Tarik Kazaz | Ghent University (original) (raw)
Papers by Tarik Kazaz
This paper presents end-to-end learning from spectrum data-an umbrella term for new sophisticated... more This paper presents end-to-end learning from spectrum data-an umbrella term for new sophisticated wireless signal identification approaches in spectrum monitoring applications based on deep neural networks. End-to-end learning allows to (i) automatically learn features directly from simple wireless signal representations, without requiring design of hand-crafted expert features like higher order cyclic moments, and (ii) train wireless signal classifiers in one end-to-end step which eliminates the need for complex multi-stage machine learning processing pipelines. The purpose of this article is to present the conceptual framework of end-to-end learning for spectrum monitoring and systematically introduce a generic methodology to easily design and implement wireless signal classifiers. Furthermore, we investigate the importance of the choice of wireless data representation to various spectrum monitoring tasks. In particular, two case studies are elaborated (i) modulation recognition and (ii) wireless technology interference detection. For each case study three convolutional neural networks are evaluated for the following wireless signal representations: temporal IQ data, the amplitude/phase representation and the frequency domain representation. From our analysis we prove that the wireless data representation impacts the accuracy depending on the specifics and similarities of the wireless signals that need to be differentiated, with different data representations resulting in accuracy variations of up to 29%. Experimental results show that using the amplitude/phase representation for recognizing modulation formats can lead to performance improvements up to 2% and 12% for medium to high SNR compared to IQ and frequency domain data, respectively. For the task of detecting interference, frequency domain representation outperformed amplitude/phase and IQ data representation up to 20%.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
—The control mechanisms that are provided today in wireless technologies are not adequate to deal... more —The control mechanisms that are provided today in wireless technologies are not adequate to deal with extreme (ultra‐low latency, ultra‐high throughput, ultra‐high reliability) and diverging (low AND high data rate, time‐critical AND non-time critical) communication needs. Interesting evolutions are happening at different levels that enable the creation of parallel network slices, each slice forming a different network sharing the underlying wireless infrastructure and spectrum. The overall ORCA vision is to drive end-to-end wireless network innovation by bridging real-time Software-Defined Radio and Software-Defined Networking, exploiting maximum flexibility at radio level, medium access level and network level, to meet very diverse application requirements.
Bookmarks Related papers MentionsView impact
Driven by the fast growth of wireless communication, the trend of sharing spectrum among heteroge... more Driven by the fast growth of wireless communication, the trend of sharing spectrum among heterogeneous technologies becomes increasingly dominant. Identifying concurrent technologies is an important step towards efficient spectrum sharing. However, due to the complexity of recognition algorithms and the strict condition of sampling speed, communication systems capable of recognizing signals other than their own type are extremely rare. This work proves that multi-model distribution of the received signal strength indicator (RSSI) is related to the signals' modulation schemes and medium access mechanisms, and RSSI from different technologies may exhibit highly distinctive features. A distinction is made between technologies with a streaming or a non-streaming property, and appropriate feature spaces can be established either by deriving parameters such as packet duration from RSSI or directly using RSSI's probability distribution. An experimental study shows that even RSSI acquired at a sub-Nyquist sampling rate is able to provide sufficient features to differentiate technologies such as Wi-Fi, Long Term Evolution (LTE), Digital Video Broadcasting-Terrestrial (DVB-T) and Bluetooth. The usage of the RSSI distribution-based feature space is illustrated via a sample algorithm. Experimental evaluation indicates that more than 92% accuracy is achieved with the appropriate configuration. As the analysis of RSSI distribution is straightforward and less demanding in terms of system requirements, we believe it is highly valuable for recognition of wideband technologies on constrained devices in the context of dynamic spectrum access.
Bookmarks Related papers MentionsView impact
Predictable network performance is key in many low-power wireless sensor network applications. In... more Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for real-time characterization of the communication performance as observed by the MAC layer. Our approach is data-driven and consists of three steps: extensive experiments for data collection , offline modeling and trace-driven performance evaluation. From our experiments and analysis, we find that a neural networks prediction model shows best performance.
Bookmarks Related papers MentionsView impact
Predictable network performance is key in many low-power wireless sensor network applications. In... more Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for real-time characterization of the communication performance as observed by the MAC layer. Our approach is data-driven and consists of three steps: extensive experiments for data collection , offline modeling and trace-driven performance evaluation. From our experiments and analysis, we find that a neural networks prediction model shows best performance.
