Comprehensive Performance Evaluations Research Articles

ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization

Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.•An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).•The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.•The model's generalization and robustness were demonstrated through comprehensive performance evaluations.

Multi-agent long-distance end-to-end indoor navigation: using imitation learning pre-training and global map

Abstract To address the navigation challenges of mobile robot swarm coordination in complex environments, this paper presents a distributed navigation approach for mobile robot swarm. The study initially formulates the problem of robot swarm navigation as a partially observable Markov decision process, employing a distributed proximal policy optimization algorithm to train decision models mapping observations to actions directly. Furthermore, it adopts imitation learning pre-training to maximize expert decisions in the initial training phase, thereby reducing exploration space. Lastly, an improved path point generation algorithm along with a spatiotemporal reachability calculation method is proposed to guide the Deep Reinforcement Learning policy in accomplishing long-distance indoor navigation. Comprehensive performance evaluations are conducted in simulated environments to compare the proposed method with existing approaches. Results demonstrate that the proposed approach effectively enhances both convergence speed and model performance, while significantly improving the navigation capabilities of robot swarms in complex environments.

Online functional connectivity analysis of large all-to-all networks in MNE Scan

Abstract The analysis of electroencephalography (EEG)/magnetoencephalography (MEG) functional connectivity has become an important tool in neuroscience. Especially the high time resolution of EEG/MEG enables important insight into the functioning of the human brain. To date, functional connectivity is commonly estimated offline, that is, after the conclusion of the experiment. However, online computation of functional connectivity has the potential to enable unique experimental paradigms. For example, changes of functional connectivity due to learning processes could be tracked in real time and the experiment be adjusted based on these observations. Furthermore, the connectivity estimates can be used for neurofeedback applications or the instantaneous inspection of measurement results. In this study, we present the implementation and evaluation of online sensor and source space functional connectivity estimation in the open-source software MNE Scan. Online capable implementations of several functional connectivity metrics were established in the Connectivity library within MNE-CPP and made available as a plugin in MNE Scan. Online capability was achieved by enforcing multithreading and high efficiency for all computations, so that repeated computations were avoided wherever possible, which allows for a major speed-up in the case of overlapping intervals. We present comprehensive performance evaluations of these implementations proving the online capability for the computation of large all-to-all functional connectivity networks. As a proof of principle, we demonstrate the feasibility of online functional connectivity estimation in the evaluation of somatosensory evoked brain activity

Establishing Trust and Security in Decentralized Metaverse: A Web 3.0 Approach

The integration of blockchain and Web 3.0 technologies offers significant advancements in identity management and trust within decentralized Metaverse environments. Despite the rapid development of numerous Metaverse platforms, these environments often operate in isolation, lacking interoperability and cohesive security measures. This paper proposes a novel architecture leveraging Self-Sovereign Identity (SSI) principles and blockchain technology to achieve secure and interoperable interactions across different Metaverse platforms. Our framework encompasses a digital wallet application, an interactive virtual environment, and a secure blockchain-based backend infrastructure. We detail the system architecture, operational specifics, and demonstrate significant improvements in scalability, efficiency, and security through comprehensive performance evaluations. Additionally, we address the challenges of real-world implementation and propose viable solutions. By enhancing user control over personal data and enabling secure cross-platform interactions, our approach aims to foster a more secure, interoperable, and user-centric decentralized Metaverse.

Real-time privacy-preserved auditing for shared outsourced data

Health providers need to share patient information across healthcare networks efficiently and securely to improve medical and health services. Timely data synchronization among relevant parties is crucial for effectively containing and preventing the worsening of the condition. However, ensuring rapid information sharing while maintaining the security of sensitive patient data remains a pressing concern. In this paper, we introduce a cloud storage integrity auditing scheme that can protect auditors from procrastinating and preserve the privacy of sensitive information. Our proposed system requires healthcare institutions to encrypt sensitive patient data before uploading it to the cloud. It mandates the use of a data sanitizer for the secure processing of encrypted data blocks. Auditors must verify data integrity and promptly submit their audit results to the blockchain within a predefined time frame. Leveraging the time-sensitive nature of blockchain technology, healthcare institutions can monitor auditor compliance within the allotted validation timeframe. We conducted comprehensive security analysis and performance evaluations to demonstrate the feasibility and effectiveness of our solution in addressing the challenges of secure and timely cloud storage in healthcare settings.

An Adaptive RF Front-End Architecture for Multi-Band SDR in Avionics.

