Minimal Computational Complexity Research Articles

Transforming Motor Imagery Analysis: A Novel EEG Classification Framework Using AtSiftNet Method

This paper presents an innovative approach for the Feature Extraction method using Self-Attention, incorporating various Feature Selection techniques known as the AtSiftNet method to enhance the classification performance of motor imaginary activities using electrophotography (EEG) signals. Initially, the EEG signals were sorted and then denoised using multiscale principal component analysis to obtain clean EEG signals. However, we also conducted a non-denoised experiment. Subsequently, the clean EEG signals underwent the Self-Attention feature extraction method to compute the features of each trial (i.e., 350×18). The best 1 or 15 features were then extracted through eight different feature selection techniques. Finally, five different machine learning and neural network classification models were employed to calculate the accuracy, sensitivity, and specificity of this approach. The BCI competition III dataset IV-a was utilized for all experiments, encompassing the datasets of five volunteers who participated in the competition. The experiment findings reveal that the average accuracy of classification is highest among ReliefF (i.e., 99.946%), Mutual Information (i.e., 98.902%), Independent Component Analysis (i.e., 99.62%), and Principal Component Analysis (i.e., 98.884%) for both 1 and 15 best-selected features from each trial. These accuracies were obtained for motor imagery using a Support Vector Machine (SVM) as a classifier. In addition, five-fold validation was performed in this paper to assess the fair performance estimation and robustness of the model. The average accuracy obtained through five-fold validation is 99.89%. The experiments’ findings indicate that the suggested framework provides a resilient biomarker with minimal computational complexity, making it a suitable choice for advancing Motor Imagery Brain–Computer Interfaces (BCI).

Object Detection in Satellite Images with Hierarchical Collective Hunter Algorithm Optimized Ensemble Classifier

Object detection in remote sensing images plays an essential role in computer vision task, which significantly identifies the position and class of the located objects with arbitrary orientation information. Recently, object detection plays an important role in various applications such as Surveillance and security in airports, organizations, and so on. However, target tracking is a very challenging task in natural images to attain appropriate detection results together with they obtain certain issues such as limited availability of high-resolute images, background complexity, and so on. To avoid these limitations, developed a Hierarchical collective Hunter algorithm with a Deep convolutional Neural network and a Bidirectional long short-term classifier (2HC-DBTM) model, which improved the interaction range of feature extraction by reducing the background complexity. Additional attributes mechanism such as the Hierarchical Collective Hunter (HCH) algorithm and hybrid attention mechanism are integrated with the proposed model for improve the ability and performance with minimum computational complexity and achieves better detection accuracy. The experimental results obtained in the evaluation of the model are achieved with high robustness and efficiency when compared with other conventional methods. The achieved performance evaluation of the model for evaluation metric F1-score is 97.71%, precision is 97.16%, recall is 98.27% and accuracy is 98.05%.

An attention-based deep learning for acute lymphoblastic leukemia classification

The bone marrow overproduces immature cells in the malignancy known as Acute Lymphoblastic Leukemia (ALL). In the United States, about 6500 occurrences of ALL are diagnosed each year in both children and adults, comprising nearly 25% of pediatric cancer cases. Recently, many computer-assisted diagnosis (CAD) systems have been proposed to aid hematologists in reducing workload, providing correct results, and managing enormous volumes of data. Traditional CAD systems rely on hematologists’ expertise, specialized features, and subject knowledge. Utilizing early detection of ALL can aid radiologists and doctors in making medical decisions. In this study, Deep Dilated Residual Convolutional Neural Network (DDRNet) is presented for the classification of blood cell images, focusing on eosinophils, lymphocytes, monocytes, and neutrophils. To tackle challenges like vanishing gradients and enhance feature extraction, the model incorporates Deep Residual Dilated Blocks (DRDB) for faster convergence. Conventional residual blocks are strategically placed between layers to preserve original information and extract general feature maps. Global and Local Feature Enhancement Blocks (GLFEB) balance weak contributions from shallow layers for improved feature normalization. The global feature from the initial convolution layer, when combined with GLFEB-processed features, reinforces classification representations. The Tanh function introduces non-linearity. A Channel and Spatial Attention Block (CSAB) is integrated into the neural network to emphasize or minimize specific feature channels, while fully connected layers transform the data. The use of a sigmoid activation function concentrates on relevant features for multiclass lymphoblastic leukemia classification The model was analyzed with Kaggle dataset (16,249 images) categorized into four classes, with a training and testing ratio of 80:20. Experimental results showed that DRDB, GLFEB and CSAB blocks’ feature discrimination ability boosted the DDRNet model F1 score to 0.96 with minimal computational complexity and optimum classification accuracy of 99.86% and 91.98% for training and testing data. The DDRNet model stands out from existing methods due to its high testing accuracy of 91.98%, F1 score of 0.96, minimal computational complexity, and enhanced feature discrimination ability. The strategic combination of these blocks (DRDB, GLFEB, and CSAB) are designed to address specific challenges in the classification process, leading to improved discrimination of features crucial for accurate multi-class blood cell image identification. Their effective integration within the model contributes to the superior performance of DDRNet.