Bookmarks Related papers MentionsView impact
To enhance system performance of future heterogeneous wireless networks the co-design of PHY, MAC... more To enhance system performance of future heterogeneous wireless networks the co-design of PHY, MAC, and higher layer protocols is inevitable. In this work, we present WiS-CoP-a novel embedded platform for experimentation, pro-totyping and implementation of integrated cross-layer network design approaches. WiSCoP is built on top of a Zynq hardware platform integrated with FMCOMMS1/2/4 RF front-ends. We demonstrate the flexibility of WiSCoP by using it to prototype a fully standard compliant IEEE 802.15.4 stack with real-time performance and cross-layer integration.
Bookmarks Related papers MentionsView impact
—Advanced 5G wireless infrastructure should support any-to-any connectivity between densely arran... more —Advanced 5G wireless infrastructure should support any-to-any connectivity between densely arranged smart objects that form the emerging paradigm known as the Internet of Everything (IoE). While traditional wireless networks enable communication between devices using a single technology, 5G networks will need to support seamless connectivity between heterogeneous wireless objects, and consequently enable the proliferation of IoE networks. To tackle the complexity and versatility of the future IoE networks, 5G has to guarantee optimal usage of both spectrum and energy resources and further support technology-agnostic connectivity between objects. This can be realized by combining intelligent network control with adaptive software-defined air interfaces. In order to achieve this, current radio technology paradigms like Cloud RAN and Software Defined Radio (SDR) utilize centralized baseband signal processing mainly performed in software. With traditional SDR platforms, composed of separate radio and host commodity computer units, computationally-intensive signal processing algorithms and high-throughput connectivity between processing units are hard to realize. In addition, significant power consumption and large form factor may preclude any real-life deployment of such systems. On the other hand, modern hybrid FPGA technology tightly couples a FPGA fabric with hard core CPU on a single chip. This provides opportunities for implementing air interfaces based on hardware/software co-processing, resulting in increased processing throughput, reduced form factor and power consumption, while at the same time preserving flexibility. This paper examines how hybrid FPGAs can be combined with novel ideas such as RF Network-on-Chip (RFNoC) and partial reconfiguration, to form a flexible and compact platform for implementing low-power adaptive air interfaces. The proposed platform merges software and hardware processing units of SDR systems on a single chip. Therefore, it can provide interfaces for on-the-fly composition and reconfiguration of software and hardware radio modules. The resulting system enables the abstraction of air interfaces, where each access technology is composed of a structured sequence of modular radio processing units.
Bookmarks Related papers MentionsView impact
Software defined radio (SDR) technology enables implementation of wireless devices that support m... more Software defined radio (SDR) technology enables implementation of wireless devices that support multiple air-interfaces and modulation formats, which is very important if consider proliferation of wireless standards. To enable such functionality SDR is using reconfigurable hardware platform such as Field Programmable Gate Array (FPGA). In this paper, we present design procedure and implementation result of SDR based QPSK modulator on Altera Cyclone IV FPGA. For design and implementation of QPSK modulator we used Altera DSP Builder Tool combined with Matlab/Simulink, Modelsim and Quartus II design tools. As reconfigurable hardware platform we used Altera DE2-115 development and education board with AD/DA daughter card. Software and Hardware-in-the-loop (HIL) simulation was conducted before hardware implementation and verification of designed system. This method of design makes implementation of SDR based modulators simpler ad faster.
Bookmarks Related papers MentionsView impact
… (BIHTEL), 2012 IX International …, 2012
VoIP (Voice over Internet) provides delivery of voice information over unsecured IP-based network... more VoIP (Voice over Internet) provides delivery of voice information over unsecured IP-based networks like the Internet. VoIP data, signaling and voice, needs to be secured in such an environment. Security mechanisms take their toll on VoIP system performance. SIP is dominant signaling protocol for VoIP. This paper measures relative decrease in VoIP performance of system with secured SIP signaling over one without it. It compares SIP with authentication enabled over three transport protocols: UDP, TCP and TLS. Peak throughput of concurrent calls, registration request delay, session request delay, SIP server CPU and RAM usage are measured. Testbed environment consists of Asterisk IP private branch exchange (PBX) as a part of Elastix server, several SIP user agents and SIPp traffic generator. Test results show that performance of SIP over TLS based signaling is four times lower than the SIP signaling over UDP in most metrics.
