similarity, so that significant short local matches may be missed. We report that, through the use of alternative encodings of the DNA sequence in the complex plane, the number of FFTs performed can be traded off against (i) signal-to-noise ratio, and (ii) a certain degree of filtering for local similarity via k-tuple correlation. Also, when comparing probe sequences against much longer targets, the algorithm can be sped up by decomposing the target and performing multiple small FFTs in an overlap-save arrangement. Finally, by decomposing the probe sequence as well, the detection of local similarities can be further enhanced. With current advances in extremely fast hardware implementations of signal-processing operations, this approach may prove more practical than heretofore.     

Sequence ordinations: a multivariate analysis approach to analysing large sequence data sets.

Ordination is a powerful method for analysing complex data sets but has been largely ignored in sequence analysis. This paper shows how to use principal coordinates analysis to find low-dimensional representations of distance matrices derived from aligned sets of sequences. The method takes a matrix of Euclidean distances between all pairs of sequence and finds a coordinate space where the distances are exactly preserved. The main problem is to find a measure of distance between aligned sequences that is Euclidean. The simplest distance function is the square root of the percentage difference (as measured by identities) between two sequences, where one ignores any positions in the alignment where there is a gap in any sequence. If one does not ignore positions with a gap, the distances cannot be guaranteed to be Euclidean but the deleterious effects are trivial. Two examples of using the method are shown. A set of 226 aligned globins were analysed and the resulting ordination very successfully represents the known patterns of relationship between the sequences. In the other example, a set of 610 aligned 5S rRNA sequences were analysed. Sequence ordinations complement phylogenetic analyses. They should not be viewed as a complete alternative.     

Object-oriented motion abstraction

An important problem in the production of an animation sequence is the great amount of information necessary to control and specify the motion. Specification of complex animation sequences with a smaller amount of information is possible if they are built over some abstracted sequences. Abstraction supports dealing with complexity by structuring, so that the necessary features are made available while those that are not necessary are hidden. In our work, motion abstraction is used to build complex animation sequences with the help of object-oriented concepts. A parametric key-frame interpolation method is used for producing the in-between frames of an animation sequence. The parameters that define the motion of a model, in our work, are position, orientation, size, shape and colour. Orientation transformations are implemented by unit quaternions.     

Optimal probabilistic evaluation functions for search controlled bystochastic context-free grammars

The possibility of using stochastic context-free grammars (SCFG's) in language modeling (LM) has been considered previously. When these grammars are used, search can be directed by evaluation functions based on the probabilities that a SCFG generates a sentence, given only some words in it. Expressions for computing the evaluation function have been proposed by Jelinek and Lafferty (1991) for the recognition of word sequences in the case in which only the prefix of a sequence is known. Corazza et al. (1991) have proposed methods for probability computation in the more general case in which partial word sequences interleaved by gaps are known. This computation is too complex in practice unless the lengths of the gaps are known. This paper proposes a method for computing the probability of the best parse tree that can generate a sentence only part of which (consisting of islands and gaps) is known. This probability is the minimum possible, and thus the most informative, upper-bound that can be used in the evaluation function. The computation of the proposed upper-bound has cubic time complexity even if the lengths of the gaps are unknown. This makes possible the practical use of SCFG for driving interpretations of sentences in natural language processing     

Synthesis and recognition of sequences

A string or sequence is a linear array of symbols that come from an alphabet. Due to unknown substitutions, insertions, and deletions of symbols, a sequence cannot be treated like a vector or a tuple of a fixed number of variables. The synthesis of an ensemble of sequences is a sequence of random elements that specify the probabilities of occurrence of the different symbols at the corresponding sites of the sequences. The synthesis is determined by a hierarchical sequence synthesis procedure (HSSP), which returns not only the taxonomic hierarchy of the whole ensemble of sequences but also the alignment and the synthesis of a group (a subset of the ensemble) of the sequences at each level of the hierarchy. The HSSP does not require the ensemble of sequences to be presented in the form of a tabulated array of data, the hierarchical information of the data, or the assumption of a stochastic process. The authors present the concept of sequence synthesis and the applicability of the HSSP as a supervised classification procedure as well as an unsupervised classification procedure     