Wet-ConViT: A Hybrid Convolutional–Transformer Model for Efficient Wetland Classification Using Satellite Data

Accurate and efficient classification of wetlands, as one of the most valuable ecological resources, using satellite remote sensing data is essential for effective environmental monitoring and sustainable land management. Deep learning models have recently shown significant promise for identifying wetland land cover; however, they are mostly constrained in practical issues regarding efficiency while gaining high accuracy with limited training ground truth samples. To address these limitations, in this study, a novel deep learning model, namely Wet-ConViT, is designed for the precise mapping of wetlands using multi-source satellite data, combining the strengths of multispectral Sentinel-2 and SAR Sentinel-1 datasets. Both capturing local information of convolution and the long-range feature extraction capabilities of transformers are considered within the proposed architecture. Specifically, the key to Wet-ConViT’s foundation is the multi-head convolutional attention (MHCA) module that integrates convolutional operations into a transformer attention mechanism. By leveraging convolutions, MHCA optimizes the efficiency of the original transformer self-attention mechanism. This resulted in high-precision land cover classification accuracy with a minimal computational complexity compared with other state-of-the-art models, including two convolutional neural networks (CNNs), two transformers, and two hybrid CNN–transformer models. In particular, Wet-ConViT demonstrated superior performance for classifying land cover with approximately 95% overall accuracy metrics, excelling the next best model, hybrid CoAtNet, by about 2%. The results highlighted the proposed architecture’s high precision and efficiency in terms of parameters, memory usage, and processing time. Wet-ConViT could be useful for practical wetland mapping tasks, where precision and computational efficiency are paramount.

Improved medical image inpainting using automatic multi-task learning driven deep learning approach

Distorted medical images can drastically reduce diagnosis accuracy using computer-aided diagnostic (CAD) systems. The objective of medical image classification is to improve diagnostic imaging precision and restore regions degraded by image inpainting. Deep Learning (DL) methods like Generative Adversarial Networks (GANs) are being used to solve these medical image inpainting issues. Recently, various improved GAN models were proposed for improved image inpainting, but challenges like computational inefficiency, unreliable restoration quality, and lack of correct analysis of discriminator block. To overcome these problems, a novel GAN model is proposed with modified Generator and Discriminator blocks for improved medical image inpainting. To improve image inpainting quality with minimum computational complexity, the Multi-Task Learning (MTL)-based generator block is designed. The MTL encoder is connected with three decoders for three tasks edge detection, organ boundary generation, and image completion. The MTL-based encoder and decoders are modified with an optimum number of layers and regularization functions to improve the outcomes. The output of the generator block is input into the discriminator block, where we designed the relevant feedback strategy to decrease generator loss by automatically changing the weights on wrong classifications. The simulation results revealed the efficiency of the proposed medical image inpainting approach and discriminator block performances over the state-of-the-art. Due to the modified MTL-based generator and discriminator block in the proposed approach, the PSNR is improved by 14.31 %, SSIM is improved by 8.56%, UQI is improved by 9.45%, and MSE is reduced by 22.78% using the proposed model compared to the state-of-the-arts.

