Filters








10,925 Hits in 4.2 sec

A Comprehensive Study of Anomaly Detection Schemes in IoT Networks Using Machine Learning Algorithms

Abebe Diro, Naveen Chilamkurti, Van-Doan Nguyen, Will Heyne
2021 Sensors  
The Internet of Things (IoT) consists of a massive number of smart devices capable of data collection, storage, processing, and communication.  ...  Unlike traditional information technology (I.T.) systems, the IoT environment is challenging to secure due to resource constraints, heterogeneity, and distributed nature of the smart devices.  ...  • Second, running machine learning models can consume extensive resources, making it challenging to deploy such models on resource-constrained devices.  ... 
doi:10.3390/s21248320 pmid:34960414 pmcid:PMC8708212 fatcat:vogif3xvhbdvvb324iwpyq5vkm

A Flexible HLS Hoeffding Tree Implementation for Runtime Learning on FPGA [article]

Luís Miguel Sousa, Nuno Paulino, João Canas Ferreira, João Bispo
2021 arXiv   pre-print
This makes them especially suitable for deployment on embedded devices. In this work we highlight the features of an HLS implementation of the Hoeffding Tree.  ...  Hoeffding Trees are a type of Decision Trees that take advantage of the Hoeffding Bound to allow them to learn patterns in data without having to continuously store the data samples for future reprocessing  ...  As edge devices are often specialised for a single task in a constrained environment, it is advantageous to build dedicated hardware to improve performance and energy efficiency.  ... 
arXiv:2112.01875v1 fatcat:lpf3i7dzpbf3bj4wd7rix2q3hm

A Comparative Analysis of Machine Learning Algorithms for Intrusion Detection in Edge-Enabled IoT Networks [article]

Poornima Mahadevappa, Syeda Mariam Muzammal, Raja Kumar Murugesan
2021 arXiv   pre-print
In this paper, a comparative analysis of conventional machine learning classification algorithms has been performed to categorize the network traffic on NSL-KDD dataset using Jupyter on Pycharm tool.  ...  A significant increase in the number of interconnected devices and data communication through wireless networks has given rise to various threats, risks and security concerns.  ...  This step provides efficient training time in identifying the attacks. This ML based-IDS has set a new benchmark on resource-constrained devices for feature reduction [10] .  ... 
arXiv:2111.01383v1 fatcat:nihfvanyazc2ra6puhkrpntoki

Improving the Efficiency of Transformers for Resource-Constrained Devices [article]

Hamid Tabani, Ajay Balasubramaniam, Shabbir Marzban, Elahe Arani, Bahram Zonooz
2021 arXiv   pre-print
However, due to their massive number of model parameters, memory and computation requirements, they are not suitable for resource-constrained low-power devices.  ...  In this paper, we present a performance analysis of state-of-the-art vision transformers on several devices.  ...  With this understanding about resource-constrained devices, we believe that the efficiency of transformers can be significantly improved.  ... 
arXiv:2106.16006v1 fatcat:5u4neus2inayfnhhjyx2xowzku

Accelerometer and GPS sensor combination based system for human activity recognition

Sahak Kaghyan, Hakob Sarukhanyan
2013 Ninth International Conference on Computer Science and Information Technologies Revised Selected Papers  
The classification stage was based on "learning with teacher" method.  ...  The availability of these sensors in mass-market communication devices creates exciting new opportunities for data mining applications.  ...  (ML) algorithm for hardware with limited resources.  ... 
doi:10.1109/csitechnol.2013.6710352 fatcat:pdybdkv5nbhxvgje76civkha5e

Learning How to Communicate in the Internet of Things: Finite Resources and Heterogeneity [article]

Taehyeun Park, Nof Abuzainab, Walid Saad
2016 arXiv   pre-print
This framework is shown to efficiently capture the different IoT device types and varying levels of available resources among the IoT devices.  ...  For a seamless deployment of the Internet of Things (IoT), there is a need for self-organizing solutions to overcome key IoT challenges that include data processing, resource management, coexistence with  ...  Such a data set needs to be quickly processed for the IoT devices to learn the environment, but the resource-constrained IoT devices may not be able to store and process the data set given that they have  ... 
arXiv:1610.01586v2 fatcat:y2cgaqojcjfqdpkgrqbvyl4wue

Virtual Things for Machine Learning Applications

Gérôme Bovet, Antonio Ridi, Jean Hennebert
2014 Proceedings of the 5th International Workshop on Web of Things - WoT '14  
Internet-of-Things (IoT) devices, especially sensors are producing large quantities of data that can be used for gathering knowledge.  ...  In this paper, we present a novel architecture able to execute machine learning algorithms within the sensor network, presenting advantages in terms of privacy and data transfer efficiency.  ...  We show the possibility to use the computational power of constrained devices already present in the sensor network to run machine learning tasks, reducing the need of pushing data on dedicated computers  ... 
doi:10.1145/2684432.2684434 dblp:conf/wot/BovetRH14 fatcat:5hx3ip5kz5bonjcko3fzw4mbm4

AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning [article]