This study introduces a reconfigurable and agile RF front-end (RFFE) architecture that significantly enhances the performance of software-defined radios (SDRs) by seamlessly adjusting to varying signal requirements, frequencies, and protocols. This flexibility greatly enhances spectrum utilization, signal integrity, and overall system efficiency-critical factors in aviation, where reliable communication, navigation, and surveillance systems are vital for safety. A versatile RF front-end is thus indispensable, enhancing connectivity and safety standards. We explore the integration of this flexible RF front-end in SDRs, focusing on the detailed design of essential components, such as receivers, transmitters, RF switches, combiners, and splitters, and their corresponding RF pathways. Comprehensive performance evaluations confirm the architecture's reliability and functionality, including an extensive analysis of receiver gain, linearity, and two-tone test results. These assessments validate the architecture's suitability for aviation radios and address considerations of size, weight, and power-cost (SWaP-C), demonstrating significant gains in operational efficiency and cost-effectiveness. The introduction of the new RF front-end on a single SDR board not only substantially reduces size and weight but also adds up to 18 dB gain to the received signal. It also allows for a high level of design flexibility, enabling seamless software transitions between different radios and the capacity to manage three times more radios with the same hardware, thereby significantly boosting the system's ability to handle multiple radio channels efficiently.

Refined one-dimensional modeling and experimental validation of scroll compressor with vapor injection for electric vehicles

Vapor injection technology represents a highly promising avenue for enhancing the efficiency of heat pump systems within electric vehicles, especially in challenging cold ambient conditions. Although a simplified isentropic process is commonly employed to assess the thermodynamic functioning of scroll compressors with vapor injection (SCVI), it diverges significantly from actual operational dynamics. This study introduces a sophisticated 1D mathematical model that incorporates key factors such as internal leakage and thermal losses, thereby providing a more accurate representation of SCVI's operational realities. The research includes comprehensive performance evaluations of a short wrap profile SCVI, with a specific focus on low-temperature ambient conditions, supported by rigorous experimental validation. Comparative analyses against non-injection scenarios reveal notable enhancements, including a maximum 17.2 % increase in mass flow, a 10.5 % rise in heating capacity, and a 2.15 % improvement in heating COP. Both the simplified isentropic process calculation model and the enhanced 1D mathematical model are utilized to analyze compressor operations. The integration of internal leakage and heat loss considerations significantly narrows the gap between calculated and experimental results for heating capacity and discharge temperature, reducing discrepancies from nearly 20 % to a mere 4 %. This refined mathematical model demonstrates a high level of alignment with experimental data, achieving an accuracy within 5 % when assessing the compressor's real-world operational dynamics.

Optimizing Autonomous UAV Navigation with D* Algorithm for Sustainable Development

Autonomous navigation for Unmanned Aerial Vehicles (UAVs) has emerged as a critical enabler in various industries, from agriculture, delivery services, and surveillance to search and rescue operations. However, navigating UAVs in dynamic and unknown environments remains a formidable challenge. This paper explores the application of the D* algorithm, a prominent path-planning method rooted in artificial intelligence and widely used in robotics, alongside comparisons with other algorithms, such as A* and RRT*, to augment autonomous navigation capabilities in UAVs’ implication for sustainability development. The core problem addressed herein revolves around enhancing UAV navigation efficiency, safety, and adaptability in dynamic environments. The research methodology involves the integration of the D* algorithm into the UAV navigation system, enabling real-time adjustments and path planning that account for dynamic obstacles and evolving terrain conditions. The experimentation phase unfolds in simulated environments designed to mimic real-world scenarios and challenges. Comprehensive data collection, rigorous analysis, and performance evaluations paint a vivid picture of the D* algorithm’s efficacy in comparison to other navigation methods, such as A* and RRT*. Key findings indicate that the D* algorithm offers a compelling solution, providing UAVs with efficient, safe, and adaptable navigation capabilities. The results demonstrate a path planning efficiency improvement of 92%, a 5% reduction in collision rates, and an increase in safety margins by 2.3 m. This article addresses certain challenges and contributes by demonstrating the practical effectiveness of the D* algorithm, alongside comparisons with A* and RRT*, in enhancing autonomous UAV navigation and advancing aerial systems. Specifically, this study provides insights into the strengths and limitations of each algorithm, offering valuable guidance for researchers and practitioners in selecting the most suitable path-planning approach for their UAV applications. The implications of this research extend far and wide, with potential applications in industries such as agriculture, surveillance, disaster response, and more for sustainability.

