Multiple Architectures Research Articles

Performance optimized approximate multiplier architecture ST-AxM - based on statistical analysis and static compensation

In this study, our primary aim is to develop a highly efficient multiplier architecture tailored for approximate computing, with a specific focus on optimizing power efficiency. Multiplication constitutes a fundamental operation in computing, profoundly impacting applications ranging from signal processing to artificial intelligence. The emerging paradigm of approximate computing seeks to enhance hardware design by balancing computational accuracy with power consumption. Our objective is to achieve this balance by implementing a novel multiplier architecture employing several key methods. We aim to harness a smart and adaptable partial product reduction technique grounded in statistical analysis to reduce adder usage, incorporate power-efficient adder structures, and introduce static error compensation mechanisms to maintain lower error levels. Our methodology involves analyzing various multiplier hardware architectures, developing the proposed approximate multiplier architecture, and rigorously validating its performance against a state-of-the-art truncation multiplier. We utilize Xilinx ISE for synthesis to obtain results pertaining to area efficiency and power efficiency. Furthermore, we employ error metrics to comprehensively compare the performance of our proposed architecture with existing designs. Finally, we assess the practical applicability of these different multipliers by integrating them into an image sharpening application and evaluating metrics such as Peak Signal to Noise Ratio (PSNR) and Similarity Index (SI). Our results indicate that the statically truncated approximate multiplier outperforms existing designs by being 18 % more area-efficient and 5 % more power-efficient, all while maintaining acceptable error levels. Moreover, in the context of image processing, it demonstrates PSNR and SI values closely aligned with those of standard fixed-point multipliers. In conclusion, our innovative approximate multiplier architecture, grounded in statistical analysis and static compensation, offers substantial improvements in area and power efficiency, rendering it suitable for error-tolerant applications such as digital signal processing and image processing.

A machine learning framework for remaining useful lifetime prediction of li-ion batteries using diverse neural networks

Accurate prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) is pivotal for enhancing their operational efficiency and safety in diverse applications. Beyond operational advantages, precise RUL predictions can also expedite advancements in cell design and fast-charging methodologies, thereby reducing cycle testing durations. Despite artificial neural networks (ANNs) showing promise in this domain, determining the best-fit architecture across varied datasets and optimization approaches remains challenging. This study introduces a machine learning framework for systematically evaluating multiple ANN architectures. Using only 30% of a training dataset derived from 124 LIBs subjected to various charging regimes, an extensive evaluation is conducted across 7 ANN architectures. Each architecture is optimized in terms of hyperparameters using this framework, a process that spans 145 days on an NVIDIA GeForce RTX 4090 GPU. By optimizing each model to its best configuration, a fair and standardized basis for comparing their RUL predictions is established. The research also examines the impact of different cycling windows on predictive accuracy. Using a stratified partitioning technique underscores the significance of consistent dataset representation across subsets. Significantly, using only the features derived from individual charge–discharge cycles, our top-performing model, based on data from just 40 cycles, achieves a mean absolute percentage error of 10.7%.

Thunderstorm prediction during pre-tactical air-traffic-flow management using convolutional neural networks

Thunderstorms can be a large source of disruption for European air-traffic management causing a chaotic state of operation within the airspace system. In current practice, air-traffic managers are provided with imprecise forecasts which limit their ability to plan strategically. As a result, weather mitigation is performed using tactical measures with a time horizon of three hours. Increasing the lead time of thunderstorm predictions to the day before operations could help air-traffic managers plan around weather and improve the efficiency of air-traffic-management operations. Emerging techniques based on machine learning have provided promising results, partly attributed to reduced human bias and improved capacity in predicting thunderstorms purely from numerical weather prediction data. In this paper, we expand on our previous work on thunderstorm forecasting, by applying convolutional neural networks (CNNs) to exploit the spatial characteristics embedded in the weather data. The learning task of predicting convection is formulated as a binary-classification problem based on satellite data. The performance of multiple CNN-based architectures, including a fully-convolutional neural network (FCN), a CNN-based encoder–decoder, a U-Net, and a pyramid-scene parsing network (PSPNet) are compared against a multi-layer-perceptron (MLP) network. Our work indicates that CNN-based architectures improve the performance of point-prediction models, with a fully-convolutional neural-network architecture having the best performance. Results show that CNN-based architectures can be used to increase the prediction lead time of thunderstorms. Lastly, a case study illustrating the applications of convection-prediction models in an air-traffic-management setting is presented.

