A Continuous Remote Emotional Health Monitoring System for Depressive Illness
Depression is a major health issue that affects over 21 million American men and women each year. Depression often goes unrecognized and untreated, and even once treatment begins it is often difficult to monitor its effectiveness. This poses particular challenges for the diagnosis and treatment of depression, particularly for those who avoid visiting a doctor or therapist due to social stigmas or a lack of energy. Currently, depression diagnosis is often based on subjective screening questionnaires or structured clinical interviews that rely on timely in-person visits as well as accurate recollections by the patient. This makes early detection of depression symptoms exceedingly difficult among this population. Yet early detection and treatment of this debilitating disorder has been shown to improve patient outcomes considerably. Along with depression’s detrimental affect on mood, it can lead to other associated problems because of reduced social interactions, decrease in personal
hygiene, increased alcohol use, and neglect of medications for current medical conditions. Assessment and treatment are often hampered by a lack objective data to corroborate patients’ retroactive self-reports about their current functioning; hence an objective symptom-monitoring tool could complement subject self-report measurement and enhance diagnostic accuracy. This project proposes an experiment with the Wireless Sensor Networks, which has a great future ahead because of their amazing feature to be able to be used wirelessly. We plan to provide a design that is unique and economical to use and features scalability. The main idea of this project is to monitor the patient overnight, which includes disrupted sleeping patterns, movement around the house, etc. which will enable us to generate data that could therefore be used to provide the person some help. So to achieve the above, we make use of Wireless motes which are placed around the house, so as to detect the movement of the person from one place to another and the same strategy could then be implied to figure out the amount of time person spent in that area of the house. This project involves two parts, namely time synchronisation and activity monitoring. Time synchronisation is used to ensure accurate timestamping of movement detection events. Activity monitoring includes sensing movements using sensors, sending the events to the sink, result processing and display by the sink.
The experiment setup
8 x Sentilla Motes
1 x Sentilla Gateway
30.5cm2 Conductive Foam (16 Pieces)
8 x Printed Circuit Breadboards
16 x LM741cn Operational Amplifier
16 x Resistors
A Few Wires
16 pieces of Pressure Pad Sensors will be placed according to the above layout.
126.96.36.199 Detecting events
The main motive of this system is to detect activity or movement of the person (we are monitoring). The design required for such system should be feasible and accurate. To achieve such a system we have designed a Pressure Pad Sensor which makes use of a conductive foam.
Pressure Pad Sensor
The concept behind this Pressure Pad Sensor is as follows:
At the stable state (No/0 Pressure), the conductive foam has a resistance of ~4.5kOhm.
When the pressure is applied on to the Pressure pad, the resistance increases.
Once the applied pressure is removed, the pad’s resistance comes back to its stable state.
Now Since the Sentilla Wireless Motes does not have a Electrical Resistance Sensor, but has a Electric Potential Sensor (Voltage Sensor). So, we converted the resistance to voltage, in such a way that the change in resistance implies a change in voltage, which we could detect through the motes.
So we used the concept of an Operational Amplifier, which is generally used to amplify the voltage but we use it to convert the resistance to voltage. Here is how its done:
RM is a known resistance of 4.64 kOhm and RF is the variable resistance which varies by the applied pressure on the Pressure Pad. This change of resistance varies the output voltage from the amplifier by the following formula:
Vo = Vref * RM / (RM + RF)
where, Vref is the known Voltage from the mote(say 2.5 V). The output Vo can therefore be sensed by the mote and can therefore be used as a motion detector.
Recover time to original state for detecting the second event
The sensor when tested, took a few seconds to come back to its stable state, after being pressurized. This is because of the fact that the increase in resistance that occurred due to the applied works vice-verse too. Which means that when the pressure is removed it indicates that too with a declination of resistance towards its stable state.
What to show on server-side
One of the major components of any software products is the client satisfaction, which also means providing the client with an interface, in our case, an interface that can show the current and previous locations where the person being monitored is moving around.
The red shows current and blue the previous. Once we get the time sequence from the motes in sync, the next step we will take in GUI development will be to show the complete path that the patient has taken.
The log shows the output from the previous processing step. An export function or an API with other programs may be added in the future.