Bookmarks Related papers MentionsView impact
… , 2012 Proceedings of …, 2012
This paper presents an approach to the development of custom agents and their integration with ne... more This paper presents an approach to the development of custom agents and their integration with network management systems. For the development of agents is given one approach, and according to this approach an implementation of the agent using Open Dynamic Management Kit (OpenDMK) libraries in the Java programming language is performed. Within the agents are implemented all standard Simple Network Management Protocol (SNMP) functionality - reading values, setting values and traps sending. Finally, the integration is performed with several network management systems such as Zenoss and Cacti. Tests have confirmed the success of this integration, thus verifying the proposed approach.
Bookmarks Related papers MentionsView impact
Drafts by Tarik Kazaz
(ACSSC 2018) 2018 Asilomar Conference on Signals, Systems and ComputersAt: Pacific Grove, CA, USA, 2018
—Synchronization and ranging in internet of things (IoT) networks are challenging due to the narr... more —Synchronization and ranging in internet of things (IoT) networks are challenging due to the narrowband nature of signals used for communication between IoT nodes. Recently, several estimators for range estimation using phase difference of arrival (PDoA) measurements of narrowband signals have been proposed. However, these estimators are based on data models which do not consider the impact of clock-skew on the range estimation. In this paper, clock-skew and range estimation are studied under a unified framework. We derive a novel and precise data model for PDoA measurements which incorporates the unknown clock-skew effects. We then formulate joint estimation of the clock-skew and range as a two-dimensional (2-D) frequency estimation problem of a single complex sinusoid. Furthermore, we propose: (i) a two-way communication protocol for collecting PDoA measurements and (ii) a weighted least squares (WLS) algorithm for joint estimation of clock-skew and range leveraging the shift invariance property of the measurement data. Finally, through numerical experiments, the performance of the proposed protocol and estimator is compared against the Cramér Rao lower bound demonstrating that the proposed estimator is asymptotically efficient.
Bookmarks Related papers MentionsView impact
This paper presents end-to-end learning from spectrum data-an umbrella term for new sophisticated... more This paper presents end-to-end learning from spectrum data-an umbrella term for new sophisticated wireless signal identification approaches in spectrum monitoring applications based on deep neural networks. End-to-end learning allows to (i) automatically learn features directly from simple wireless signal representations, without requiring design of hand-crafted expert features like higher order cyclic moments, and (ii) train wireless signal classifiers in one end-to-end step which eliminates the need for complex multi-stage machine learning processing pipelines. The purpose of this article is to present the conceptual framework of end-to-end learning for spectrum monitoring and systematically introduce a generic methodology to easily design and implement wireless signal classifiers. Furthermore, we investigate the importance of the choice of wireless data representation to various spectrum monitoring tasks. In particular, two case studies are elaborated (i) modulation recognition and (ii) wireless technology interference detection. For each case study three convolutional neural networks are evaluated for the following wireless signal representations: temporal IQ data, the amplitude/phase representation and the frequency domain representation. From our analysis we prove that the wireless data representation impacts the accuracy depending on the specifics and similarities of the wireless signals that need to be differentiated, with different data representations resulting in accuracy variations of up to 29%. Experimental results show that using the amplitude/phase representation for recognizing modulation formats can lead to performance improvements up to 2% and 12% for medium to high SNR compared to IQ and frequency domain data, respectively. For the task of detecting interference, frequency domain representation outperformed amplitude/phase and IQ data representation up to 20%.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
—The control mechanisms that are provided today in wireless technologies are not adequate to deal... more —The control mechanisms that are provided today in wireless technologies are not adequate to deal with extreme (ultra‐low latency, ultra‐high throughput, ultra‐high reliability) and diverging (low AND high data rate, time‐critical AND non-time critical) communication needs. Interesting evolutions are happening at different levels that enable the creation of parallel network slices, each slice forming a different network sharing the underlying wireless infrastructure and spectrum. The overall ORCA vision is to drive end-to-end wireless network innovation by bridging real-time Software-Defined Radio and Software-Defined Networking, exploiting maximum flexibility at radio level, medium access level and network level, to meet very diverse application requirements.
