ELM-HTM guided bio-inspired unsupervised learning for anomalous trajectory classification

Artificial intelligent systems often model the solutions of typical machine learning problems, inspired by biological processes, because of the biological system is faster and much adaptive than deep learning. The utility of bio-inspired learning methods lie in its ability to discover unknown patterns, and its less dependence on mathematical modeling or exhaustive training. In this paper, we propose a new bio-inspired learning model for a single-class classifier to detect abnormality in video object trajectories. The method uses a simple but dynamic extreme learning machine (ELM) and hierarchical temporal memory (HTM) together referred to as ELM-HTM in an unsupervised way to learn and classify time series patterns. The method has been tested on trajectory sequences in traffic surveillance to find abnormal behaviors such as high-speed, unusual stops, driving in wrong directions, loitering, etc. Experiments have also been performed with 3D air signatures captured using sensors and used for biometric authentication(forged/genuine). The results indicate a significant gain over training time and classification accuracy. The proposed method outperforms in predicting long-time patterns by observing small steps with an average accuracy gain of 15% as compared to the state-of-the-art HTM. The method has applications in detecting abnormal activities in videos by learning the movement patterns as well as in biometric authentication.     

Buying an electric car: A rational choice or a norm-directed behavior?

The diffusion of electric cars can contribute to more sustainability in the transport sector, but diffusion rates in most countries are still low. We investigated motives for electric car adoption in German households from an environmental psychology perspective. The public debate focuses on rational aspects such as the purchase price or new technological demands (e.g., limited range and a new charging system). Psychological research on energy-related investment decisions in households confirms the relevance of rational motives, but additionally points to the importance of norm-directed motives (moral and social norms). We investigated the relevance of different motives in an online questionnaire with n = 220 members of German households interested in buying a new car. The questionnaire included possible rational and norm-related predictors of electric car adoption. We tested three action models to explain adoption intention: An adjusted technology acceptance model (TAM), an adjusted norm activation model (NAM), and an integrative model with predictors from both models. We analyzed the hypothesized models with path analyses. All models explained a substantial share of variance in adoption intention. The explained share of variance in the NAM was higher than in the TAM and comparably high to the integrative model. The results demonstrate the important role of moral and social motives for households’ investment decisions. Additionally, the technology’s perceived usefulness was an important rational motive. We discuss the context dependency of the results, as household members might have little knowledge about the new technology during the early stages of a technology’s diffusion process. The results strongly suggest broadening political support schemes, such as informational and image campaigns, as a way to more effectively foster electric car diffusion. More comprehensive assessments appear to be necessary in future analyses of electric car adoption as well as energy-related investment decisions.     

Life skills development in physical education: A self-determination theory-based investigation across the school term

ObjectivesGrounded in self-determination theory (SDT), the main aim of this study was to examine the longitudinal associations between teacher autonomy support, students’ basic psychological need satisfaction and life skills development in physical education (PE).DesignThis study employed a two-wave longitudinal research design.MethodStudents (N = 266, Mage = 12.94 years, SD = 0.70) completed measures assessing perceived autonomy-supportive teaching, need satisfaction (autonomy, competence, and relatedness), and life skills development in PE (teamwork, goal setting, social skills, problem solving and decision making, emotional skills, leadership, time management, and interpersonal communication). Data collections took place during week 6 (timepoint 1; T1) and week 15 (timepoint 2; T2) of the autumn school term.ResultsCross-lagged panel analyses showed that T1 teacher autonomy support did not significantly predict students’ three basic psychological needs, total need satisfaction or life skills development at T2. Students’ T1 total need satisfaction positively predicted their development of all eight life skills at T2. Additionally, students’ T1 autonomy satisfaction positively predicted their teamwork, social skills, emotional skills, leadership, and interpersonal communication skills at T2, T1 competence satisfaction positively predicted students’ teamwork skills at T2, and students’ T1 relatedness satisfaction positively predicted their social skills at T2.ConclusionsProviding partial support for SDT, the findings highlighted that satisfaction of students’ three basic psychological needs had some positive effects on students’ life skills development in PE. As such, a climate that satisfies students’ basic psychological needs should help to develop their life skills in PE.     

