Machine learning at the network edge for automated home intrusion monitoring
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Monitoring of residences and businesses can be effectively performed using machine learning algorithms. As sensors and devices used for monitoring become more complex, having humans process the information to detect intrusions would be expensive and difficult to scale. We propose an automated home/business monitoring system which resides on edge servers performing online learning on streaming data coming from homes and businesses in the neighborhood. The edge servers run Open-NetVM, a Network Function Virtualization (NFV) platform, and host multiple machine learning applications instantiated on demand. This enables us to serve a set of customers in the neighborhood on a timely basis, permitting customization and learning of the behavior of each home. We combine the results of the multiple classifiers, with each classifier examining a distinct feature related to a distinct sensor, to finally infer whether the entry is a normal one or an intrusion. Our results show that our system is able to classify intrusions better than basing the decision on a single classifier, thus reducing false alarms. We have also shown that our system can effectively scale and monitor thousands of homes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Like use cases in [118], [119], edge computing is deployed to optimize indoor positioning systems and home intrusion monitoring so that they can get lower latency than using cloud computing as well as the better accuracy.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [119]
Citations
Cites
A Mathematical Theory of Evidence
Shafer, G. (2020) · Princeton University Press eBooks · doi:10.2307/j.ctv10vm1qb · Cited by 11,711
A Mathematical Theory of Evidence
Shafer, G. (1976) · Princeton University Press eBooks · doi:10.1515/9780691214696 · Cited by 9,083
Upper and Lower Probabilities Induced by a Multivalued Mapping
Dempster, A. P. (1967) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177698950 · Cited by 6,126
Upper and Lower Probabilities Induced by a Multivalued Mapping
Dempster, A. P. (2008) · Studies in Fuzziness and Soft Computing · doi:10.1007/978-3-540-44792-4_3 · Cited by 5,296 · cited 1×
“The Dempster-Shafer (D-S) theory of evidence [9] [10] has been widely used as a method to fuse multiple decisions from different ML classifiers to make an overall inference.”
MethodThe problem of concept drift: definitions and related work
Tsymbal, A. (2004) · Cited by 929
(2016) · Cited by 844
OpenNetVM: A Platform for High Performance Network Service Chains
Zhang, W., Liu, G., Zhang, W., Shah, N., Lopreiato, P., Todeschi, G., Ramakrishnan, K. K., & Wood, T. (2016) · Proceedings of the 2016 workshop on Hot topics in Middleboxes and Network Function Virtualization · doi:10.1145/2940147.2940155 · Cited by 204 · cited 2×
“We have used OpenNetVM[2] as the platform to run our ML classifiers.”
MethodSelf-citationVirtual function placement and traffic steering in flexible and dynamic software defined networks
Mohammadkhan, A., Ghapani, S., Liu, G., Zhang, W. D., Ramakrishnan, K. K., & Wood, T. (2015) · IEEE International Symposium on Local and Metropolitan Area Networks (LANMAN) · doi:10.1109/lanman.2015.7114738 · Cited by 111 · cited 1×
“OpenNetVM’s simplifies the process of developing and hosting the NFs and efficiently route the packets through the NF service chains[6].”
MethodSelf-citationCumulative and averaging fusion of beliefs
Jøsang, A., Diaz, J., & Rifqi, M. (2009) · Information Fusion · doi:10.1016/j.inffus.2009.05.005 · Cited by 73 · cited 1×
“2) Dempster’s Rule of Combination: We can use Dempster’s rule of cumulative combination (DRC) [11] that is used to combine evidence from different independent sources.”
MethodActivity Learning as a Foundation for Security Monitoring in Smart Homes
Dahmen, J., Thomas, B., Cook, D. J., & Wang, X. (2017) · Sensors · doi:10.3390/s17040737 · Cited by 68 · cited 4×
“With the growth of machine learning algorithms, and their effectiveness increased by the availability of more powerful computation resources, automating home monitoring is becoming increasingly feasible[1].”
BackgroundMethodInfluential
Cited by
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“Like use cases in [118], [119], edge computing is deployed to optimize indoor positioning systems and home intrusion monitoring so”
MethodAll one needs to know about fog computing and related edge computing paradigms: A complete survey
Yousefpour, A., Fung, C., Nguyen, T., Kadiyala, K., Jalali, F., Niakanlahiji, A., Kong, J., & Jue, J. P. (2019) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2019.02.009 · Cited by 1,368
“Applications [20, 51, 61, 100, 154, 159, 174, 175, 190, 191, 247, 263, 271, 276, 287, 306, 320, 321, 323, 330–379]”
Deep learning for edge computing applications: A State-of-the-Art survey
Wang, F., Zhang, M., Wang, X., Ma, X., & Liu, J. (2020) · IEEE Access · doi:10.1109/access.2020.2982411 · Cited by 259
“Dhakal AND Ramakrishnan [93] developed an automated home/business monitoring system which on Network Function Virtualization (NFV) edge servers performing online learning on streaming data coming from homes and businesses in the neighborhood.”
