Low Resource Consumption Research Articles

Topology optimization of a superconducting photonic crystal power beam splitter

The design of photonic crystals using novel materials holds significant importance in constructing high-performance, next-generation photonic crystal devices. In this study, aiming at the requirements for enhanced transmission and selectivity, we utilized a topology optimization method based on the method of moving asymptotes (MMA) to realize a high-temperature superconducting photonic crystal power splitter with low transmission loss and selectivity effects, which allows for flexible control and manipulation of optical signals. The method addresses the shortcomings of traditional scanning techniques, such as low efficiency and high resource consumption, by allowing for multi-parameter optimization. This improvement enhances the precision and effectiveness of the numerical computational iterative process. The research offers insights into the design of novel optical devices.

A Kansei engineering-based decision-making method for offline medical service quality evaluation with multidimensional attributes

The evaluation of doctors’ offline medical service quality plays a vital role in evaluating hospital performance. There are two challenges that need to be addressed: (1) Currently, telephone follow-up and questionnaire surveys are the main methods for evaluating the quality of offline (mainly outpatient and inpatient) medical services in hospitals. However, these methods suffer from drawbacks such as low efficiency and resource consumption. (2) There are certain limitations to determining attribute dimensions and weighting patient evaluation attributes based solely on word frequency. To this end, this study proposes a Kansei engineering-based decision-making method for offline medical service quality evaluation with multidimensional attributes. First, this study constructs a medical Kansei lexicon based on speed and cosine similarity. Second, a concept of Kansei utility values is been defined to represent attribute values in medical service quality evaluation. Additionally, this study builds upon the Kano model to obtain the Kano classification of each attribute. On that basis, a novel approach to obtaining the implicit importance of the attributes is proposed. Thus, the weight vector of the attributes can be calculated as the combination of explicit and implicit importance. Finally, the evaluation result is obtained by using the multiattribute decision-making method. The effectiveness of the proposed method is verified through an analysis of online reviews from Haodf.com. The case study reveals that offline patients consider medical ethics and communication skills as the ”must-be” dimension of attributes, medical competence as a one-dimensional attribute, and medical advice and prescriptions as the attractive dimension of attributes. A comparative analysis with the traditional method is conducted to demonstrate the importance of dimensional analysis for offline medical service quality evaluation. The main contributions of this study include the following: (1) A medical Kansei lexicon is constructed based on Kansei engineering, and (2) a novel decision-making framework for medical service evaluation based on both appearance and implicit importance is constructed.

Using 5G Standards for Smart Healthcare Applications and Designing an Artificial Intelligence‐Based Industry 4.0 Communication System

ABSTRACTThe introduction of Industry 4.0, to improve Internet of Things (IoT) standards, has sparked the creation of 5G, or highly sophisticated wireless networks. There are several barriers standing in the way of 5G green communication systems satisfying the expectations for faster networks, more user capacity, lower resource consumption, and cost‐effectiveness. 5G standards implementation would speed up data transmission and increase the reliability of connected devices for Industry 4.0 applications. The demand for intelligent healthcare systems has increased globally as a result of the introduction of the novel COVID‐19. Designing 5G communication systems presents research problems such as optimizing resource usage, managing mobility, ensuring cost‐efficiency, managing interference, and maximizing spectral efficiency. The fast advancement of artificial intelligence (AI) in several domains yields improved performance in contrast to traditional methods. Hence, including AI in 5G standards would enhance performance by catering to diverse end‐user applications. Initially, we provide an overview of concepts such as Industry 4.0, the 5G standard, and recent developments in the sphere of wireless communications in the future. The goal is to use 5G technology to look at current research problems. We present a new architecture for Industry 4.0 and 5G‐compliant smart healthcare systems. We develop and run the proposed model to investigate the current 5G methods using the Network Simulator (NS2). The results of the simulation show that 5G resource management and interference management approaches already in use face challenges including performance trade‐offs.

