scholarly journals UniMiB AAL: An Android Sensor Data Acquisition and Labeling Suite

2018 ◽  
Vol 8 (8) ◽  
pp. 1265 ◽  
Author(s):  
Davide Ginelli ◽  
Daniela Micucci ◽  
Marco Mobilio ◽  
Paolo Napoletano

In recent years, research on techniques to identify and classify activities of daily living (ADLs) has significantly grown. This is justified by the many application domains that benefit from the application of these techniques, which span from entertainment to health support. Usually, human activities are classified by analyzing signals that have been acquired from sensors. Inertial sensors are the most commonly employed, as they are not intrusive, are generally inexpensive and highly accurate, and are already available to the user because they are mounted on widely used devices such as fitness trackers, smartphones, and smartwatches. To be effective, classification techniques should be tested and trained with datasets of samples. However, the availability of publicly available datasets is limited. This implies that it is difficult to make comparative evaluations of the techniques and, in addition, that researchers are required to waste time developing ad hoc applications to sample and label data to be used for the validation of their technique. The aim of our work is to provide the scientific community with a suite of applications that eases both the acquisition of signals from sensors in a controlled environment and the labeling tasks required when building a dataset. The suite includes two Android applications that are able to adapt to both the running environment and the activities the subject wishes to execute. Because of its simplicity and the accuracy of the labeling process, our suite can increase the number of publicly available datasets.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
José Antonio Santoyo-Ramón ◽  
Eduardo Casilari-Pérez ◽  
José Manuel Cano-García

AbstractWearable Fall Detection Systems (FDSs) have gained much research interest during last decade. In this regard, Machine Learning (ML) classifiers have shown great efficiency in discriminating falls and conventional movements or Activities of Daily Living (ADLs) based on the analysis of the signals captured by transportable inertial sensors. Due to the intrinsic difficulties of training and testing this type of detectors in realistic scenarios and with their target audience (older adults), FDSs are normally benchmarked against a predefined set of ADLs and emulated falls executed by volunteers in a controlled environment. In most studies, however, samples from the same experimental subjects are used to both train and evaluate the FDSs. In this work, we investigate the performance of ML-based FDS systems when the test subjects have physical characteristics (weight, height, body mass index, age, gender) different from those of the users considered for the test phase. The results seem to point out that certain divergences (weight, height) of the users of both subsets (training ad test) may hamper the effectiveness of the classifiers (a reduction of up 20% in sensitivity and of up to 5% in specificity is reported). However, it is shown that the typology of the activities included in these subgroups has much greater relevance for the discrimination capability of the classifiers (with specificity losses of up to 95% if the activity types for training and testing strongly diverge).


Author(s):  
Daniela Micucci ◽  
Marco Mobilio ◽  
Paolo Napoletano

Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being increasingly used to monitor human activities. Data acquired by the hosted sensors are usually processed by machine-learning-based algorithms to classify human activities. The success of those algorithms mostly depends on the availability of training (labeled) data that, if made publicly available, would allow researchers to make objective comparisons between techniques. Nowadays, publicly available data sets are few, often contain samples from subjects with too similar characteristics, and very often lack of specific information so that is not possible to select subsets of samples according to specific criteria. In this article, we present a new smartphone accelerometer dataset designed for activity recognition. The dataset includes 11,771 activities performed by 30 subjects of ages ranging from 18 to 60 years. Activities are divided in 17 fine grained classes grouped in two coarse grained classes: 9 types of activities of daily living (ADL) and 8 types of falls. The dataset has been stored to include all the information useful to select samples according to different criteria, such as the type of ADL performed, the age, the gender, and so on. Finally, the dataset has been benchmarked with two different classifiers and with different configurations. The best results are achieved with k-NN classifying ADLs only, considering personalization, and with both windows of 51 and 151 samples.


2019 ◽  
Vol 17 (1) ◽  
pp. 55-68
Author(s):  
Fitri Ummu Habibah

Da'wah is a process of delivering or certain ways that a da'i tells mad'u to achieve a goal on the basis of wisdom and compassion. At this time many da'i appeared in the midst of society, conveying their da'wah with special methods so as to attract the attention of the public. Of the many da'i who were able to make mad'u amazed at his distinctive style of speech when delivering his da'wah material was KH. Yahya Zainul Ma'arif (hereinafter referred to as Buya Yahya). He is a person who has a friendly nature, it can be seen from the look on his face in each conveying his preaching and his attitude that appears when interacting directly with the worshipers. This research is a subject research and missionary activity. The purpose of the study was to find out the method of da'wah KH. Yahya Zainul Ma'arif. This type of research is a character qualitative study with taxonomic analysis specifications. The design of taxonomic analysis is to describe the subject domain of research and all aspects that shape its role in the field of Islamic da'wah. The results of the study showed that the da'wah method used by KH. Yahya Zainul Ma'arif is a tabligh method. Tabligh is done by forming a lecture assembly. After the tabligh was conducted, Buya Yahya developed tabligh by doing cadre. The cadre was carried out by means of tarbiyah from this tarbiyah. Ulama will emerge who will continue the missionary mission in the future. Therefore, Buya Yahya founded the Islamic Boarding School Islamic Boarding School (LPD) al Bahjah. Actually in tabligh activity, Buya Yahya explores the potential to invite tabligh together. In bertabligh also uses a variety of media, such as sound systems and other media, such as radio, TV, live streaming, facebook, Instagram, android applications (Buya Yahya in the playstore) and the web so that the tabligh reaches the wider community. The tabligh method includes four things, namely al hikmah, mauidzah al hasanah and mujadalah and question and answer


Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 768
Author(s):  
Caetano Mazzoni Ranieri ◽  
Scott MacLeod ◽  
Mauro Dragone ◽  
Patricia Amancio Vargas ◽  
Roseli Aparecida Francelin Romero 

Worldwide demographic projections point to a progressively older population. This fact has fostered research on Ambient Assisted Living, which includes developments on smart homes and social robots. To endow such environments with truly autonomous behaviours, algorithms must extract semantically meaningful information from whichever sensor data is available. Human activity recognition is one of the most active fields of research within this context. Proposed approaches vary according to the input modality and the environments considered. Different from others, this paper addresses the problem of recognising heterogeneous activities of daily living centred in home environments considering simultaneously data from videos, wearable IMUs and ambient sensors. For this, two contributions are presented. The first is the creation of the Heriot-Watt University/University of Sao Paulo (HWU-USP) activities dataset, which was recorded at the Robotic Assisted Living Testbed at Heriot-Watt University. This dataset differs from other multimodal datasets due to the fact that it consists of daily living activities with either periodical patterns or long-term dependencies, which are captured in a very rich and heterogeneous sensing environment. In particular, this dataset combines data from a humanoid robot’s RGBD (RGB + depth) camera, with inertial sensors from wearable devices, and ambient sensors from a smart home. The second contribution is the proposal of a Deep Learning (DL) framework, which provides multimodal activity recognition based on videos, inertial sensors and ambient sensors from the smart home, on their own or fused to each other. The classification DL framework has also validated on our dataset and on the University of Texas at Dallas Multimodal Human Activities Dataset (UTD-MHAD), a widely used benchmark for activity recognition based on videos and inertial sensors, providing a comparative analysis between the results on the two datasets considered. Results demonstrate that the introduction of data from ambient sensors expressively improved the accuracy results.


Author(s):  
Daniela Micucci ◽  
Marco Mobilio ◽  
Paolo Napoletano

Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being increasingly used to monitor human activities. Data acquired by the hosted sensors are usually processed by machine-learning-based algorithms to classify human activities. The success of those algorithms mostly depends on the availability of training (labeled) data that, if made publicly available, would allow researchers to make objective comparisons between techniques. Nowadays, publicly available data sets are few, often contain samples from subjects with too similar characteristics, and very often lack of specific information so that is not possible to select subsets of samples according to specific criteria. In this article, we present a new smartphone accelerometer dataset designed for activity recognition. The dataset includes 11,771 activities performed by 30 subjects of ages ranging from 18 to 60 years. Activities are divided in 17 fine grained classes grouped in two coarse grained classes: 9 types of activities of daily living (ADL) and 8 types of falls. The dataset has been stored to include all the information useful to select samples according to different criteria, such as the type of ADL performed, the age, the gender, and so on. Finally, the dataset has been benchmarked with two different classifiers and with different configurations. The best results are achieved with k-NN classifying ADLs only, considering personalization, and with both windows of 51 and 151 samples.


2014 ◽  
Vol 11 (01) ◽  
pp. 35-42
Author(s):  
M. Hermans

SummaryThe author presents his personal opinion inviting to discussion on the possible future role of psychiatrists. His view is based upon the many contacts with psychiatrists all over Europe, academicians and everyday professionals, as well as the familiarity with the literature. The list of papers referred to is based upon (1) the general interest concerning the subject when representing ideas also worded elsewhere, (2) the accessibility to psychiatrists and mental health professionals in Germany, (3) being costless downloadable for non-subscribers and (4) for some geographic aspects (e.g. Belgium, Spain, Sweden) and the latest scientific issues, addressing some authors directly.