ADVANCING MEMORY DENSITY: A NOVEL DESIGN FOR MULTIPLE-BIT-PER-CELL PHASE CHANGE MEMORY

Multiple-bit-per-cell phase-change memory (MPCM) has emerged as a promising solution to address the escalating demands for high-density, low-power, and fast-access memory in modern computing and data storage systems. This paper presents a novel device design aimed at enabling multiple bits per cell in phase-change memory, thereby significantly enhancing memory density while maintaining performance and reliability. Leveraging innovative material compositions and advanced fabrication techniques, the proposed design demonstrates the potential to push the boundaries of memory capacity, efficiency, and scalability. Through comprehensive simulation analysis and performance evaluations, we showcase the feasibility and advantages of the new device design, highlighting its potential to revolutionize memory architectures and meet the evolving needs of next-generation computing systems.

Solar photovoltaic fed synchronous reluctance motor with optimized rotor flux barriers: Design and performance optimization

This paper focuses on enhancing the design of a synchronous reluctance motor (SyRM) specifically tailored for solar photovoltaic (PV) water pumping applications. With growing adoption of green technologies and renewable energy sources, particularly solar power, there is a need to boost the motor's efficiency to meet the demands of such applications. Utilizing renewable energy for water pumping offers significant advantages in terms of sustainability, scalability, and environmentally friendly energy generation. Achieving optimal efficiency and reliability is paramount, as it reduces overall system cost and enhances reliability. SyRM design methodology in this study integrates both analytical and finite element (FE) procedures. Unlike other motor types, the rotor structure of the SyRM does not include any cages, magnets, or windings, resulting in a robust, reliable, and cost-effective manufacturing process. In SyRM, the rotor is constructed solely with barriers, which significantly impact torque shaping, torque ripple content, and power factor. This paper primarily examines the influence of various air-barrier shapes on different motor performance parameters, such as average torque, torque ripple, saturation, cross-section, and saliency ratio. The selected motor configuration for this investigation is a 4-pole, 100 Hz synchronous reluctance motor with 24 stator slots. The accuracy of the FE analysis findings is validated through a prototype of designed SyRM, followed by comprehensive performance evaluations conducted in a controlled laboratory environment. Additionally, this paper addresses an improved control strategy for a SyRM-based photovoltaic (PV) water pumping system. It eliminates the need for a speed controller in the position sensor-less field-oriented control (FOC) of SyRM. The solar water pump drive involves two stages of power conversion.

FMD-UNet: fine-grained feature squeeze and multiscale cascade dilated semantic aggregation dual-decoder UNet for COVID-19 lung infection segmentation from CT images

With the advancement of computer-aided diagnosis, the automatic segmentation of COVID-19 infection areas holds great promise for assisting in the timely diagnosis and recovery of patients in clinical practice. Currently, methods relying on U-Net face challenges in effectively utilizing fine-grained semantic information from input images and bridging the semantic gap between the encoder and decoder. To address these issues, we propose an FMD-UNet dual-decoder U-Net network for COVID-19 infection segmentation, which integrates a Fine-grained Feature Squeezing (FGFS) decoder and a Multi-scale Dilated Semantic Aggregation (MDSA) decoder. The FGFS decoder produces fine feature maps through the compression of fine-grained features and a weighted attention mechanism, guiding the model to capture detailed semantic information. The MDSA decoder consists of three hierarchical MDSA modules designed for different stages of input information. These modules progressively fuse different scales of dilated convolutions to process the shallow and deep semantic information from the encoder, and use the extracted feature information to bridge the semantic gaps at various stages, this design captures extensive contextual information while decoding and predicting segmentation, thereby suppressing the increase in model parameters. To better validate the robustness and generalizability of the FMD-UNet, we conducted comprehensive performance evaluations and ablation experiments on three public datasets, and achieved leading Dice Similarity Coefficient (DSC) scores of 84.76, 78.56 and 61.99% in COVID-19 infection segmentation, respectively. Compared to previous methods, the FMD-UNet has fewer parameters and shorter inference time, which also demonstrates its competitiveness.