A modified fuzzy Adomian decomposition method for solving time-fuzzy fractional partial differential equations with initial and boundary conditions

This research article introduces a novel approach based on the fuzzy Adomian decomposition method (FADM) to solve specific time fuzzy fractional partial differential equations with initial and boundary conditions (IBCs). The proposed approach addresses the challenge of incorporating both initial and boundary conditions into the FADM framework by employing a modified approach. This approach iteratively generates a new initial solution using the decomposition method. The method presented here offers a significant contribution to solving fuzzy fractional partial differential equations (FFPDEs) with fuzzy IBCs, a topic that has received limited attention in the literature. Furthermore, it satisfies a high convergence rate with minimal computational complexity, establishing a novel aspect of this research. By providing a series solution with a small number of recursive formulas, this method enhances accuracy and emerges as a preferred choice for tackling FFPDEs with mixed initial and boundary conditions. The effectiveness of the proposed technique is further supported by the inclusion of several illustrative examples.

Light4Mars: A lightweight transformer model for semantic segmentation on unstructured environment like Mars

Auto-semantic segmentation is important for robots on unstructured and dynamic environments like planets where ambient conditions cannot be controlled and the scale is larger than that found indoors. Current learning-based methods have achieved breathtaking improvements on this topic. For onboard applications, however, all those methods still suffer from huge computational costs and are difficult to deploy on edge devices. In this paper, unlike previous transformer-based SOTA approaches that heavily relied on complex design, we proposed Light4Mars, a lightweight model with minimal computational complexity while maintaining high segmenting accuracy. We designed a lightweight squeeze window transformer module that focuses on window-scale feature extraction and is more effective in learning global and local contextual information. The aggregated local attention decoder is utilized to fuse semantic information at different scales, especially for unstructured scenes. Since there are few all-terrain datasets for semantic segmentation of unstructured scenes like Mars, we built a synthetic dataset SynMars-TW, referencing images collected by the ZhuRong rover on the Tianwen-1 mission and the Curiosity rover. Extensive experiments on SynMars-TW and the real Mars dataset, MarsScapes show that our approach achieves state-of-the-art performance with favorable computational simplicity. To the best of our knowledge, the proposed Light4Mars-T network is the first segmentation model for Mars image segmentation with parameters lower than 0.1M. Code and datasets are available at https://github.com/CVIR-Lab/Light4Mars.

Implementation of companding scheme for performance enhancement of optical OFDM structure

Abstract Due to its great spectral efficiency and resistance to multi-path fading, OFDM, or orthogonal frequency division multiplexing, is commonly utilized in optical communication systems. However, because of nonlinear distortions in optical components, OFDM signals are prone to a high peak-to-average power ratio (PAPR), which can severely impair bit error rate (BER) performance. This paper introduces a companding scheme to address high PAPR in optical OFDM systems and improve BER performance. The proposed scheme uses a nonlinear transformation to compress signal peaks and expand valleys, effectively reducing PAPR. Specifically, we investigate the µ-law companding technique, known for its simplicity and effectiveness in handling the active range of OFDM signals in optical communication. The companded signals are transmitted through an optical link and demodulated at the receiver. Simulation results show that the µ-law companding technique substantially reduces PAPR, leading to a significant improvement in BER performance. The companding process maintains signal integrity and spectral efficiency with minimal computational complexity and implementation cost. By mitigating nonlinearities introduced by optical components, this companding scheme enhances the overall reliability and efficiency of the optical OFDM system. An SNR gain of 2 dB–3 dB was achieved at a BER of 10−3.

Capacitance health monitoring in the modular multilevel converter using a method with minimum number of sensors and computational burden

SummaryThis paper proposes a method for capacitance health monitoring (CHM) of submodule capacitors in modular multilevel converters (MMCs) that uses a reduced number of voltage sensors. In the proposed method, the MMC arms are divided into some groups of submodules and one voltage sensor is used for each group. In addition, a capacitor voltage estimation technique with minimal computational complexity is used to determine the capacitor voltage. The ratio of the estimated to measured capacitor voltage during positive arm current is also used to demonstrate a simple and efficient capacitance monitoring method. Moreover, contrary to the limitations associated with traditional CHM methods, the proposed method reduces the required voltage sensors and minimizes data exchange between the power system and the central processor. The effectiveness of the proposed method is validated through simulation and experimental results under various operating conditions.