ASIC implementation of ECG denoising FIR filter by using hybrid Vedic–Wallace tree multiplier

AbstractThe design of hand‐held portable devices for cardiovascular health monitoring based on the analysis of electrocardiogram (ECG) is a hot topic of research nowadays. Digital filters, possibly designed using digital multipliers, are a critical module in the design of such analysis systems. This paper presents the ASIC design of a 64th‐order digital low‐pass FIR filter to be used in ECG denoising applications. The FIR filter is optimized for usage in battery‐operated portable systems, wherein power consumption and on‐chip area are crucial parameters of concern. These challenges are met by employing a novel multiplier architecture, which we design by hybridizing the two popular digital multiplication algorithms, namely, the Vedic multiplication algorithm and the Wallace tree multiplication algorithm. The proposed multiplier consumes lower area and power consumption than either of the aforementioned conventional multiplication algorithms. This is established through FPGA‐based implementations on Artix‐7 FPGA, for the various wordlengths. The area and power optimizations are further exercised by two proposed techniques, namely, elimination of redundant multipliers, and power gating using the proposed zero‐detector circuit. RTL‐to‐GDSII flow has been completed using Cadence digital design and sign‐off tools for SCL 180 nm technology. The results indicate that the proposed filter architecture occupies 16.38% lower area and 79.58% lower power consumption than the contemporary designs described in the literature.

S-Net: a multiple cross aggregation convolutional architecture for automatic segmentation of small/thin structures for cardiovascular applications.

With the success of U-Net or its variants in automatic medical image segmentation, building a fully convolutional network (FCN) based on an encoder-decoder structure has become an effective end-to-end learning approach. However, the intrinsic property of FCNs is that as the encoder deepens, higher-level features are learned, and the receptive field size of the network increases, which results in unsatisfactory performance for detecting low-level small/thin structures such as atrial walls and small arteries. To address this issue, we propose to keep the different encoding layer features at their original sizes to constrain the receptive field from increasing as the network goes deeper. Accordingly, we develop a novel S-shaped multiple cross-aggregation segmentation architecture named S-Net, which has two branches in the encoding stage, i.e., a resampling branch to capture low-level fine-grained details and thin/small structures and a downsampling branch to learn high-level discriminative knowledge. In particular, these two branches learn complementary features by residual cross-aggregation; the fusion of the complementary features from different decoding layers can be effectively accomplished through lateral connections. Meanwhile, we perform supervised prediction at all decoding layers to incorporate coarse-level features with high semantic meaning and fine-level features with high localization capability to detect multi-scale structures, especially for small/thin volumes fully. To validate the effectiveness of our S-Net, we conducted extensive experiments on the segmentation of cardiac wall and intracranial aneurysm (IA) vasculature, and quantitative and qualitative evaluations demonstrated the superior performance of our method for predicting small/thin structures in medical images.

XCovNet: A wide deep learning model for CXR-based COVID-19 detection

The high death toll and economic impact of the COVID-19 pandemic emphasize the need for effective population screening technologies. The high cost, limited availability, and slow nature of CT scans and PCR-based tests renders them impractical for frequent use among the general public. As chest X-ray (CXR) imaging is fast and economical, a high accuracy CXR-based test would be well-suited for such screenings. Deep learning algorithms are widely used to aid medical image diagnoses. We use a collection of state-of-the-art pre-trained deep neural network models with additional layers to detect the COVID-19 cases from a sample of healthy, COVID-19, and pneumonia patients. We observed models trained with concatenated features of multiple pre-trained deep learning architectures outperform the individual and ensemble models. Our final model obtained a recall of greater than 98% and a precision of greater than 95% on two separate datasets. The wide architecture of xCovNet may contribute to its robust behavior, providing a systematic approach to construct a reliable deep learning model for emerging datasets.

