Sam E. John

Noor E Karishma Shaik, Bryce Widdicombe, Dechuan Sun et al.

A multispectral camera records image data in various wavelengths across the electromagnetic spectrum to acquire additional information that a conventional camera fails to capture. With the advent of high-resolution image sensors and colour filter technologies, multispectral imagers in the visible wavelengths have become popular with increasing commercial viability in the last decade. However, multispectral imaging in longwave infrared (LWIR: 8 to 14 microns) is still an emerging area due to the limited availability of optical materials, filter technologies, and high-resolution sensors. Images from LWIR multispectral cameras can capture emission spectra of objects to extract additional information that a human eye fails to capture and thus have important applications in precision agriculture, forestry, medicine, and object identification. In this work, we experimentally demonstrate an LWIR multispectral image sensor with three wavelength bands using optical elements made of an aluminum-based plasmonic filter array sandwiched in germanium. To realize the multispectral sensor, the filter arrays are then integrated into a 3D printed wheel stacked on a low-resolution monochrome thermal sensor. Our prototype device is calibrated using a blackbody and its thermal output has been enhanced with computer vision methods. By applying a state-of-the-art deep learning method, we have also reconstructed multispectral images to a better spatial resolution. Scientifically, our work demonstrates a versatile spectral thermography technique for detecting target signatures in the LWIR range and other advanced spectral analyses.

Johnson Zhou, Joseph West, Krista A. Ehinger et al.

Objective. Electroencephalography (EEG) data is derived by sampling continuous neurological time series signals. In order to prepare EEG signals for machine learning, the signal must be divided into manageable segments. The current naive approach uses arbitrary fixed time slices, which may have limited biological relevance because brain states are not confined to fixed intervals. We investigate whether adaptive segmentation methods are beneficial for machine learning EEG analysis. Approach. We introduce a novel adaptive segmentation method, CTXSEG, that creates variable-length segments based on statistical differences in the EEG data and propose ways to use them with modern machine learning approaches that typically require fixed-length input. We assess CTXSEG using controllable synthetic data generated by our novel signal generator CTXGEN. While our CTXSEG method has general utility, we validate it on a real-world use case by applying it to an EEG seizure detection problem. We compare the performance of CTXSEG with fixed-length segmentation in the preprocessing step of a typical EEG machine learning pipeline for seizure detection. Main results. We found that using CTXSEG to prepare EEG data improves seizure detection performance compared to fixed-length approaches when evaluated using a standardized framework, without modifying the machine learning method, and requires fewer segments. Significance. This work demonstrates that adaptive segmentation with CTXSEG can be readily applied to modern machine learning approaches, with potential to improve performance. It is a promising alternative to fixed-length segmentation for signal preprocessing and should be considered as part of the standard preprocessing repertoire in EEG machine learning applications.

Sam John, Akshay Gadde, Balu Adsumilli

We present an efficient codec-agnostic method for bitrate allocation over a large scale video corpus with the goal of minimizing the average bitrate subject to constraints on average and minimum quality. Our method clusters the videos in the corpus such that videos within one cluster have similar rate-distortion (R-D) characteristics. We train a support vector machine classifier to predict the R-D cluster of a video using simple video complexity features that are computationally easy to obtain. The model allows us to classify a large sample of the corpus in order to estimate the distribution of the number of videos in each of the clusters. We use this distribution to find the optimal encoder operating point for each R-D cluster. Experiments with AV1 encoder show that our method can achieve the same average quality over the corpus with $22\%$ less average bitrate.