Charlier polynomials (CHPs) and their moments are commonly used in image processing due to their salient performance in the analysis of signals and their capability in signal representation. The major issue of CHPs is the numerical instability of coefficients for high-order polynomials. In this study, a new recurrence algorithm is proposed to generate CHPs for high-order polynomials. First, sufficient initial values are obtained mathematically. Second, the reduced form of the recurrence algorithm is determined. Finally, a new symmetry relation for CHPs is realized to reduce the number of recurrence times. The symmetry relation is applied to calculate $\sim$50% of the polynomial coefficients. The performance of the proposed recurrence algorithm is evaluated in terms of computational cost and reconstruction error. The evaluation involves a comparison with existing recurrence algorithms. Moreover, the maximum size that can be generated using the proposed recurrence algorithm is investigated and compared with those of existing recurrence algorithms. Comparison results; indicate that the proposed algorithm exhibits better performance because it can generate a polynomial 44 times faster than existing recurrence algorithms. In addition, the improvement of the proposed algorithm over the traditional recurrence algorithms in terms of maximum-generated size is between 19.25 and 42.85.

Discrete Krawtchouk polynomials are widely utilized in different fields for their remarkable characteristics, specifically, the localization property. Discrete orthogonal moments are utilized as a feature descriptor for images and video frames in computer vision applications. In this paper, we present a new method for computing discrete Krawtchouk polynomial coefficients swiftly and efficiently. The presented method proposes a new initial value that does not tend to be zero as the polynomial size increases. In addition, a combination of the existing recurrence relations is presented which are in the n- and x-directions. The utilized recurrence relations are developed to reduce the computational cost. The proposed method computes approximately 12.5% of the polynomial coefficients, and then symmetry relations are employed to compute the rest of the polynomial coefficients. The proposed method is evaluated against existing methods in terms of computational cost and maximum size can be generated. In addition, a reconstruction error analysis for image is performed using the proposed method for large signal sizes. The evaluation shows that the proposed method outperforms other existing methods.

The unprecedented dissemination of edge devices is accompanied by a growing demand for neuromorphic chips that can process time-series data natively without cloud support. Echo state network (ESN) is a class of recurrent neural networks that can be used to identify unique patterns in time-series data and predict future events. It is known for minimal computing resource requirements and fast training, owing to the use of linear optimization solely at the readout stage. In this work, a custom-design neuromorphic chip based on ESN targeting edge devices is proposed. The proposed system supports various learning mechanisms, including structural plasticity and synaptic plasticity, locally on-chip. This provides the network with an additional degree of freedom to continuously learn, adapt, and alter its structure and sparsity level, ensuring high performance and continuous stability. We demonstrate the performance of the proposed system as well as its robustness to noise against real-world time-series datasets while considering various topologies of data movement. An average accuracy of 95.95% and 85.24% are achieved on human activity recognition and prosthetic finger control, respectively. We also illustrate that the proposed system offers a throughput of 6× $\bm {10}^{\boldsymbol{4}}$ samples/sec with a power consumption of 47.7 mW on a 65 nm process.

This paper presents a point multiplication processor over the binary field GF (2233) with internal registers integrated within the point-addition architecture to enhance the Performance Index (PI) of scalar multiplication. The proposed design uses one of two types of finite field multipliers, either the Montgomery multiplier or the interleaved multiplier supported by the additional layer of internal registers. Lopez Dahab coordinates are used for the computation of point multiplication on Koblitz Curve (K-233bit). In contrast, the metric used for comparison of the implementations of the design on different types of FPGA platforms is the Performance Index. The first approach attains a performance index of approximately 0.217610202 when its realization is over Virtex-6 (6vlx130tff1156-3). It uses an interleaved multiplier with 3077 register slices, 4064 lookup tables (LUTs), 2837 flip-flops (FFs) at a maximum frequency of 221.6Mhz. This makes it more suitable for high-frequency applications. The second approach, which uses the Montgomery multiplier, produces a PI of approximately 0.2228157 when its implementation is on Virtex-4 (6vlx130tff1156-3). This approach utilizes 3543 slices, 2985 LUTs, 3691 FFs at a maximum frequency of 190.47MHz. Thus, it is found that the implementation of the second approach on Virtex-4 is more suitable for applications with a low frequency of about 86.4Mhz and a total number of slices of about 12305.

Computer vision seeks to mimic the human visual system and plays an essential role in artificial intelligence. It is based on different signal reprocessing techniques; therefore, developing efficient techniques becomes essential to achieving fast and reliable processing. Various signal preprocessing operations have been used for computer vision, including smoothing techniques, signal analyzing, resizing, sharpening, and enhancement, to reduce reluctant falsifications, segmentation, and image feature improvement. For example, to reduce the noise in a disturbed signal, smoothing kernels can be effectively used. This is achievedby convolving the distributed signal with smoothing kernels. In addition, orthogonal moments (OMs) are a crucial technique in signal preprocessing, serving as key descriptors for signal analysis and recognition. OMs are obtained by the projection of orthogonal polynomials (OPs) onto the signal domain. However, when dealing with 3D signals, the traditional approach of convolving kernels with the signal and computing OMs beforehand significantly increases the computational cost of computer vision algorithms. To address this issue, this paper develops a novel mathematical model to embed the kernel directly into the OPs functions, seamlessly integrating these two processes into a more efficient and accurate approach. The proposed model allows the computation of OMs for smoothed versions of 3D signals directly, thereby reducing computational overhead. Extensive experiments conducted on 3D objects demonstrate that the proposed method outperforms traditional approaches across various metrics. The average recognition accuracy improves to 83.85% when the polynomial order is increased to 10. Experimental results show that the proposed method exhibits higher accuracy and lower computational costs compared to the benchmark methods in various conditions for a wide range of parameter values.

Future generations of wireless communications systems are expected to evolve toward allowing massive ubiquitous connectivity and achieving ultra-reliable and low-latency communications (URLLC) with extremely high data rates. Massive multiple-input multiple-output (m-MIMO) is a crucial transmission technique to fulfill the demands of high data rates in the upcoming wireless systems. However, obtaining a downlink (DL) training sequence (TS) that is feasible for fast channel estimation, i.e., meeting the low-latency communications required by future generations of wireless systems, in m-MIMO with frequency-division-duplex (FDD) when users have different channel correlations is very challenging. Therefore, a low-complexity solution for designing the DL training sequences to maximize the achievable sum rate of FDD systems with limited channel coherence time (CCT) is proposed using a waterfilling power allocation method. This achievable sum rate maximization is achieved using sequences produced from a summation of the user’s covariance matrices and then applying a waterfilling power allocation method to the obtained low-complexity training sequence. The results show that the proposed TS outperforms the existing methods in the medium and high SNR regimes while reducing computational complexity. The obtained results signify the proposed TS’s feasibility for practical consideration compared with the existing DL training sequence designs.