Enhancing usability testing through datamining techniques: A novel approach to detecting usability problem patterns for a context of use

Usability is a software attribute usually associated with the “ease of use and to learn” of a given interactive system. Nowadays usability evaluation is becoming an important part of software development, providing results based on quantitative and qualitative estimations. In this context, qualitative results are usually obtained through a Qualitative Usability Testing process which includes a number of different methods focused on analyzing the interface of a particular interactive system. These methods become complex when a large number of interactive systems belonging to the same context of use have to be jointly considered to provide a general diagnosis, as a considerable amount of information must be visualized and treated simultaneously. However, diagnosing the most general usability problems of a context of use as a whole from a qualitative viewpoint is a challenge for UE nowadays. Identifying such problems can help to evaluate a new interface belonging to this context, and to prevent usability errors when a novel interactive system is being developed. From a quantitative viewpoint, condensing results in singles scores, metrics or statistical functions is an acceptable solution for processing huge amounts of usability related information. Nevertheless, QUT processes need to keep their richness by prioritizing the “what” over the “how much/how many” questions related to the detection of usability problems.To cope with the above situation, this paper presents a new approach in which two datamining techniques (association rules and decision trees) are used to extend the existing Qualitative Usability Testing process in order to provide a general usability diagnosis of a given context of use from a qualitative viewpoint. In order to validate our proposal, usability problems patterns belonging to academic webpages in Spanish-speaking countries are assessed by processing 3450 records which store qualitative information collected by means of a Heuristic Evaluation.     

On-line diagnosis and uncertainty management using evidence theory––experimental illustration to anaerobic digestion processes

The on-line diagnosis is a key requirement in biological processes. This is particularly true in the case of wastewater treatment processes due to the composition of media, the requirements of operating conditions and the wide variety of possible disturbances that necessitate careful and constant monitoring of the processes. Moreover, because only partial information is available in an on-line context and because of the technical and biological complexities of the involved processes, specific characteristics are required for diagnosis purposes. Several approaches like quantitative model based, qualitative model based and process history based methods were applied over the years. This paper present a methodological framework based on evidence theory to manage the fault signals generated by conventional approaches (i.e., residuals from hardware and software redundancies, fuzzy logic based modules for process state assessment) and to account for uncertainty. The advantages of using evidence theory like modularity, detection of conflict and doubt in the information sources are illustrated with experimental results from a 1 m³ fixed bed anaerobic digestion process used for the treatment of industrial distillery wastewater.     

An algorithmic approach for system-specific modelling of activated sludge bulking in an SBR

Using a step-by-step approach, a system-specific non-mechanistic model based on statistical analyses of real-world response of process parameters to bulking, was formulated for an aerobic Sequencing Batch Reactor (SBR). The approach involved 2 phases — “Diagnosis” and “Analysis”. In “Diagnosis” phase, model parameters were identified via statistical rules and existing knowledge base on bulking, while in the “Analysis” phase, the parameters were modelled with the Sludge Volume Index (SVI) to formulate the non-mechanistic model. Validation results yielded satisfactory results for the modelling analysis. The statistical approach was executed using a multivariate data analysis package and resulted in a non-mechanistic model that was practically appealing to practitioners for its ease of use as a predictive tool for bulking. This approach, being dependent only on data analysis and statistical modelling, required no bench-scale experiments to be conducted for preliminary identification of the bulking problem. Furthermore, such an approach being algorithmic in nature, could potentially form the concept behind design of expert systems for very rapid, and economical diagnosis of bulking problems before a more in-depth and slow analytical approach involving costly laboratory procedures is adopted.     

An alignment-based framework to check the conformance of declarative process models and to preprocess event-log data

Process mining can be seen as the “missing link” between data mining and business process management. The lion's share of process mining research has been devoted to the discovery of procedural process models from event logs. However, often there are predefined constraints that (partially) describe the normative or expected process, e.g., “activity A should be followed by B” or “activities A and B should never be both executed”. A collection of such constraints is called a declarative process model. Although it is possible to discover such models based on event data, this paper focuses on aligning event logs and predefined declarative process models. Discrepancies between log and model are mediated such that observed log traces are related to paths in the model. The resulting alignments provide sophisticated diagnostics that pinpoint where deviations occur and how severe they are. Moreover, selected parts of the declarative process model can be used to clean and repair the event log before applying other process mining techniques. Our alignment-based approach for preprocessing and conformance checking using declarative process models has been implemented in ProM and has been evaluated using both synthetic logs and real-life logs from a Dutch hospital.     