Resource-optimized cnns for real-time rice disease detection with ARM cortex-M microprocessors

This study explores the application of Artificial Intelligence (AI), specifically Convolutional Neural Networks (CNNs), for detecting rice plant diseases using ARM Cortex-M microprocessors. Given the significant role of rice as a staple food, particularly in Malaysia where the rice self-sufficiency ratio dropped from 65.2% in 2021 to 62.6% in 2022, there is a pressing need for advanced disease detection methods to enhance agricultural productivity and sustainability. The research utilizes two extensive datasets for model training and validation: the first dataset includes 5932 images across four rice disease classes, and the second comprises 10,407 images across ten classes. These datasets facilitate comprehensive disease detection analysis, leveraging MobileNetV2 and FD-MobileNet models optimized for the ARM Cortex-M4 microprocessor. The performance of these models is rigorously evaluated in terms of accuracy and computational efficiency. MobileNetV2, for instance, demonstrates a high accuracy rate of 97.5%, significantly outperforming FD-MobileNet, especially in detecting complex disease patterns such as tungro with a 93% accuracy rate. Despite FD-MobileNet’s lower resource consumption, its accuracy is limited to 90% across varied testing conditions. Resource optimization strategies highlight that even slight adjustments, such as a 0.5% reduction in RAM usage and a 1.14% decrease in flash memory, can result in a notable 9% increase in validation accuracy. This underscores the critical balance between computational resource management and model performance, particularly in resource-constrained settings like those provided by microcontrollers. In summary, the deployment of CNNs on microcontrollers presents a viable solution for real-time, on-site plant disease detection, demonstrating potential improvements in detection accuracy and operational efficiency. This study advances the field of smart agriculture by integrating cutting-edge AI with practical agricultural needs, aiming to address the challenges of food security in vulnerable regions.

AI for Cloud Cost Management: Predictive and Prescriptive Analytics

With reference to the previous information and literature review, the purpose of this research paper is to evaluate the impact of multithreading concerning computer resource utilization and performance by undertaking and comparing various crucial multithreading techniques, including work stealing, fork join, and the use of the thread pool control. In an experimental context, benchmark applications that can be characteristic of several domains were evaluated in a controlled multicore computing platform. Time, CPU occupation, memory usage and throughputs were determined systematically and compared according to the various workloads. The results highlight the superiority of the work-steing algorithm in keeping the execution time and CPU usage low compared to the rest as a sign of its efficiency in managing work loads. Further, the memory usage and the throughput statistics showed the degree of inefficiency of each algorithm and performance penalty. Interviews with developers elaborated on more practical issues of multithreading as the generally rigid nature of the problems suggested that optimal solutions called for adaptive measures in practice. Based on the results achieved in this research, developers and researchers can increase their knowledge about available multithreading algorithms and make suggestions to choose and apply them with high efficiency and low resource consumption.

A combination learning framework to uncover cyber attacks in IoT networks

The Internet of Things (IoT) is rapidly expanding, connecting an increasing number of devices daily. Having diverse and extensive networking and resource-constrained devices creates vulnerabilities to various cyber-attacks. The IoT with the supervision of Software Defined Network (SDN) enhances the network performance through its flexibility and adaptability. Different methods have been employed for detecting security attacks; however, they are often computationally efficient and unsuitable for such resource-constraint environments. Consequently, there is a significant requirement to develop efficient security measures against a range of attacks. Recent advancements in deep learning (DL) models have paved the way for designing effective attack detection methods. In this study, we leverage Genetic Algorithm (GA) with a correlation coefficient as a fitness function for feature selection. Additionally, mutual information (MI) is applied for feature ranking to measure their dependency on the target variable. The selected optimal features were used to train a hybrid DNN model to uncover attacks in IoT networks. The hybrid DNN integrates Convolutional Neural Network, Bi-Gated Recurrent Units (Bi-GRU), and Bidirectional Long Short-Term Memory (Bi-LSTM) for training the input data. The performance of our proposed model is evaluated against several other baseline DL models, and an ablation study is provided. Three key datasets InSDN, UNSW-NB15, and CICIoT 2023 datasets, containing various types of attacks, were used to assess the performance of the model. The proposed model demonstrates an impressive accuracy and detection time over the existing model with lower resource consumption.