Distributed swarm system with hybrid-flocking control for small fixed-wing UAVs: Algorithms and flight experiments

This paper presents a distributed swarm system for small fixed-wing unmanned aerial vehicles (UAVs). In particular, to perform various missions with multiple UAVs that are densely gathered and collision free, a hybrid-flocking control algorithm is synthesized by using three types of control protocols: vector field guidance (for path following/loitering), augmented Cucker-Smale (ACS) model (for collective flocking behavior), and potential field (for collision avoidance). In particular, to address the issue of conflicts between different control protocols, the adaptive ACS model is proposed and the optimization problem is formulated to determine the suitable mixing weights of control protocols. We also design the transition of multiple operation modes and communication architecture for the swarm system. The system is evaluated using the proposed hybrid-flocking control algorithm by proof-of-concept real flight experiments using 18 small fixed-wing UAVs as well as extensive numerical simulations. Flight experiments are successfully performed for multiple consecutive tasks including the individual task, circular path loitering and elliptical path loitering while avoiding collisions among UAVs.

Rational design and additive manufacturing of grain boundary-inspired, multi-architecture lattice structures

The advent of additive manufacturing has facilitated the design and fabrication of hybrid lattice structures with multiple morphologies. These structures combine multiple distinct architectures into a single structure with an exceptional performance that far exceeds that of each constituting architecture. However, combining strut-based lattices poses serious challenges in establishing effective connections, primarily due to complications in formulating mathematical expressions. Here, we introduce a novel approach, inspired by the connections observed in the grain boundaries of polycrystalline materials, to design the interconnections of hybrid structures. This strategy involves shrinking the unit cell linkage, thereby addressing the difficulty of forming efficient connections at arbitrary spatial interfaces within strut-based lattice structures. We then use the relevant design theories to tune the performance of these connections and simplify the design process for hybrid structures – even for inexperienced designers. Our experimental observations confirm the efficacy of the proposed strategy, bridging the knowledge gap in the design of connected strut-based multi-lattice structures. Furthermore, this approach enhances the design of tailored hybrid structures and fosters the development of metamaterials with advanced, unique functionalities. The proposed approach has important implications for the development of designer materials, with applications in medical devices, (soft) robotics, and implants.

Ensemble Learning Based Convolutional Neural Networks for Remaining Useful Life Prediction of Aircraft Engines

Remaining useful life (RUL) prediction is an essential task of Prognostics and Health Management (PHM) of aircraft engines performed utilizing the huge data collected from multiple sensors attached to them to ensure their safe operation. While many studies have been reported on RUL prediction for aircraft engines, only a few of them focus on ensemble learning of CNN models for RUL prediction. The success of ensemble learning which is a combination of several base models developed using either same or different machine learning or deep learning algorithms, critically depends on the diversity among the base models generated. This paper proposes a new data-driven approach for RUL prediction of aircraft engines using ensemble learning based convolution neural networks (CNN) by investigating various steps to generate more diverse base models.
 The main objectives and contributions of this paper are as follows:
 