Ayush Chopra, Surya Kant Sahu, Abhishek Singh, Abhinav Java, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar
2021 arXiv   pre-print
Distributed deep learning frameworks like federated learning (FL) and its variants are enabling personalized experiences across a wide range of web clients and mobile/IoT devices.  ...  This flexibility is extremely useful for low-compute setups but is often achieved at cost of increase in bandwidth consumption and may result in sub-optimal convergence, especially when client data is  ...  Various local learning configurations are proposed where a local objective can be used greedily for each layer [4, 51] , for a set of layers on each device [41] or layers across multiple devices [25  ... 
arXiv:2112.01637v1 fatcat:vy4wlwt4tjaojlqayrykhu6tzq

On-Device Machine Learning: An Algorithms and Learning Theory Perspective [article]

Sauptik Dhar, Junyao Guo, Jiayi Liu, Samarth Tripathi, Unmesh Kurup, Mohak Shah
2020 arXiv   pre-print
This survey finds a middle ground by reformulating the problem of on-device learning as resource constrained learning where the resources are compute and memory.  ...  The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device.  ...  ALGORITHMS FOR ON-DEVICE LEARNING The algorithms approach targets developing resource-efficient techniques that work with existing resource-constrained platforms.  ... 
arXiv:1911.00623v2 fatcat:fokmxmy3x5g7ne7yggm4zpyqta

Exterminating Computational Limits of Machine Learning with Merits of Serverless

Harpreet Kaur, Prabhpreet Kaur
2018 International Journal of Engineering Research and  
The trend of determining patterns using the various machine-learning, data mining, deep-learning or neural networks are limited due to the computational power of machines.  ...  Resources are elastic, which can expand and shrink according to the input data sets, resulting in lesser computational costs.  ...  Such a data set needs to be quickly processed for the IoT devices to learn the environment, but the resource-constrained IoT devices may not be able to store and process the data set given that they have  ... 
doi:10.17577/ijertv7is010147 fatcat:xsbi5flvkjgtjnxctkspzggxhu

Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices [article]

Ramyad Hadidi, Jiashen Cao, Matthew Woodward, Michael S. Ryoo, Hyesoon Kim
2018 arXiv   pre-print
However, IoT networks are usually composed of resource-constrained devices, and a single device is not powerful enough to process real-time data.  ...  We propose Musical Chair to enable efficient, localized, and dynamic real-time recognition by harvesting the aggregated computational power from the resource-constrained devices in the same IoT network  ...  For instance, Microsoft created a library (ELL) [19] that designs and deploys in-telligent machine-learned models onto resource-constrained platforms, such as Raspberry Pi, Arduino, and micro:bit.  ... 
arXiv:1802.02138v3 fatcat:5s3h4j5rnzgppdv4qoqxwdvspq

Deep Learning for Phishing Detection

Wenbin Yao, Yuanhao Ding, Xiaoyong Li
2018 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom)  
Machine learning techniques have recently been introduced for phishing detection.  ...  The attackers try to deceive online users by mimicking a uniform resource locator (URL) and a webpage. Traditionally, phishing detection is largely based on manual reports from users.  ...  deep learning model in a resource-constrained computing device.  ... 
doi:10.1109/bdcloud.2018.00099 dblp:conf/ispa/YaoD018a fatcat:hawrzoyi2jcgte2lzlfvkjj5fy

Learning How to Communicate in the Internet of Things: Finite Resources and Heterogeneity

Taehyeun Park, Nof Abuzainab, Walid Saad
2016 IEEE Access  
This framework is shown to efficiently capture the different IoT device types and varying levels of available resources among the IoT devices.  ...  For a seamless deployment of the Internet of Things (IoT), there is a need for self-organizing solutions to overcome key IoT challenges that include data processing, resource management, coexistence with  ...  Such a data set needs to be quickly processed for the IoT devices to learn the environment, but the resource-constrained IoT devices may not be able to store and process the data set given that they have  ... 
doi:10.1109/access.2016.2615643 fatcat:4krlq2y4oneixh477lttdicyoi

A Deep-Learning-Driven Light-Weight Phishing Detection Sensor

Bo Wei, Rebeen Ali Hamad, Longzhi Yang, Xuan He, Hao Wang, Bin Gao, Wai Lok Woo
2019 Sensors  
Machine learning techniques have recently been introduced for phishing detection.  ...  The attackers try to deceive online users by mimicking a uniform resource locator (URL) and a webpage. Traditionally, phishing detection is largely based on manual reports from users.  ...  deep learning model in a resource-constrained computing device.  ... 
doi:10.3390/s19194258 fatcat:25ac374mvzbrrnokgzddzztysa

Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices

Hamid Dadkhahi, Benjamin M. Marlin
2017 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17  
This work is motivated by research in the area of mobile health where energy efficient real time detectors integrating information from multiple wireless on-body sensors and a smart phone are needed for  ...  In this paper, we present a new approach to learning cascaded classifiers for use in computing environments that involve networks of heterogeneous and resource-constrained, low-power embedded compute and  ...  Acknowledgments The authors would like to thank Deepak Ganesan, Nazir Saleheen, and Santosh Kumar for helpful discussions of this research.  ... 
doi:10.1145/3097983.3098169 pmid:29333328 pmcid:PMC5765542 dblp:conf/kdd/DadkhahiM17 fatcat:fnjpeeb575hsfa2ektwsozdyt4
« Previous Showing results 1 — 15 out of 10,925 results