Nowadays, Machine Learning is commonly integrated into most daily life applications in various fields. The K Nearest Neighbor (KNN), which is a robust Machine Learning algorithm, is traditionally used in classification tasks for its simplicity and training-less nature. Hardware accelerators such as FPGAs and ASICs are greatly needed to meet the increased requirements of performance for these applications. It is well known that ASICs are non-programmable and only fabricated once with high expenses, this makes the fabrication of a complete chip for a specific classification problem inefficient. As a better alternative to this challenge, in this work, a reconfigurable hardware architecture of the KNN algorithm is proposed where the employed dataset, the algorithm parameters, and the distance metric used to evaluate the nearest neighbors are all updatable after fabrication, in the ASIC case, or after programming, in the FPGA case. The architecture is also made flexible to accommodate different memory requirements and allow variable arithmetic type and precision selection. Both parameters can be adjusted before fabrication to account only for the expected memory requirement and the fixed point precision required or floating point arithmetic if needed. The proposed architecture is realized on the Genesys 2 board based on Xilinx’s Kintex-7 FPGA. The results obtained from the experiment are consistent with those obtained from the simulation and software analysis. The proposed realization reaches a frequency of up to around 110 MHz and a power consumption of less than 0.4 watts © 2023 Elsevier GmbH
Software and hardware realizations for different designs of chaos-based secret image sharing systems
Secret image sharing (SIS) conveys a secret image to mutually suspicious receivers by sending meaningless shares to the participants, and all shares must be present to recover the secret. This paper proposes and compares three systems for secret sharing, where a visual cryptography system is designed with a fast recovery scheme as the backbone for all systems. Then, an SIS system is introduced for sharing any type of image, where it improves security using the Lorenz chaotic system as the source of randomness and the generalized Arnold transform as a permutation module. The second SIS system further enhances security and robustness by utilizing SHA-256 and RSA cryptosystem. The presented architectures are implemented on a field programmable gate array (FPGA) to enhance computational efficiency and facilitate real-time processing. Detailed experimental results and comparisons between the software and hardware realizations are presented. Security analysis and comparisons with related literature are also introduced with good results, including statistical tests, differential attack measures, robustness tests against noise and crop attacks, key sensitivity tests, and performance analysis. © The Author(s) 2024.
Hardware realization of a secure and enhanced s-box based speech encryption engine
This paper presents a secure and efficient substitution box (s-box) for speech encryption applications. The proposed s-box data changes every clock cycle to swap the input signal with different data, where it generated based on a new algorithm and a memristor chaotic system. Bifurcation diagrams for all memristor chaotic system parameters are introduced to stand for the chaotic range of each parameter. Moreover, the effect of each component inside the proposed encryption system is studied, and the security of the system is validated through perceptual and statistical tests. The size of the encryption key is 175 bits to meet the global standards for the optimum encryption key width (> 128). MATLAB software is used to calculate entropy, MSE, and correlation coefficient. Both chaotic circuit and encryption/decryption schemes are designed using Verilog HDL and simulated by Xilinx ISE 14.7. Xilinx Virtex 5 FPGA kit is used to realize the proposed algorithm with a throughput 0.536 of Gbit/s. The cryptosystem is tested using two different speech files to examine its efficiency. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.
A Study on Fractional Power-Law Applications and Approximations
The frequency response of the fractional-order power-law filter can be approximated by different techniques, which eventually affect the expected performance. Fractional-order control systems introduce many benefits for applications like compensators to achieve robust frequency and additional degrees of freedom in the tuning process. This paper is a comparative study of five of these approximation techniques. The comparison focuses on their magnitude error, phase error, and implementation complexity. The techniques under study are the Carlson, continued fraction expansion (CFE), Padé, Charef, and MATLAB curve-fitting tool approximations. Based on this comparison, the recommended approximation techniques are the curve-fitting MATLAB tool and the continued fraction expansion (CFE). As an application, a low-pass power-law filter is realized on a field-programmable analog array (FPAA) using two techniques, namely the curve-fitting tool and the CFE. The experiment aligns with and validates the numerical results. © 2024 by the authors.