Class incremental learning with analytic learning for hyperspectral image classification

Hyperspectral image classification (HSIC) is crucial for applications in agriculture and environmental monitoring. As ground objects evolve and remote sensing technology progresses, there is a growing need for HSIC models that can adapt to new data classes without requiring to be retrained from scratch. Throughout the continual learning procedure, the model is expected to not only effectively extract spatial–spectral features from the hyperspectral image but also alleviate the issue of catastrophic forgetting, i.e., the model forgets the learned classes’ knowledge when accessing novel classes during the training process. In this paper, for the HSIC task, we propose a class incremental learning method (HSI-CIL) that is based on analytic learning, a technique that converts network training into linear problems. Specifically, The HSI-CIL model consists of a lightweight feature extractor, a Feature Processing Module (FPM) and an Analytic Linear Classifier (ALC). This model does not need data storage for old and new classes and has only one epoch in the incremental learning stage, so it has lower consumption of resources and training time than several attempts have been proposed for addressing catastrophic forgetting. We perform abundant experiments with the proposed HSI-CIL on three publicly available hyperspectral datasets including Indian Pines, Pavia University, and Salinas. The experiments demonstrate that our HSI-CIL exceeds the state-of-the-art class incremental learning (CIL) techniques applied in HSIC with a certain gap.

Evaluating Sustainable Digitalization: A Carbon-Aware Framework for Enhancing Eco-Friendly Business Process Reengineering

In an era where sustainability is paramount, understanding the environmental impact of digitalizing business processes is critical. Despite the growing emphasis on sustainable practices, there is a lack of comprehensive methodologies to evaluate how digitalization impacts environmental sustainability compared to traditional processes. This paper introduces a carbon-aware methodological framework specifically designed to assess the sustainability of business process reengineering through digitalization. The Digital Green framework quantitatively analyzes the environmental costs associated with digital transformation, ensuring that truly sustainable digitalization results in lower resource consumption relative to the complexity of the process being digitalized. To demonstrate its effectiveness, the framework was applied to a case study involving the reengineering of an administrative process at a small university in southern Italy. The case study highlighted the framework’s ability to quantify the environmental benefits or detriments of digital transformation, thus guiding organizations toward more sustainable digital practices. This research contributes to the field by offering a concrete tool for aligning digitalization efforts with ecological sustainability, and by paving the way for integration with initiatives such as the Green Software Foundation’s Software Carbon Intensity (SCI) specifications.

Approaching Breakthrough: Resource-Efficient Micropollutant Removal with MBR-GAC Configuration

The removal of micropollutants from municipal wastewater is crucial to mitigate negative environmental impacts on aquatic ecosystems. However, existing advanced treatment techniques often require extensive fossil resources to achieve the targeted removal of a broad range of micropollutants. This study presents the combination of Membrane Bioreactors (MBRs) and subsequent Granular Activated Carbon (GAC) filters as a resource-efficient solution. Based on long-term pilot studies at a municipal WWTP in Stockholm, Sweden, this investigation explores the MBR-GAC configuration as a sustainable alternative for quaternary treatment at WWTPs. Results from over three years demonstrate a high removal efficiency of over 80% for targeted pharmaceuticals and other organic micropollutants, such as per- and polyfluoroalkyl substances (PFASs), from the WWTP inlet to the outlet. The synergy between MBR and GAC technologies provides this high removal efficiency with considerably lower resource consumption and cost compared to traditional GAC installations. No breakthrough of micropollutants has been observed to date indicating even better resource efficiency than presented in this paper.