Bookmarks Related papers MentionsView impact
Driven by the fast growth of wireless communication, the trend of sharing spectrum among heteroge... more Driven by the fast growth of wireless communication, the trend of sharing spectrum among heterogeneous technologies becomes increasingly dominant. Identifying concurrent technologies is an important step towards efficient spectrum sharing. However, due to the complexity of recognition algorithms and the strict condition of sampling speed, communication systems capable of recognizing signals other than their own type are extremely rare. This work proves that multi-model distribution of the received signal strength indicator (RSSI) is related to the signals' modulation schemes and medium access mechanisms, and RSSI from different technologies may exhibit highly distinctive features. A distinction is made between technologies with a streaming or a non-streaming property, and appropriate feature spaces can be established either by deriving parameters such as packet duration from RSSI or directly using RSSI's probability distribution. An experimental study shows that even RSSI acquired at a sub-Nyquist sampling rate is able to provide sufficient features to differentiate technologies such as Wi-Fi, Long Term Evolution (LTE), Digital Video Broadcasting-Terrestrial (DVB-T) and Bluetooth. The usage of the RSSI distribution-based feature space is illustrated via a sample algorithm. Experimental evaluation indicates that more than 92% accuracy is achieved with the appropriate configuration. As the analysis of RSSI distribution is straightforward and less demanding in terms of system requirements, we believe it is highly valuable for recognition of wideband technologies on constrained devices in the context of dynamic spectrum access.
Bookmarks Related papers MentionsView impact
Predictable network performance is key in many low-power wireless sensor network applications. In... more Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for real-time characterization of the communication performance as observed by the MAC layer. Our approach is data-driven and consists of three steps: extensive experiments for data collection , offline modeling and trace-driven performance evaluation. From our experiments and analysis, we find that a neural networks prediction model shows best performance.
Bookmarks Related papers MentionsView impact
Predictable network performance is key in many low-power wireless sensor network applications. In... more Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for real-time characterization of the communication performance as observed by the MAC layer. Our approach is data-driven and consists of three steps: extensive experiments for data collection , offline modeling and trace-driven performance evaluation. From our experiments and analysis, we find that a neural networks prediction model shows best performance.
Bookmarks Related papers MentionsView impact
To enhance system performance of future heterogeneous wireless networks the co-design of PHY, MAC... more To enhance system performance of future heterogeneous wireless networks the co-design of PHY, MAC, and higher layer protocols is inevitable. In this work, we present WiS-CoP-a novel embedded platform for experimentation, pro-totyping and implementation of integrated cross-layer network design approaches. WiSCoP is built on top of a Zynq hardware platform integrated with FMCOMMS1/2/4 RF front-ends. We demonstrate the flexibility of WiSCoP by using it to prototype a fully standard compliant IEEE 802.15.4 stack with real-time performance and cross-layer integration.
Bookmarks Related papers MentionsView impact
—Advanced 5G wireless infrastructure should support any-to-any connectivity between densely arran... more —Advanced 5G wireless infrastructure should support any-to-any connectivity between densely arranged smart objects that form the emerging paradigm known as the Internet of Everything (IoE). While traditional wireless networks enable communication between devices using a single technology, 5G networks will need to support seamless connectivity between heterogeneous wireless objects, and consequently enable the proliferation of IoE networks. To tackle the complexity and versatility of the future IoE networks, 5G has to guarantee optimal usage of both spectrum and energy resources and further support technology-agnostic connectivity between objects. This can be realized by combining intelligent network control with adaptive software-defined air interfaces. In order to achieve this, current radio technology paradigms like Cloud RAN and Software Defined Radio (SDR) utilize centralized baseband signal processing mainly performed in software. With traditional SDR platforms, composed of separate radio and host commodity computer units, computationally-intensive signal processing algorithms and high-throughput connectivity between processing units are hard to realize. In addition, significant power consumption and large form factor may preclude any real-life deployment of such systems. On the other hand, modern hybrid FPGA technology tightly couples a FPGA fabric with hard core CPU on a single chip. This provides opportunities for implementing air interfaces based on hardware/software co-processing, resulting in increased processing throughput, reduced form factor and power consumption, while at the same time preserving flexibility. This paper examines how hybrid FPGAs can be combined with novel ideas such as RF Network-on-Chip (RFNoC) and partial reconfiguration, to form a flexible and compact platform for implementing low-power adaptive air interfaces. The proposed platform merges software and hardware processing units of SDR systems on a single chip. Therefore, it can provide interfaces for on-the-fly composition and reconfiguration of software and hardware radio modules. The resulting system enables the abstraction of air interfaces, where each access technology is composed of a structured sequence of modular radio processing units.
