A Novel Hybrid Deep Learning Model for Human Activity Recognition Based on Transitional Activities

In recent years, a plethora of algorithms have been devised for efficient human activity recognition. Most of these algorithms consider basic human activities and neglect postural transitions because of their subsidiary occurrence and short duration. However, postural transitions assume a significant part in the enforcement of an activity recognition framework and cannot be neglected. This work proposes a hybrid multi-model activity recognition approach that employs basic and transition activities by utilizing multiple deep learning models simultaneously. For final classification, a dynamic decision fusion module is introduced. The experiments are performed on the publicly available datasets. The proposed approach achieved a classification accuracy of 96.11% and 98.38% for the transition and basic activities, respectively. The outcomes show that the proposed method is superior to the state-of-the-art methods in terms of accuracy and precision.

Stability and Variability of Indoor Room Transitions and Mild Cognitive Impairment in Older Adults

Indoor room transition is an underexplored real-world activity outcome. We estimated the stability and variability of indoor room transitions and their associations with mild cognitive impairment (MCI) in older adults. Older adults living-alone (n=159, age=78.3±8.8 years, 14% MCI) from the Oregon Center for Aging & Technology (ORCATECH) and the Minority Aging Research Study (MARS) were included. Room transitions were detected using passive infrared motion sensors in bathroom, bedroom, kitchen, and living room. The hourly number of room transitions was used to calculate the interdaily stability and intradaily variability of room transitions. MCI was operationalized by the Clinical Dementia Rating equaled 0.5. Generalized estimating equations models adjusted for demographics, health, and environmental factors revealed that older adults with MCI had a lower interdaily stability of room transitions than cognitive healthy peers (z=-2.06,p=0.03). A pervasive-sensing system deployed in homes can obtrusively measure room transition activities to inform cognitive health in older adults.

Barns övergång från förskola till skola

The aim of this study was to investigate the parents’ perspectives of children’s transitions from preschool to school (preschool class and recreation centre) in two Swedish municipalities. The aim was also to investigate the importance of transition activities from the parents’ perspectives. In this study, a transition is understood as a mesosystem, a discontinuity and a non-linear process. A questionnaire with close-ended questions in paper form was constructed and distributed to the parents with the help of the heads and teachers. 131 parents, whose children had recently moved from preschool to school, received the questionnaire, while 70 parents answered it. The data was statistically analysed. The results showed that i) the parents, with few exceptions, experienced children’s transitions as safe and well-functioning, ii) about half of the parents felt some concern or concern in conjunction with the children’s transitions, iii) the parents of children in need of extra support and/or extra stimulation and challenges felt some concern or were concerned more often and iv), overall, the parents considered transition activities to be important. The study has relevance for staff working in preschools and schools, heads and teachers in training, researchers and others interested in educational transitions and transition activities.

Managing your mind: how simple activities within the curriculum can improve undergraduate students' mental health and wellbeing

The transition into higher education stretches students socially, academically and within their personal lives requiring adaptation and development of resilience. For many, such demands may lead to decreased mental well-being and, for some, mental ill-health.This project aimed to trial simple mental health awareness and well-being tasks with first year undergraduate students, and to determine whether students find these interventions beneficial and worthy of embedding as transition activities within the first-year curriculum. Four activities were trialled with 185 first-year students who reported the activities as beneficial. All activities caused an overall increase in student knowledge of how to maintain good mental well-being. In the light of this project’s findings, such activities are recommended for embedding into the first-year curriculum and throughout higher education.

