This research focused on the implementation of a reliable intelligent fall detection system so as to reduce accidental falls among the elderly people. A video-based detection system was used because it preserved privacy while monitoring the activities of the senior citizens. Another advantage of the video-based system is that the senior citizens are able to move freely without experiencing any hassles in wearing them as opposed to portable fall detection sensors so that they can have a more independent and happy life. A scientific research method was employed to improve the existing fall detection systems in terms of reliability and accuracy. This thesis consists of four stages where the first stage reviews the literature on the current fall detection systems, the second stage investigates the various algorithms of these existing fall detection systems, the third stage describes the proposed fall detection algorithm in detecting falls using two distinct approaches. The first approach deals with the use of specific features of the silhouette, an extracted binary map obtained from the subtraction of the foreground from the background, to determine the fall angle (FA), the bounding box (BB) ratio, the Hidden Markov Models (HMM) and the combination of FA, BB, and HMM. The second approach used is the neural network approach which is incorporated in the algorithm to identify a predetermined set of situations such as praying, sitting, standing, bending, kneeling, and lying down. The fourth stage involves the evalua- tion of the developed video-based fall detection system using different metrics which measure sensitivity (i.e. the capacity of the fall detection system to detect as well as declare a fall) and specificity (i.e. the capacity of the algorithm to detect only falls) of this algorithm. The video camera was properly positioned to avoid any occluding objects and also to cover a certain range of motion of the stunt participants performing the falls. The silhouette is extracted using an approximate median filtering approach and the threshold criteria value of 30 pixels was used. Morphological filtering methods that were dilation and erosion were used to remove any spurious noises from the extracted image prior to subsequent feature analysis. Then, this extracted silhouette was scaled and quantised using 8 bits/pixel and compared to the set of predetermined scenarios using a neural network of perceptrons. This neural network was trained based on various situations and the falls of the participants which represent inputs to the neural network algorithm during the neural learning process. In this research study, the built neural network consisted of 600 inputs, as well as 10 neurons in the hidden layer together with 7 distinct outputs which represent the set of predefined situations. Furthermore, an alarm generation algorithm was included in the fall detection algorithm such that there were three states that were STATE NULL (set at 0), STATE LYING (set at 1) and STATE ALL OTHERS (set at 2) and the initial alarm count was set to 90 frames (meaning 3 seconds of recorded consecutive images at 30 frames per second). Therefore, an alarm was generated only when the in-built counter surpassed this threshold of 90 frames to signal that a fall occurred. Following the evaluation stage, it was found that the combination of the first approach fall detection algorithm method (fall angle, bounding box, and hidden Markov) was 89% with specificity and 84.2% with sensitivity which is better than individual performance. Moreover, it was found that the second approach fall detection algorithm method (neural network performance) 94.3% of the scenarios were successfully classified whereby the specificity of the developed algorithm was determined to be 94.8% and the sensitivity was 93.8% which altogether show a promising overall performance of the fall detection video-based intelligent system. Moreover, the developed fall detection system were tested using two types of handicaps such as limping and stumbling stunt participants to observe how well this detection algorithm can detect falls as in the practical situations encountered or present in elderly people. In these cases it was found that about 90.2% of the falls were detected which showed still that the developed algorithm was quite robust and reliable subjected to these two physical handicaps motion behaviours.

Fall among the elderly is an important health issue. Fall detection and movement tracking techniques are therefore instrumental in dealing with this issue. This thesis responds to the challenge of classifying different movement types as a part of a system designed to fulfill the need for a wearable device to collect data for fall and near-fall analysis. Four different fall activities (forward, backward, left and right), three normal activities (standing, walking and lying down) and near-fall situations are identified and detected. Different machine learning algorithms are compared and the best one is used for the real time classification. The comparison is made using Waikato Environment for Knowledge Analysis or in short WEKA. The system also has the ability to adapt to different gaits of different people. A feature selection algorithm is also introduced to reduce the number of features required for the classification problem.

Fall among the elderly is an important health issue. Fall detection and movement tracking techniques are therefore instrumental in dealing with this issue. This thesis responds to the challenge of classifying different movement types as a part of a system designed to fulfill the need for a wearable device to collect data for fall and near-fall analysis. Four different fall activities (forward, backward, left and right), three normal activities (standing, walking and lying down) and near-fall situations are identified and detected. Different machine learning algorithms are compared and the best one is used for the real time classification. The comparison is made using Waikato Environment for Knowledge Analysis or in short WEKA. The system also has the ability to adapt to different gaits of different people. A feature selection algorithm is also introduced to reduce the number of features required for the classification problem.

