Data-oriented Algorithms Research Articles

Performance of Qure.ai automatic classifiers against a large annotated database of patients with diverse forms of tuberculosis.

Availability of trained radiologists for fast processing of CXRs in regions burdened with tuberculosis always has been a challenge, affecting both timely diagnosis and patient monitoring. The paucity of annotated images of lungs of TB patients hampers attempts to apply data-oriented algorithms for research and clinical practices. The TB Portals Program database (TBPP, https://TBPortals.niaid.nih.gov) is a global collaboration curating a large collection of the most dangerous, hard-to-cure drug-resistant tuberculosis (DR-TB) patient cases. TBPP, with 1,179 (83%) DR-TB patient cases, is a unique collection that is well positioned as a testing ground for deep learning classifiers. As of January 2019, the TBPP database contains 1,538 CXRs, of which 346 (22.5%) are annotated by a radiologist and 104 (6.7%) by a pulmonologist–leaving 1,088 (70.7%) CXRs without annotations. The Qure.ai qXR artificial intelligence automated CXR interpretation tool, was blind-tested on the 346 radiologist-annotated CXRs from the TBPP database. Qure.ai qXR CXR predictions for cavity, nodule, pleural effusion, hilar lymphadenopathy was successfully matching human expert annotations. In addition, we tested the 12 Qure.ai classifiers to find whether they correlate with treatment success (information provided by treating physicians). Ten descriptors were found as significant: abnormal CXR (p = 0.0005), pleural effusion (p = 0.048), nodule (p = 0.0004), hilar lymphadenopathy (p = 0.0038), cavity (p = 0.0002), opacity (p = 0.0006), atelectasis (p = 0.0074), consolidation (p = 0.0004), indicator of TB disease (p = < .0001), and fibrosis (p = < .0001). We conclude that applying fully automated Qure.ai CXR analysis tool is useful for fast, accurate, uniform, large-scale CXR annotation assistance, as it performed well even for DR-TB cases that were not used for initial training. Testing artificial intelligence algorithms (encapsulating both machine learning and deep learning classifiers) on diverse data collections, such as TBPP, is critically important toward progressing to clinically adopted automatic assistants for medical data analysis.

Topological reconstruction of sub-cellular motion with Ensemble Kalman velocimetry

Microscopy imaging of plant cells allows the elaborate analysis of sub-cellular motions of organelles. The large video data set can be efficiently analyzed by automated algorithms. We develop a novel, data-oriented algorithm, which can track organelle movements and reconstruct their trajectories on stacks of image data. Our method proceeds with three steps: (ⅰ) identification, (ⅱ) localization, and (ⅲ) linking. This method combines topological data analysis and Ensemble Kalman Filtering, and does not assume a specific motion model. Application of this method on simulated data sets shows an agreement with ground truth. We also successfully test our method on real microscopy data.

Lazy Management for Frequency Table on Hardware-Based Stream Lossless Data Compression

The demand for communicating large amounts of data in real-time has raised new challenges with implementing high-speed communication paths for high definition video and sensory data. It requires the implementation of high speed data paths based on hardware. Implementation difficulties have to be addressed by applying new techniques based on data-oriented algorithms. This paper focuses on a solution for this problem by applying a lossless data compression mechanism on the communication data path. The new lossless data compression mechanism, called LCA-DLT, provides dynamic histogram management for symbol lookup tables used in the compression and the decompression operations. When the histogram memory is fully used, the management algorithm needs to find the least used entries and invalidate these entries. The invalidation operations cause the blocking of the compression and the decompression data stream. This paper proposes novel techniques to eliminate blocking by introducing a dynamic invalidation mechanism, which allows achievement of a high throughput data compression.

DATA-ORIENTED ALGORITHM FOR ROUTE CHOICE SET GENERATION IN A METROPOLITAN AREA WITH MOBILE PHONE GPS DATA

Abstract. Nowadays, for the estimation of traffic demand or people flow, modelling route choice activity in road networks is an important task and many algorithms have been developed to generate route choice sets. However, developing an algorithm based on a small amount of data that can be applied generally within a metropolitan area is difficult. This is because the characteristics of road networks vary widely. On the other hand, recently, the collection of people movement data has lately become much easier, especially through mobile phones. Lately, most mobile phones include GPS functionality. Given this background, we propose a data-oriented algorithm to generate route choice sets using mobile phone GPS data. GPS data contain a number of measurement errors; hence, they must be adjusted to account for these errors before use in advanced people movement analysis. However, this is time-consuming and expensive, because an enormous amount of daily data can be obtained. Hence, the objective of this study is to develop an algorithm that can easily manage GPS data. Specifically, at first movement data from all GPS data are selected by calculating the speed. Next, the nearest roads in the road network are selected from the GPS location and count such data for each road. Then An algorithm based on the GSP (Gateway Shortest Path) algorithm is proposed, which searches the shortest path through a given gateway. In the proposed algorithm, the road for which the utilization volume calculated by GPS data is large is selected as the gateway. Thus, route choice sets that are based on trends in real GPS data are generated. To evaluate the proposed method, GPS data from 0.7 million people a year in Japan and DRM (Digital Road Map) as the road network are used. DRM is one of the most detailed road networks in Japan. Route choice sets using the proposed algorithm are generated and the cover rate of the utilization volume of each road under evaluation is calculated. As a result, the proposed route generation algorithm and GPS data cleaning process work well and a huge variety of routes that have high potential to be used in the real world can be generated.