A cationic three-dimensional covalent organic framework membrane for nanofiltration of molecules and rare Earth ions

Permanently microporous materials have evolved as focal point of research for tackling issues in separation science and membrane technology. Covalent organic frameworks (COFs) stand out for their distinctive synergy of crystalline nature, uniform channels, and structural diversities. Three-dimensional (3D) COFs, distinguished by angstrom-sized and interconnected channels, hold special promise for separating small targets; however, this potential remains underexplored. Here, we report feasible growth of cationic 3D COF membranes on a flexible polymer substrate for versatile nanofiltration toward both molecules and ions. Through comprehensive performance evaluations, we reveal that the resultant membrane exhibits durable and prominent molecular selectivity to separate fine species with molecular weights above 300 g mol−1 at fast methanol permeation. Lanthanide ions of industrial value also can be harvested by the membrane with rejection rates of up to 91.4%. Together with its nonselectivity to competing ions, our membrane implements efficient extraction of rare earth elements from ion mixtures. These findings illuminate the potential of 3D COFs for liquid separation and offer a solution to building versatile membranes.

An advanced cryptographic scheme for DICOM medical image encryption using a novel spatiotemporal chaotic lattice

Ensuring the privacy and security of medical imaging data is crucial. Most existing methods focus on encrypting images in common formats, neglecting the unique challenges posed by medical formats. In this paper an advanced encryption algorithm based on a multi-dimensional and multi-parametric spatiotemporal coupled chaotic lattice (Double-MsCcL) system is proposed. The Double-MsCcL system enhances the complexity of chaotic sequences, and provides a robust foundation for medical image encryption. The encryption method proposed combines double-layer random DNA diffusion and fractal random permutation. Medical information is embedded in the image pixels, serving as the cryptosystem key. The designed double-layer DNA random diffusion algorithm alters pixel values, while the fractal random permutation algorithm disrupts pixel positions. This proposed approach effectively hides sensitive information, strengthens resistance to plaintext attacks, and address the often-overlooked Uint16 format of DICOM images. Comprehensive performance evaluations have shown that the proposed encryption scheme offers significant advantages in protecting sensitive medical imaging data. Our algorithm exhibits better performance in resisting plaintext analysis, statistical, and differential attacks, demonstrating significant security compared to existing state-of-the-art methods, which can be widely applied in the field of modern medical data protection.

Game-Theoretic Adversarial Interaction-Based Critical Scenario Generation for Autonomous Vehicles

Ensuring safety and efficiency in the rapidly advancing autonomous vehicle (AV) industry presents a significant engineering challenge. Comprehensive performance evaluations and critical scenario testing are essential for identifying situations that AVs cannot handle. Thus, generating critical scenarios is a key problem in AV testing system design. This paper proposes a game-theoretic adversarial interaction method to efficiently generate critical scenarios that challenge AV systems. Initial motion prediction for adversarial and surrounding vehicles is based on kinematic models and road constraints, establishing interaction action spaces to determine possible driving domains. A novel evaluation approach combines reachability sets with adversarial intensity to assess collision risks and adversarial strength for any state, used to solve behavior values for each interaction action state. Further, equilibrium action strategies for the vehicles are derived using Stackelberg game theory, yielding optimal actions considering adversarial interactions in the current traffic environment. Simulation results show that the adversarial scenarios generated by this method significantly increase incident rates by 158% to 1313% compared to natural driving scenarios, while ride comfort and driving efficiency decrease, and risk significantly increases. These findings provide critical insights for model improvement and demonstrate the proposed method’s suitability for assessing AV performance in dynamic traffic environments.

Sustainable polyurethane coatings derived from alkyds of Camelina oil monoglycerides

AbstractThis study presents the synthesis of sustainable urethane coatings derived from alkyds of Camelina oil (CO) monoglycerides, offering a sustainable alternative to petrochemical resources. Utilizing immobilized lipase for a low‐temperature glycerolysis reaction, high‐yield monoglycerides were obtained from CO. These were then reacted with dibasic acids (phthalic, succinic, and maleic anhydride) to produce alkyd diols, confirmed by both nuclear magnetic resonance (NMR) and Fourier transform infrared (FTIR) spectroscopy. The hydroxyl functionality of the alkyd diols showed a significant enhancement (up to 2200%) over crude CO produced Camelina‐based alkyd diols were incorporated into polyurethane formulations and applied to metal substrates. Comprehensive performance evaluations revealed their superior mechanical, thermal, and chemical properties in comparison with previously reported plant‐based alkyd‐urethane coatings, especially for the phthalic anhydride‐derived alkyd diol. The present research underscores the potential of Camelina‐derived alkyds in creating high‐performance, plant‐based coatings, aligning with recent sustainability trends in material science.