Chaotic Dynamics and FPGA Implementation of a Fractional-Order Chaotic System with Time Delay
This article proposes a numerical solution approach and Field Programmable Gate Array implementation of a delayed fractional-order system. The proposed method is amenable to a sufficiently efficient hardware realization. The system’s numerical solution and hardware realization have two requirements. First, the delay terms are implemented by employing LookUp Tables to keep the already required delayed samples in the dynamical equations. Second, the fractional derivative is numerically approximated using Grünwald-Letnikov approximation with a memory window size, L, according to the short memory principle such that it balances between accuracy and efficiency. Bifurcation diagrams and spectral entropy validate the chaotic behaviour of the system for commensurate and incommensurate orders. Additionally, the dynamic behaviour of the system is studied versus the delay parameter, ?, and the window size, L. The system is realized on Nexys 4 Artix-7 FPGA XC7A100T with throughput 1.2 Gbit/s and hardware resources utilization 15% from the total LookUp Tables and 4% from the slice registers. Oscilloscope experimental results verify the numerical solution of the delayed fractional-order system. The amenability to digital hardware realization, which is experimentally validated in this article, is added to the system’s advantages and encourages its utilization in future digital applications such as chaos control and synchronization and chaos-based communication applications. © 2020 IEEE.
Bio-inspired adsorption sheets from waste material for anionic methyl orange dye removal
Abstract: Nano zero-valent iron (nZVI), bimetallic nano zero-valent iron-copper (Fe0–Cu), and Raw algae (sargassum dentifolium) activated carbon-supported bimetallic nano zero-valent iron-copper (AC-Fe0–Cu) are synthesized and characterized using FT-IR, XRD, and SEM. The maximum removal capacity is demonstrated by bimetallic activated carbon AC-Fe0–Cu, which is estimated at 946.5 mg/g capacity at the condition pH = 7, 30 min contact time under shaking at 120 rpm at ambient temperature, 200 ppm of M.O, and 1 g/l dose of raw algae-Fe0–Cu adsorbent. The elimination capability of the H3PO4 chemical AC-Fe0–Cu adsorbent is 991.96 mg/g under the conditions of pH = 3, 120 min contact time under shaking at 120 rpm at room temperature, 200 ppm of M.O, and 2 g/l doses of H3PO4 chemical AC-Fe0–Cu adsorbent. The Bagasse activated carbon adsorbent sheet achieves a removal capacity of 71.6 mg/g MO dye solution. Kinetic and isothermal models are used to fit the results of time and concentration experiments. The intra-particle model yields the best fit for bimetallic Fe0–Cu, AC-Fe0–Cu, H3PO4 chemical AC-Fe0–Cu and bagasse activated carbon(CH), with corrected R-Squared values of 0.9656, 0.9926, 0.964, and 0.951respectively. The isothermal results emphasize the significance of physisorption and chemisorption in concentration outcomes. Response surface methodology (RSM) and artificial neural networks (ANN) are employed to optimize the removal efficiency. RSM models the efficiency and facilitates numerical optimization, while the ANN model is optimized using the moth search algorithm (MSA) for optimal results. Highlights: 1.The Fe0–Cu composite, when combined with activated carbon from Bagasse Pulp (CH), exhibited the most effective decolorization effectiveness for anionic colours present in wastewater.2.The utilization of composites presents a promising opportunity for efficient dye removal due to its cost-effectiveness and environmentally sustainable nature. 3.The utilization of response surface approach and artificial neural network modelling improves the efficacy of removal processes and treatment techniques. © 2023, The Author(s).
