Kamal Singh

ORCID: 0000-0002-5451-9751
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Semantic Web and Ontologies
  • Topic Modeling
  • Advanced Wireless Network Optimization
  • Opportunistic and Delay-Tolerant Networks
  • Natural Language Processing Techniques
  • Cooperative Communication and Network Coding
  • Vehicular Ad Hoc Networks (VANETs)
  • Video Coding and Compression Technologies
  • IoT and Edge/Fog Computing
  • Network Security and Intrusion Detection
  • Image and Video Quality Assessment
  • Indoor and Outdoor Localization Technologies
  • Advanced MIMO Systems Optimization
  • Data Management and Algorithms
  • Advanced Database Systems and Queries
  • Mobile Ad Hoc Networks
  • Internet Traffic Analysis and Secure E-voting
  • Wireless Networks and Protocols
  • Human Mobility and Location-Based Analysis
  • Software-Defined Networks and 5G
  • Millimeter-Wave Propagation and Modeling
  • Speech and Audio Processing
  • Logic, Reasoning, and Knowledge
  • IoT Networks and Protocols
  • Privacy-Preserving Technologies in Data

Université Jean Monnet
2015-2024

Université Claude Bernard Lyon 1
2016-2024

Laboratoire Hubert Curien
2015-2024

Centre National de la Recherche Scientifique
2016-2024

Aditya Birla (India)
2024

Institute of Engineering
2024

École Nationale d'Ingénieurs de Saint-Étienne
2021

University of Freiburg
2019

Kurukshetra University
2019

University of Alberta
2017

Security has become a critical issue for Industry 4.0 due to different emerging cyber-security threats.Recently, many Deep Learning (DL) approaches have focused on intrusion detection.However, such often require sending data central entity.This in turn raises concerns related privacy, efficiency, and latency.Despite the huge amount of generated by Internet Things (IoT) devices 4.0, it is difficult get labeled data, because labeling costly time-consuming.This poses challenges several DL...

10.1109/tii.2022.3156642 article EN IEEE Transactions on Industrial Informatics 2022-03-07

Video services are being adopted widely in both mobile and fixed networks. For their successful deployment, the content providers increasingly becoming interested evaluating performance of such traffic from final users' perspective, that is, Quality Experience (QoE). this purpose, subjective quality assessment methods costly can not be used real time. Therefore, automatic estimation QoE is highly desired. In paper, we propose a no-reference monitoring module for adaptive HTTP streaming using...

10.1109/ccnc.2012.6181070 preprint EN 2012-01-01

Localization and energy efficiency is very important for UAVs. In this work, we propose a new mechanism data routing based on localization in GPS-denied or GPS-challenged areas. The proposed relies weighted centroid technique, where the position of unknown UAV nodes are calculated using fuzzy logic. organized into clusters. algorithm first localizes UAVs, then elects next cluster head order to minimize consumption whole network consequently increase its lifetime. Evaluation proposal shows...

10.1109/mcom.2018.1700453 article EN IEEE Communications Magazine 2018-04-01

Today's mobile customers desire to remain connected anywhere, at any time, and using device. This phenomenon has encouraged network operators build complex architectures by incorporating new features extensions, which are harder manage operate. In this article we propose a novel simplified architecture for networks. The proposed architecture, call CSDN (Cellular SDN), leverages software defined networking (SDN) functions virtualization (NFV). SDN abstracts the separates control plane from...

10.1109/mcom.2015.7120043 article EN IEEE Communications Magazine 2015-06-01

In the last two decades a new part of web grew significantly, namely Semantic Web. It contains many Knowledge Bases (KB) about different areas like music, books, publications, live science and more. Question Answering (QA) over KBs is seen as most promising approach to bring this data end-users. We describe WDAqua-core1, QA service for querying RDF knowledge-bases. multilingual, it supports knowledge bases understands both full natural language questions keyword questions.

10.1145/3184558.3191541 preprint EN 2018-01-01

Network function virtualization (NFV) will simplify deployment and management of network telecommunication services. NFV provides flexibility by virtualizing the functions moving them to a platform. In order achieve its full potential, is being extended mobile or wireless networks considering radio functions. A typical service setup requires allocation virtual function-forwarding graph (VNF-FG). VNF-FG allocated resource constraints lower infrastructure. This topic has been well-studied in...

10.1109/tnsm.2018.2876623 article EN IEEE Transactions on Network and Service Management 2018-10-17

10.1007/s00521-020-05440-2 article EN Neural Computing and Applications 2020-11-11

Edge Computing in 5G and Beyond is a promising solution for ultra-low latency applications (e.g. Autonomous Vehicle, Augmented Reality, Remote Surgery), which have an extraordinarily low tolerance the delay require fast data processing very high volume of data. The requirements delay-sensitive Low latency, proximity, Location/Context-awareness) cannot be satisfied by Cloud due to between User Equipment Cloud. Nevertheless, beyond can promise ultra-high-speed caused placing computation...

