Marco Breiling - Academia.edu (original) (raw)
Papers by Marco Breiling
2019 IEEE Nordic Circuits and Systems Conference (NORCAS): NORCHIP and International Symposium of System-on-Chip (SoC)
Traditionally, Recurrent Neural Networks (RNNs) are used for time-series prediction. However, rec... more Traditionally, Recurrent Neural Networks (RNNs) are used for time-series prediction. However, recent results have shown that Temporal Convolutional Networks (TCNs) outperform RNNs in terms of accuracy and training time. By using dilated convolutions TCNs are able to capture long term temporal dependencies from time series. The use of existing Convolutional Neural Networks (CNNs) inference accelerators for the computation of dilated convolutions significantly decreases the throughput and causes computation overhead. In order to take into account the one-dimensionality of the convolutions and presence of dilation, this paper proposes a dedicated hardware inference accelerator for TCNs. We use this accelerator to run an adaptation of WaveNet for anomaly detection in an ECG time series dataset. Our results show that it can achieve 6.3 · 10−4 DRAM access/MAC, 0.043 on-chip SRAM access/MAC and 8 ms/inference. This lower number of on-chip and off-chip memory accesses significantly decreases the overall power consumption and increases the throughput.
2017 IEEE Conference on Standards for Communications and Networking (CSCN), 2017
In this paper, we present a Vehicular version of the Shared UE-side Distributed Antenna System (S... more In this paper, we present a Vehicular version of the Shared UE-side Distributed Antenna System (SUDAS) i.e. Vehicular SUDAS which enables high throughput wireless communication in high mobility Vehicle-to-X (V2X) scenarios. Vehicular SUDAS uses shared virtual antennas, termed UE-side Radio Units (URUs), which utilize both licensed sub-6 GHz band and unlicensed millimetre wave band, to achieve a virtual MIMO gain in in-vehicle UEs. A simulation study is performed to evaluate and analyze an upper bound of the maximum achievable sum rate in the downlink of the proposed system, assuming perfect Doppler spread compensation. The proposed Vehicular SUDAS shows excellent performance, positioning itself as a strong contender for next V2X communication services.
2018 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2018
Shared UE-side Distributed Antenna System (SUDAS) is a very promising technique in order to deliv... more Shared UE-side Distributed Antenna System (SUDAS) is a very promising technique in order to deliver an improved coverage and high throughput beyond 10 Gbit/s to the users in the indoor and intra-vehicular scenarios for 5G applications. This paper presents an implementation perspective and comparison analysis of different candidate hardware architectures suitable for the Shared UE-side Distributed Antenna Component (SUDAC), which is the main building block of the SUDAS and acts as a relay and performs massive spatial-to-frequency domain translation and vice versa. Based on the defined comparison criteria and scoring of different architectures, it has been established that Analog SUDAC with Slight Frequency Shifting (SFS), Analog SUDAC with Digital Control, Digital SUDAC with 802.11ad and Digital SUDAC with Frequency Domain Equalization (FDE) are the top candidates for hardware implementation and future deployment.
2017 IEEE 86th Vehicular Technology Conference (VTC-Fall), 2017
In this paper, we consider resource allocation for an outdoor-to-indoor shared user-equipment (UE... more In this paper, we consider resource allocation for an outdoor-to-indoor shared user-equipment (UE)- side distributed antenna system (SUDAS) employing multiple independently operating compress-and- forward (CF) relays which utilize both licensed and unlicensed frequency bands to enhance indoor data throughput. First, a non-convex matrix-valued resource allocation problem for maximization of the weighted sum rate is formulated. Next, the non-convex problem is simplified to obtain a low- complexity suboptimal resource allocation algorithm based on sequential quadratic programming (SQP). The proposed algorithm is shown to provide excellent performance in practical scenarios. Furthermore, the algorithm has a low channel state information (CSI) feedback requirement and can accommodate arbitrary communication bands and technologies for indoor relaying. Therefore, the proposed CF-SUDAS scheme can help achieve high outdoor-to-indoor data throughput at low complexity, a crucial requirement fo...
Ein Faltungs-Interleaver zum Verarbeiten eines Codeworts, das von einem Eingangsblock von Symbole... more Ein Faltungs-Interleaver zum Verarbeiten eines Codeworts, das von einem Eingangsblock von Symbolen unter Verwendung einer Redundanz-hinzufugenden-Codierung abgeleitet ist, und das mehr Symbole als der Eingangsblock aufweist, wobei das Codewort eine Sequenz von Verschachtelungseinheiten aufweist, wobei jede Verschachtelungseinheit wenigstens zwei Symbole aufweist, umfasst eine Verschachtelungseinrichtung. Die Verschachtelungseinrichtung verandert die Sequenz von Verschachtelungseinheiten, um ein verschachteltes Codewort zu erhalten, das eine veranderte Sequenz von Verschachtelungseinheiten aufweist. Insbesondere wird durch die Verschachtelungseinrichtung die Reihenfolge der Symbole innerhalb einer Verschachtelungseinheit nicht verandert. Allerdings wird die Reihenfolge der Verschachtelungseinheiten im Codewort untereinander oder bezuglich eines vorhergehenden oder nachfolgenden Codeworts verandert.
