In this paper, a novel terahertz (THz) spectroscopy technique and a new graphene-based sensor is proposed. The proposed sensor consists of a graphene-based metasurface (MS) that operates in reflection mode over a broad range of frequency band (0.2 - 6 THz) and can detect relative permittivity of up to 4 with a resolution of 0.1 and a thickness ranging from 5 μm to 600 μm with a resolution of 0.5 μm. To the best of author's knowledge, such a THz sensor with such capabilities has not been reported yet. Additionally, an equivalent circuit of the novel unit cell is derived and compared with two conventional grooved structures to showcase the superiority of the proposed unit cell. The proposed spectroscopy technique utilizes some unique spectral features of a broadband reflection wave including Accumulated Spectral power (ASP) and Averaged Group Delay (AGD), which are independent to resonance frequencies and can operate over a broad range of spectrum. ASP and AGD can be combined to analyse the magnitude and phase of the reflection diagram as a coherent technique for sensing purposes. This enables the capability to distinguish between different analytes with high precision which, to the best of author's knowledge, has been accomplished for the first time.

Emojis have changed the way humans communicate today. They are the most convenient non-linguistic social cues available to us in this era of social media. But there is no methodology wherein users can creatively interact with their systems to generate personalised emojis or edit existing ones. While there have been some experiments that enable networks to create images, there is no comprehensive solution that gives users the control to create personalised emoticons. In this work, we propose an end-to-end architecture to create a realistic emoji from a roughly drawn sketch. Our generated emojis show a PSNR value of 20.30dB and a SSIM of 0.914. Additionally, we look at a multi-modal architecture which generates an emoji when given an incomplete sketch along with a handwritten word describing the associated emotion.

The proliferation of connected cars globally has the potential to produce torrents of Big Data that will enable improvements in driver safety, new location based services, improvements in vehicle quality, and optimized vehicle designs. One aspect of connected car data involves driving behavior data and its use for Usage Based Insurance (UBI). UBI has become one of the most widely used applications of driving behavior data. Currently, the transmission and processing of high frequency driving behavior data from the connected car to the cloud is limited by wireless data costs and in-vehicle hardware complexity. To alleviate these issues, we detail the development of a machine learning framework utilizing a kinematic classification methodology applied to down sampled time series vehicle data sets for accurate imputation of driving behavior events in UBI applications. The down-sampled data, consisting of 5 second frames with data fields of timestamp, vehicle speed, and vehicle acceleration is classified into unique kinematic clusters to standardize any driving behavior data distributions. Subsequently, machine learning is used to impute harsh driving events for each 5 second frame in select kinematic clusters. This novel machine learning methodology reduced data set sizes by 75%, utilized a limited set of five attributes, and achieved an average precision and recall of 84.5% and 63.5% for two distinct connected car data sets with 1/5 Hz down-sampled data.

Image processing and machine learning have become valuable tools for predictive maintenance applications for a wide variety of industrial and commercial components. We present a novel light transmission image processing methodology utilizing statistical distance algorithms (Wasserstein distance (WD), Kolmogorov-Smirnov statistic (K-S)) for physical attribute correlation combined with Bayesian linear regression to estimate wear level and lifetime prediction for air filters. Robustness of this machine learning algorithm was evaluated using spatial block bootstrapping to generate synthetic training data to estimate the 95% prediction interval for air filter lifetime. Validation of this lifetime prediction was performed using imaging measurements on a test air filter, which showed good agreement with the machine learning model. The proposed machine learning based image analytics framework effectively enables robust predictions of component wear for predictive maintenance.

Auto-completion is a major feature in all keyboard based mobile devices. However, not a lot of work has been done to extend this feature into handwritten text based input. Generally, auto-complete options are ranked on the basis of previous context and word probabilities. However, this leads to missing out on the user intended word simply because there are more frequently used words with the same prefix, in the same context. In this paper, we propose a gesture-based solution to recognize and complete partially-written words, where the user indicates to the system the missing text length by a stroke gesture, thus ruling out a huge subset of possibilities. We also propose a length dependent hybrid score ranking system, to improve the prediction accuracy and speed. Our results show that using a gesture stroke length based searching method not only reduced the processing time by 27% but also showed an accuracy increase of 10%, when the top 3 candidates are considered.

On-line handwriting recognition has seen major improvements in the last few years with the successful application of deep learning techniques. While the training data is massive and training times are large, the current accuracies are very good even with reasonable small model sizes (when compared to models in image recognition tasks). However, the important task of personalizing such deep models (after a new user has downloaded the model onto his mobile device) to the writing style of the new user, resulting in an improved model with significantly higher accuracy, has not been investigated so far. It is clearly not feasible to download the massive training data for each new user, and re-train the model on the device itself (after mixing original data with the limited quantity of training samples a new user can supply). To our knowledge, it is not known so far with what adaptation technique, with what old training data (in addition to the user's new samples), how flexibly the retraining can be done on the device, how much accuracy gain can be expected, and whether the model can be simplified as a result of the retraining. In this paper we address all these important questions regarding deep network models on device: we demonstrate simple but robust continued-training techniques for adapting a pre-trained model to a specific user's writing style. The pre-training is done using Long Short Term Memory (LSTM) network and a Connectionist Temporal Classification (CTC) loss function. It is seen that only a small set of the old training data can be used along with the user's samples to successfully retrain the model. The retrained (adapted) model achieves around 2.5% more accuracy than the roughly 92% accuracy of the non-personalized model for on-line handwritten Hindi text recognition, also surpassing all existing techniques. We also derive some additional insights into the questions posed above.