Relationship between environmental factors and burnout of psychotherapists: Meta‐analytic approach

The present study aims to extend the scope of understanding on the relationships between environmental factors and burnout symptoms by targeting and including more extensive occupational demanding variables related to therapist burnout. The present study includes not only common occupational stressors (e.g., working hours, role overload and role conflict) but also variables reflecting the quality of relationship with clients (e.g., case load and negative clientele) that have not been dealt with before in meta‐analytic studies. A meta‐analysis was conducted on 27 original studies published from the year 2006 to 2018. The findings showed that, among environmental factors, role overload had the most significant positive correlations with exhaustion. In addition, negative clientele had the most significant positive correlations with depersonalisation and reduced accomplishment. Furthermore, caseload and low income had relatively weak relations with therapist burnout. Based on these results, implications and limitations of the study are discussed.     

Lasso回归：从解释到预测

传统的最小二乘回归法关注于对当前数据集的准确估计, 容易导致模型的过拟合, 影响模型结论的可重复性。随着方法学领域的发展, 涌现出的新兴统计工具可以弥补传统方法的局限, 从过度关注回归系数值的解释转向提升研究结果的预测能力也愈加成为心理学领域重要的发展趋势。Lasso方法通过在模型估计中引入惩罚项的方式, 可以获得更高的预测准确度和模型概化能力, 同时也可以有效地处理过拟合和多重共线性问题, 有助于心理学理论的构建和完善。     

A thematic analysis of practitioners' understanding of domestic abuse in terms of post‐traumatic stress disorder (PTSD) and complex‐PTSD (C‐PTSD)

There is a growing body of evidence suggesting that domestic abuse (DA) should be conceptualised within the complex post‐traumatic stress disorder (C‐PTSD) model. Recently, in the draft of the International Classification of Diseases, Eleventh Revision, produced by the World Health Organization (WHO), C‐PTSD was included as a separate criterion in which DA is incorporated (ICD‐11, WHO, 2018). In this study, a thematic analysis was used to explore to what extent practitioners working with DA survivors are familiar with PTSD and C‐PTSD. Research into such a prevalent and detrimental problem as DA is important to understand whether the development of theoretical knowledge about DA and C‐PTSD is addressed in practice. In a Women's Centre in South London, six semi‐structured interviews with middle‐aged female practitioners were conducted to investigate each counsellor's experiences, knowledge and reflections. Six final themes were constructed to summarise the main results. The findings demonstrate limited practitioner understanding of DA in terms of C‐PTSD, which seems to impact not only the effectiveness of treatment plans with DA survivors, but also counsellors’ own psychological and physical states. It is also indicated that DA can be conceptualised within the C‐PTSD model that corresponds with previous literature indicating the complex nature of DA. The overall results of the current research acknowledge that DA sectors should not be neglected and better funding and effective psychoeducation in this field are needed.     

内隐创业领导与多层次积极追随力的互动机制

多层次积极追随力是创业企业成长的重要保证。已有研究强调不同显性领导对积极追随力的影响, 结论存在较多争议。对此, 以内隐领导理论为基础, 构建了“内隐创业型领导-积极追随力”的多层次互动模型。根据此模型, 内隐创业型领导通过关系认同和领导代表性对个体与团队积极追随力产生促进作用; 团队积极追随力通过积极心理资本塑造内隐创业型领导; 团队差序氛围、员工传统性和领导特质调节焦点是互动关系重要的边界条件。     

中学教师工作狂类型与工作绩效的关系研究：基于潜在剖面分析

以229名中学教师对研究对象,采用潜在剖面分析方法探索其工作狂类型,并进一步揭示这些类型与工作绩效间的关系。结果表明:（1）教师按工作狂得分可分为三类：重度工作狂、中等偏高工作狂和中等偏低工作狂;（2）不同类别工作狂会对工作绩效产生不同程度的影响。     

变量间的网络分析模型及其应用

变量间的网络分析模型近年来被广泛应用于心理学研究。不同于将潜变量作为观测变量的共同先导因素的潜变量模型, 网络分析模型将观测变量作为初级指标, 采用图论的方法建立观测变量之间的关系网络, 其中变量为网络的节点, 而变量间的关系是节点之间的连线。因此网络分析可以突显观测变量之间的联系以及观测变量相互影响而形成的系统。通过变量网络中基于各个节点特征的指标(如中心性)以及基于整体结构特征的指标(如小世界性), 网络分析为研究各种心理现象提供了新的可视化的描述方式和理解视角。近10年来, 网络分析的方法已在人格心理学、社会心理学和临床心理学等领域得到一定的应用。未来研究应继续发展和完善网络分析模型的理论和方法, 使之运用到更多的数据类型和更广的研究领域中。