Examining multiple feature evaluation and classification methods for improving the diagnosis of Parkinson’s disease

An accurate diagnosis of Parkinson’s disease by specialists involves many neurological, psychological and physical examinations. The specialists investigate a number of symptoms and signs when examining the nervous system conditions of a person. The diagnosis involves reviewing the medical history and genetic factor of the person. The recent diagnosis methodology to Parkinson’s disease relies on voice disorders analysis. This methodology entails extracting feature sets of a recorded person’s voice then utilizing a machine learning technique to identify the healthy and Parkinson’s cases from the voice. This paper attempts to improve the diagnoses of Parkinson’s disease by testing multiple feature evaluation and classification machine learning methods based on the voice disorders analysis. The aim of this paper is to find the optimal solution to the problem by (i) proposing a new Multiple Feature Evaluation Approach (MFEA) of a multi-agent system (ii) implementing five independent classification schemas which are Decision Tree, Naïve Bayes, Neural Network, Random Forests, and Support Vector Machine on the Parkinson’s diagnosis before and after applying the MFEA, and (iii) evaluating the diagnosis accuracy of the results. The methodology of the tests encompasses 10-fold cross-validation to evaluate the learning of methods and track variation in their performance. The test results show that the MFEA of the multi-agent system finds the best set of features and improves the performance of the classifiers. The average rate of improvement in the diagnostic accuracy of the classifiers are Decision Tree 10.51%, Naïve Bayes 15.22%, Neural Network 9.19%, Random Forests 12.75%, and Support Vector Machine 9.13%. These results show that the MFEA makes a significant improvement to the classifiers’ diagnosis results.     

La résilience et le bien-être psychologique au travail au service de la thèse du travailleur heureux-productif

Based on broaden-and-build theory, this study proposes to expand the happy-productive worker thesis by exploring an emergent operationalization of happiness. To do so, the mediating effect of the dimensions of psychological well-being at work (i.e., relation to oneself, to others and to work) on the relation between resilience and task performance has been tested. A total of 280 Quebec workers filled out validated measures. Obtained by structural equation modelling analyses, the results indicate that the rapport with oneself of psychological well-being at work acts as the only mediator between resilience and task performance. These findings underscore the importance of encouraging the development of interventions that build on the resilience and positive experience of workers to optimize their work performance.     

大学生社会排斥对社交焦虑的影响：负面评价恐惧与人际信任的作用

为探讨大学生社会排斥对社交焦虑的影响以及负面评价恐惧和人际信任在二者之间的作用机制,研究采用大学生社会排斥问卷（SEQU）、社交焦虑量表（SASSCS）、负面评价恐惧量表（BFNES）及人际信任量表（ITS）对450名大学生进行测试。结果表明：（1）大学生社会排斥不仅对个体的社交焦虑水平产生影响,还会通过负面评价恐惧的中介作用对社交焦虑产生影响;（2）人际信任能够调节大学生社会排斥对社交焦虑的直接作用,具体而言,与高人际信任的大学生相比较,较低人际信任的大学生的社会排斥对社交焦虑的预测作用更加显著。     

多目标追踪在各类人群评价与训练中的应用

多目标追踪范式主要用来探讨动态情景下对多个目标的视觉注意和记忆加工过程, 早期研究侧重于追踪过程中的影响因素及加工机制。近年来, 越来越多的研究应用多目标追踪范式对各类人群进行评价与训练, 包括儿童、老年人、神经发育障碍患者、驾驶员、运动员、电子游戏玩家以及一些其他职业群体。总体来看, 多目标追踪表现越好, 在复杂快速的动态情境中的专业表现越好; 反之, 多目标追踪表现差, 标志着认知功能可能发育不成熟或出现衰退。并且, 多目标追踪还可作为认知训练的手段, 改善老年人和神经发育障碍患者的认知功能, 提高各职业人群的专业表现。未来, 多目标追踪作为评价和训练的方法还有很大的发展空间, 包括加强特殊职业人群的模拟训练, 扩展目标人群, 结合立体视觉和真实场景, 结合身体活动, 探索多人合作的多目标追踪, 拓展用于进行情绪和社会功能的评价与训练等。     

Choose your lunch companion wisely: the relationships between lunch break companionship,psychological detachment,and daily vigour

This diary study examines psychological detachment, companionship, and content of conversation during lunch break as predictors of daily vigour after lunch break and at the end of the working day. Drawing on resource regulation theory and the effort recovery model (ERM), we hypothesize that companionship of the supervisor during lunch break is negatively and companionship of colleagues positively related to employee’s daily vigour. The companionship of both, supervisors and colleagues, as well as work-related conversations are hypothesized to decrease psychological detachment during lunch breaks. In total, 71 persons in administrative jobs completed daily surveys over one working week. Results of hierarchical linear modelling showed that psychological detachment is positively related to vigour after lunch break, but unrelated to vigour at the end of the working day. Lunch breaks with the supervisor predicted a lower level of vigour at the end of the working day, but a higher level of vigour after lunch break. Lunch breaks with colleagues were unrelated to vigour after lunch break, but associated with higher vigour at the end of a working day. The companionship of both—colleagues and supervisors—as well as work-related conversation decreased psychological detachment during lunch break.     

A computational analysis of general intelligence tests for evaluating cognitive development

The progression in several cognitive tests for the same subjects at different ages provides valuable information about their cognitive development. One question that has caught recent interest is whether the same approach can be used to assess the cognitive development of artificial systems. In particular, can we assess whether the ‘fluid’ or ‘crystallised’ intelligence of an artificial cognitive system is changing during its cognitive development as a result of acquiring more concepts? In this paper, we address several IQ tests problems (odd-one-out problems, Raven’s Progressive Matrices and Thurstone’s letter series) with a general learning system that is not particularly designed on purpose to solve intelligence tests. The goal is to better understand the role of the basic cognitive operational constructs (such as identity, difference, order, counting, logic, etc.) that are needed to solve these intelligence test problems and serve as a proof-of-concept for evaluation in other developmental problems. From here, we gain some insights into the characteristics and usefulness of these tests and how careful we need to be when applying human test problems to assess the abilities and cognitive development of robots and other artificial cognitive systems.     

How identity related goals moderate the role of attributes in product evaluation

This research examines how identity related goals influence product evaluation. It is proposed that products are evaluated based on an attribute level to fulfill an identity related goal. Further, the positive relationship between an attribute level and product evaluation is strengthened by goal activation (the degree to which a goal occupies a consumer's thinking) and goal‐product fit (the extent to which consumers think a product is related to a particular goal). Results of three experimental studies support the above propositions. The research makes contributions in that it identifies two moderators, that is, goal activation and goal‐product fit, in the relationship between attributes ability and product evaluation. First, identity‐related goals are higher order and likely to have higher priority for consumers. However, results in this paper show that it still needs to be activated before it can exert an influence on attribute importance. Specifically, when an identity related goal (e.g., one supportive of the fair trade goal) is activated, it takes over a lower‐order goal (e.g., seek for a good taste or a good priced coffee in this case). As goal activation increases, relevant attributes become more important, and the positive relationship between an attribute level and product evaluation strengthens. Second, this paper introduces a new construct of goal‐product fit into identity‐related goals and product evaluation literature. The results of study three suggest that when goal‐product fit becomes stronger, the relevant attribute that can fulfill the goal becomes more important in the overall product evaluation.