The aim of the invention is to reduce the out-of-band radiation in a distortion-free manner. A pl... more The aim of the invention is to reduce the out-of-band radiation in a distortion-free manner. A plurality of candidate transmission sequences is produced (10) from an information word. One of the candidate transmission sequences which meets a predetermined criterion is then selected (30). A different tag is added (12) to the information word respectively for producing the different candidate transmission sequences. The information word, together with the added tag, is subsequently processed by means of an invertable feedback combination algorithm (16) for obtaining a combined information word, wherein the information units are combined to each other and/or the added tag in such a way that the combined information word is clearly identified by the tag. The combined information word is fed to an algorithm in the receiver. Said algorithm is inverse in relation to the feedback combination algorithm and is automatically controlled by the tag for reproducing the information word. The infor...
Interleaver means (110) for common transmission of a first and a second transport channel (TC1; T... more Interleaver means (110) for common transmission of a first and a second transport channel (TC1; TC2) via a transmission channel, wherein the first transport channel (TC1) a sequence of first interleave units (IU (1, n)) and the second transport channel (TS2 ) a sequence of second interleave units (IU (2, n)), wherein each interleave including at least one symbol, comprising: a Faltungsverschachtelungseinrichtung (10-1; 10-2) for varying the sequence of the first interleave units according to a first Faltungsverschachtelungsvorschrift (40; 50; 112), the first transmission resources (41; 51) defined for the common transmission, a first interleaved transport channel ( to obtain 52) which has an altered sequence of first interleave units, and (for varying the sequence of the second interleaver according to a second Faltungsverschachtelungsvorschrift 60;; 42 70; 114), the second transmission resources (61; 71) for the common transmission defined, a second interleaved transport channel (6...
Micromachines, 2021
Pattern recognition as a computing task is very well suited for machine learning algorithms utili... more Pattern recognition as a computing task is very well suited for machine learning algorithms utilizing artificial neural networks (ANNs). Computing systems using ANNs usually require some sort of data storage to store the weights and bias values for the processing elements of the individual neurons. This paper introduces a memory block using resistive memory cells (RRAM) to realize this weight and bias storage in an embedded and distributed way while also offering programming and multi-level ability. By implementing power gating, overall power consumption is decreased significantly without data loss by taking advantage of the non-volatility of the RRAM technology. Due to the versatility of the peripheral circuitry, the presented memory concept can be adapted to different applications and RRAM technologies.
2019 IEEE Nordic Circuits and Systems Conference (NORCAS): NORCHIP and International Symposium of System-on-Chip (SoC)
Traditionally, Recurrent Neural Networks (RNNs) are used for time-series prediction. However, rec... more Traditionally, Recurrent Neural Networks (RNNs) are used for time-series prediction. However, recent results have shown that Temporal Convolutional Networks (TCNs) outperform RNNs in terms of accuracy and training time. By using dilated convolutions TCNs are able to capture long term temporal dependencies from time series. The use of existing Convolutional Neural Networks (CNNs) inference accelerators for the computation of dilated convolutions significantly decreases the throughput and causes computation overhead. In order to take into account the one-dimensionality of the convolutions and presence of dilation, this paper proposes a dedicated hardware inference accelerator for TCNs. We use this accelerator to run an adaptation of WaveNet for anomaly detection in an ECG time series dataset. Our results show that it can achieve 6.3 · 10−4 DRAM access/MAC, 0.043 on-chip SRAM access/MAC and 8 ms/inference. This lower number of on-chip and off-chip memory accesses significantly decreases the overall power consumption and increases the throughput.
2017 IEEE Conference on Standards for Communications and Networking (CSCN), 2017
In this paper, we present a Vehicular version of the Shared UE-side Distributed Antenna System (S... more In this paper, we present a Vehicular version of the Shared UE-side Distributed Antenna System (SUDAS) i.e. Vehicular SUDAS which enables high throughput wireless communication in high mobility Vehicle-to-X (V2X) scenarios. Vehicular SUDAS uses shared virtual antennas, termed UE-side Radio Units (URUs), which utilize both licensed sub-6 GHz band and unlicensed millimetre wave band, to achieve a virtual MIMO gain in in-vehicle UEs. A simulation study is performed to evaluate and analyze an upper bound of the maximum achievable sum rate in the downlink of the proposed system, assuming perfect Doppler spread compensation. The proposed Vehicular SUDAS shows excellent performance, positioning itself as a strong contender for next V2X communication services.
