250 Hits in 6.4 sec

COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations [article]

Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra
2020 arXiv   pre-print
We evaluate the quality of our embedding model, measuring its performance as a feature extractor on three different tasks (namely, sound event recognition, and music genre and musical instrument classification  ...  Our results are promising, sometimes in par with the state-of-the-art in the considered tasks and the embeddings produced with our method are well correlated with some acoustic descriptors.  ...  Xavier Favory is also grateful for the GPU donated by NVidia.  ... 
arXiv:2006.08386v2 fatcat:ed6ztnuwm5fp7dlx4ngi2osmky

Supporting the Wellness at Work and Productivity of Ageing Employees in Industrial Environments: The sustAGE Project

Maria Pateraki, Manolis Lourakis, Leonidas Kallipolitis, Frank Werner, Petros Patias, Christos Pikridas
2019 Zenodo  
A plethora of applications further extends to the home setting for assisted living applications.  ...  When taking the complete data set with a separation of 70 % training and 30 % test data, on average the network ended up with a 97.6 % classification accu- racy, outperforming the KNN by about 2%.  ...  Virtual and augmented reality technologies can support the process of clinical rehabilitation, making therapy more engaging, challenging and measurable for people with disabilities or injury, encouraging  ... 
doi:10.5281/zenodo.4294256 fatcat:ovybcpqny5eppniw7hb5vcsevy

Learning Sound Representations Using Triplet-loss

Kohki Mametani, Xavier Favory, Frederic Font
2020 Zenodo  
Our code for this project is available on GitHub: An additional tool to visualize audio representations with audio-playing feature is available on GitHub:  ...  Recent studies have demonstrated that machine learning approaches which rely on large sound collections successfully learn such representations.  ...  Look, Listen, and Learn (L3-Net) [54] is a pioneering work in this venue.  ... 
doi:10.5281/zenodo.4091494 fatcat:ttuxpvdzhfdzlhf4c5fnoinhh4

Hot Chips 27 Highlights

Rajeevan Amirtharajah, Behnam Robatmili
2016 IEEE Micro  
in embedded applications.  ...  application, but they share a single optimized shifted neural network processor for classification.  ... 
doi:10.1109/mm.2016.30 fatcat:lfptn75qcjax5nsul3lhm5gyn4

Locating cache performance bottlenecks using data profiling

Aleksey Pesterev, Nickolai Zeldovich, Robert T. Morris
2010 Proceedings of the 5th European conference on Computer systems - EuroSys '10  
The costs due to frequent cache misses on a given piece of data, however, may be spread over instructions throughout the application.  ...  The improvements provide a 16-57% throughput improvement on a range of memcached and Apache workloads.  ...  We thank our shepherd Alexandra Fedorova and the anonymous reviewers for making suggestions that improved this paper.  ... 
doi:10.1145/1755913.1755947 dblp:conf/eurosys/PesterevZM10 fatcat:ignxcwf5dbbcxijp7vegskmtmq

LIPIcs : an Open-Access Series for International Conference Proceedings

Marc Herbstritt, Wolfgang Thomas
2016 ERCIM News  
On the one hand, we have applied VFDT, the reference method for classification tree induction.  ...  the subscription journals' business model for the necessary large-scale transformation to open access' [L3].  ...  The MUSA IDE will allow embedding security agents in the application components for self-protection, i.e. they will enable the activation of security monitors and controls at runtime without modifying  ... 
doi:10.18154/rwth-2018-223393 fatcat:ddo7qz65l5b7peuksw2amaoxai

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

John T. Schwartz, Michael Gao, Eric A. Geng, Kush S. Mody, Christopher M. Mikhail, Samuel K. Cho
2019 Neurospine  
Developments in machine learning in recent years have precipitated a surge in research on the applications of artificial intelligence within medicine.  ...  The limitations and future challenges for machine learning research using electronic medical records are also discussed.  ...  A breakdown of common types of machine learning algorithms used in medical applications. t-SNE, t-Stochastic Neighbor Embedding. *Deep learning algorithms.  ... 
doi:10.14245/ns.1938386.193 pmid:31905452 pmcid:PMC6945000 fatcat:ltytnozvevfpln3vu76v2avjma

Deep Room Recognition Using Inaudible Echos [article]

Qun Song, Chaojie Gu, Rui Tan
2018 arXiv   pre-print
Compared with the state-of-the-art approaches based on support vector machine, RoomRecognize significantly improves the Pareto frontier of recognition accuracy versus robustness against interfering sounds  ...  Based on this result, we design a RoomRecognize cloud service and its mobile client library that enable the mobile application developers to readily implement the room recognition functionality without  ...  We acknowledge the support of NVIDIA Corporation with the donation of the Quadro P5000 GPU used in this research.  ... 
arXiv:1809.00531v2 fatcat:prv26marpnbpbezu6ew577gkxq