 Explore various CNN model architectures for RUL prediction - After data preprocessing and exploratory data analysis, two different CNN approaches, namely 2D CNN and 1D CNN with multiple channels, are investigated employing time window approach for time-series input preparation for better feature extraction by CNN. Each approach is experimented with multiple architectures to achieve the best possible outcome.
 Investigate engine specific RUL target function - For RUL prediction of turbofan engines using the C-MAPSS dataset, typically two RUL target functions, namely linear and piecewise linear, are used to determine RUL target values. In the piecewise linear RUL target function approach, which yields better performance in the reported studies, the RUL target value is assigned based on a piecewise linear degradation model which assumes a constant (and maximum) RUL target value in the early phase before linearly degrading the RUL targets. In the literature, this maximum RUL target value was chosen same for all the engines by taking a value of 125 or 130 without providing proper rationale. In this study, we adopt an approach based on the widely known health index to determine an engine specific initial (and maximum) RUL target value that can be used with the piecewise linear degradation model to determine RUL target values.
 Investigate hyperparameter optimization of CNN models to generate diverse base models - For the purpose of developing a high performance ensemble CNN model for RUL prediction, hyperparameter optimization of CNN models is performed to optimally determine the network structure (such as # of filters, filter size, stride, padding, # of convolutional, pooling, and dense layers, activation functions etc.) as well as the hyperparameters that determine the network training process (such as optimization method, learning rate, momentum, batch size etc.).
 Investigate ensemble learning to select and combine diverse CNN models for RUL prediction – In order to develop model combiners, diverse CNN models as base learners are selected using multiple performance measures such as RMSE, score function, MAE, and R2 score, and employing the non-negative least squares method, random forest regression, and extreme learning machine (ELM) to train model combiners.
 Evaluate the above proposed approach using the C-MAPSS dataset - To show the effectiveness of the proposed approach, various evaluations for RUL prediction using the popular C-MAPSS dataset (including all the four sub-datasets denoted as FD001, FD002, FD003 and FD004) are carried out and the results will be compared against the state-of-the-art results on the same dataset.
 
 Major emphasis of this proposed approach is on the generation of diverse CNN base models by carrying out various steps as explained above, and it is expected the results of this proposed approach will contribute towards enhancing the RUL prediction performance especially on the sub-datasets FD002 and FD004 which are challenging for the existing state-of-the-art RUL prediction techniques.

A deep local-temporal architecture with attention for lightweight human activity recognition

Human Activity Recognition (HAR) is an essential area of pervasive computing deployed in numerous fields. In order to seamlessly capture human activities, various inertial sensors embedded in wearable devices have been used to generate enormous amounts of signals, which are multidimensional time series of state changes. Therefore, the signals must be divided into windows for feature extraction. Deep learning (DL) methods have recently been used to automatically extract local and temporal features from signals obtained using wearable sensors. Likewise, multiple input deep learning architectures have been proposed to improve the quality of learned features in wearable sensor HAR. However, these architectures are often designed to extract local and temporal features on a single pipeline, which affects feature representation quality. Also, such models are always parameter-heavy due to the number of weights involved in the architecture. Since resources (CPU, battery, and memory) of end devices are limited, it is crucial to propose lightweight deep architectures for easy deployment of activity recognition models on end devices. To contribute, this paper presents a new deep parallel architecture named DLT, based on pipeline concatenation. Each pipeline consists of two sub-pipelines, where the first sub-pipeline learns local features in the current window using 1D-CNN, and the second sub-pipeline learns temporal features using Bi-LSTM and LSTMs before concatenating the feature maps and integrating channel attention. By doing this, the proposed DLT model fully harnessed the capabilities of CNN and RNN equally in capturing more discriminative features from wearable sensor signals while increasing responsiveness to essential features. Also, the size of the model is reduced by adding a lightweight module to the top of the architecture, thereby ensuring the proposed DLT architecture is lightweight. Experiments on two publicly available datasets showed that the proposed architecture achieved an accuracy of 98.52% on PAMAP2 and 97.90% on WISDM datasets, outperforming existing models with few model parameters.

