Smart City
ULTRASONIC BIRD DETERRING SYSTEM
AP134 »
The majority of birds under migration do so at night, when the atmosphere is cold and quiet, and they frequently find themselves deviating into cities due to their bright light. Birds are naturally drawn to light, according to scientists, therefore when they fly over a bright metropolis with tall structures at night, they are naturally drawn to it, unknowing that they are in perilous territory. This has a significant impact on avian diversity. In order to curb this complication, we opt for an ultrasonic based bird deterrent system using image processing and cloud technology. The Intel FPGA Cyclone controller was employed in our project. The reason for choosing FPGA Cyclone controller because of its low power consumption, high bandwidth performance, and inexpensive cost. Our target users are people who own sky-scrappers and ornithophiles(bird lovers).
Water Related
Monitoring and Predicting Urban Water Reservoirs
AP135 »
Water scarcity is a global crisis which is faced by many countries across the world. It is one of the most serious risk faced by the world at different sector(social, economic, political and environmental). Around 1.2 billion people, or almost one-fifth of the world's population, live in areas of water scarcity, and 500 million people are approaching this situation. Another 1.6 billion people, or almost one quarter of the world's population, face economic water shortage (where countries lack the necessary infrastructure to take water from rivers and aquifers).
Other: Biodiversity
SGP: AIoT based platform for snow leopard tracking
EM045 »
The goal of this project is to develop an AIoT based platform to detect and track snow leopards in Sanjiangyuan region, China.
Smart City
Word Level Sign Language Detector
AP136 »
Sign language is used by members of deaf community to communicate .Each hand gestures in the language corresponds to a meaning.
In India there are over 5-million deaf people but there are only 250 certified interpreters which is one Interpreter for every 20000 deaf-people .
It is a practically impossible to balance this ratio between Interpreters and Deaf people ,this is where our project comes into action.
We propose "Word Level Sign language Detector " for Indian Sign language by using INCLUDE Dataset which contains 2-3 second videos with the sign mentioned.
This can prove as a Game-Changer for deaf community people to interact with other people.
This detector device can be used in places like Information service centers in railway stations for deaf people to get interact and communicate with people and can get the required information with less effort.This device increases the inclusivity for the deaf people and makes them feel comfortable in public places.
First we are planning to extract key pose features points (body-positions ) and then we feed these videos in to Neural network architecture to find the spatial differences between the frames, with that we think we can build an model to classify the signs to words.
This Word Level Sign language Detector model is finally deployed in FPGA . A camera is connected in FPGA which is placed infront of the signer which captures the real time video of the sign and predicts the respective class of the sign.
Food Related
Smart Embedded System for Food authentication using NIR
AP137 »
Food authentication has become a well-recognized regarding issue in food markets as, nowadays, several customers have to be compelled to be assured spiritual authentication in their food decisions and additionally different protection against counterfeit practices in food industries. Food authentication validates label info regarding the food origin and production method. Food authentication may be a speedily growing field thanks to raising public awareness engross food quality and safety. This paper presents crucial the analytical techniques that square measure used for genuineness analysis, explaining however and why they furnish possible solutions. Classification of various technology relies on genuineness indicators providing insight into forthcoming developments. The planned paradigm system consists of 2 elements. the primary section is that the sensing and therefore the second is knowledge assortment. This extremely integrated device delivers a 6- channel multi-spectral sensing within the near-infrared wavelengths from roughly 610nm to 860nm with fullwidth half-max of 40nm
Smart City
SMART WASTE MANAGEMENT SYSTEM
AP138 »
The project is based on a waste management system, which helps in maintaining environmental hygiene. Overflowing dustbins has always been a problem to the environment. So for a smart lifestyle, cleanliness is needed, and cleanliness begins with the Garbage Bin. This project will help to eradicate or minimize the garbage disposal problem. This process is effectively carried out with the help of IOT, an advanced technology.
Health
Smart Health Care Monitoring Unit for Bed Ridden Patients
AP139 »
A comfortable health monitoring unit which is wearable for
patients is presented .The unit is based on a wearable interface
implemented by temperature sensor, pulse detector, ammonia gas
sensor and accelerometer.
This unit works with existing devices including above mentioned
sensors. They are attached to patients cloth that transmits data in
wireless medium to central monitor.