Behavioral process mining for unstructured processes

Real world applications provide many examples of unstructured processes, where process execution is mainly driven by contingent decisions taken by the actors, with the result that the process is rarely repeated exactly in the same way. In these cases, traditional Process Discovery techniques, aimed at extracting complete process models from event logs, reveal some limits. In fact, when applied to logs of unstructured processes, Process Discovery techniques usually return complex, “spaghetti-like” models, which usually provide limited support to analysts. As a remedy, in the present work we propose Behavioral Process Mining as an alternative approach to enlighten relevant subprocesses, representing meaningful collaboration work practices. The approach is based on the application of hierarchical graph clustering to the set of instance graphs generated by a process. We also describe a technique for building instance graphs from traces. We assess advantages and limits of the approach on a set of synthetic and real world experiments.     

Fault diagnosis of a cstr using fuzzy neural networks

On-line process fault diagnosis using fuzzy neural networks is described in this paper. The fuzzy neural network is obtained by adding a fuzzification layer to a conventional feed forward neural network. The fuzzification layer converts increments in on-line measurements and controller outputs into three fuzzy sets: “increase”, “steady”, and “decrease”. Abnormalities in a process are represented by qualitative increments in on-line measurements and controller outputs. These are classified into various categories by the network. By representing abnormalities in qualitative form, training data can be condensed. The fuzzy approach ensures smooth transitions from one fuzzy sets to another and, hence, robustness to measurement noise is enhanced. The technique has been successfully applied to a CSTR system.     

Building instance graphs for highly variable processes

Organizations increasingly rely on business process analysis to improve operations performance. Process Mining can be exploited to distill models from real process executions recorded in event logs, but existing techniques show some limitations when applied in complex domains, where human actors have high degree of freedom in the execution of activities thus generating highly variable processes instances. This paper contributes to the research on Process Mining in highly variable domains, focusing on the generation of process instance models (in the form of instance graphs) from simple event logs. The novelty of the approach is in the exploitation of filtering Process Discovery (PD) techniques coupled with repairing, which allows obtaining accurate models for any instance variant, even for rare ones. It is argued that this provides the analyst with a more complete and faithful knowledge of a highly variable process, where no process execution can be really targeted as “wrong” and hence overlooked. The approach can also find application in more structured domains, in order to obtain accurate models of exceptional behaviors. The quality of generated models will be assessed by suitable metrics and measured in empirical experiments enlightening the advantage of the approach.     

模糊控制在SBR污水处理中的应用

该文主要介绍了模糊控制器在序批式活性污泥法(SBR)污水处理厂自动控制系统中的设计和应用.SBR是目前在污水处理中得到广泛应用的生物处理技术,但其有非线性、不确定性以及由此引起的难以建立准确的数学模型的特点.本文利用模糊良好的控制功能设计了SBR法的污水处理系统,该系统能够根据在线检测的COD浓度值自动控制曝气量,保证出水质量,节省运行费用.     

SBR污水生化处理系统的最优控制及改进

针对序批式反应器污水处理工艺,提出一种以排水质量指标为约束条件,以能量消耗最小为日标的最优控制方案．由于生化过程机理复杂,导致这个最优问题求解困难．所构造的解法是首先建立通用的序批式反应器模型;然后借助仿真工具试差求取次优解．为解决搜索求解计算量大的问题,进一步结合进退法提出了一种改进的优化算法,显著提高了求解效率。     

Model-100: Specification language for interacting processes

Basic ideas and constructs of the Model-100 language designed for describing behavior of interacting processes are discussed. Process interaction rules are specified by clauses of the form “if … then …” (Horn clauses). Structure of the interactions is presented by a graph described by a rational term. Execution of one step of the program reduces to simultaneous application of all rules to all nodes to which the rule can be applied (i.e., to all rational subterms with which the Horn clause can be unified).     