Translational photometric alignment of single-view image sequences

Photometric stereo is a well-established method to estimate surface normals of an object. When coupled with depth-map estimation, it can be used to reconstruct an object’s height field. Typically, photometric stereo requires an image sequence of an object under the same viewpoint but with differing illumination directions. One crucial assumption of this configuration is perfect pixel correspondence across images in the sequence. While this assumption is often satisfied, certain setups are susceptible to translational errors or misalignments across images. Current methods to align image sequences were not designed specifically for single-view photometric stereo. Thus, they either struggle to account for changing illumination across images, require training sets, or are overly complex for these conditions. However, the unique nature of single-view photometric stereo allows one to model misaligned image sequences using the underlying image formation model and a set of translational shifts. This paper introduces such a technique, entitled translational photometric alignment, that employs the Lambertian model of image formation. This reduces the alignment problem to minimizing a nonlinear sum-squared error function in order to best reconcile the observed images with the generative model. Thus, the end goal of translational photometric alignment is not only to align image sequences, but also to produce the best surface-normal estimates given the observed images. Controlled experiments on the Yale Face Database B demonstrate the high accuracy of translational photometric alignment. The utility and benefits of the technique are further illustrated by additional experiments on image sequences suffering from uncontrolled real-world misalignments.     

A search for common patterns in many sequences.

A new approach to search for common patterns in many sequences is presented. The idea is that one sequence from the set of sequences to be compared is considered as a 'basic' one and all its similarities with other sequences are found. Multiple similarities are then reconstructed using these data. This approach allows one to search for similar segments which can differ in both substitutions and deletions/insertions. These segments can be situated at different positions in various sequences. No regions of complete or strong similarity within the segments are required. The other parts of the sequences can have no similarity at all. The only requirement is that the similar segments can be found in all the sequences (or in the majority of them, given the common segments are present in the basic sequence). Working time of an algorithm presented is proportional to n.L2 when n sequences of length L are analyzed. The algorithm proposed is implemented as programs for the IBM-PC and IBM/370. Its applications to the analysis of biopolymer primary structures as well as the dependence of the results on the choice of basic sequence are discussed.     

基于聚类与时间耦合执行序列的任务分解方法

本文针对复杂任务分析中的高度耦合任务不易分解且需重构排序的问题,提出了一种基于聚类分析与改进时间-耦合执行序列的自适应任务分解方法。在矩阵最值遴选模型和任务序列转移策略相结合的基础上,设计了基于中间任务序列的任务矩阵分割算法;并进一步采用粒度自主循环调整机制,最终实现了复杂任务的自适应解耦分析。仿真验证结果表明,该方法能够有效实现复杂任务的解耦及序列重构,在作战任务分析领域具有很好的推广应用前景。     

A Self-Organizing Context-Based Approach to the Tracking of Multiple Robot Trajectories

We have combined competitive and Hebbian learning in a neural network designed to learn and recall complex spatiotemporal sequences. In such sequences, a particular item may occur more than once or the sequence may share states with another sequence. Processing of repeated/shared states is a hard problem that occurs very often in the domain of robotics. The proposed model consists of two groups of synaptic weights: competitive interlayer and Hebbian intralayer connections, which are responsible for encoding respectively the spatial and temporal features of the input sequence. Three additional mechanisms allow the network to deal with shared states: context units, neurons disabled from learning, and redundancy used to encode sequence states. The network operates by determining the current and the next state of the learned sequences. The model is simulated over various sets of robot trajectories in order to evaluate its storage and retrieval abilities; its sequence sampling effects; its robustness to noise and its tolerance to fault.     