In this thesis, new computer vision based techniques are proposed to detect falls of an elderly person living alone. This is an important problem in assisted living. Different types of information extracted from video recordings are exploited for fall detection using both analytical and machine learning techniques. Initially, a particle filter is used to extract a 2D cue, head velocity, to determine a likely fall event. The human body region is then extracted with a modern background subtraction algorithm. Ellipse fitting is used to represent this shape and its orientation angle is employed for fall detection. An analytical method is used by setting proper thresholds against which the head velocity and orientation angle are compared for fall discrimination. Movement amplitude is then integrated into the fall detector to reduce false alarms. Since 2D features can generate false alarms and are not invariant to different directions, more robust 3D features are next extracted from a 3D person representation formed from video measurements from multiple calibrated cameras. Instead of using thresholds, different data fitting methods are applied to construct models corresponding to fall activities. These are then used to distinguish falls and non-falls. In the final works, two practical fall detection schemes which use only one un-calibrated camera are tested in a real home environment. These approaches are based on 2D features which describe human body posture. These extracted features are then applied to construct either a supervised method for posture classification or an unsupervised method for abnormal posture detection. Certain rules which are set according to the characteristics of fall activities are lastly used to build robust fall detection methods. Extensive evaluation studies are included to confirm the efficiency of the schemes.

Wearable sensor systems composed of small and light sensing nodes have the potential to revolutionise healthcare. While uptake has increased over time in a variety of application areas, it has been slowed by problems such as lack of infrastructure and the functional capabilities of the systems themselves. An important application of wearable sensors is the detection of falls, particularly for elderly or otherwise vulnerable people. However, existing solutions do not provide the detection accuracy required for the technology to gain the trust of medical professionals. This thesis aims to improve the state of the art in automated human fall detection algorithms through the use of a machine learning based algorithm combined with novel data annotation and feature extraction methods. Most wearable fall detection algorithms are based on thresholds set by observational analysis for various fall types. However, such algorithms do not generalise well for unseen datasets. This has thus led to many fall detection systems with claims of high performance but with high rates of False Positive and False Negative when evaluated on unseen datasets. A more appropriate approach, as proposed in this thesis, is a machine learning based algorithm for fall detection. The work in this thesis uses a C4.5 Decision Tree algorithm and computes input features based on three fall stages: pre-impact, impact and post-impact. By computing features based on these three fall stages, the fall detection algorithm can learn patterns unique to falls. In total, thirteen features were selected across the three fall stages out of an original set of twenty-eight features. Further to the identification of fall stages and selection of appropriate features, an annotation technique named micro-annotation is proposed that resolves annotation-related ambiguities in the evaluation of fall detection algorithms. Further analysis on factors that can impact the performance of a machine learning based algorithm were investigated. The analysis defines a design space which serves as a guideline for a machine learning based fall detection algorithm. The factors investigated include sampling frequency, the number of subjects used for training, and sensor location. The optimal values were found to be10Hz, 10 training subjects, and a single sensor mounted on the chest. Protocols for falls and Activities of Daily Living (ADL) were designed such that the developed algorithms are able to cope under a variety of real world activities and events. A total of 50 subjects were recruited to participate in the data gathering exercise. Four common types of falls in the sagittal and coronal planes were simulated by the volunteers; and falls in the sagittal plane were additionally induced by applying a lateral force to blindfolded volunteers. The algorithm was evaluated based on leave one subject out cross validation in order to determine its ability to generalise to unseen subjects. The current state of the art in the literature shows fall detectors with an F-measure below 90%. The commercial Tynetec fall detector provided an F-measure of only 50% when evaluated here. Overall, the fall detection algorithm using the proposed micro-annotation technique and fall stage features provides an F-measure of 93% at 10Hz, exceeding the performance provided by the current state of the art.