2018 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2018
Shared UE-side Distributed Antenna System (SUDAS) is a very promising technique in order to deliv... more Shared UE-side Distributed Antenna System (SUDAS) is a very promising technique in order to deliver an improved coverage and high throughput beyond 10 Gbit/s to the users in the indoor and intra-vehicular scenarios for 5G applications. This paper presents an implementation perspective and comparison analysis of different candidate hardware architectures suitable for the Shared UE-side Distributed Antenna Component (SUDAC), which is the main building block of the SUDAS and acts as a relay and performs massive spatial-to-frequency domain translation and vice versa. Based on the defined comparison criteria and scoring of different architectures, it has been established that Analog SUDAC with Slight Frequency Shifting (SFS), Analog SUDAC with Digital Control, Digital SUDAC with 802.11ad and Digital SUDAC with Frequency Domain Equalization (FDE) are the top candidates for hardware implementation and future deployment.
2017 IEEE 86th Vehicular Technology Conference (VTC-Fall), 2017
In this paper, we consider resource allocation for an outdoor-to-indoor shared user-equipment (UE... more In this paper, we consider resource allocation for an outdoor-to-indoor shared user-equipment (UE)- side distributed antenna system (SUDAS) employing multiple independently operating compress-and- forward (CF) relays which utilize both licensed and unlicensed frequency bands to enhance indoor data throughput. First, a non-convex matrix-valued resource allocation problem for maximization of the weighted sum rate is formulated. Next, the non-convex problem is simplified to obtain a low- complexity suboptimal resource allocation algorithm based on sequential quadratic programming (SQP). The proposed algorithm is shown to provide excellent performance in practical scenarios. Furthermore, the algorithm has a low channel state information (CSI) feedback requirement and can accommodate arbitrary communication bands and technologies for indoor relaying. Therefore, the proposed CF-SUDAS scheme can help achieve high outdoor-to-indoor data throughput at low complexity, a crucial requirement fo...
Ein Faltungs-Interleaver zum Verarbeiten eines Codeworts, das von einem Eingangsblock von Symbole... more Ein Faltungs-Interleaver zum Verarbeiten eines Codeworts, das von einem Eingangsblock von Symbolen unter Verwendung einer Redundanz-hinzufugenden-Codierung abgeleitet ist, und das mehr Symbole als der Eingangsblock aufweist, wobei das Codewort eine Sequenz von Verschachtelungseinheiten aufweist, wobei jede Verschachtelungseinheit wenigstens zwei Symbole aufweist, umfasst eine Verschachtelungseinrichtung. Die Verschachtelungseinrichtung verandert die Sequenz von Verschachtelungseinheiten, um ein verschachteltes Codewort zu erhalten, das eine veranderte Sequenz von Verschachtelungseinheiten aufweist. Insbesondere wird durch die Verschachtelungseinrichtung die Reihenfolge der Symbole innerhalb einer Verschachtelungseinheit nicht verandert. Allerdings wird die Reihenfolge der Verschachtelungseinheiten im Codewort untereinander oder bezuglich eines vorhergehenden oder nachfolgenden Codeworts verandert.
The aim of the invention is to reduce the out-of-band radiation in a distortion-free manner. A pl... more The aim of the invention is to reduce the out-of-band radiation in a distortion-free manner. A plurality of candidate transmission sequences is produced (10) from an information word. One of the candidate transmission sequences which meets a predetermined criterion is then selected (30). A different tag is added (12) to the information word respectively for producing the different candidate transmission sequences. The information word, together with the added tag, is subsequently processed by means of an invertable feedback combination algorithm (16) for obtaining a combined information word, wherein the information units are combined to each other and/or the added tag in such a way that the combined information word is clearly identified by the tag. The combined information word is fed to an algorithm in the receiver. Said algorithm is inverse in relation to the feedback combination algorithm and is automatically controlled by the tag for reproducing the information word. The infor...
Interleaver means (110) for common transmission of a first and a second transport channel (TC1; T... more Interleaver means (110) for common transmission of a first and a second transport channel (TC1; TC2) via a transmission channel, wherein the first transport channel (TC1) a sequence of first interleave units (IU (1, n)) and the second transport channel (TS2 ) a sequence of second interleave units (IU (2, n)), wherein each interleave including at least one symbol, comprising: a Faltungsverschachtelungseinrichtung (10-1; 10-2) for varying the sequence of the first interleave units according to a first Faltungsverschachtelungsvorschrift (40; 50; 112), the first transmission resources (41; 51) defined for the common transmission, a first interleaved transport channel ( to obtain 52) which has an altered sequence of first interleave units, and (for varying the sequence of the second interleaver according to a second Faltungsverschachtelungsvorschrift 60;; 42 70; 114), the second transmission resources (61; 71) for the common transmission defined, a second interleaved transport channel (6...
Micromachines, 2021
Pattern recognition as a computing task is very well suited for machine learning algorithms utili... more Pattern recognition as a computing task is very well suited for machine learning algorithms utilizing artificial neural networks (ANNs). Computing systems using ANNs usually require some sort of data storage to store the weights and bias values for the processing elements of the individual neurons. This paper introduces a memory block using resistive memory cells (RRAM) to realize this weight and bias storage in an embedded and distributed way while also offering programming and multi-level ability. By implementing power gating, overall power consumption is decreased significantly without data loss by taking advantage of the non-volatility of the RRAM technology. Due to the versatility of the peripheral circuitry, the presented memory concept can be adapted to different applications and RRAM technologies.