No abstract

A fall of an elderly person often leads to serious injuries or even death. Many falls occur in the home environment and remain unrecognized. Therefore, a reliable fall detection is absolutely necessary for a fast help. Wrist-worn accelerometer based fall detection systems are developed, but the accuracy and precision are not standardized, comparable, or sometimes even known. In this work, we present an overview about existing public databases with sensor based fall datasets and harmonize existing wrist-worn datasets for a broader and robust evaluation. Furthermore, we are analyzing the current possible recognition rate of fall detection using deep learning algorithms for mobile and embedded systems. The presented results and databases can be used for further research and optimizations in order to increase the recognition rate to enhance the independent life of the elderly. Furthermore, we give an outlook for a convenient application and wrist device.

No abstract

There is a growing need to reduce the use of poisonous chemicals in the food production. We need a system to monitor and manage such chemical usage. Due to globalization, the supplier and the consumer can be across the countries or continents. Hence global crop quality standards must consider; local regulations, grower's knowledge/skills and also agro input ecosystem. We need to carefully study the entire supply-chain, various stakeholders and find the points of exchange of the products or services. Digital technology can help to map and manage this diversity, across different time zones, culture, language and practices. mKRISHI® provides a digital platform to identify the farm, record, the laborer skills, manage pesticide inventory and including consumption date, time, dosage, etc. Each plot was identified by plot code and Global Gap Number (GGN). Hence, it's easy to trace back the produce (grape box) to the plot as well as get the agro inputs used to produce it. Using a QR code and a mobile app, it's easy for the consumer to get the desired information at their fingertips. Such end to end supply chain digitization not only improves the traceability but also creates a digital mapping framework from farm to fork. 

In-situ stress variability within a reservoir is a primary parameter that controls hydraulic fracture initiation, growth, connectivity, and ultimately drainage and well spacing. This paper highlights the importance of characterizing the variability of in-situ stress and demonstrates the risk of underestimating stimulation treatment size when a treatment design is applied in a “copy-paste” fashion without any modifications to account for variation in pore pressure and in-situ stress across a basin. Thermal maturity and hydrocarbon generation from unconventional shales has a direct effect on pore pressure and the in-situ stress distribution in reservoir and barrier rocks. An examination of the Bakken Petroleum System (BPS) identifies regions of thermal maturity and higher pore pressure due to hydrocarbon expulsion. Consequently, the elevated pore pressure and the resulting in-situ stress vary vertically and laterally within the basin. Multiple pore pressure profiles and corresponding stress profiles across the BPS were considered to quantify the impact of in-situ stress variability on hydraulic fracture geometry. These profiles include effects of normal pore pressure regime, over-pressure regime or pressure profiles transitioning from over pressure to normal pressure regimes. For a given stress profile, hydraulic fracture geometries are estimated using a fracture simulator, with multiple calibration points. The hydraulic fracture system and reservoir interactions are simulated in a subsequent production modeling phase which estimates drainage area characteristics, recovery forecasts and optimum well spacing for developing an asset. Results from stress profile sensitivity emphasize the need to address variability of in-situ stress as it directly impacts well spacing considerations in an asset development plan. For example, stress profile with a normal pore pressure regime results in longer hydraulic fracture lengths in the Middle Bakken (MB) thus requiring three wells per section to infill the asset. Conversely, stress profile with over-pressure regime in MB results in much shorter hydraulic fracture lengths thus requiring more than three wells per section to develop the asset. Incorrectly assuming overpressure in a normally pressured zone could lead to over-engineering of wells and unnecessary costs, whereas incorrectly assuming normal pressure in zones that are in fact overpressured could lead to sub-optimal completions and/or a reduction in overall production.