A performance portable implementation of the semi-Lagrangian algorithm in six dimensions

This paper describes our approach to developing a simulation software application for the fully kinetic 6D-Vlasov equation, which will be used to explore physics beyond the reduced gyrokinetic model. Simulating the fully kinetic Vlasov equation requires efficient utilization of compute and storage capabilities due to the high dimensionality of the problem. In addition, the implementation needs to be extensible regarding the physical model and flexible regarding the hardware for production runs. We start on the algorithmic background to simulate the 6-D Vlasov equation using a semi-Lagrangian algorithm. The performance portable software stack, which enables production runs on pure CPU as well as AMD or Nvidia GPU accelerated nodes, is presented. The extensibility of our implementation is guaranteed through the described software architecture of the main kernel, which achieves a memory bandwidth of almost 500 GB/s on a V100 Nvidia GPU and around 100 GB/s on an Intel Xeon Gold CPU using a single code base. We provide performance data on multiple node-level architectures discussing utilized and further available hardware capabilities. Finally, the network communication bottleneck of 6-D grid-based algorithms is quantified. A verification of physics beyond gyrokinetic theory, for the example of ion Bernstein waves, concludes the work.

The multiple sulfur isotope architecture of the Kambalda nickel camp, Western Australia

New data on the multiple sulfur isotope signature of Archean sulfides from country rocks and magmatic mineralization at the Moran deposit (Kambalda, Western Australia) were combined with previously published geochemical data to constrain the various stages of the dynamic evolution of this magmatic system, unveiling new insights into the transport mechanisms of sulfide liquids in komatiite magmas. Sulfides in the Archean magmatic and sedimentary host rocks of the komatiites display a unique mass-independent sulfur isotope signature (Δ33S), which records a photochemical reaction of sulfur in an oxygen-poor atmosphere prior to the Great Oxidation Event.Sedimentary rocks that are thought to be assimilated by komatiite show a distinctly positive Δ33S signature (+ 0.9 to + 2.4‰). Early ore sulfides situated above these sedimentary rocks contain relatively few valuable metals and display an overlapping Δ33S range (+ 0.6 to + 1.0‰). Subsequent but still early ore sulfides are situated above basalt, as the sedimentary rocks were thermo-mechanically eroded by the sulfide melt, displaying more mantle-like signatures (+ 0.2 to + 0.3‰) and valuable metal content - indistinguishable from the main ore deposit. This reflects a progressive dilution of the contaminant signature by the magmatic isotope signature of the komatiite liquid. Calculated volumes of the interaction of silicate melt and sulfide melt to explain the metal tenor of the ore and its Δ33S signature indicate a decoupling between chemical and isotopic signatures. This can be explained by upgrading the sulfide melt with valuable metals simultaneously with the dissolution of sulfur in the komatiite melt.

Active learning for extracting surgomic features in robot-assisted minimally invasive esophagectomy: a prospective annotation study

BackgroundWith Surgomics, we aim for personalized prediction of the patient's surgical outcome using machine-learning (ML) on multimodal intraoperative data to extract surgomic features as surgical process characteristics. As high-quality annotations by medical experts are crucial, but still a bottleneck, we prospectively investigate active learning (AL) to reduce annotation effort and present automatic recognition of surgomic features.MethodsTo establish a process for development of surgomic features, ten video-based features related to bleeding, as highly relevant intraoperative complication, were chosen. They comprise the amount of blood and smoke in the surgical field, six instruments, and two anatomic structures. Annotation of selected frames from robot-assisted minimally invasive esophagectomies was performed by at least three independent medical experts. To test whether AL reduces annotation effort, we performed a prospective annotation study comparing AL with equidistant sampling (EQS) for frame selection. Multiple Bayesian ResNet18 architectures were trained on a multicentric dataset, consisting of 22 videos from two centers.ResultsIn total, 14,004 frames were tag annotated. A mean F1-score of 0.75 ± 0.16 was achieved for all features. The highest F1-score was achieved for the instruments (mean 0.80 ± 0.17). This result is also reflected in the inter-rater-agreement (1-rater-kappa > 0.82). Compared to EQS, AL showed better recognition results for the instruments with a significant difference in the McNemar test comparing correctness of predictions. Moreover, in contrast to EQS, AL selected more frames of the four less common instruments (1512 vs. 607 frames) and achieved higher F1-scores for common instruments while requiring less training frames.ConclusionWe presented ten surgomic features relevant for bleeding events in esophageal surgery automatically extracted from surgical video using ML. AL showed the potential to reduce annotation effort while keeping ML performance high for selected features. The source code and the trained models are published open source.Graphical abstract

Bi2O2Se-Based Bimode Noise Generator for the Application of Generative Adversarial Networks.