Author(s):  
Pierre Iselin

Pierre Iselin broaches the subject of early modern music and aims at contextualising Twelfth Night, one of Shakespeare’s most musical comedies, within the polyphony of discourses—medical, political, poetic, religious and otherwise—on appetite, music and melancholy, which circulated in early modern England. Iselin examines how these discourses interact with what the play says on music in the many commentaries contained in the dramatic text, and what music itself says in terms of the play’s poetics. Its abundant music is considered not only as ‘incidental,’ but as a sort of meta-commentary on the drama and the limits of comedy. Pinned against contemporary contexts, Twelfth Night is therefore regarded as experimenting with an aural perspective and as a play in which the genre and mode of the song, the identity and status of the addressee, and the more or less ironical distance that separates them, constantly interfere. Eventually, the author sees in this dark comedy framed by an initial and a final musical event a dramatic piece punctuated, orchestrated and eroticized by music, whose complex effects work both on the onstage and the offstage audiences. This reflection on listening and reception seems to herald an acoustic aesthetics close to that of The Tempest.


2021 ◽  
Author(s):  
Andi Asrifan ◽  
Abd Ghofur

Anyone who wants to get ahead in academic or professional life today knows that it’s a question of publish or perish. This applies to colleges, universities, and even hospital Trusts. Yet writing for publication is one of the many skills which isn’t formally taught. Once beyond undergraduate level, it’s normally assumed that you will pick up the necessary skills as you go along.Writing for Academic Journalsseeks to rectify this omission. Rowena Murray is an experienced writer on the subject (author of How to Write a Thesis and How to Survive Your Viva) and she is well aware of the time pressures people are under in their professional lives. What she has to say should be encouraging for those people in ‘new’ universities, people working in disciplines which have only recently been considered academic, and those in professions such as the health service which are under pressure to become more academic.


2020 ◽  
Vol 384 (2) ◽  
pp. 222-232
Author(s):  
P. V. Menshikov ◽  
G. K. Kassymova ◽  
R. R. Gasanova ◽  
Y. V. Zaichikov ◽  
V. A. Berezovskaya ◽  
...  

A special role in the development of a pianist as a musician, composer and performer, as shown by the examples of the well-known, included in the history of art, and the most ordinary pianists, their listeners and admirers, lovers of piano music and music in general, are played by moments associated with psychotherapeutic abilities and music features. The purpose of the study is to comprehend the psychotherapeutic aspects of performing activities (using pianists as an example). The research method is a theoretical analysis of the psychotherapeutic aspects of performing activities: the study of the possibilities and functions of musical psychotherapy in the life of a musician as a “(self) psychotherapist” and “patient”. For almost any person, music acts as a way of self-understanding and understanding of the world, a way of self-realization, rethinking and overcoming life's difficulties - internal and external "blockages" of development, a way of saturating life with universal meanings, including a person in the richness of his native culture and universal culture as a whole. Art and, above all, its metaphorical nature help to bring out and realize internal experiences, provide an opportunity to look at one’s own experiences, problems and injuries from another perspective, to see a different meaning in them. In essence, we are talking about art therapy, including the art of writing and performing music - musical psychotherapy. However, for a musician, music has a special meaning, special significance. Musician - produces music, and, therefore, is not only an “object”, but also the subject of musical psychotherapy. The musician’s training includes preparing him as an individual and as a professional to perform functions that can be called psychotherapeutic: in the works of the most famous performers, as well as in the work of ordinary teachers, psychotherapeutic moments sometimes become key. Piano music and performance practice sets a certain “viewing angle” of life, and, in the case of traumatic experiences, a new way of understanding a difficult, traumatic and continuing to excite a person event, changing his attitude towards him. It helps to see something that was hidden in the hustle and bustle of everyday life or in the patterns of relationships familiar to a given culture. At the same time, while playing music or learning to play music, a person teaches to see the hidden and understand the many secrets of the human soul, the relationships of people.


2017 ◽  
pp. 527-537
Author(s):  
Aleksandra Ljustina

Migration is one of the oldest and most used strategies for overcoming negative social issues. Despite the fact that it is historically deeply rooted, environmental migration as a social phenomenon has only recently become the subject research of numerous scientific fields. However, the study of current environmental migration is characterized by a number of issues, such as absence of an adequate definition and multi-causality of environmental migration. In this paper, through conceptual framework, author analyzed two main questions: who are environmental migrants and what reasons cause environmental migration. Due to the destruction of the global environmental balance, as well as accumulated environmental disturbances, it is likely that environmental migration will increase in future and there is nowhere you cannot make more use of scientific and professional projection of the future than in demographic and environmental spheres of human life. There is no doubt that our future is unpredictable. However, the environmental factors influencing the pattern of human interaction with the environment must be taken into account when projecting future development of the modern society. Such is the context in which the complex relation among migration, change and the environment has to be studied. In order to establish the basis for controlling environmental migration caused by negative changes in the environment, it is necessary to adopt a consistent strategy instead of ad hoc activities that are being used. In this paper, author analyzed societal response for the challenges caused by environmental migration, specifically regarding actions related to governing environmental migrations.


Sign in / Sign up

Export Citation Format

Share Document