Search
Results
-
Injecting Descriptive Meta-Information into Pre-Trained Language Models with Hypernetworks
(2021)Proceedings of Interspeech 2021There is a growing trend to deploy deep neural networks at the edge for high-accuracy, real-time data mining and user interaction. Applications such as speech recognition and language understanding often apply a deep neural network to encode an input sequence and then use a decoder to generate the output sequence. A promising technique to accelerate these applications on resource-constrained devices is network pruning, which compresses ...Conference Paper -
Automatic Energy-Hotspot Detection and Elimination in Real-Time Deeply Embedded Systems
(2021)2021 IEEE Real-Time Systems Symposium (RTSS)Today’s deeply embedded systems, with real-time interactions to the environment, are largely battery-operated, and peripheral modules like LTE, WiFi, and GPS are among the most energy-hungry components of them. These components are often under the direct control of an embedded software. Some pieces of the software program are called energy hotspots if they can be transformed towards better system energy consumption while leaving it ...Conference Paper -
TIP-Air: Tracking Pollution Transfer for Accurate Air Quality Prediction
(2021)Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers (UbiComp-ISWC '21 Adjunct)Air quality is of vital importance to human health. Accurately predicting air quality, especially its sudden changes, is highly valuable for citizens and governments to make personal and local decisions, design intelligent policies and control pollution at minimal cost. However, none of the existing methods achieves sufficient prediction accuracy for time intervals of sudden pollution change due to inability of existing models to take ...Conference Paper -
Energy-efficient scheduling on homogeneous multiprocessor platforms
(2010)Proceedings of the 2010 ACM Symposium on Applied Computing (SAC '10)Low-power and energy-efficient system implementations have become very important design issues to extend operation duration or cut power bills. To balance the energy consumption resulting from the dynamic power consumption and the static power consumption, the concept of critical speed has been adopted widely in the literature. Most scheduling algorithms for such systems assume that the critical speed is the lowest speed for scheduling ...Conference Paper -
Computing a Language-Based Guarantee for Timing Properties of Cyber-Physical Systems
(2014)2014 Design, Automation & Test in Europe Conference & Exhibition (DATE)Real-time systems are often guaranteed in terms of schedulability, which verifies whether or not all jobs meet their deadlines. However, such a guarantee can be insufficient in certain applications. In this paper, we propose a method to compute a language-based guarantee which provides a more detailed description of the deadline miss patterns of an observed task. The only requirement of our method is that the timing behavior of the real-time ...Conference Paper -
Pruning-Aware Merging for Efficient Multitask Inference
(2021)Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD '21)Many mobile applications demand selective execution of multiple correlated deep learning inference tasks on resource-constrained platforms. Given a set of deep neural networks, each pre-trained for a single task, it is desired that executing arbitrary combinations of tasks yields minimal computation cost. Pruning each network separately yields suboptimal computation cost due to task relatedness. A promising remedy is to merge the networks ...Conference Paper -
PermaDAQ: A scientific instrument for precision sensing and data recovery in environmental extremes
(2009)2009 International Conference on Information Processing in Sensor Networks (IPSN 2009)The PermaSense project has set the ambitious goal of gathering real-time environmental data for high-mountain permafrost in unattended operation over multiple years. This paper discusses the specialized sensing and data recovery architecture tailored to meet the precision, reliability and durability requirements of scientists utilizing the data for model validation. We present a custom sensor interface board including specialized sensors ...Conference Paper -
Reliability-Aware Mapping Optimization of Multi-Core Systems with Mixed-Criticality
(2014)2014 Design, Automation & Test in Europe Conference & Exhibition (DATE)This paper presents a novel mapping optimization technique for mixed critical multi-core systems with different reliability requirements. For this scope, we derived a quantitative reliability metric and presented a scheduling analysis that certifies given mixed-criticality constraints. Our framework is capable of investigating re-execution, passive replication, and modular redundancy with optimized voter placement, while typical hardening ...Conference Paper -
COOLIP: Simple yet Effective Job Allocation for Distributed Thermally-Throttled Processors
(2014)2014 Design, Automation & Test in Europe Conference & Exhibition (DATE)Thermal constraints limit the time for which a processor can run at high frequency. Such thermal-throttling complicates the computation of response times of jobs. For multiple processors, a key decision is where to allocate the next job. For distributed thermally-throttled procesosrs, we present COOLIP with a simple allocation policy: a job is allocated to the earliest available processor, and if there are several available simultaneously, ...Conference Paper -
Participatory Air Pollution Monitoring Using Smartphones
(2012)Proceedings of the 2nd International Workshop on Mobile SensingConference Paper