In the emerging technology, the generative aversive networks (GANs), randomness, and unpredictability of inputting noises are the keys to the uniqueness, diversity, robustness, and security of the generated images. Compared with deterministic software-based noise generation, hardware-based noise generation introduces physical entropy sources, such as electronic and photonic noises, to add unpredictability. In this study, bimode Bi2O2Se-based noise generators have been demonstrated for the application of GANs. Harnessing its ultrahigh carrier mobility, excellent air stability, marvelous optoelectronic performance, as well as the unique surface resistive switching effect and defect locations in the energy diagram, Bi2O2Se provides a good material platform to easily integrate with multiple device architectures for generating noises in different physical sources. The noise of the black current mode in a photodetector architecture and the random telegraph noise in a memristor mode were measured, characterized, compared, and analyzed. A method of Markov chain equipped with K-means clustering was carried out to calculate the discrete noise states and the transition probability matrix between them. To evaluate the generated properties of the GANs based on the hardware noise source, the inception score and Fréchet inception distance were evaluated.

Classification of integers based on residue classes via modern deep learning algorithms

Judging whether an integer can be divided by prime numbers such as 2 or 3 may appear trivial to human beings, but it can be less straightforward for computers. Here, we tested multiple deep learning architectures and feature engineering approaches to classifying integers based on their residues when divided by small prime numbers. We found that the ability of classification critically depends on the feature space. We also evaluated automated machine learning (AutoML) platforms from Amazon, Google, and Microsoft and found that, without appropriately engineered features, they failed on this task. Furthermore, we introduced a method that utilizes linear regression on Fourier series basis vectors and demonstrated its effectiveness. Finally, we evaluated large language models (LLMs) such as GPT-4, GPT-J, LLaMA, and Falcon, and we demonstrated their failures. In conclusion, feature engineering remains an important task to improve performance and increase interpretability of machine learning models, even in the era of AutoML and LLMs.

Zero time waste in pre-trained early exit neural networks

The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by attaching additional Internal Classifiers (ICs) to intermediate layers of a neural network. ICs can quickly return predictions for easy examples and, as a result, reduce the average inference time of the whole model. However, if a particular IC does not decide to return an answer early, its predictions are discarded, with its computations effectively being wasted. To solve this issue, we introduce Zero Time Waste (ZTW), a novel approach in which each IC reuses predictions returned by its predecessors by (1) adding direct connections between ICs and (2) combining previous outputs in an ensemble-like manner. We conduct extensive experiments across various multiple modes, datasets, and architectures to demonstrate that ZTW achieves a significantly better accuracy vs. inference time trade-off than other early exit methods. On the ImageNet dataset, it obtains superior results over the best baseline method in 11 out of 16 cases, reaching up to 5 percentage points of improvement on low computational budgets.