Remote Sensing Building Damage Assessment Based on Machine Learning

Abstract After the occurrence of various types of disasters, including natural disasters and man-made damage, aid workers need accurate and timely data, such as the damage status of buildings, in order to take effective measures for rescue. So as to solve this problem, this paper researches and designs a building damage classification system based on machine learning. The damage assessment system consists of two network models (building extraction network and damage classification network). This article analyzes and designs the structure of each network model, and discusses the principles related to computer vision in machine learning. Buildings in satellite images are segmented through Siamese Convolutional Neural Network, the BottleNeck Module and Feature Pyramid Network are used in the damage classification assessment network to detect damage to buildings in sub-temporal remote sensing images. Subsequently, the model was trained and tested on different disaster events on the xBD dataset. The results show that the building damage detection system based on Siamese-CNN achieves good detection accuracy, and the system has the advantages of simple operation, good timeliness and low resource consumption, and can well meet the needs of disaster assessment.

Theoretical analysis and technical application of mechanical intelligent manufacturing based on system digital-driven technology

With the accelerating process of global industrialization, the automated fabrication industry, as an important part of the industry, is also developing rapidly. Due to the low efficiency and high resource consumption of traditional manufacturing, it is more important to improve the production efficiency of conventional manufacturing and realize the resource-saving development mode. Due to the characteristics of system digital-driven technology, it can promote the intelligent development of the manufacturing industry. Therefore, the deep integration of system digital-driven technology and manufacturing is conducive to the intelligent promotion of manufacturing. Comparing the difference between the traditional manufacturing industry and the intelligent manufacturing industry, the application potential of system digitalization technology in the manufacturing field is analyzed. Based on the analysis of the theoretical basis of the system digital-driven technology and the application of the system digital technology in the main fields, the importance of the technology for the improvement of the accuracy index in the manufacturing process is emphatically analyzed. The maximum increase can be 5.3%, and the minimum increase can be 3.3%. It can be seen that the deep integration of digital-driven technology and manufacturing can not only improve the intelligent level of manufacturing, realize the intensive development of the industry, but also realize the data sharing of the entire industrial chain.

Dynamic elicitation and forecasting innovation requirement of smart product-service system via user-manufacturer value co-creation perspective using multi-source data

Achieving greater efficiency and lower resource consumption is a constant pursuit for successfully developing smart product-service system (PSS). Conducting dynamic requirements analysis is increasingly important in the process while the value co-creation of smart PSS stakeholders has not been sufficiently considered. This study adopts a user-manufacturer value co-creation perspective to explore smart PSS dynamic requirement elicitation and forecasting. Using multi-source data of user online reviews, historical descriptive texts and patent abstracts, this study dynamically elicits the smart PSS innovation requirements using dynamic topic model (DTM) and bidirectional encoder representation from transformers (BERT). Furthermore, the key innovation requirements of smart PSS are identified by integrating their importance and satisfaction values into a dynamic importance-performance analysis (DIPA). Then, the trend of smart PSS key innovation requirements is predicted by the grey forecasting model to determine the smart PSS improvement direction. An empirical study of smartwatch service system is conducted to validate the proposed approach. By blending both user and manufacturer requirements, this study provides a novel framework for dynamic requirement elicitation and forecasting of smart PSS based on multi-source data. It contributes to facilitating the value co-creation during smart PSS development to optimize manufacturer’s R&D resource allocation and enhance user experience.

MDADroid: A novel malware detection method by constructing functionality-API mapping

As the Android ecosystem develops, malware also evolves to adapt to the changes. Consequently, malware remains a significant threat, posing a challenge in developing a low-resource consumption malware detection method that can adjust to updates in the Android API versions. We propose a novel method called MDADroid, which detects malware based on self-built Functionality-API mapping. We start by building a set of permission-related APIs using open-source knowledge. Then, we construct a Functionality-App-API heterogeneous graph based on collected data and establish a Functionality-API mapping from it. Finally, MDADroid transforms app features from the API level to the functionality level for malware detection, ensuring model resilience to API changes. We also design an API similarity calculation method that updates the Functionality-API mapping at a low cost. We evaluate MDADroid on multiple datasets, and the results show that MDADroid achieves an accuracy of 95.22%, 96.23%, 98.77%, and 99.56% on the AndroZoo, CICAndMal 2017, CICMalDroid 2020, and Drebin datasets, respectively, with training and testing times of 2 s, 0.6188 s, 1.34 s, and 1.02 s. Moreover, our method demonstrates excellent performance in the tests for resilience capabilities.

