Motivation Human genomic datasets often contain sensitive information that limits use and sharing of the data. In particular, simple anonymization strategies fail to provide sufficient level of protection for genomic data, because the data are inherently identifiable. Differentially private machine learning can help by guaranteeing that the published results do not leak too much information about any individual data point. Recent research has reached promising results on differentially private drug sensitivity prediction using gene expression data. Differentially private learning with genomic data is challenging because it is more difficult to guarantee privacy in high dimensions. Dimensionality reduction can help, but if the dimension reduction mapping is learned from the data, then it needs to be differentially private too, which can carry a significant privacy cost. Furthermore, the selection of any hyperparameters (such as the target dimensionality) needs to also avoid leaking private information. Results We study an approach that uses a large public dataset of similar type to learn a compact representation for differentially private learning. We compare three representation learning methods: variational autoencoders, principal component analysis and random projection. We solve two machine learning tasks on gene expression of cancer cell lines: cancer type classification, and drug sensitivity prediction. The experiments demonstrate significant benefit from all representation learning methods with variational autoencoders providing the most accurate predictions most often. Our results significantly improve over previous state-of-the-art in accuracy of differentially private drug sensitivity prediction. Availability and implementation Code used in the experiments is available at https://github.com/DPBayes/dp-representation-transfer.
In this paper, fuel consumption of a 5.7-ton municipal tractor in a wheel loader application is studied, and methods for improving the fuel efficiency are compared with each other. Experimental data from the baseline machine with load-sensing hydraulics has been gathered during a y-pattern cycle, and the data is inputted to an optimization function having realistic loss models for a hydraulic pump and diesel engine. Dynamic programming is used to analyze different system configurations in order to determine optimal control sequence for each system. Besides optimization of variable engine rotational speed on the baseline system during the working cycle (considering the point of operation), three hybrid supply systems are studied: 1) a hydraulic flywheel, 2) parallel supply pumps and 3) a throttled accumulator. These systems utilize a hydraulic accumulator as an energy source/sink alongside the diesel engine. The optimal sequence for charging and discharging of the accumulator is examined in order to minimize the fuel consumption of the machine. The idea is to use the lowest acceptable, constant engine rotational speed, to cut down the diesel losses. In addition, the study covers an analysis of adjusting the engine rotational speed for each point of operation also when the hybrid systems are considered. The results show that finding advantageous engine rotational speed for each loading condition can decrease the fuel consumption of the baseline machine around 14%, whereas hybridization of the supply system can further improve the result by a couple of percentage units. Hybrid systems also reduce engine’s maximum load by making it more uniform, which allegedly reduces emissions. The possibility of engine downsizing to further improve the fuel efficiency of hybrid systems is not considered, because the maximum engine power is usually determined by the hydrostatic transmission of a municipal tractor. However, the study assumes that actuators are controlled using traditional 4/3 proportional control valves; hence, there are still potential for greater fuel savings. For example, applying independent metering valves on the actuator control can further decrease the system losses.
Shuffle model of differential privacy is a novel distributed privacy model based on a combination of local privacy mechanisms and a trusted shuffler. It has been shown that the additional randomisation provided by the shuffler improves privacy bounds compared to the purely local mechanisms. Accounting tight bounds, especially for multi-message protocols, is complicated by the complexity brought by the shuffler. The recently proposed Fourier Accountant for evaluating (ε, δ)-differential privacy guarantees has been shown to give tighter bounds than commonly used methods for non-adaptive compositions of various complex mechanisms. In this paper we show how to compute tight privacy bounds using the Fourier Accountant for multi-message versions of several ubiquitous mechanisms in the shuffle model and demonstrate looseness of the existing bounds in the literature.
A combination of digital hydraulic four notch control valves and the digital hydraulic power management system (the DHPMS) has many controller levels, both parallel and series. The DHPMS is a multi-port sink/source of hydraulic power. Digital hydraulic valves are used to control the actuators. Both the DHPMS and the digital valves are based on the idea that all complexity is in the software and the hardware is based on arrays of mechanically simple base units. Controllers work together merging into a power flow system where the whole power transfer line is controlled from a single pumping piston within the pump to the movement of the tip of the boom. Or vice versa, if the operating conditions allow negative power to be routed backwards. In the paper certain measurements are looked into; second by second and a signal by a signal. The paper presents and verifies functionality of the novel combination of technologies. How signals flow in the controllers and how they actually control the power flow in the system is explained. The test system is a two-actuator boom, and as two is the smallest example of multi, the controller is designed by a simple and robust control method.
WorkPartner is a mobile interactive service robot designed for lightweight outdoor tasks in co-operation with humans. WorkPartner participated in the ISR 2004 (35 th International Symposium on Robotics) exhibition on CLAWAR stand in Paris 22 -26 March 2004. During the five days a lot of information was collected about human-machine interaction. The robot communicated with humans using speech and gestures, and observed environment using vision system. The visitors seemed to get a very humane impression of the robot.
The Digital Hydraulic Power Management System (DHPMS) is a solution based on the digital pump-motor technology and has shown to be a promising approach to improve the energy efficiency of hydraulic systems. The DHPMS is controlled by active on/off valves, but unlike the digital pump-motors the DHPMS has multiple independent outlets; hence, the DHPMS can operate also as a transformer. In this experimental study, a proportional control of a mobile boom is compared with a displacement control when a six-piston DHPMS is used. In the proportional control, the system pressure is controlled by the DHPMS and a lift cylinder with a proportional valve. In the displacement control, the cylinder fluid volumes are controlled directly using the DHPMS. Firstly, the systems under study are presented along with the control methods. Then the control performance of the DHPMS is studied and finally, the energy losses in the systems are analysed. The results show the versatility of the DHPMS; it is capable of fast and accurate pressure control but also handles the direct flow control. According to the measurements, the losses are significantly smaller in the displacement controlled system thanks to the minimised throttling losses and the energy recovery. Nevertheless, the energy losses in the prototype DHPMS are rather high due to the leakage in the control valves and their low flow capacity, and therefore improvements in the design are needed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.