Background
Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to sensor errors. As a result, inaccurate CGM readings would affect BG prediction and make it unreliable, even if the most optimal machine learning model is used.
Methods
In this work, we propose a novel approach to predicting blood glucose level with a stacked Long short-term memory (LSTM) based deep recurrent neural network (RNN) model considering sensor fault. We use the Kalman smoothing technique for the correction of the inaccurate CGM readings due to sensor error.
Results
For the OhioT1DM (2018) dataset, containing eight weeks’ data from six different patients, we achieve an average RMSE of 6.45 and 17.24 mg/dl for 30 min and 60 min of prediction horizon (PH), respectively.
Conclusions
To the best of our knowledge, this is the leading average prediction accuracy for the ohioT1DM dataset. Different physiological information, e.g., Kalman smoothed CGM data, carbohydrates from the meal, bolus insulin, and cumulative step counts in a fixed time interval, are crafted to represent meaningful features used as input to the model. The goal of our approach is to lower the difference between the predicted CGM values and the fingerstick blood glucose readings—the ground truth. Our results indicate that the proposed approach is feasible for more reliable BG forecasting that might improve the performance of the artificial pancreas and insulin infusion system for T1D diabetes management.
Due to the inherent property of the processing resource request from mobile active or passive devices as part of internet of things (IoT), processing capacity as well as latency become major optimization criteria. To achieve overall optimized uses of cloud resources -having dynamic tracking, monitoring as well as orchestration framework is one of the key challenges to overcome. In the same context, enhanced uses of computing devices at distributed location is predicted to facilitate the success of IoT; subsequently the success of fifth generation (5G) of Wireless technologies. This opens enormous potential to integrate the unused resources of such distributed computed devices within the conventional cloudlet or cloud federation. However, this requires an efficient micro-level distributed computing resource tracking, monitoring and orchestration; where resources are distributed in geo-location as well as the availability of unused resources are time variant in nature. In this paper, we have proposed a cognitive edge-computing based framework solution for these requirements in order to achieve an efficient use of these distributed resources. This provides the end-user with a dynamic soft extension of computing facilities of cloudlet and cloud federation, as well as a revenue generation avenue to enduser. The simulation results show that such extension can be an exponential function of the number of local processing platforms agreed to participate in the proposed cognitive resource sharing.
Generally, blind people use a traditional cane (known as white cane) for moving from one place to another. Although, white cane is the international symbol of blindness, it could not help them to detect place and to avoid obstacles. In this paper, we represent a model of walking stick for blind people. It consists of GPS module, GPS Antenna, Arduino, ultrasonic sensor and buzzer. This stick can detect place and obstacles. Position detection part is done with GPS module and GPS antenna. Ultrasonic sensor is used for detecting obstacles. Here, the buzzer produces two types of sound. When the blind reaches to his destination, buzzer buzzes continuously. When the blind faces any obstacles, buzzer buzzes with interruption. By discovering these two types of sound, blind can be confirmed about his destination and also can avoid obstacles in front of him. The whole system is designed to be small, light and is used in conjunction with the white cane so that it could ensure safety of the blind.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.