Tumor movements should be accurately predicted to improve delivery accuracy and reduce unnecessary radiation exposure to healthy tissue during radiotherapy. The tumor movements pertaining to respiration are divided into intra-fractional variation occurring in a single treatment session and inter-fractional variation arising between different sessions. Most studies of patients' respiration movements deal with intra-fractional variation. Previous studies on inter-fractional variation are hardly mathematized and cannot predict movements well due to inconstant variation. Moreover, the computation time of the prediction should be reduced. To overcome these limitations, we propose a new predictor for intra- and inter-fractional data variation, called intra- and inter-fraction fuzzy deep learning (IIFDL), where FDL, equipped with breathing clustering, predicts the movement accurately and decreases the computation time. Through the experimental results, we validated that the IIFDL improved root-mean-square error (RMSE) by 29.98% and prediction overshoot by 70.93%, compared with existing methods. The results also showed that the IIFDL enhanced the average RMSE and overshoot by 59.73% and 83.27%, respectively. In addition, the average computation time of IIFDL was 1.54 ms for both intra- and inter-fractional variation, which was much smaller than the existing methods. Therefore, the proposed IIFDL might achieve real-time estimation as well as better tracking techniques in radiotherapy.

Blockchain is a developing technology that can be utilized for secure data storage and sharing. In this work, we examine the cost of Blockchain-based data storage for constrained Internet of Things (IoT) devices. We had two phases in the study. In the first phase, we stored data retrieved from a temperature/humidity sensor connected to an Ethereum testnet blockchain using smart contracts in two different ways: first, appending the new data to the existing data, storing all sensor data; and second, overwriting the new data onto the existing data, storing only a recent portion of the data. In the second phase, we stored simulated data from several sensors on the blockchain assuming sensor data is numeric. We proposed a method for encoding the data from the sensors in one variable and compared the costs of storing the data in an array versus storing the encoded data from all sensors in one variable. We also compared the costs of carrying out the encoding within the smart contract versus outside the smart contract. In the first phase, our results indicate that overwriting data points is more cost-efficient than appending them. In the second phase, using the proposed encoding method to store the data from several sensors costs significantly less than storing the data in an array, if the encoding is done outside the smart contract. If the encoding is carried out in the smart contract, the cost is still less than storing the data in an array, however, the difference is not significant. The study shows that even though expensive, for applications where the integrity and transparency of data are crucial, storing IoT sensor data on Ethereum could be a reliable solution.

The extended Kalman filter (EKF) can be used for the purpose of training nonlinear neural networks to perform desired input-output mappings. To improve the computational requirements of the EKF, Puskorius proposed the decoupled EKF (DEKF) as a practical remedy for the proper management of computational resources. This approach, however, sacrifices computational accuracy of estimates because it ignores the interactions between the estimates of mutually exclusive weights. To overcome such a limitation, therefore, we proposed hybrid implementation based on EKF (HEKF) for respiratory motion estimation, which uses the channel number for the mutually exclusive groups and the coupling technique to compensate the computational accuracy. Moreover, the authors restricted to a DEKF algorithm in which the weights connecting the inputs to a node are grouped together. If there are multiple input training sequences with respect to the time stamp, the complexity can increase by the power of the input channel number. To improve the computational complexity, we split the complicated neural network into a couple of simple neural networks to adjust separate input channels. The experimental results validated that the prediction overshoot of the proposed HEKF was improved by 62.95% in the average prediction overshoot values. The proposed HEKF showed a better performance of 52.40% improvement in the average of the prediction time horizon. We have evaluated that the proposed HEKF can outperform DEKF by comparing the prediction overshoot values, the performance of the tracking estimation value, and the normalized root-mean-squared error.

Objective: To introduce an MRI in-plane resolution enhancement method that estimates High-Resolution (HR) MRIs from Low-Resolution (LR) MRIs. Method & Materials: Previous CNN-based MRI super-resolution methods cause loss of input image information due to the pooling layer. An Autoencoder-inspired Convolutional Network-based Super-resolution (ACNS) method was developed with the deconvolution layer that extrapolates the missing spatial information by the convolutional neural network-based nonlinear mapping between LR and HR features of MRI. Simulation experiments were conducted with virtual phantom images and thoracic MRIs from four volunteers. The Peak Signal-to-Noise Ratio (PSNR), Structure SIMilarity index (SSIM), Information Fidelity Criterion (IFC), and computational time were compared among: ACNS; Super-Resolution Convolutional Neural Network (SRCNN); Fast Super-Resolution Convolutional Neural Network (FSRCNN); Deeply-Recursive Convolutional Network (DRCN). Results: ACNS achieved comparable PSNR, SSIM, and IFC results to SRCNN, FSRCNN, and DRCN. However, the average computation speed of ACNS was 6, 4, and 35 times faster than SRCNN, FSRCNN, and DRCN, respectively under the computer setup used with the actual average computation time of 0.15 s per $100\times100$ pixels. Conclusion: The result of this study implies the potential application of ACNS to real-time resolution enhancement of 4D MRI in MRI guided radiation therapy.

Emerging nanotechnology presents great potential to change human society. Nanoscale devices are able to be included with Internet. This new communication paradigm, referred to as Internet of Nanothings (IoNT), demands very short-range connections among nanoscale devices. IoNT raises many challenges to realize it. Current network protocols and techniques may not be directly applied to communicate with nanosensors. Due to the very limited capability of nanodevices, the devices must have simple communication and simple medium sharing mechanism in order to collect the data effectively from nanosensors. Moreover, nanosensors may be deployed at organs of the human body, and they may produce large data. In this process, the data transmission from nanosensors to gateway should be controlled from the energy efficiency point of view. In this paper, we propose a wireless nanosensor network (WNSN) at the nanoscale that would be useful for intrabody disease detection. The proposed conceptual network model is based on On-Off Keying (OOK) protocol and TDMA framework. The model assumes hexagonal cell-based nanosensors deployed in cylindrical shape 3D hexagonal pole. We also present in this paper the analysis of the data transmission efficiency, for the various combinations of transmission methods, exploiting hybrid, direct, and multi-hop methods.

Tracking human motion with multiple body sensors has the potential to promote a large number of applications such as detecting patient motion, and monitoring for home-based applications. With multiple sensors, the tracking system architecture and data processing cannot perform the expected outcomes because of the limitations of data association. For the collaborative and intelligent applications of motion tracking (Polhemus Liberty AC magnetic tracker), we propose a human motion tracking system with multichannel interacting multiple model estimator (MC-IMME). To figure out interactive relationships among distributed sensors, we used a Gaussian mixture model (GMM) for clustering. With a collaborative grouping method based on GMM and expectation-maximization algorithm for distributed sensors, we can estimate the interactive relationship with multiple body sensors and achieve the efficient target estimation to employ a tracking relationship within a cluster. Using multiple models with filter divergence, the proposed MC-IMME can achieve the efficient estimation of the measurement and the velocity from measured datasets of human sensory data. We have newly developed MC-IMME to improve overall performance with a Markov switch probability and a proper grouping method. The experiment results shows that the prediction overshoot error can be improved on average by 19.31% by employing a tracking relationship.