This thesis aims at developing a prototype for a fall detection bracelet that can connect to the cellular network. The bracelet consists of a processing unit, three sensors, a LTE USB modem and a powerbank. The prototype is aimed at elderly people since up to one out of three over the age of 65-years-old fall each year. Besides elderly people this system can be used in activities which involves substantial height, e.g. climbing and roofing. Statistics has shown that most serious consequences are not a direct result of falling, but from the lack of fast assistance and treatment. If a fall is detected a distress signal, in the form of an SMS message, is sent to a predefined emergency contact. The contents of the SMS messages includes time and date of fall, ambient temperature, fall location coordinates as well as an URL that redirects to the location as seen in Google Maps. The fall detection algorithm is threshold based and was created by first analyzing falls in different direction. It can successfully identify 74,4% of all falls, but as good as up to 91% of falls that are either backwards, forwards or to the left given that the bracelet is attached to the left wrist. The algorithm can further filter out 100% of studied activities that are not falls. Such activities include walking, running and sitting down. This gives an overall Accuracy of 93% for the system. The Accuracy takes into account how well a fall is detected and how well other activities are filtered out. Furthermore, the bracelet was worn for 40 hours, spread out over 11 days, in order to capture data during this persons every day life. During this time no false distress signal was sent to the emergency contact. Limitations of the system has been found to be the GPS module and the fact that the algorithm is threshold based. The location tracking can be improved by utilizing AGPS, which is the same technique that cellphones use. The threshold based system can't be circumvent in a wearable device solution. From this thesis it is indicated that a wearable bracelet can be a reliable fall detection unit. With more extensive falls and field testing even better results can be achieved and it can eventually be pushed as a real product.

By far the biggest injury risk faced by people with late onset dementia is a serious fall. Commercial fall detectors are available which automatically alert a call centre or carer if they detect a fall. They use accelerometers to look for the kinematics of a fall but this method is unreliable and the frequent false alarms must be cancelled by the wearer. This is inappropriate for someone with dementia. This thesis examines how a wrist-worn fall detector better suited to someone with dementia might be built. It reviews what other sensors could be used alongside accelerometers, and whether looking for the physiological effects of falling might be beneficial. It concludes that the pulse provides a source of data and describes three empirical trials to examine whether the body pose can be determined from the pulse waveform. A small convenience sample proved the viability of the concept, followed by a larger study to investigate it further, and finally a trial in people of the same age group as late onset dementia sufferers. Producing a technically better device is not sufficient, as it must also be usable by the people it is intended for. The thesis describes two qualitative studies which use carers to define, and then evaluate, a conceptual fall detector suitable for people with moderate or severe dementia which fits underneath a wrist watch. The thesis argues that wearable fall detectors should utilise physiological data to complement kinematic data. It demonstrates the practicality of a novel technique for determining body position using the pulse waveform, and finally concludes that it would be possible to build the conceptual fall detector utilising this technique.

No description available.

Injuries associated with fall accidents pose a significant health problem to society, both in terms of human suffering and economic losses. Existing fall intervention approaches are facing various limitations. This dissertation presented an effort to advance indirect type of injury prevention approach. The overall objective was to develop a new fall event detection algorithm and a new integrative ambulatory measurement (IAM) framework which could further improve the fall detection algorithm's performance in detecting slip-induced backward falls. This type of fall was chosen because slipping contributes to a major portion of fall-related injuries. The new fall detection algorithm was designed to utilize trunk angular kinematics information as measured by Inertial Measurement Units (IMU). Two empirical studies were conducted to demonstrate the utility of the new detection algorithm and the IAM framework in fall event detection. The first study involved a biomechanical analysis of trunk motion features during common Activities of Daily Living (ADLs) and slip-induced falls using an optical motion analysis system. The second study involved collecting laboratory data of common ADLs and slip-induced falls using ambulatory sensors, and evaluating the performance of the new algorithm in fall event detection. Results from the current study indicated that the backward falls were characterized by the unique, simultaneous occurrence of an extremely high trunk extension angular velocity and a slight trunk extension angle. The quadratic form of the two-dimensional discrimination function showed a close-to-ideal overall detection performance (AUC of ROCa = 0.9952). The sensitivity, specificity, and the average response time associated with the specific configuration of the new algorithm were found to be 100%, 95.65%, and 255ms, respectively. The individual calibration significantly improved the response time by 2.4% (6ms). Therefore, it was concluded that slip-induced backward fall was clearly distinguishable from ADLs in the trunk angular phase plot. The new algorithm utilizing a gyroscope and orientation sensor was able to detect backward falls prior to the impact, with a high level of sensitivity and specificity. In addition, individual calibration provided by the IAM framework was able to further enhance the fall detection performance. / Ph. D.

No description available.