The document proposes a cascade-AdaBoost support vector machine (SVM) classifier to complete a triaxial accelerometer-based fall detection method. The method uses acceleration signals from daily activity data to calculate feature values from a sliding window as input vectors. The cascade-AdaBoost-SVM algorithm then self-constructs based on the training vectors, with each AdaBoost layer selecting optimal weak classifiers to form a strong classifier, accelerating testing processing speed by only using selected features. Experimental results using data from ankle, chest, and waist accelerometers showed the proposed method achieved the highest accuracy, detection rate, and lowest false alarm rate compared to other classifiers.

1. TRIAXIAL ACCELEROMETER-BASED FALL DETECTION
METHOD USING A SELF-CONSTRUCTING CASCADEADABOOST-SVM CLASSIFIER
ABSTRACT
In this paper, we propose a cascade-AdaBoost support vector machine (SVM)
classifier to complete the triaxial accelerometer-based fall detection method. The method uses
the acceleration signals of daily activities of volunteers from a database and calculates feature
values. By taking the feature values of a sliding window as an input vector, the cascadeAdaBoost-SVM algorithm can self-construct based on training vectors, and the AdaBoost
algorithm of each layer can automatically select several optimal weak classifiers to form a
strong classifier, which accelerates effectively the processing speed in the testing phase,
requiring only selected features rather than all features. In addition, the algorithm can
automatically determine whether to replace the AdaBoost classifier by support vector
machine. We used the UCI database for the experiment, in which the triaxial accelerometers
are, respectively, worn around the left and right ankles, and on the chest as well as the waist.
The results are compared to those of the neural network, support vector machine, and the
cascade-AdaBoost classifier. The experimental results show that the triaxial accelerometers
around the chest and waist produce optimal results, and our proposed method has the highest
accuracy rate and detection rate as well as the lowest false alarm rate.
EXISTING SYSTEM
Falls are one of the most common adverse events in hospitals and fall management
remains a major challenge in the medical care quality. Falls in patients are associated with
major health complications that can result in health decline and increased medical care cost.
To deliver medical care in time, reliable location-aware fall detection is needed.
PROPOSED SYSTEM
In this paper, we propose a patient alert alarm for fall management. It is SMS
location awareness fall detection system that provides immediate position information to the
care givers as soon as the fall happened. Obviously, the integration of location awareness and

2. fall detection technologies fulfills the requirements of delivering critical information to
relative professions and improve the medical care quality.
This project gives the location awareness such as in-time information about the
location of their patients, doctors, and medical staffs when medical emergencies arise .For
example, inpatients might fall somewhere in the hospital during the midnight, a patient alert
alarm system for fall management provides location information to the night shift nurses.In
this project, we use a location-aware fall detection system by using tri-axial accelerometers as
fall detecting sensors. The proposed system can provide emergency alert and position
information to caregivers through SMS as the patients fall happened.
BLOCK DIAGRAM
APPLICATIONS
1.
Fall detection of patients
2.
Accident awareness
HARDWARE REQUIREMENTS
1.
89C51 microcontroller
2.
Accelerometer sensor

3. 3.
ADC
4.
Power supply
5.
GSM modem
6.
Mobile
SOFTWARE REQUIREMENTS
1.
Keil IDE
2.
Flash magic