To continuously monitor the health care aspects such as body
temperature, odour of NH3 gas , activity movement and location
of bed ridden patients.
Smart City
Blending Tech with TEK
AS047 »
As we move forward into a post-climate-change future, temperature regulation proves to be increasingly important for human survival and comfort, which makes up a significant portion of a building’s energy consumption. As such, our project focuses on improving the energy efficiency of temperature regulation in buildings through the use of Traditional Ecological Knowledge and smart-home design (with the help of the Azure cloud).
Ventilation, cooling, and heating account for 33% of energy use in U.S. commercial buildings, which relies upon conventional systems of cooling down air via refrigerants and pushing the air into rooms. However, there are different methods of cooling that utilize more passive properties of airflow. The Eastgate Centre in Zimbabwe is the biggest example of this.
The Eastgate Centre was designed with biomimicry in mind, to emulate the ability of termites to cool down and ventilate their nests while using less energy than conventional systems. It succeeds in this: despite still using high-powered fans, the Eastgate Centre uses only 10% of the energy compared to similarly-sized buildings using air conditioning, and uses 65% of the energy while actively cooling.
However, the Eastgate Centre’s design leaves some room for improvement, such as the usage of fans. Termites are able to do what they do by selectively opening and closing vents in the nest to maximize the flow of cool air. Our project improves upon the Eastgate design by more closely imitating the termite model and utilizing an FPGA-run system that uses actuator-operated windows to control airflow and further reduce energy consumption. It can accomplish this by sensing the temperature outside and inside of the building at the actuator locations, and opening and closing the windows accordingly. By opening the windows when it is cooler outside, the building takes advantage of cross-ventilation to passively draw in cool air without the use of fans. It will not be the same temperature on every side of the building; thus, the system opens the windows only at the specific sensor, and keeps it closed on the hotter sides.
An additional problem with both conventional AC and with the Eastgate Centre design is that they are reactive rather than predictive systems. Our design connects to the Azure cloud to obtain weather forecasts, which it then uses to pre-cool the building. This not only means the cooling system doesn’t work as hard during a specific period of time, but this also helps reduce energy use during an electric grid’s peak hours. It is also easier for the system to cool the building while it is still relatively cool than to do so when it has already become hot.
Overall, our system improves upon previous designs to reduce energy consumption when cooling buildings in three ways: by utilizing passive cross-ventilation as a cooling method, by taking into account the weather forecast, and by using the FPGA to monitor and manage all of these components together. By using an embedded system (the FPGA and the cloud) we are able to create a more proactive and energy efficient system than conventional AC systems.
Water Related
BioCam
AP140 »
Design and build an underwater BioCam for monitoring aquatic life, utilizing DE10Nano
Health
Multimodal analysis of complete behaviour of elderly and differently-abled people
EM046 »
What problem: Our mental health is as important as our physical health. To evaluate a person's overall behaviour, especially for the elderly and the differently-abled people, it is necessary to accurately analyse both physical and mental behaviour. Through the various camera, inertial and location sensors, it is possible to build a complete model which is able to describe the overall behaviour of human beings with details including emotional, physical and environmental aspects. In this project, we aim to address this issue and try to solve it. Furthermore, we will incorporate the advantage of edge computing and build a near-sensor solution that can monitor the overall well being of an individual.
What and how: In this project, we approach solving the problem by designing an efficient Deep Neural Network architecture.
First, in order to perform emotion analysis and correctly classify various human emotions of sadness, happiness or anger, a Convolutional Neural Network (CNN) based model would be designed. Information from camera sensors would be fed into this CNN model, which would correctly classify human emotions.
Next, we would design a hybrid network that employs the advantages of spatially deep CNN and temporally deep Long Short Term Memory (LSTM). This hybrid CNN-LSTM network would be used for analysing various complex human activities including walking, sitting and lying down - all of which would be collected using inertial sensors attached to the human body.
Lastly, a final deep neural network (DNN) model would be designed, which would combine the processed information of an individual's emotional analysis and activity recognition. This NN model would be crucial to accurately analyse the overall well being of the individual, for example, whether the person is having a problem while walking or not. When an individual is found to be in any distress - physical or mental, the responsible caregiver would be alerted by a signal or a message sent to him/her.