Dual conformational recognition by Z-DNA binding protein is important for the B–Z transition process

Left-handed Z-DNA is radically different from the most common right-handed B-DNA and can be stabilized by interactions with the Zα domain, which is found in a group of proteins, such as human ADAR1 and viral E3L proteins. It is well-known that most Zα domains bind to Z-DNA in a conformation-specific manner and induce rapid B–Z transition in physiological conditions. Although many structural and biochemical studies have identified the detailed interactions between the Zα domain and Z-DNA, little is known about the molecular basis of the B–Z transition process. In this study, we successfully converted the B–Z transition-defective Zα domain, vvZαE3L, into a B–Z converter by improving B-DNA binding ability, suggesting that B-DNA binding is involved in the B–Z transition. In addition, we engineered the canonical B-DNA binding protein GH5 into a Zα-like protein having both Z-DNA binding and B–Z transition activities by introducing Z-DNA interacting residues. Crystal structures of these mutants of vvZαE3L and GH5 complexed with Z-DNA confirmed the significance of conserved Z-DNA binding interactions. Altogether, our results provide molecular insight into how Zα domains obtain unusual conformational specificity and induce the B–Z transition.

Catering for Socio-technical Transformations: Rethinking Technology Policy for Inclusive Transformation

This chapter zooms out from looking at concrete pilot projects to looking more broadly at the implications of discussions on pilot projects as sites of politics. We discuss how such a perspective might feed into the work of innovators, funding bodies and the making of broader technology policy agendas. The chapter highlights the great potential in pilot projects as a mode of innovation for energy transitions, but bring to the fore the way such innovation activities often take on traditional and technology-centred characteristics. We argue that there is a need to change not only the ways that projects are funded to ensure diverse scientific participation. It is equally important to challenge the underlying assumptions and questions asked in pilot activities, as well as the goals of such energy transition activities. This entails a distributed agenda, where actors across the ecology of innovation share responsibilities for moving towards more just, democratic and humane modes of experimenting for sustainability.

Transition Activity Recognition System Based on Standard Deviation Trend Analysis

With the development and popularity of micro-electromechanical systems (MEMS) and smartphones, sensor-based human activity recognition (HAR) has been widely applied. Although various kinds of HAR systems have achieved outstanding results, there are still issues to be solved in this field, such as transition activities, which means the transitional process between two different basic activities, discussed in this paper. In this paper, we design an algorithm based on standard deviation trend analysis (STD-TA) for recognizing transition activity. Compared with other methods, which directly take them as basic activities, our method achieves a better overall performance: the accuracy is over 80% on real data.

Barns övergång från förskola till skola: en multipel fallstudie om övergångsaktiviteter

The aim of this study was to study children’s transitions from preschool to school in two municipalities in Sweden and also activities that were intended to make these transitions effective. A mixed method approach and a multiple-case study design were used. The result showed that children’s transitions from preschool to school differed, that several transition activities were performed, that transition activities were general or extra and also proximal or distal – seen from a child perspective. Several development areas appeared as being particularly important when working towards improvement of preschool-school transitions.

STUDY OF GAIT PATTERN RECOGNITION BASED ON FUSION OF MECHANOMYOGRAPHY AND ATTITUDE ANGLE SIGNAL

The study of lower limb movements plays an important role in many fields, such as rehabilitation and treatment of disabled patients, detection, and monitoring of daily life, as well as the interaction between people and machine, like the application of intelligent prosthetics. In this paper, the wireless device was used to collect the mechanomyography (MMG) signals of four thigh muscles (rectus femoris, vastus lateralis, vastus medialis, and semitendinosus) and the attitude angle of rectus femoris. High precision was achieved in 11 gait movements, including 3 static activities, 4 dynamic transition activities, and 4 dynamic activities. It has been verified that the hidden Markov model (HMM) could not only be applied to the MMG-based gait recognition with high veracity but also support comparative analysis between support vector machine (SVM) and quadratic discriminant analysis (QDA). In addition, the experiment was conducted from the perspectives of feature selections, channel combinations, and muscle contribution rates. The results show that the average classification accuracy of dynamic motions based on MMG is 98.27%, while based on attitude angle, the average recognition rate of static motions and dynamic transition motions could achieve 98.33% and 100%, respectively. Generally, the average recognition rate of 11 gait motions is 98.91%.