MethodGrzesik, P., & Mrozek, D. (2024) · Electronics · doi:10.3390/electronics13030640 · Cited by 75
“A system for home intrusion monitoring has been introduced by Dhakal and Ramakrishnan in their work [96].”
MethodSupporting IoT Applications with Serverless Edge Clouds
Wang, I., Liri, E., & Ramakrishnan, K. K. (2020) · IEEE International Conference on Cloud Networking · doi:10.1109/cloudnet51028.2020.9335805 · Cited by 28
“[9] proposes a home/office monitoring system using IoT devices and multiple classifiers to determine when a home intrusion occurs.”
BackgroundSelf-citationNetML: An NFV Platform with Efficient Support for Machine Learning Applications
Dhakal, A., & Ramakrishnan, K. K. (2019) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft.2019.8806698 · Cited by 16
“[4] However, offloading any task to edge or cloud server comes with overheads which increases end-to-end latency.”
BackgroundSelf-citationOn Preempting Advanced Persistent Threats Using Probabilistic Graphical ModelsPreprint
Cao, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.08826 · Cited by 12
Edge-based Parametric Digital Twins for Intelligent Building Indoor Climate Modeling
Ni, Z., Zhang, C., Karlsson, M., & Gong, S. (2024) · IEEE International Workshop on Factory Communication Systems (WFCS) · doi:10.1109/wfcs60972.2024.10540966 · Cited by 11
“Many studies have reported applying intelligent edge computing in the built environment, such as indoor localization [31], home intrusion monitoring [32], and resource allocation [33].”
BackgroundMethodEdge Computing: A Paradigm Shift for Delay-Sensitive AI Application
Nigam, S., & Karyakarte, M. S. (2023) · Signals and communication technology · doi:10.1007/978-3-031-29713-7_4 · Cited by 8
iTempDT: AI-Powered Digital Twin for Forecasting Indoor Temperature in Smart Buildings
Islam, M. B., Guerrieri, A., Gravina, R., Pontieri, L., Rizzo, L., Scala, F., Vinci, A., & Fortino, G. (2025) · IEEE Conference on Pervasive and Intelligent Computing (PICom) · doi:10.1109/picom68402.2025.00022 · Cited by 6
“In the context of home security, another edge-based system processed sensor data locally using kNN and DNN to detect intrusions with low latency and strong privacy [22].”
Fusing Heterogeneous Data for Network Asset Classification – A Two-layer Approach
Sedláček, O., & Bartoš, V. (2024) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms59830.2024.10575154 · Cited by 4
“Dhakal and Ramakrishnan [6] show that using the D-S theory to perform information fusion lowers the number of false positives and improves overall reliability.”
MethodArtificial Intelligence Applications on Edge
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_4 · Cited by 2
TempTwin: Digital Twin for Energy Efficient and Comfort-Oriented Indoor Temperature Forecasting
Islam, M. B., Guerrieri, A., Li, Q., Qi, W., Gravina, R., Rizzo, L., & Fortino, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460842 · Cited by 1
Investigation of Edge-Fog Layer for Accuracy and Power Consumption
Iyeswariya, K., & Muthubharathi, R. (2020) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs48705.2020.9074194 · Cited by 1
“The paper shows the scalable detection of intrusion by reduction of false alarms [7].”
BackgroundEdge Analytics and Deep Learning for Sustainable Development
Singh, S. K., Chakraborty, S., & Soodan, V. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-70183-3_10 · Cited by 1
Poster Abstract: Camera-Assisted Training of Non-Vision Sensors for Anomaly Detection
Albazzai, N., RANA, O. F., & Perera, C. (2023) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1145/3576842.3589164
“We evaluate our approach by implementing a case study that detects open doors as anomalies due to their potential security risks, impact on Heating, Ventilation and Air Conditioning (HVAC) systems, and energy usage [2].”
MethodData-Driven Smart Maintenance of Historic Buildings
Ni, Z. (2025) · Linköping studies in science and technology. Dissertations · doi:10.3384/9789181180602
Machine Learning Approach to Classify Gas and Position for Single Elder Home
Abdelfattah, E., & Bowlyn, K. (2025) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon67449.2025.11267627
Metadata
- Authors
- Dhakal, A., & Ramakrishnan, K. K.
- Affiliations
- University of California System (US)
- Venue
- 2017 IEEE 25th International Conference on Network Protocols (ICNP)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 1-6
- ISSN
- 1092-1648 (ISSN-L)
- OpenAlex
- W2770288335
- Cited by
- 17
- References
- 14
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 3 · 2023: 2 · 2021: 1 · 2020: 5 · 2019: 3
- FWCI
- 1.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Network Protocols (ICNP) (publishedVersion)
- Funders
- National Science Foundation
- Research, Development and Engineering Command
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT-based Smart Home Systems
- Keywords
- edge computing, online learning, data streams, network function virtualization, multi-classifier ensemble, sensor fusion, false alarm reduction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.