Circuit realization and FPGA-based implementation of a fractional-order chaotic system for cancellable face recognition
Biometric security has been developed in recent years with the emergence of cancellable biometric concepts. The idea of the cancellable biometric traits is concerned with creating encrypted or distorted traits of the original ones to protect them from hacking techniques. So, encrypted or distorted biometric traits are stored in databases instead of the original ones. This can be accomplished through non-invertible transforms or encryption schemes. In this paper, a cancellable face recognition algorithm is introduced based on face image encryption through a fractional-order multi-scroll chaotic system. The fundamental concept is to create random keys that will be XORed with the three components of color face images (red, green, and blue) to obtain encrypted face images. These random keys are generated from the Least Significant Bits of all state variables of a proposed fractional-order multi-scroll chaotic system. Lastly, the encrypted color components of face images are combined to produce a single cancellable trait for each color face image. The results of encryption with the proposed system are full-encrypted face images that are suitable for cancellable biometric applications. The strength of the proposed system is that it is extremely sensitive to the user’s selected initial conditions. The numerical simulation of the proposed chaotic system is done with MATLAB. Phase and bifurcation diagrams are used to analyze the dynamic performance of the proposed fractional-order multi-scroll chaotic system. Furthermore, we realized the hardware circuit of the proposed chaotic system on the PSpice simulator. The proposed chaotic system can be implemented on Field Programmable Gate Arrays (FPGAs). To model our generator, we can use Verilog Hardware Description Language HDL, Xilinx ISE 14.7 and Xilinx FPGA Artix-7 XC7A100T based on Grunwald-Letnikov algorithms for mathematical analysis. The numerical simulation, the circuit simulation and the hardware experimental results confirm each other. Cancellable face recognition based on the proposed fractional-order chaotic system has been implemented on FERET, LFW, and ORL datasets, and the results are compared with those of other schemes. Some evaluation metrics containing Equal Error Rate (EER), and Area under the Receiver Operating Characteristic (AROC) curve are used to assess the cancellable biometric system. The numerical results of these metrics show EER levels close to zero and AROC values of 100%. In addition, the encryption scheme is highly efficient. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
Commercial Versus Natural Activated Carbon Fabricated Sheets: Applied to Dyes Removal Application
Industrial dyes are considered one of the main causes of increased water pollution of water. Many businesses, such as steel and paper, are located along riverbanks because they require large amounts of water in their manufacturing processes, and their wastes, which contain acids, alkalis, dyes, and other chemicals, are dumped and poured into rivers as effluents. For example, chemical enterprises producing aluminum emit a significant quantity of fluoride into the air and effluents into water bodies. Fertilizer facilities produce a lot of ammonia, whereas steel plants produce cyanide. Many nations consider employing wastewater treatment plants using physical, biological, and chemical methods to clean the wastewater to address environmental crises. The treated water can be used for targeting the irrigation systems in its majority, as it is biologically acceptable for that specific use, industrial dyes are considered one of the leading causes of increased water pollution of water. Many businesses, such as steel and paper, are located along riverbanks because they require large amounts of water in their manufacturing processes, and their wastes, which contain acids, alkalis, dyes, and other chemicals, are dumped and poured into rivers as effluents. For example, chemical enterprises producing aluminum emit a significant quantity of fluoride into the air and effluents into water bodies. Fertilizer facilities produce much ammonia, whereas steel plants produce cyanide. Chromium salts are used in. Many nations consider employing wastewater treatment plants using physical, biological, and chemical methods to clean the wastewater to address environmental crises. The treated water can target the majority of irrigation systems, as it is biologically acceptable for that specific use, which economizes the use of freshwater sources for municipal use. This study presents a novel method for fabricating an efficient adsorbent sheet for wastewater treatment. The sheets are fabricated by combining sugarcane bagasse pulp as a scaffold with commercial, naturally activated carbon, and bimetallic-prepared adsorbents. Sugarcane bagasse is utilized in producing activated carbon because of its high carbon contents, availability, and low cost. The prepared composite sheets are synthesized and investigated for pollutants removal of crystal violet (CV), methyl orange (MO), and Chromium (CI) dyes. Different weight ratios of activated carbon are used to form a bio-composite mixed sheet. The formed sheets’ morphology is performed via a high scanning electron microscope (SEM) and Fourier Transform Infrared Spectroscopy (FTIR). To determine the adsorption mechanism, the intra-particle diffuse screening experiment is used to test the experimental data. All the prepared sheets can retain the pollutants, with the best removal efficiency of 98% for methyl orange adsorption onto the bio-composite mixed sheet. The results of the parameter (time, concentration, and dose) sets provided valuable proof that the adsorption of methyl orange onto the bio-composite sheet mixed with naturally activated carbon is an endothermic phenomenon involving physical adsorption. © 2024 Wiley-VCH GmbH.