Compliance with the SDGS: Eco-Efficiency Index of Thedistrict Municipality of Pichanaqui, Province Ofchanchamayo - Peru

Objective: Determine the eco-efficiency index of the District Municipality of Pichanaqui from June to December 2023. Method: The methodology of the Ministry of Environment of 2016 was used to diagnose the eco-efficiency baseline, to determine the degree of importance of the eco-efficiency indexes, the Delphi survey was applied and the methodology to estimate the level of sustainable development of territories was used for the eco-efficiency index. Results: The eco-efficiency index result was 0.52, representing an unstable state of eco-efficiency. Contribution: It will help the municipality obtain greater value with a lower consumption of resources or raw materials for the production of goods or services they produce, in addition to mitigating the negative effects on the environment that directly or indirectly affect society.

CSA-SA-CRTNN: A Dual-Stream Adaptive Convolutional Cyclic Hybrid Network Combining Attention Mechanisms for EEG Emotion Recognition.

In recent years, EEG-based emotion recognition technology has made progress, but there are still problems of low model efficiency and loss of emotional information, and there is still room for improvement in recognition accuracy. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification and 97.69% and 98.05% in ternary classification, and on the SEED dataset, we achieved an accuracy of 98.63%, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

Enhanced removal of tetrabromobisphenolA (TBBPA) from e-waste by Fe–S nanoparticles and Fe–S/CuS nanocomposite with response surface methodology (RSM)

TetrabromobisphenolA is a well-known member of the brominated flame retardant group and is widely used as a highly effective fire-retardant additive in electronic and electrical equipment. TBBPA is commonly found in various environmental sources and can be harmful to human health. This study presents a simple approach to preparing a magnetic nanocomposite, offering a straightforward method that results in consistent quality and low resource consumption. The nanocomposite has a high surface-to-volume ratio for the removal of tetrabromobisphenolA. Various characterization techniques, including XRD, FTIR, EDX, FESEM, VSM, TEM, and BET analyses were used to characterize the Fe–S nanoparticles and Fe–S/CuS. The results showed that Fe–S/CuS nanocomposite successfully removed over 97% of the initial TBBPA (15 mg L−1) under optimized conditions determined by RSM, such as a contact time of 15 min, pH of 7, Fe–S/CuS nanocomposite dosage of 0.69 g L−1, and salt concentration of 0.10%. The RSM analysis provided a second-order polynomial model with a confidence level of 93% (F = 29.58; p < 0.0001) to predict the TBBPA removal efficiency at various concentrations. In the adsorption kinetic studies, the second-order kinetic model provided the best fit for the experimental data. Additionally, Fe–S/CuS nanocomposite shows great potential for practical applications and environmental remediation efforts, making it a valuable asset for real-sample use in environmental settings.

A lightweight security defense algorithm for multimodal attack blocking in industrial control networks based on momentum enhanced feature graphs

AbstractAs the infrastructure of modern industry, the safe and stable operation of lightweight industrial control network is crucial for industrial production. Multi‐mode attack is a kind of highly customized and low resource consumption network attack method, which can target the specific vulnerabilities and configuration weaknesses of lightweight industrial control network. In order to improve the defense capability of industrial control network against multimodal attacks, a lightweight security defense algorithm based on momentum‐enhanced feature graph is proposed. The lightweight industrial control network operation mode is determined by abstract relationship, and the ontology structure of industrial control network multi‐mode attack is established; with reference to the ontology structure, the multi‐mode attack map of industrial control network is defined; the normal behavior and lightweight attack behavior are divided, and the convolutional network is used to enhance the characteristics of lightweight attack; and the momentum‐enhanced feature map technology is used to correspond to the enhancement process, and to block and defend against the multi‐mode attack of industrial control network. The results show that the studied algorithm can realize accurate prediction of attack behaviors with different attack behaviors as test objects, and ensure accurate blocking of all kinds of attack behaviors with better security defense effect.

