A Deterministic Low-Complexity Approximate (Multiplier-Less) Technique for DCT Computation

Huang, Junqi; Kumar, T. Nandha; Almurib, Haider A. F.; Lombardi, Fabrizio

doi:10.1109/tcsi.2019.2902415

Cited by 24 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…us, surveillance IoT applications are required to employ compression techniques to minimize the restrictions of bandwidth, energy, and data storage. Generally, the compression technique requires higher computational power and higher energy consumption to achieve a high-compression rate [31]. Nevertheless, the DCT techniques have decreased the amount of computation and enhance energy performance by minimizing some accuracy in the compression [31,32], resulting in decreased bandwidth and storage requirement for the surveillance IoT systems.…”

Section: A Lightweight Cryptosystemmentioning

confidence: 99%

“…First, we compress the keyframes using DCT and the spectrum is compressed by spectrum cutting. We employ the DCTdue to its energy properties with limited resources devices [31]. Next, we employ a secure and fast pseudorandom number algorithm [33] to produce a random matrix for the discrete fractional random transform (DFRT) [34].…”

Section: A Lightweight Cryptosystemmentioning

confidence: 99%

“…As a result, we can ensure that the proposed cryptosystem can withstand different attacks. [31,32]. In this case, the compression ratio can be computed by comparing the uncompressed size 2 187 Zhou et al [23] 2 300 Zhang and Tong [37] 2 256 Zhu and Zhu [38] 2 280 Complexity with the compressed size.…”

Section: Security Analysismentioning

confidence: 99%

See 2 more Smart Citations

An Efficient Cryptosystem for Video Surveillance in the Internet of Things Environment

et al. 2019

View full text Add to dashboard Cite

Surveillance systems paradigm envisions the pervasive interconnection and cooperation of interactive devices over the Internet infrastructure. Nevertheless, dissemination and processing of surveillance video amid the Internet of Things (IoT) applications become a susceptible issue due to the large volume and the significant information of these data. Moreover, surveillance devices on IoT have very limited resources such as memory and storage. The actual security methods are not quite appropriate for surveillance IoT systems. Thus, a particular cryptosystem technique is required for surveillance data security. In this paper, we propose an efficient cryptosystem to secure IoT-based surveillance systems. The proposed cryptosystem framework contains three parts. First, a lightweight automatic summarization technique based on a fast histogram-clustering approach is used to extract the keyframes from the surveillance video. Then, we employ a discrete cosine transform (DCT) technique to compress the extracted data size. Finally, the proposed framework performs an efficient image encryption algorithm by employing a discrete fractional random transform (DFRT). The testing results and analysis confirm the features of the proposed cryptosystem on surveillance systems. The proposed framework is fast and ensures secure and efficient real-time processing by minimizing the transmission cost and storage.

show abstract

Section: A Lightweight Cryptosystemmentioning

confidence: 99%

Section: A Lightweight Cryptosystemmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Cryptosystem for Video Surveillance in the Internet of Things Environment

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Approximate computing is a new paradigm where an acceptable error is induced in the computing to achieve more energy-efficient processing [ 28 , 29 , 30 , 31 , 32 , 33 ]. It has been introduced at different system levels [ 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 ], and a large number of approximate arithmetic circuits have been designed to save chip area and energy [ 35 , 38 , 46 , 47 , 48 , 49 , 50 , 51 ]. Multiplication is a very common, but expensive operation, with exact multipliers being large circuits that consume a significant amount of energy.…”

Section: Introductionmentioning

confidence: 99%

An Approximate GEMM Unit for Energy-Efficient Object Detection

Pilipović

Risojević

Božič

et al. 2021

Sensors

View full text Add to dashboard Cite

Edge computing brings artificial intelligence algorithms and graphics processing units closer to data sources, making autonomy and energy-efficient processing vital for their design. Approximate computing has emerged as a popular strategy for energy-efficient circuit design, where the challenge is to achieve the best tradeoff between design efficiency and accuracy. The essential operation in artificial intelligence algorithms is the general matrix multiplication (GEMM) operation comprised of matrix multiplication and accumulation. This paper presents an approximate general matrix multiplication (AGEMM) unit that employs approximate multipliers to perform matrix–matrix operations on four-by-four matrices given in sixteen-bit signed fixed-point format. The synthesis of the proposed AGEMM unit to the 45 nm Nangate Open Cell Library revealed that it consumed only up to 36% of the area and 25% of the energy required by the exact general matrix multiplication unit. The AGEMM unit is ideally suited to convolutional neural networks, which can adapt to the error induced in the computation. We evaluated the AGEMM units’ usability for honeybee detection with the YOLOv4-tiny convolutional neural network. The results implied that we can deploy the AGEMM units in convolutional neural networks without noticeable performance degradation. Moreover, the AGEMM unit’s employment can lead to more area- and energy-efficient convolutional neural network processing, which in turn could prolong sensors’ and edge nodes’ autonomy.

show abstract

“…An inexact lower part‐OR adder is proposed in [9] to design an approximate

4 \times 4

DCT system. A deterministic low‐complexity DCT scheme is proposed in [10] by utilising a zigzag scanning‐based look‐up table to remove redundant calculations.…”

Section: Introductionmentioning

confidence: 99%

Approximate computing using frequency upscaling

Huang¹,

Kumar²,

Abbas³

et al. 2019

IET Circuits, Devices & Systems

Self Cite

View full text Add to dashboard Cite

This study presents frequency upscaling as a technique for developing error resilient arithmetic designs in approximate computing whereby the input signal frequency of the circuit is upscaled beyond its largest operating value in generating errors in the arithmetic operation while speeding up the computational throughput. This study initially presents the mathematical modelling of frequency upscaling for both exact and inexact full adders. An exhaustive simulation and evaluation of 4 and 8 bits subtraction followed by addition of two images and approximate discrete cosine transform (DCT) is pursued using exact and inexact circuits when subjected to the proposed technique. The results estimated using the proposed model show good agreement with the simulation results. The normalised mean error distance of subtraction using an inexact circuit is close to the exact value for different technology nodes. The peak signal-to-noise ratio (PSNR) results for the addition of two images show that the inexact full adder achieves a higher output image quality than the exact circuit when the frequency is scaled up. Also, in an approximate DCT, the input frequency of an inexact full adder can be scaled up significantly higher than an exact full adder without a significant decrease in PSNR value.

show abstract

A Deterministic Low-Complexity Approximate (Multiplier-Less) Technique for DCT Computation

Cited by 24 publications

References 24 publications

An Efficient Cryptosystem for Video Surveillance in the Internet of Things Environment

An Efficient Cryptosystem for Video Surveillance in the Internet of Things Environment

An Approximate GEMM Unit for Energy-Efficient Object Detection

Approximate computing using frequency upscaling

Contact Info

Product

Resources

About