Improved Temporal Fuzzy Reasoning Spiking Neural P Systems for Power System Fault Diagnosis

Fuzzy and temporal reasoning can effectively improve the accuracy of fault diagnosis methods. However, there are challenges in practical applications, such as missing alarm messages, temporal reasoning with complex calculations, and complex modeling processes. Therefore, this study proposes an improved temporal fuzzy reasoning spiking neural P (ITFRSNP) system for power system fault diagnosis. First, the ITFRSNP system and its reasoning method are proposed to perform association reasoning between confidence degrees and temporal constraints. Second, a general fault diagnosis model and process are developed based on the ITFRSNP system to diagnose various faulty components and simplify the modeling process. In addition, a search method is provided for identifying suspected faulty components, considering the missing alarm message of the circuit breaker. Simulation results of fault cases demonstrate that the proposed method exhibits high accuracy and fault tolerance. It can precisely identify faulty components despite incorrect operations or inaccurate alarm messages of protective relays and circuit breakers. Moreover, the search method effectively narrows down the diagnostic scope without missing suspected faulty components in scenarios where alarms from boundary circuit breakers are missing, thereby enhancing the fault diagnosis efficiency. The fault diagnosis model features a straightforward structure and reasoning process with minimal computational complexity, making it suitable for real-time diagnosis of complex faults within power systems.

New Agricultural Tractor Manufacturer’s Suggested Retail Price (MSRP) Model in Europe

Research investigating models for assessing new tractor pricing is notably scarce, despite its fundamental importance in conducting comprehensive cost analyses. This study aims to identify a model that is both user-friendly and robust, evaluating both parametric and Machine Learning-optimized non-parametric models. Among parametric models, the second-order polynomial model demonstrated superior performance in terms of R-squared (R2) of 0.97469 and a Root Mean Square Error (RMSE) of 15,633. Conversely, Machine Learning-optimized Gaussian Processes Regressions exhibited the most favorable overall R-squared (R2) of 0.99951 and a Root Mean Square Error (RMSE) of 2321. While the parametric polynomial model offers a solution with minimal mathematical and computational complexity, the non-parametric GPR model delivers highly robust outcomes, presenting stakeholders involved in new agriculture tractor transactions with superior data-driven decision-making capabilities.

Characterization of Gauss–Markov stochastic sequences for mission analysis

In real scenarios, the spacecraft deviates from the intended paths owing to uncertainties in dynamics, navigation, and command actuation. Accurately quantifying these uncertainties is crucial for assessing the observability, collision risks, and mission viability. This issue is further magnified for CubeSats because they have limited control authority and thus require accurate dispersion estimates to avoid rejecting viable trajectories or selecting unviable ones. Trajectory uncertainties arise from random variables (e.g., measurement errors and drag coefficients) and processes (e.g., solar radiation pressure and low-thrust acceleration). Although random variables generally present minimal computational complexity, handling stochastic processes can be challenging because of their noisy dynamics. Nonetheless, accurately modeling these processes is essential, as they significantly influence the uncertain propagation of space trajectories, and an inadequate representation can result in either underestimation or overestimation of the stochastic characteristics associated with a given trajectory. This study addresses the gap in characterizing process uncertainties, represented as Gauss–Markov processes in mission analysis, by presenting models, evaluating derived quantities, and providing results on the impact of spacecraft trajectories. This study emphasizes the importance of accurately modeling random processes to properly characterize stochastic spacecraft paths.

HIKS: A K‐shell‐weighted hybrid approach method for detecting influential nodes in complex networks using possible edge weights

SummaryThe influential node in the network is the node that has a higher impact on network functioning compared to the other nodes. The influential node detection in the complex network is crucial for rumor containment, virus spreading, viral marketing, and so forth. The researchers designed several influential node detection methods; still, detecting community and influential node selection with minimal computational complexity by considering the relationship between the nodes is challenging. Hence, an optimal community detection along with the hybrid K‐shell decomposition method is introduced in this research. Initially, the optimal community from the complex network is identified to reduce the computation burden. For this, the Improved Dingo (IDingo) algorithm is introduced by hybridizing the hunting behavior of Dingo and the rough encircling behavior of Harris Hawk. After detecting the optimal community, the influential node identification is devised using the proposed hybrid K‐shell decomposition methods. The potential edge weights are considered while ranking the nodes. The performance of a proposed method is analyzed using six various datasets and accomplished the maximal cluster coefficient of 0.56578, 0.25674, 0.24022, 0.5968, 0.23419, and 0.10196 for Karate, Dolphins, C‐Elegance, Facebook, Gowalla, and Power Grid Dataset.