Crystal violet removal using algae-based activated carbon and its composites with bimetallic Fe0-Cu
The textile industry is considered a source of pollution because of the discharge of dye wastewater. The dye wastewater effluent has a significant impact on the aquatic environment. According to the World Bank, textile dyeing, and treatment contribute 17 to 20% of the pollution of water. This paper aims to prepare the bimetallic nano zero-valent iron-copper (Fe0-Cu), algae-activated carbon, and their composites (AC-Fe0-Cu), which are employed as adsorbents. In this paper, Synthetic adsorbents are prepared and examined for the adsorption and removal of soluble cationic crystal violet (CV) dye. The influence of synthetic adsorbents on the adsorption and removal of soluble cationic crystal violet (CV) dye is investigated using UV-V spectroscopy at different pH (3-10), time intervals (15-180) min, and initial dye concentrations (50-500 ppm). Raw algae exhibit an impressive 96.64% removal efficiency under the following conditions: pH 7, contact time of 180 min, rotational speed of 120 rpm, temperature range of 25 °C-30 °C, concentration of 300 ppm in the CV dye solution, and a dose of 4 g l?1 of raw algae adsorbent. The best removal efficiencies of Raw algae Fe0-Cu, and H3PO4 chemical AC-Fe0-Cu are 97.61 % and 97.46 %, respectively, at pH = 7, contact time = 150 min, rotational speed = 120 rpm, T = (25-30) °C, concentration = 75 ppm of CV dye solution, and 1.5 g l?1 doses of raw algae F e0-Cu adsorbent and 1 g l?1 dose of H3PO4 chemical AC-Fe0-Cu adsorbent. The maximum amounts (q max) of Bi-RA and RA adsorbed for the adsorption process of CV are 85.92 mg g?1 and 1388 mg g?1, respectively. The Bi-H3A-AC model, optimized using PSO, demonstrates superior performance, with the highest adsorption capacity estimated at 83.51 mg g?1. However, the Langmuir model predicts a maximum adsorption capacity (q e ) of 275.6 mg g?1 for the CV adsorption process when utilizing Bi-H3A-AC. Kinetic and isothermal models are used to fit the data of time and concentration experiments. DLS, zeta potential, FT-IR, XRD, and SEM are used to characterize the prepared materials. Response surface methodology (RSM) is used to model the removal efficiency and then turned into a numerical optimization approach to determine the ideal conditions for improving removal efficiency. An artificial neural network (ANN) is also used to model the removal efficiency. © 2024 The Author(s). Published by IOP Publishing Ltd.
Chaotic neural network quantization and its robustness against adversarial attacks
Achieving robustness against adversarial attacks while maintaining high accuracy remains a critical challenge in neural networks. Parameter quantization is one of the main approaches used to compress deep neural networks to have less inference time and less storage memory size. However, quantization causes severe degradation in accuracy and consequently in model robustness. This work investigates the efficacy of stochastic quantization to enhance robustness and accuracy. Noise injection during quantization is explored to understand the impact of noise types and magnitudes on model performance. A comprehensive comparison between different applying scenarios for stochastic quantization and different noise types and magnitudes was implemented in this paper. Compared to the baseline deterministic quantization, chaotic quantization achieves a comparable accuracy, however, it achieves up to a 43% increase in accuracy against various attack scenarios. This highlights stochastic quantization as a promising defense mechanism. In addition, there is a crucial role played by the choice of noise type and magnitude in stochastic quantization. Lorenz and Henon noise distributions in stochastic quantization outperform traditional uniform and Gaussian noise in defending against attacks. A transferability analysis was discussed to understand the generalizability and effectiveness of the proposed stochastic quantization techniques. A cross-validation definition was newly evaluated in this scope to analyse the model’s stability and robustness against attacks. The study outperformed a quantization network technique and improved the model’s robustness and stability against adversarial attacks using chaotic quantization instead of deterministic quantization or even instead of stochastic quantization using traditional noise. © 2024 Elsevier B.V.