scholarly journals Fall detection for elderly-people monitoring using learned features and recurrent neural networks

2020 ◽  
Vol 1 ◽  
Author(s):  
Daniele Berardini ◽  
Sara Moccia ◽  
Lucia Migliorelli ◽  
Iacopo Pacifici ◽  
Paolo di Massimo ◽  
...  

AbstractElderly care is becoming a relevant issue with the increase of population ageing. Fall injuries, with their impact on social and healthcare cost, represent one of the biggest concerns over the years. Researchers are focusing their attention on several fall-detection algorithms. In this paper, we present a deep-learning solution for automatic fall detection from RGB videos. The proposed approach achieved a mean recall of 0.916, prompting the possibility of translating this approach in the actual monitoring practice. Moreover to enable the scientific community making research on the topic the dataset used for our experiments will be released. This could enhance elderly people safety and quality of life, attenuating risks during elderly activities of daily living with reduced healthcare costs as a final result.

2021 ◽  
Vol 10 (2) ◽  
pp. 129
Author(s):  
Sumalee Sungsri

Thailand is becoming an elderly society like many countries in the world. The number of elderly people is increasing continuously every year. In order to enable the elderly to live with good quality of life in the rapidly changing society, knowledge and information related to their health and living factors are considered to be necessary for them. Therefore, this study was carried out in order to develop a model of knowledge provision for promoting quality of life of the elderly in rural areas of the country. The samples were drawn from every region of the country which included 480 elderly people, 480 elderly caretakers, and 160 people representing the community leaders, community committee members and staff of local government agencies. Both quantitative and qualitative methods were employed for data collection. The study found that there were five areas of knowledge for promoting quality of life of the elderly: physical health, mental health, social relationship, economic, and learning. The model of knowledge provision to the elderly synthesized from the study could enable the elderly to gain necessary knowledge deemed useful for promoting their quality of life. The elderly, the elderly care caretakers and related people were found to be satisfied with the model.


2006 ◽  
Vol 24 (18_suppl) ◽  
pp. 18610-18610
Author(s):  
G. Ferrero ◽  
F. Testore ◽  
S. Milanese ◽  
G. Porcile ◽  
C. Caroti ◽  
...  

18610 Background: Pain is probably under-recognized and under-treated in the Elderly with advanced cancer disease but the effect of a therapy with high potency opioids is not studied so much in geriatric age people. To evaluate efficacy and tollerability of escalating doses of Transdermal Fentanyl (TTS-F) or equipollent doses of oral morphine long acting with Immediate Release Oral Morphine (IROM) as rescue medication for treatment of moderate-severe cancer pain, we have started a Multicentric Observational Analysis in four cancer centres of north-western Italy. Studies of oncological palliation using valid measures of quality of life show that patients may be willing to accept some side effects of treatment as long as they gain relief from tumor-related symptoms Methods: -TIQ (Therapy Impact Questionnaire) -VAS (Visual Analogic Scale): 0 to 10 -Toxicity (WHO criteria) -Geriatric Assessment for pts aged >70 yrs (only at time 0): CIRS (Comorbility Index) IADL/ADL (Instrumental Activities Daily Living/Activities Daily Living). Patients characteristics -159 pts -Total Median Age: 66 yrs (range 38–86) -Median ECOG PS: 1 (range 0–2) -Elderly (>70 yrs): 75. Pain Starting situation -Median starting VAS: 5.5 (range 3–9) -TIQ: depression 70 pts, cachexia 55 pts, dispnoea 40 pts -CIRS (Comorbidity index): comorbidity were present among 66 pts. TTS-Fentanyl starting dose: 25 mcg/h every 72 h (range 25–50 mcg) or oral morphine long acting 60–90 mg plus IROM 10 mg every 4–6 hours for breakthrough pain present in 38 pts Results: -Quickly pain VAS downloading during first two weeks of treatment (median VAS 1) -Analgesic doses were not significantly increased after two months and not exceeded WHO grade 2 -IROM rescue was similar to that observed for the overall population -TIQ, ADL and IADL were not influenced by therapy. Conclusions: High potency opioids (TTS-F or long acting morphine equipollent doses, plus Rescue-IROM) offers durable long term maintenance pain relief wild acceptable toxicity also in elderly people, is particularly useful for cancer pts with compliance problems and may be considered as first-line treatment for moderate/severe cancer pain. No significant financial relationships to disclose.


Author(s):  
Sai Siong Jun ◽  
Hafiz Rashidi Ramli ◽  
Azura Che Soh ◽  
Noor Ain Kamsani ◽  
Raja Kamil Raja Ahmad ◽  
...  

Falls are dangerous and contribute to over 80% of injury-related hospitalization especially amongst the elderly. Hence, fall detection is important for preventing severe injuries and accidental deaths. Meanwhile, recognizing human activity is important for monitoring health status and quality of life as it can be applied in geriatric care and healthcare in general. This research presents the development of a fall detection and human activity recognition system using Threshold Based Method (TBM) and Neural Network (NN). Intentional forward fall and six other activities of daily living (ADLs), which include running, jumping, walking, sitting, lying, and standing are performed by 15 healthy volunteers in a series of experiments. There are four important stages involved in fall detection and ADL recognition, which are signal filtering, segmentation, features extraction and classification. For classification, TBM achieved an accuracy of 98.41% and 95.40% for fall detection and activity recognition respectively whereas NN achieved an accuracy of 97.78% and 96.77% for fall detection and activity recognition respectively.


2018 ◽  
Vol 21 (4) ◽  
pp. 480-487
Author(s):  
Esmeraldino Monteiro de Figueiredo Neto ◽  
José Eduardo Corrente

Abstract Objective: the aim of the present study was to evaluate the quality of life of elderly people enrolled in specialized elderly care centers in Manaus and compare the findings with the results of already published studies. Method: a cross-sectional study was conducted with 741 elderly people enrolled in three of the centers in the city, from November 2015 to March 2017 using a socioeconomic and demographic questionnaire and the Flanagan Quality of Life Scale (FQLS). Interviews were carried out by previously trained physiotherapy students of the Federal University of Amazonas. Results: the majority of the elderly were female, with a mean age of 69±6.6 years, married, retired but still working, with a low income and low educational level. When they assessed their quality of life, however, they appeared satisfied. When compared to populations in other countries and regions of Brazil, despite their low socioeconomic profile, they demonstrated a higher quality of life than populations of developed countries. Some domains of the scale were inverted in relation to the original scale. Conclusion: the results allow us to conclude that even elderly persons with low socioeconomic status are satisfied with their quality of life.


2019 ◽  
Vol 8 (S2) ◽  
pp. 13-16
Author(s):  
S. Divya

Smartphone’s are programmable and embed various sensors; these phones have the potential to change the way how healthcare is delivered. Fall detection is definitely one of the possibilities. Injuries due to falls are dangerous, especially for elderly people, diminishing the quality of life or even resulting in death. This study presents the implementation of a fall detection prototype for the Android-based platform. The proposed system has three components: sensing the accelerometer data from the mobile embedded sensors, learning the relationship between the fall behavior and the collected data, and alerting preconfigured contacts through message while detecting fall. We adopt different fall detection algorithms and conduct various experiments to evaluate performance. The results show that the proposed system can recognize the fall from human activities, such as sitting, walking and standing, with 72.22% sensitivity and 73.78% specificity. The experiment also investigates the impact of different locations where the phone attached. In addition, this study further analyzes the trade-off between sensitivity and specificity and discusses the additional powers consumption of the devices.


Sign in / Sign up

Export Citation Format

Share Document