An Efficient Noise Reduction Method for Power Transformer Voiceprint Detection Based on Poly-Phase Filtering and Complex Variational Modal Decomposition

The transformer is a core component in power systems, and its reliable operation is crucial for the safety and stability of the power grid. Transformer faults can be diagnosed early using acoustic signals. However, effective acoustic features are often affected by complex environmental noise, which reduces the accuracy of fault identification. As a solution, this study proposes a poly-phase filtering (PF)-based noise reduction algorithm for complex variational mode decomposition (CVMD) of multiple acoustic sources in power transformers. The algorithm dissects the received signal from the power transformer into subbands, downsizing their sampling rates via PF. Subsequently, it independently targets noise reduction within these subbands, focusing on specific acoustic sources. Leveraging complex signal transformations, we extend the variational mode decomposition (VMD) to mitigate the field of complex signals and utilize the CVMD to reduce the noise of each acoustic source within each subband for every acoustic source. The experimental results reveal that the proposed method effectively separates and denoises the sound signal of transformer operation under the interference of multiple sound sources in the substation. Its powerful noise reduction ability, combined with minimal computational complexity, greatly improves the accuracy of transformer fault identification and the reliability of the system.

Channel Attention-Based Approach with Autoencoder Network for Human Action Recognition in Low-Resolution Frames

Action recognition (AR) has many applications, including surveillance, health/disabilities care, man-machine interactions, video-content-based monitoring, and activity recognition. Because human action videos contain a large number of frames, implemented models must minimize computation by reducing the number, size, and resolution of frames. We propose an improved method for detecting human actions in low-size and low-resolution videos by employing convolutional neural networks (CNNs) with channel attention mechanisms (CAMs) and autoencoders (AEs). By enhancing blocks with more representative features, convolutional layers extract discriminating features from various networks. Additionally, we use random sampling of frames before main processing to improve accuracy while employing less data. The goal is to increase performance while overcoming challenges such as overfitting, computational complexity, and uncertainty by utilizing CNN-CAM and AE. Identifying patterns and features associated with selective high-level performance is the next step. To validate the method, low-resolution and low-size video frames were used in the UCF50, UCF101, and HMDB51 datasets. Additionally, the algorithm has relatively minimal computational complexity. Consequently, the proposed method performs satisfactorily compared to other similar methods. It has accuracy estimates of 77.29, 98.87, and 97.16%, respectively, for HMDB51, UCF50, and UCF101 datasets. These results indicate that the method can effectively classify human actions. Furthermore, the proposed method can be used as a processing model for low-resolution and low-size video frames.

Enhancing Accuracy of Groundwater Level Forecasting with Minimal Computational Complexity Using Temporal Convolutional Network

Multiscale forecasting of groundwater levels (GWLs) is essential for ensuring the sustainable management of groundwater resources, particularly considering the potential impacts of climate change. Such forecasting requires a model that is not only accurate in predicting GWLs but also computationally efficient, ensuring its suitability for practical applications. In this study, a temporal convolutional network (TCN) is implemented to forecast GWLs for 17 monitoring wells possessing diverse hydrogeological characteristics, located across South Korea. Using deep learning, the influence of meteorological variables (i.e., temperature, precipitation) on the forecasted GWLs was investigated by dividing the input features into three categories. Additionally, the models were developed for three forecast intervals (at 1-, 3-, and 6-month lead times) using each category input. When compared with state-of-the-art models, that is, long short-term memory (LSTM) and artificial neural network (ANN), the TCN model showed superior performance and required much less computational complexity. On average, the TCN model outperformed the LSTM model by 24%, 21%, and 25%, and the ANN model by 24%, 37%, and 47%, respectively, for 1-, 3-, and 6-month lead times. Based on these results, the proposed TCN model can be used for real-time GWL forecasting in hydrological applications.