10.1109/tc.2021.3066579 article EN IEEE Transactions on Computers 2021-03-17

We present QAnswer, a Question Answering system which queries at the same time 3 core datasets of Semantic Web, that are relevant for end-users. These Wikidata with Lexemes, LinkedGeodata and Musicbrainz. Additionally, it is possible to query these in English, German, French, Italian, Spanish, Pourtuguese, Arabic Chinese. Moreover, QAnswer includes fallback option search engine Qwant when answer question cannot be found mentioned above. features make as first prototype System over...

10.1145/3308558.3314124 preprint EN 2019-05-13

Network Function Virtualization (NFV) and service orchestration simplify the deployment management of network telecommunication services. The these services require, typically, allocation Virtual - Forwarding Graph (VNF-FG), which implies not only fulfillment service's requirements in terms Quality Service (QoS), but also considering constraints underlying infrastructure. This topic has been well-studied existing literature, however, its complexity uncertainty unveil many challenges for...

10.1109/infcomw.2019.8845184 article EN IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) 2019-04-01

In this paper, we present FLUIDS, a Federated Learning with semi-sUpervised approach for Intrusion Detection System. FLUIDS formulates the intrusion detection into semi-supervised learning where both supervised (using labeled data) and unsupervised (no label are combined in collaborative way. The combination of federated allows solution to: better preserve privacy, improve training inference efficiency, achieve accuracy, be cheaper to deploy.

10.1109/ccnc49033.2022.9700632 preprint EN 2022-01-08

Multimedia streaming over multihop ad hoc networks is an emerging application. Consequently, a novel routing algorithm designed for video necessary. Existing solutions focus on technical parameters such as bandwidth, jitter, delay, etc. However, these are not perfectly correlated to the quality of experience (QoE) perceived by users. In this paper, we study QoE-based problem in wireless networks. We use pseudosubjective assessment (PSQA) tool derive mean opinion score (MOS). As PSQA implicit...

10.1109/tvt.2016.2552041 article EN IEEE Transactions on Vehicular Technology 2016-04-07

With the increasing development of 5G/Beyond 5G and network softwarization techniques, we have more flexibility agility in network. This can be exploited by Machine Learning (ML) to integrate intelligence improve as well service management edge-cloud environment. Intrusion detection systems (IDS) is one challenging issues for managing However, traditional approaches this domain require all data (and their associated labels) centralized at same location. In context, such lead to: (i) a large...

10.1109/icc45855.2022.9839042 article EN ICC 2022 - IEEE International Conference on Communications 2022-05-16

The scalable extension of H.264, known as Scalable Video Coding (SVC), is recently finalized and adapted by the Joint Team. Scalability achieved in temporal, spatial, quality (SNR), or any combination those domains. One example using video scalability saving bandwidth when same media content required to be sent simultaneously at different resolutions support heterogeneous devices networks. Meanwhile, Quality Experience (QoE) key criteria for evaluating service such SVC. Unlike QoS metrics...

10.1109/icc.2011.5963252 preprint EN 2011-06-01

ROHC Bormann C., et al. (2001) is the new standard for header compression proposed by IETF (Internet engineering task force) to compress different protocol headers. needs be configured afford changes in characteristics of UMTS radio link and enable a better IPv6 flows. In this document we will introduce behavior ROHC. Also study parameters that are recommended as implementation dependent specification show how configure them. This can help improve efficiency robustness when it used scarce...

10.1109/pimrc.2003.1259149 preprint EN 2004-06-21

This paper demonstrates the feasibility of an hybrid/semi-supervised classification method for detecting environment active mobile phone, based on both labeled and unlabeled cellular radio data. Precisely, we provide answers to following question: what is user when it is/was experiencing a service/application: indoor or outdoor? Implementing this within network interesting operators since has low complexity, less human intrusive (minimal intervention users) more accurate. The semi-supervised...

10.1109/ccnc.2019.8651736 preprint EN 2019-01-01

Detecting whether a mobile user is indoor or outdoor an important issue which significantly impacts behavior contextualization and network resource management. Indoor Outdoor Detection (IOD) can be performed within networks in terminals. Implementing IOD interesting for operators as it less costly, easier to deploy, more energy efficient with centralized computing. This paper investigates hybrid/semi-supervised Deep Learning-based methods detecting the environment of active phone user. They...

10.1109/icc.2019.8761297 preprint EN 2019-05-01
Coming Soon ...