Automatic face recognition for video indexing applications

This paper presents an efficient automatic face recognition scheme useful for video indexing applications. In particular the following problem is addressed: given a set of known face images and given a complex video sequence to be indexed, find where the corresponding faces appear in the shots of the sequence. The main and final objective is to develop a tool to be used in the MPEG-7 standardization effort to help video indexing activities. Conventional face recognition schemes are not well suited for this application and alternative and more efficient schemes have to be developed. In this paper, in the context of Principal Component Analysis for face recognition, the concept of self-eigenfaces is introduced. In addition, the color information is also incorporated in the face recognition stage. The face recognition scheme is used in combination with an automatic face detection scheme which makes the overall approach highly useful. The resulting scheme is very efficient to find specific face images and to cope with the different face conditions present in a complex video sequence. Results are presented using the test sequences accepted in the MPEG-7 video content sequences set.     

点发序列问题的控制策略

在离散事件系统的Petri网模型下,讨论是否存在控制策略使得仅有希望的序列使 能,而又保持事件的并发性的问题.证明了存在这种策略的必要充分条件是给定的目标序 列集是可控的.在目标序列集不可控而所考虑的序列集都是Petri网点发序列集时,提出了 综合给定序列集的极大可控子序列集生成器的方法.     

基于网络方法的DNA序列编码区·非编码区性质研究

利用了一种基于图论理论的方法对DNA序列(片段),其编码区及非编码区进行分析。该方法通过复杂网络研究生物体的拓扑结构,主要通过测量聚类系数(也可称:集团系数)构建网络的拓扑结构。依据DNA序列的前缀、后缀关联性质构造了所选取DNA序列(片段),其编码区和非编码区的相关网络,发现以上网络分布满足幂率特征,有较大的聚类系数(集团系数)。结果表明构建得到的网络同时满足小世界网络和无尺度网络的特征,证明DNA序列不全是随机的序列,而是有随机扰动的确定结构的序列,特别是编码区。     

不规则采样序列的平移等价性

研究了包含钟控序列在内的一般不规则采样序列的平移等价性,解决了这类序列平移等价分类问题.具体给出了一般不规则采样序列平移等价与被采序列和采样距序列平移等价的关系和两个一般不规则采样序列平移等价的充分条件,并针对一个特殊的不规则间选序列,给出了其平移等价与被采序列和采样距序列所对应两个线性移位寄存器序列反馈函数相等的充分必要条件.     

Monostable Circuit Triggered with Pulse Trains†

The behaviour of a monostable trigger circuit, which is triggered with periodic pulse, trains is analysed by determining the sequence of its division ratio. Some general properties of these sequences are found, from which it follows that the sequence may show irregular changes, periodical changes or take a constant value of the division ratio after a sufficient number of cycles. Some conditions are found which must be satisfied for the sequence to have one of the above-mentioned properties. Periodical changes are obtained only in exceptional cases.     

TCPN的组合可调度分析

时间约束Petri网(Timing Constraints Petri nets,简称TCPNs)是一类重要的时间Petri网系统.针对TCPNs中变迁可调度原始语义的不足,本文对相关定义重新定义,丰富并完善了TPCNs理论.本文首先给出了新的针对单个变迁或变迁序列的可调度分析策略.如果一个特定的变迁序列是可调度的,则相应的活动序列也同样可以顺利地完成自身的执行;否则,不可调度的变迁需要调整自己的时间约束;然后提出了组合式的可调度分析策略以分析复杂变迁序列,最后提出时序一致性的概念.     

A fast DNA sequence handling program for Apple II computer in BASIC and 6502 assembler

A fast general purpose DNA handling program has been developed in BASIC and machine language. The program runs on the Apple II plus or on the Apple IIe microcomputer, without additional hardware except for disk drives and printer. The program allows file insertion and editing, translation into protein sequence, reverse translation, search for small strings and restriction enzyme sites. The homology may be shown either as a comparison of two sequences or through a matrix on screen. Two additional features are: (i) drawing restriction site maps on the printer; and (ii) simulating a gel electrophoresis of restriction fragments both on screen and on paper. All the operations are very fast. The more common tasks are carried out almost instantly; only more complex routines, like finding homology between large sequences or searching and sorting all the restriction sites in a long sequence require longer, but still quite acceptable, times (generally under 30 s).