基于退火的蚁群算法在连续空间优化中的应用

研究了蚁群算法在连续空间的函数寻优问题。通过修改蚂蚁信息素的留存方式和行走规则,定义了一个连续空间的蚁群算法。模拟蚂蚁用触角交流信息的过程提出了直接通信的学习机制,增强了蚂蚁的搜索能力。为了防止出现“早熟”现象,在局部搜索过程中嵌入了模拟退火的思想。同时为避免过大的残留信息,选择了新的信息增量计算函数。实例运算证明了算法的有效性。     

SLOTSEQ: A FORTRAN IV program for comparing two sequences of observations

The program described has been of use in comparing physical logs from two boreholes when the aim has been to “line up”, or correlate, the boreholes in order to identify sections where the physical logs show similar patterns. This is achieved by slotting the two sequences of measurements into one joint sequence which preserves the stratigraphic ordering within each of the original sequences, and subject to this requirement, insures that similar sets of measurements are placed near to one another in the joint sequence. Various types of constraint also may be imposed on the allowable slottings, for example readings from different logs which occur in a persistent marker bed can be required to be close together in the joint slotting. The method is illustrated on a set of data comprising gamma, sonic, and induction logs from two wells. Detailed input specifications and a listing of the program are given.     

Security Log Management

Have your systems been configured to write events to the system logs? Most people would answer “Yes”. Are they using the standard default settings? The answer to this will vary. How often are the logs examined? Most people would answer only “when there is a problem”.     

P systems with control nuclei: The concept

We describe an extension of P systems where each membrane has an associated control nucleus responsible with the generation of the rules to be applied in that membrane. The nucleus exports a set of rules which are applied in the membrane region (only for one step, but in the usual maximal-parallel way), then the rules are removed and a new iteration of this process takes place. This way, powerful control mechanisms may be included in P systems themselves, as opposed to using the level of “strategies” previously exploited for simulating P systems. The nuclei may contain general programs for generating rules, ranging from those using information on the full system, to more restricted programs where only local information in the nuclei themselves and the associated membranes is used. The latter approach, mixed with a particular mechanism for the representation of the control programs, the rules, and the export procedure is powerful enough for modeling complex biological applications, e.g., to develop a detailed model for cell growth and division in normal and abnormal (tumoral) evolution of biological systems.     

序批式反应器污水处理系统仿真模型的建立

序批式反应器污水处理系统(SBR)是目前应用很广的一种污水处理工艺。该文以国际水质量协会(IWA)发布的活性污泥生化污水处理系统标准模型ASM2d以及benchmark组成协议为基础,结合序批式反应器污水处理系统的特点,分析了序批示反应器各阶段的物料平衡,从而开发了脱氮除磷SBR系统的Matlab仿真模型。模型运行检验表明,该模型能较好地模拟脱氮除磷序批式反应器污水处理系统中的生化反应过程,可以作为一般SBR系统运行仿真平台用于SBR系统的优化、控制及监视策略的研究。     

高维数据聚类可视分析方法综述

数据聚类的可视分析方法利用可视化与交互技术帮助用户对聚类过程与结果进行 多角度分析,从而发现数据内部隐藏的结构和关系。但由于高维数据自身的“维度诅咒”问题 使得聚类分析面临着许多挑战,例如模型参数设定、数据特征捕捉、结果解释以及可视化展现 等。本文从高维数据聚类过程中遇到的问题出发,首先总结了高维数据聚类过程中常用的数据 处理方法并对其性能进行了比较,这些方法能够较好地解决“维度诅咒”问题,帮助用户挖掘 数据中存在的聚类模式。在分析和理解不同聚类结果中包含的数据内部结构和规律时,由于前 期采取的数据处理方法不同,因此需要采取不同的探索分析策略,所以本文将近10 年来高维数 据聚类的可视分析方法分为2 大类进行总结,即基于降维的聚类可视分析方法和基于子空间聚 类的可视分析方法。最后对该领域目前存在的机遇与挑战进行了讨论。     

Developing a streaming data processing workflow for querying space–time activities from geotagged tweets

The critical dimensions in describing space–time activities are “what“, “where”, “when”, and “who”, which are frequently applied to collect data about basic functions people perform in space in the course of a day. Collecting data about these dimensions using activity-based surveys has presented researchers with a number of technical and social limitations, ranging from the restricted period of time participants have to record their activities to the level of accuracy with which participants complete a survey. This paper proposes a new streaming data processing workflow for querying space–time activities (STA) as a by-product of microblogging communication. It allows exploring a large volume of geotagged tweets to discover STA patterns of daily life in a systematic manner. A sequence of tasks have been implemented using different cloud-based computing resources for handling over one million of daily geotagged tweets from Canada for a period of six months. The STA patterns have revealed activity choices that might be attributable to personal motivations for communicating an activity in social networks.