The lack of publicly available large scale measure- ments has hindered the derivation of empirical path loss (PL) models for Narrowband Internet of Things (NB-IoT). Therefore, simulation-based investigations currently rely on models con- ceived for other cellular technologies, which are characterized, however, by different available bandwidth, carrier frequency, and infrastructure deployment, among others. In this paper, we take advantage of data from a large scale measurement campaign in the city of Oslo, Norway, to provide the first empirical characterization of NB-IoT PL in an urban scenario. For the PL average term, we characterize Alpha-Beta-Gamma (ABG) and Close-In (CI) models. By analyzing multiple NB- IoT cells, we propose a statistical PL characterization, i.e., the model parameters are not set to a single, constant value across cells, but are randomly extracted from well-known distributions. Similarly, we define the PL shadowing distribution, correlation over distance, and inter-site correlation. Finally, we give initial insights on outdoor-to-indoor propagation, using measurements up to deep indoor scenarios. The proposed models improve PL estimation accuracy compared to the ones currently adopted in NB-IoT investigations, enabling more realistic simulations of urban scenarios similar to the sites covered by our measurements. 

Gastrointestinal endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance.   The high missed rate of such abnormalities during endoscopy is thus a  critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic  GI  disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the  Medico  GI  challenges:  Medical  Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018,  and  BioMedia  ACM  MM  Grand  Challenge  2019.  These challenges are initiative to set-up  a  benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a  period of three consecutive years and provide a  detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings.  Our analysis revealed that the participants achieved an improvement on maximum  Mathew correlation coefficient  (MCC)  from  82.68%  in  2017  to  93.98%  in  2018  and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.

Computer-aided detection, localization, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the increasing number of researched computer vision methods that can be applied to polyp datasets. Benchmarking of novel methods can provide a direction to the development of automated polyp detection and segmentation tasks. Furthermore, it ensures that the produced results in the community are reproducible and provide a fair comparison of developed methods. In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images for polyp detection, localization, and segmentation evaluating both method accuracy and speed. Whilst, most methods in literature have competitive performance over accuracy, we show that the proposed ColonSegNet achieved a better trade-off between an average precision of 0.8000 and mean IoU of 0.8100, and the fastest speed of 180 frames per second for the detection and localization task. Likewise, the proposed ColonSegNetachieved a competitive dice coefficient of 0.8206 and the best average speed of 182.38 frames per second for the segmentation task. Our comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimize miss-detection rates.