Detection of solidification crack formation in laser beam welding videos of sheet metal using neural networks

AbstractLaser beam welding has become widely applied in many industrial fields in recent years. Solidification cracks remain one of the most common welding faults that can prevent a safe welded joint. In civil engineering, convolutional neural networks (CNNs) have been successfully used to detect cracks in roads and buildings by analysing images of the constructed objects. These cracks are found in static objects, whereas the generation of a welding crack is a dynamic process. Detecting the formation of cracks as early as possible is greatly important to ensure high welding quality. In this study, two end-to-end models based on long short-term memory and three-dimensional convolutional networks (3D-CNN) are proposed for automatic crack formation detection. To achieve maximum accuracy with minimal computational complexity, we progressively modify the model to find the optimal structure. The controlled tensile weldability test is conducted to generate long videos used for training and testing. The performance of the proposed models is compared with the classical neural network ResNet-18, which has been proven to be a good transfer learning model for crack detection. The results show that our models can detect the start time of crack formation earlier, while ResNet-18 only detects cracks during the propagation stage.

Kalman filter based sensor fault detection in wireless sensor network for smart irrigation

Ensuring the reliability of data obtained from Wireless Sensor Networks (WSNs) deployed in farmland to monitor soil parameters is crucial for optimizing smart irrigation. These distributed sensor nodes encounter various challenges and are vulnerable to sensor faults that can significantly degrade the network's service quality. In this article, we present an innovative approach for detecting sensor faults within WSNs for smart irrigation by combining an autoregressive model with a Kalman filter. Integrating the Kalman filter and the autoregressive model combines their strengths in a synergistic manner. The algorithm is developed with consideration for the resource constraints of the sensor nodes and addresses the challenge of lacking ground truth information for the monitored area. The primary advantage of this proposed technique lies in its simplicity of implementation, requiring minimal computational complexity while enhancing the application's reliability. Through experimentation and validation, we demonstrate the effectiveness of this combined approach in detecting sensor fault detection in real-world WSNs scenarios.

Security-Reliability Analysis of AF Full-Duplex Relay Networks Using Self-Energy Recycling and Deep Neural Networks.

This paper investigates the security-reliability of simultaneous wireless information and power transfer (SWIPT)-assisted amplify-and-forward (AF) full-duplex (FD) relay networks. In practice, an AF-FD relay harvests energy from the source (S) using the power-splitting (PS) protocol. We propose an analysis of the related reliability and security by deriving closed-form formulas for outage probability (OP) and intercept probability (IP). The next contribution of this research is an asymptotic analysis of OP and IP, which was generated to obtain more insight into important system parameters. We validate the analytical formulas and analyze the impact on the key system parameters using Monte Carlo simulations. Finally, we propose a deep learning network (DNN) with minimal computation complexity and great accuracy for OP and IP predictions. The effects of the system's primary parameters on OP and IP are examined and described, along with the numerical data.

Neuromorphic computing with hybrid CNN–Stochastic Reservoir for time series WiFi based human activity recognition

Wi-Fi Channel State Information (CSI) based human activity recognition (HAR) which using channel disturbances caused by signal reflection is a novel way of environment sensing and motion recognition. The collected channels characteristics are heavily influenced by the environment, human activity patterns and subject’s weight and height. These signal variations reflected from body components are mainly affected by static multipath effects comprises random noise and behave differently in individuals, and thus an active field of research. To reach further for achieving automated real-time classification, lower computational cost and easy adaptability to hardware are necessary. In this work, a CSI-based HAR with hybrid framework, Convolutional Neural Network (CNN)-Stochastic Reservoir (SR) (CNN-SR) has been proposed, enabling a subject adaptable and more efficient hardware implementation with minimal computational complexity. A subcarrier correlation matrix is first computed and portrayed in image without preprocessing based on the reflection of the raw CSI signal induced by human activities at regular intervals, allowing visual observation of whole pattern changes. The time-based features are subsequently extracted through CNN and these feature arrays are then feed into SR which based on stochastic spiking neural network (SSNN) in simple cycle reservoir architecture for template matching. SR offers attractive power savings over typical von Neumann systems, by doing stochastic computations. The proposed method has also been demonstrated that is capable for HAR based on partially captured signals. The signal pattern of each segment can be observed in a single sight and then employed for person-to-person template recognition. This enables HAR with minimal computational complexity and solving the inter-person variability concerns. The results demonstrate that the proposed CNN-SR achieves impressive performance in recognizing human activities and surpasses existing models with an average accuracy of 93.49%.