Today, a majority of the DNNs are implemented on the cloud. This design will remove any drawbacks associated with communication links to the cloud and will use the benefits of edge computing. The concepts of stochastic computing (SC) will be used in order to reduce the hardware resource utilisation of the DNN implementation. SC also reduces the complexity of the individual operations of the neural networks. For example, a multiplier can be implemented by only an AND gate or an XNOR gate and an adder can be implemented by a MUX in SC. This significantly improves this implementation and makes it ideal for edge computing.
Today, a majority of the DNNs are implemented on the cloud. Our design will remove any drawbacks associated with communication links to the cloud and will use the benefits of edge computing.
According to our knowledge, there is no existing autonomous solution that can accurately monitor the overall well being of an individual in their daily lives. In our project, we will design a DNN model which can compute and analyse the information near the sensor and not depend on cloud computing. Our model will be extremely useful in monitoring the health of any individual - especially the elderly and the differently-abled. They would be under constant supervision even if the designated caregiver is not physically present right next to the individual.
The prebuilt face and object detection models will be used . We would use the smart camera and these prebuilt algorithms would help us to correctly analyse the emotions and locality of the individual under supervision. Another advantage of using the provided kit with the FPGA board is to be able to parallekize our CNN and hybrid CNN-LSTM models, as there is no data dependency between them. The video processing based emotion analysis can be done much faster compared to CPU or GPU implementations by using the concepts of pipelining. The SD card would be loaded with sensor signal data and these data would then be processed by the neural networks. The CNN model will be used to process the data from the camera sensor and analyse the video frames and detect people, their emotions and also their locality. The inertial sensor data will be fed to the CNN- LSTM model that will correctly analyse human activities. The final DNN would then use the already processed information and provide a complete description combination for our models to run faster and better.
Water Related
Irrigation Truth
AS048 »
We propose to develop a miniature and low power Soil Moisture Radar (SMR) designed to be mounted on either a land based farm tractor or a low flying airborne platform such as a drone. A GPS module will allow the system to construct soil moisture maps during normal daily farm operation. These maps will allow managers to view the field as a whole and to identify irrigation patterns that are not as easily recognized at ground level, reducing water use and allowing selective crop irrigation thereby reducing water consumption and increasing crop yield.
Food Related
FarmoDictor
AP141 »
Maintaining soil fertility is essential for the prosperity and sustainability of any agricultural system. With the rise in population and increase in food demand, soil fertility management is essential. Lack of resources and improper soil management was the main cause of the problem resulting in soil degradation and nutrient, hence a decrease in productivity.
Accordingly, the objective of the project will be, to estimate the soil fertility on a real-time basis and to give suggestions regarding the suitable crop to be grown on a particular land along with fertilizer and compost usage. This project will educate the farmers about the variety of crops that can be grown on the soil which can have several financial and environmental benefits.
The project will provide crop advisory to the farmers by taking various factors such as weather conditions, soil nutrients, moisture levels and land type into consideration. The whole system will consist of a Hardware Device, Cloud Database and a Mobile Application and a Website. The Hardware device will be integrated with Soil Nutrient Sensors that will detect the macronutrients such as Nitrogen, Phosphorous and Potassium along with Soil pH, through the principle of Electrical conductivity. The device will also record real-time soil moisture, atmospheric temperature and humidity levels, rainfall, wind and light intensities which will be fed to the Cloud for further analysis. Later on, the collected data will be analyzed in the Cloud and a list of suitable crops that could produce better yield will be provided along with the amount of fertilizer to be used according to the crop type. In the Mobile application, climatic conditions and other geographical features along with the detailed soil nutrient report will be displayed on a real-time basis. Farmers will also be notified to perform soil tests regularly over a particular period, and the required amount of fertilizer will be suggested. It will also connect the farmers to agricultural experts for providing support and improving their overall yield.
Through this project, we are trying to break the rice-wheat monocultural practices which in turn reduces the pressure on the water table as rice and wheat, which are among the most water-consuming crops. Also, as the farmers would get a better understanding of the type and amount of fertilisers that can be used in the soil, this could lead to a reduction in soil and groundwater pollution. Variation in cropping patterns can also increase the income of farmers and improve their financial condition. Lastly, as the buffer stocks are filled with a variety of crops, the prices of these crops will go down in the market and benefit the consumers as well.