Professional Documents
Culture Documents
Bed Fall Prediction System CONFERENCE PAPER - V4
Bed Fall Prediction System CONFERENCE PAPER - V4
Bed Fall Prediction System CONFERENCE PAPER - V4
*Note: Sub-titles are not captured in Xplore and should not be used
line 1: 1st Given Name Surname line 1: 2nd Given Name Surname line 1: 3rd Given Name Surname
line 2: dept. name of organization line 2: dept. name of organization line 2: dept. name of organization
(of Affiliation) (of Affiliation) (of Affiliation)
line 3: name of organization line 3: name of organization line 3: name of organization
(of Affiliation) (of Affiliation) (of Affiliation)
line 4: City, Country line 4: City, Country line 4: City, Country
line 5: email address or ORCID line 5: email address or ORCID line 5: email address or ORCID
line 1: 4th Given Name Surname line 1: 5th Given Name Surname line 1: 6th Given Name Surname
line 2: dept. name of organization line 2: dept. name of organization line 2: dept. name of organization
(of Affiliation) (of Affiliation) (of Affiliation)
line 3: name of organization line 3: name of organization line 3: name of organization
(of Affiliation) (of Affiliation) (of Affiliation)
line 4: City, Country line 4: City, Country line 4: City, Country
line 5: email address or ORCID line 5: email address or ORCID line 5: email address or ORCID
Abstract—Patients with impaired mobility and neurological Bed rails are the most common existing solution to this
disorders such as Alzheimer’s disease, Parkinson’s disease, problem. However, In [2], it can be seen that statistically,
dementia etc. are vulnerable to bed falls which can be
damaging to their physical and psychological well-being. 60-70% of hospital accidents and 80% of home accidents
Existing systems are mostly fall detection based with wearable are bed falls and even with bed rails, 50-90% of bed falls
devices which can be uncomfortable to wear or ambient still occur. Therefore, approaching this growing problem
devices such as cameras that invade privacy. The proposed
with technological assistance makes the solution more
system in this paper, is designed thoughtfully to tackle these
issues. The system can identify the patient’s different on-bed reliable. The problem has been widely recognized and
positions, via force sensitive resistors, to determine the several existing fall detection and prediction systems have
possibility of bed falls. In case of any risky position, the been developed and a generic classification of similar
caretaker will be alerted to mobile applications via the Internet
of Things (IoT), making patient monitoring more accessible systems have been discussed in [2].
and manageable. This integrated system yields an average of
92% accuracy for 5 different on-bed positions. The bed fall This article is divided into the following sections. Section II
prediction system will facilitate caretakers/nurses to take care covers the background and related existing bed fall
of them conveniently at homes, hospitals and assisted care prediction systems and its literature gap. Section III
facilities to ensure their health and safety.
overviews the experimental setup. Methodology with its
Keywords—bed falls; force sensitive resistors; prediction subdivisions — system overview, sensor layout/placement,
system; remote monitoring; Internet of Things prediction algorithm and optimization, and error evaluation
I. INTRODUCTION — are discussed in Section IV. Section V provides the
results and its analysis. Finally, the paper is concluded in
Falling off a bed is a frequent and dangerous accident that
Section VI.
can result in severe physical and emotional damage. Patients
with both neurological and motor system disorders require II. RELATED WORK
special attention when they are lying down on the bed.
Ibrahim et al. [2] studied several systems related to bed falls
Conditions such as Parkinson’s disease, dementia, impaired
and divided them into three categories depending on their
mobility, and even old age can make them vulnerable to bed
sensor placement: wearable systems, non-wearable systems,
falls and it is a common concern of the caretakers of the
and fusion systems. Furthermore, the global categorization
patients for their well-being and safety, especially in the
of analytical methods was discussed to process the data
absence of nursing personnel at night. According to research
collected from the sensors. The methods are as follows:
in [1], about 25% of the population is above the age of 65
Rule-based Method (RM has a guideline of rules),
and as mentioned in [2], it is expected to reach 1.4 billion by
Threshold-based Method (THM has threshold values fixed),
the year 2030 and 2.1 billion by 2050. There is a significant
and Machine Learning-based Method (MLM) based on
gap in the ratio of nursing personnel to patients in most
classification algorithms).
hospitals and assisted living facilities [3]. Especially at night
shifts when fewer nursing personnel are stationed [4], bed Choi et al. [5] proposed a design where an accelerometer
falls occur more often. Thus, it is difficult to monitor and had been attached to the patient’s chest and a
stay beside patients at all times. threshold-based analytical method was used to determine
the prediction. The system was very fast and low cost;
however, the wearable design can be uncomfortable to wear
𝑇𝑃
Precision = 𝑇𝑃 + 𝐹𝑃
(1)
𝑇𝑝
Recall = 𝑇𝑃 + 𝐹𝑁
(2)
𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 × 𝑅𝑒𝑐𝑎𝑙𝑙
F1 score = 2 × 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 + 𝑅𝑒𝑐𝑎𝑙𝑙
(3)
𝑇𝑃
F1 score = 1 (4)
𝑇𝑃 + 2
(𝐹𝑃 + 𝐹𝑁)
[5] W.-C. Chou, W.-Y. Lin, M.-Y. Lee, and K. F. Lei, “Design and
assessment of a real-time accelerometer-based lying-to-sit sensing
system for bed fall prevention,” in Proc. IEEE Int. Conf. Syst., Man,
Cybern., Oct. 2013, pp. 1471–1475.
[12] “Blynk IoT platform: for businesses and developers,” Blynk IoT
platform: for businesses and developers. https://blynk.io/