A knowledge graph algorithm enabled deep recommendation system.

Personalized learning resource recommendations may help resolve the difficulties of online education that include learning mazes and information overload. However, existing personalized learning resource recommendation algorithms have shortcomings such as low accuracy and low efficiency. This study proposes a deep recommendation system algorithm based on a knowledge graph (D-KGR) that includes four data processing units. These units are the recommendation unit (RS unit), the knowledge graph feature representation unit (KGE unit), the cross compression unit (CC unit), and the feature extraction unit (FE unit). This model integrates technologies including the knowledge graph, deep learning, neural network, and data mining. It introduces cross compression in the feature learning process of the knowledge graph and predicts user attributes. Multimodal technology is used to optimize the process of project attribute processing; text type attributes, multivalued type attributes, and other type attributes are processed separately to reconstruct the knowledge graph. A convolutional neural network algorithm is introduced in the reconstruction process to optimize the data feature qualities. Experimental analysis was conducted from two aspects of algorithm efficiency and accuracy, and the particle swarm optimization, neural network, and knowledge graph algorithms were compared. Several tests showed that the deep recommendation system algorithm had obvious advantages when the number of learning resources and users exceeded 1,000. It has the ability to integrate systems such as the particle swarm optimization iterative classification, neural network intelligent simulation, and low resource consumption. It can quickly process massive amounts of information data, reduce algorithm complexity and requires less time and had lower costs. Our algorithm also has better efficiency and accuracy.

Light-YOLO: A Study of a Lightweight YOLOv8n-Based Method for Underwater Fishing Net Detection

Detecting small dark targets underwater, such as fishing nets, is critical to the operation of underwater robots. Existing techniques often require more computational resources and operate under harsh underwater imaging conditions when handling such tasks. This study aims to develop a model with low computational resource consumption and high efficiency to improve the detection accuracy of fishing nets for safe and efficient underwater operations. The Light-YOLO model proposed in this paper introduces an attention mechanism based on sparse connectivity and deformable convolution optimized for complex underwater lighting and visual conditions. This novel attention mechanism enhances the detection performance by focusing on the key visual features of fishing nets, while the introduced CoTAttention and SEAM modules further improve the model’s recognition accuracy of fishing nets through deeper feature interactions. The results demonstrate that the proposed Light-YOLO model achieves a precision of 89.3%, a recall of 80.7%, and an mAP@0.5 of 86.7%. Compared to other models, our model has the highest precision for its computational size and is the lightest while maintaining similar accuracy, providing an effective solution for fishing net detection and identification.

A Real-Time Adaptive Station Beamforming Strategy for Next Generation Phased Array Radio Telescopes.

The next generation phased array radio telescopes, such as the Square Kilometre Array (SKA) low frequency aperture array, suffer from RF interference (RFI) because of the large field of view of antenna element. The classical station beamformer used in SKA-low is resource efficient but cannot deal with the unknown sidelobe RFI. A real-time adaptive beamforming strategy is proposed for SKA-low station, which trades the capability of adaptive RFI nulling at an acceptably cost, it doesn't require hardware redesign but only modifies the firmware accordingly. The proposed strategy uses a Parallel Least Mean Square (PLMS) algorithm, which has a computational complexity of 4N+2 and can be performed in parallel. Beam pattern and output SINR simulation results show deeply nulling performance to sidelobe RFI, as well as good mainlobe response similar to the classical beamformer. The convergence performance depends on the signal-and-interference environments and step size, wherein too large a step size leads to a non-optimal output SINR and too small a step size leads to slow convergence speed. FPGA implementation demonstrations are implemented and tested on a NI FPGA module, and test results demonstrate good real-time performance and low slice resource consumption.