Bookmarks Related papers MentionsView impact
Software defined radio (SDR) technology enables implementation of wireless devices that support m... more Software defined radio (SDR) technology enables implementation of wireless devices that support multiple air-interfaces and modulation formats, which is very important if consider proliferation of wireless standards. To enable such functionality SDR is using reconfigurable hardware platform such as Field Programmable Gate Array (FPGA). In this paper, we present design procedure and implementation result of SDR based QPSK modulator on Altera Cyclone IV FPGA. For design and implementation of QPSK modulator we used Altera DSP Builder Tool combined with Matlab/Simulink, Modelsim and Quartus II design tools. As reconfigurable hardware platform we used Altera DE2-115 development and education board with AD/DA daughter card. Software and Hardware-in-the-loop (HIL) simulation was conducted before hardware implementation and verification of designed system. This method of design makes implementation of SDR based modulators simpler ad faster.
Bookmarks Related papers MentionsView impact
… (BIHTEL), 2012 IX International …, 2012
VoIP (Voice over Internet) provides delivery of voice information over unsecured IP-based network... more VoIP (Voice over Internet) provides delivery of voice information over unsecured IP-based networks like the Internet. VoIP data, signaling and voice, needs to be secured in such an environment. Security mechanisms take their toll on VoIP system performance. SIP is dominant signaling protocol for VoIP. This paper measures relative decrease in VoIP performance of system with secured SIP signaling over one without it. It compares SIP with authentication enabled over three transport protocols: UDP, TCP and TLS. Peak throughput of concurrent calls, registration request delay, session request delay, SIP server CPU and RAM usage are measured. Testbed environment consists of Asterisk IP private branch exchange (PBX) as a part of Elastix server, several SIP user agents and SIPp traffic generator. Test results show that performance of SIP over TLS based signaling is four times lower than the SIP signaling over UDP in most metrics.
Bookmarks Related papers MentionsView impact
… , 2012 Proceedings of …, 2012
This paper presents an approach to the development of custom agents and their integration with ne... more This paper presents an approach to the development of custom agents and their integration with network management systems. For the development of agents is given one approach, and according to this approach an implementation of the agent using Open Dynamic Management Kit (OpenDMK) libraries in the Java programming language is performed. Within the agents are implemented all standard Simple Network Management Protocol (SNMP) functionality - reading values, setting values and traps sending. Finally, the integration is performed with several network management systems such as Zenoss and Cacti. Tests have confirmed the success of this integration, thus verifying the proposed approach.
Bookmarks Related papers MentionsView impact
(ACSSC 2018) 2018 Asilomar Conference on Signals, Systems and ComputersAt: Pacific Grove, CA, USA, 2018
—Synchronization and ranging in internet of things (IoT) networks are challenging due to the narr... more —Synchronization and ranging in internet of things (IoT) networks are challenging due to the narrowband nature of signals used for communication between IoT nodes. Recently, several estimators for range estimation using phase difference of arrival (PDoA) measurements of narrowband signals have been proposed. However, these estimators are based on data models which do not consider the impact of clock-skew on the range estimation. In this paper, clock-skew and range estimation are studied under a unified framework. We derive a novel and precise data model for PDoA measurements which incorporates the unknown clock-skew effects. We then formulate joint estimation of the clock-skew and range as a two-dimensional (2-D) frequency estimation problem of a single complex sinusoid. Furthermore, we propose: (i) a two-way communication protocol for collecting PDoA measurements and (ii) a weighted least squares (WLS) algorithm for joint estimation of clock-skew and range leveraging the shift invariance property of the measurement data. Finally, through numerical experiments, the performance of the proposed protocol and estimator is compared against the Cramér Rao lower bound demonstrating that the proposed estimator is asymptotically efficient.
Bookmarks Related papers MentionsView impact