Accelerators such as graphics processing units (GPUs) provide an inexpensive way of improving the performance of cluster systems. In such an arrangement, the individual nodes of the cluster are directly connected to o...
详细信息
This paper presents a system that is able to monitor the patient vital signs (Heart Rate, SPO 2 , NIBP, ECG, temperature and respiration rate) and send them continuously to the doctor's android phone device. The s...
详细信息
This paper presents a system that is able to monitor the patient vital signs (Heart Rate, SPO 2 , NIBP, ECG, temperature and respiration rate) and send them continuously to the doctor's android phone device. The system enables multiple patients to be connected to the same doctor. Within the system, the health care professional may activate/deactivate any of the vital signs sensors. He can also set a prescription for the patient, schedule a meeting,... When bad activities are received, a message is directly sent to the doctor and to the patient relatives in order to alert them. Note that the Bluetooth connection is used to send/receive data between the patient platform and its android system. The tested results showed an almost error free system with an accuracy above 95% and a few milliseconds delay between the vital signs reading and their upload over the server.
Logistic Regression (LR) is a widely used statistical model for classification problems. However, its training and evaluation in a shared environment increase the possibility of information leaking. A federated LR red...
详细信息
ISBN:
(数字)9798350354812
ISBN:
(纸本)9798350354829
Logistic Regression (LR) is a widely used statistical model for classification problems. However, its training and evaluation in a shared environment increase the possibility of information leaking. A federated LR reduces security issues by using only locally available data for training. In a Federated Learning (FL) environment, LR receives the coefficients of local models to create the federated LR model, which is then distributed to update the local models. The exchange process does not leak confidential information when LR coefficients are encrypted. Homomorphic Encryption (HE) allows the merging of local LR models with privacy preservation (HE-LR). This work presents a novel training policy to reduce the training time with only slightly decreased quality in an FL environment with HE. We analyze the accuracy and time of FL policies with HE-LR that progressively reduce the amount of training data and exchange the LR coefficients in a privacy-preserving manner. The results show that the proposed policy can speed up the training time between 12% and 69%, compared to the traditional FL approach, with an average decrease in accuracy of 1.79% and 1.95%.
Selective laser melting (SLM) is a three dimensional (3D) printing process which can manufacture functional parts with complex geometries as an alternative to using traditional processes (i.e. via machining of wrought...
详细信息
We goal of the work is to derive four-voice music pieces from given musical plans, which describe the harmonic flow and the intentions of a desired composition. We developed the experimentation platform COMPOzE for in...
详细信息
We goal of the work is to derive four-voice music pieces from given musical plans, which describe the harmonic flow and the intentions of a desired composition. We developed the experimentation platform COMPOzE for intention based composition. COMPOzE is based on constraint programming over finite domains of integers. We argue that constraint programming provides a suitable technology for this task and that the libraries and tools available for the constraint programming system Oz effectively support the implementation of COMPOzE. This work links the research areas of automatic music composition on one hand and finite domain constraint programming on the other, and contributes the tool COMPOzE, which practically demonstrates the potential of constraint programming to open up new areas of application for automatic music composition.
Maintenance starts with reliable diagnostics. programming Logic Controllers (PLCs) are often equipped with a high degree of diagnostic procedures in order to ensure that the processing unit is functioning correctly. I...
详细信息
ISBN:
(纸本)9781629935881
Maintenance starts with reliable diagnostics. programming Logic Controllers (PLCs) are often equipped with a high degree of diagnostic procedures in order to ensure that the processing unit is functioning correctly. It is vital to verify that the system with its programme is still within a 'healthy' state, otherwise a safety function is called and the system is brought into a safe state, or if possible, defect and malfunctioning components are exchanged during operation and the process can continue without shutting down the system. However, when it comes to smaller devices such as intelligent sensors, embedded controller devices with the functionality of an e.g. PID (Proportional-Integral-Derivative), predictive controller, filter or analytical algorithm, which is embedded into a FPGA or micro-controller then diagnostics and verification methods are often not considered in the way they should be. For example, if an intelligent sensor system is not able to diagnose that the sensor-head is malfunctioning, but the sensor-head still provides some data, then the smart algorithm bases its calculation on wrong data, which can cause a dangerous situation. This paper investigates and shows recent results to combine diagnostic methods for small scale devices. Several safety-related structures are considered with a high degree of diagnostic coverage. The paper presents relevant procedures and structures to increase the reliability of small devices without utilising a full scale microcontroller system.
Feature models are the de facto standard for modelling variabilities and commonalities. Concrete models in different domains exist;however, many are in private or sparse repositories or belong to discontinued projects...
详细信息
The overwhelming acceptance of social media creates opportunities to learn about facts and events that are echoed in posts, tweets and messages uploaded by users. Analysis of these data can lead to interesting observa...
详细信息
The overwhelming acceptance of social media creates opportunities to learn about facts and events that are echoed in posts, tweets and messages uploaded by users. Analysis of these data can lead to interesting observations and conclusions. Of special importance are aspects related to temporal and dynamic nature of these findings. This paper presents a simple fuzzy-based approach of pre-processing and analyzing Twitter hashtags. The obtained fuzzy clusters are further examined in order to gain insight related to temporal trends and patterns of hashtags' popularity.
We present novel concepts, technologies and potentials of optical data communication, especially for future computer architectures. The WDM (wavelength division multiplexing) and the optical wiring technologies are ex...
详细信息
We present novel concepts, technologies and potentials of optical data communication, especially for future computer architectures. The WDM (wavelength division multiplexing) and the optical wiring technologies are explained in detail. Experimental results of tunable optical filters, which play a major role in WDM systems, are reported. New concepts for novel optical interconnectors and novel miniaturized lasers for direct generation of green light are proposed as examples for possible next generation components to improve the performance of optical communication based computer architecture.
This paper describes the development of an auto-active verification technique in the Frama-C framework. We outline the lemma functions method and present the corresponding ACSL extension, its implementation in Frama-C...
详细信息
暂无评论