A taxonomy of grid monitoring systems

Serafeim Zanikolas, Rizos Sakellariou
2005 Future generations computer systems  
The paper concludes with, among others, a discussion of the considered systems, as well as directions for future research.  ...  Monitoring grid resources is a lively research area given the challenges and manifold applications.  ...  NWS Ganglia MDS2 MonALISA Paradyn/ MRNet RGMA Classification L2b.A L2b.N L2b.G L2c.G L3.G L3.G.S L3.G.S L3.A L3.G.S Producer Local monitor SNMP services and benchmark collectors  ... 
doi:10.1016/j.future.2004.07.002 fatcat:flzstw3rvvhcvh5kot7odlnmsa

Deep Learning-Based Real-Time Multiple-Object Detection and Tracking from Aerial Imagery via a Flying Robot with GPU-Based Embedded Devices

Hossain, Lee
2019 Sensors  
We propose a very effective method for this application based on a deep learning framework.  ...  These are suitable for real-time onboard computing power on small flying drones with limited space.  ...  I would also like to pay a deep sense of gratitude to all CAIAS (Center for Artificial Intelligence and Autonomous System) lab members for their support and CAIAS lab for providing me all the facilities  ... 
doi:10.3390/s19153371 fatcat:htf3ilkn3ndrxjzoaos6vj6fc4

Unit commitment considering multiple charging and discharging scenarios of plug-in electric vehicles

Zhile Yang, Kang Li, Qun Niu, Aoife Foley
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
Open Set Recognition [#15579] Douglas Cardoso, Felipe Franca and Joao Gama 3:40PM The Generalized Group Lasso [#15480] Carlos M.  ...  Classification with Imbalanced Data [#15687] Everlandio Fernandes, Andre Carvalho and Andre Coelho 2:10PM Lattice point sets for efficient kernel smoothing models [#15285] Cristiano Cervellera,  ... 
doi:10.1109/ijcnn.2015.7280446 dblp:conf/ijcnn/YangLNF15 fatcat:6xlakikcfzfyhhm2spooe2j7ra

AntMonitor: A System for On-Device Mobile Network Monitoring and its Applications [article]

Anastasia Shuba, Anh Le, Emmanouil Alimpertis, Minas Gjoka, Athina Markopoulou
2017 arXiv   pre-print
Second, we show that AntMonitor is uniquely positioned to serve as a platform for passive on-device mobile network monitoring and to enable a number of applications, including: (i) real-time detection  ...  and prevention of private information leakage from the device to the network; (ii) passive network performance monitoring; and (iii) application classification and user profiling.  ...  , which provides a network performance SDK that can be embedded in other mobile applications; and Mobilyzer [25] , which provides an open platform for controllable mobile network measurements.  ... 
arXiv:1611.04268v2 fatcat:3jydntogrnbo5mndzkkiqh3toq

Using Embedded Feature Selection and CNN for Classification on CCD-INID-V1—A New IoT Dataset

Zhipeng Liu, Niraj Thapa, Addison Shaver, Kaushik Roy, Madhuri Siddula, Xiaohong Yuan, Anna Yu
2021 Sensors  
RF and XGBoost are the embedded models to reduce less impactful features. (3) We attempt anomaly (binary) classifications and attack-based (multiclass) classifications on CCD-INID-V1 and two other IoT  ...  ); (2) we propose a hybrid lightweight form of IDS—an embedded model (EM) for feature selection and a convolutional neural network (CNN) for attack detection and classification.  ...  Our proposed hybrid method combines an embedded model (EM) for feature selection and a CNN for attack classification.  ... 
doi:10.3390/s21144834 fatcat:bszezvdebvd4xivpnfu2czns3u

SFC Path Tracer: A troubleshooting tool for Service Function Chaining

Rafael Anton Eichelberger, Tiago Ferreto, Sebastien Tandel, Pedro Arthur P. R. Duarte
2017 2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)  
This work presents the SFC Path Tracer, a tool for troubleshooting SFC in NFV/SDN environments.  ...  ABSTRACT Service Function Chaining (SFC) is an important research field in networking area with many encapsulation and forwarding mechanisms being proposed.  ...  For instance, on the enterprise middlebox survey [54] , a deployment is mentioned with 2850 L3 routers have a total of 1946 middleboxes. 19 The management of this variety of Middleboxes is complicated  ... 
doi:10.23919/inm.2017.7987331 dblp:conf/im/EichelbergerFTD17 fatcat:t53yuktyifaytii5kdyhqfjxku

The IX Operating System

Adam Belay, George Prekas, Mia Primorac, Ana Klimovic, Samuel Grossman, Christos Kozyrakis, Edouard Bugnion
2016 ACM Transactions on Computer Systems  
The control plane dynamically adjusts core allocations and voltage/frequency settings to meet service-level objectives.  ...  With three varying load patterns, the control plane saves 46%-54% of processor energy, and it allows background jobs to run at 35%-47% of their standalone throughput. . 2016.  ...  ACKNOWLEDGMENTS The authors would like to thank David Mazières for his many insights into the system and his detailed feedback on the article.  ... 
doi:10.1145/2997641 fatcat:6nt2zson6jfjrieodatckxbfhi
« Previous Showing results 1 — 15 out of 250 results