Area, power efficient Vedic multiplier architecture using novel 4:2 compressor

Area, power efficient Vedic multiplier architecture using novel 4:2 compressor

Comparison of RNN Architectures and Non-RNN Architectures in Sentiment Analysis

This study compares the sentiment analysis performance of multiple Recurrent Neural Network architectures and One-Dimensional Convolutional Neural Networks. THE METHODS EVALUATED ARE simple Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Bidirectional Recurrent Neural Network, and 1D ConvNets. A dataset comprising text reviews with positive or negative sentiment labels was evaluated. All evaluated models demonstrated an extremely high accuracy, ranging from 99.81% to 99.99%. Apart from that, the loss generated by these models is also low, ranging from 0.0043 to 0.0021. However, there are minor performance differences between the evaluated architectures. The Long Short-Term Memory and Gated Recurrent Unit models mainly perform marginally better than the Simple Recurrent Neural Network, albeit with slightly lower accuracy and loss. In the meantime, the Bidirectional Recurrent Neural Network model demonstrates competitive performance, as it can effectively manage text context from both directions. Additionally, One-Dimensional Convolutional Neural Networks provide satisfactory results, indicating that convolution-based approaches are also effective in sentiment analysis. The findings of this study provide practitioners with essential insights for selecting an appropriate architecture for sentiment analysis tasks. While all models yield excellent performance, the choice of architecture can impact computational efficiency and training time. Therefore, a comprehensive comprehension of the respective characteristics of Recurrent Neural Network architectures and One-Dimensional Convolutional Neural Networks is essential for making more informed decisions when constructing sentiment analysis models.

A novel approach and hybrid parallel algorithms for solving the fixed charge transportation problem

This article is dedicated to the efficient resolution of the fixed charge transport problem (FCTP) with the goal of identifying optimal solutions within reduced timeframes. FCTP is a combinatorial and NP-complete problem known for its exponential time complexity relative to problem size. Metaheuristic methods, including genetic algorithms, represent effective techniques for obtaining high-quality FCTP solutions. Consequently, the integration of parallel algorithms emerges as a strategy for expediting problem-solving. The proposed approach, referred to as the parallel genetic algorithm (PGA), entails the application of a genetic algorithm across multiple parallel architectures to tackle the FCTP problem. The primary aim is to explore fresh solutions for the fixed charge transportation problem using genetic algorithms while concurrently optimizing the time required to achieve these solutions through parallelism. The FCTP problem is fundamentally a linear programming challenge, revolving around the determination of optimal shipment quantities from numerous source locations to multiple destinations with the overarching objective of minimizing overall transportation costs. This necessitates consideration of constraints tied to product availability at the sources and demand dynamics at the destinations. In this study, a pioneering approach to addressing the Fixed Charge Transportation Problem (FCTP) using parallel genetic algorithms (PGA) is unveiled. The research introduces two distinct parallel algorithms: The Master-Slave Approach (MS-GA) and the Coarse-Grained Approach (CG-GA). Additionally, investigation into the hybridization of these approaches has led to the development of the NMS-CG-GA approach. The numerical results reveal that our parallelism-based approaches significantly improve the performance of genetic algorithms. Specifically, the Master-Slave (MS-GA) approach demonstrates its advantages in solving smaller instances of the FCTP problem, while the Coarse-Grained (CG-GA) approach exhibits greater effectiveness for larger problem instances. The conclusion reached is that the novel hybrid parallel genetic algorithm approach (NMS-CG-GA) outperforms its predecessors, yielding outstanding results, particularly across diverse FCTP problem instances.

On the Use of Low-power Devices, Approximate Adders and Near-threshold Operation for Energy-efficient Multipliers

With the rising importance of power consumption in battery-powered devices, approximate computing techniques have emerged as a promising approach to strike a balance between exact computation and power savings, leading to improved delays. This paper investigates the combination of near-threshold operation and approximate adders to design power-efficient multipliers. We analyzed four multiplier architectures using 16 nm low-power and high-performance models. At the transistor level, three strategies for approximate full adders are explored, focusing on both partial product reduction and the final addition stage of the multipliers. Eleven test cases are thoroughly evaluated to identify the most suitable approximate circuit, considering the trade-offs among power, performance, and accuracy. The obtained results demonstrate a substantial reduction in power consumption at near-threshold operation. The replacement of exact full adders with the approximate copy strategy in the least significant bits of the multipliers leads to a reduction of up to 34.4% in power consumption and 19.2% in delay. The design-space exploration carried out in this study provides valuable insights for designers to choose the best approximate multiplier based on specific design requirements.