Machine learning and interactive GUI for concrete compressive strength prediction

Concrete compressive strength (CS) is a crucial performance parameter in concrete structure design. Reliable strength prediction reduces costs and time in design and prevents material waste from extensive mixture trials. Machine learning techniques solve structural engineering challenges such as CS prediction. This study used Machine Learning (ML) models to enhance the prediction of CS, analyzing 1030 experimental CS data ranging from 2.33 to 82.60 MPa from previous research databases. The ML models included both non-ensemble and ensemble types. The non-ensemble models were regression-based, evolutionary, neural network, and fuzzy-inference-system. Meanwhile, the ensemble models consisted of adaptive boosting, random forest, and gradient boosting. There were eight input parameters: cement, blast-furnace-slag, aggregates (coarse and fine), fly ash, water, superplasticizer, and curing days, with the CS as the output. Comprehensive performance evaluations include visual and quantitative methods and k-fold cross-validation to assess the study’s reliability and accuracy. A sensitivity analysis using Shapley-Additive-exPlanations (SHAP) was conducted to understand better how each input variable affects CS. The findings showed that the Categorical-Gradient-Boosting (CatBoost) model was the most accurate prediction during the testing stage. It had the highest determination-coefficient (R2) of 0.966 and the lowest Root-Mean-Square-Error (RMSE) of 3.06 MPa. The SHAP analysis showed that the age of the concrete was the most critical factor in the predictive accuracy. Finally, a Graphical User Interface (GUI) was offered for designers to predict concrete CS quickly and economically instead of costly computational or experimental tests.

The Influence of Lecturer Performance Evaluation on Improving the Quality of Learning at STKIP Harapan Bima

This research examines the influence of lecturer performance evaluation on the quality of learning at STKIP Harapan Bima using quantitative and qualitative approaches. Data was collected through questionnaires from 200 students and in-depth interviews with lecturers and students. The research results show that 75% of students are satisfied with lecturers' performance, with an average satisfaction score of 4.2 out of 5. The quality of learning has increased, shown by 60% of students getting an A or B grade and 70% of students feeling an increase in the quality of learning after routine lecturer performance evaluations are carried out. Statistical analysis with Pearson correlation shows a significant positive correlation between lecturer performance evaluation and learning quality (r = 0.65, p < 0.01), with lecturer performance evaluation explaining 42% of the variability in learning quality (R² = 0.42). The most influential factor is the availability of lecturers for consultation. Perceptions of lecturers and students show that objective and constructive performance evaluations can increase lecturer motivation and, ultimately, the quality of learning. Research recommendations include implementing comprehensive and routine performance evaluations, using evaluation results for lecturer professional development, and further studies on specific factors and more extensive evaluation methods.

Analytical model and comprehensive index construction of indoor air purification effect based on dynamic characteristics and energy efficiency

Meeting environmental regulation requirements while improving energy usage efficiency are crucial endeavors to achieve decarbonization and indoor environmental regulation. In this study, experimental testing, data analysis, and modeling are performed for the dynamic purification process of indoor PM2.5 (fine particulate matter) in the context of regulating the indoor environment of buildings. The results show that indoor PM2.5 levels are dynamically matched to the outdoor environment state and the requirements of environmental control. An analytical model of the effect of PM2.5 purification is constructed, which can accurately reflect the dynamic changes in the PM2.5 mass concentration during the indoor air purification process considering the outdoor PM2.5 concentration and the purification efficiency of the purification filters and purification systems, thus supporting the prediction of purification outcomes and accurately constraining the actual indoor air quality purification process. Meanwhile, an indoor air quality control index (IAQCI) is established based on the purification effect and purification energy efficiency under various combinations of air filters and purification systems. This approach is used to quantitatively assess the dual control of energy efficiency and environmental regulation, as well as the purification effect and efficiency of indoor purification schemes based on outdoor dynamic PM2.5 conditions.This study provides a set of innovative and feasible research methods for realizing comprehensive indoor environmental performance evaluations of buildings.

A Stealthy Communication Model with Blockchain Smart Contract for Bidding Systems

With the widespread adoption of blockchain technology, its public ledger characteristic enhances transaction transparency but also amplifies the risk of privacy breaches. Attackers can infer users’ real identities and behaviors by analyzing public transaction patterns and address relationships, posing a severe threat to users’ privacy and security, and thus hindering further advancements in blockchain applications. To address this challenge, covert communication has emerged as an effective strategy for safeguarding the privacy of blockchain users and preventing information leakage. But existing blockchain-based covert communication schemes rely solely on the immutability of blockchain itself for robustness and suffer from low transmission efficiency. To tackle these issues, this paper proposes a stealthy communication model with blockchain smart contract for bidding systems. The model initiates by preprocessing sensitive information using a secret-sharing algorithm-the Shamir (t, n) threshold scheme-and subsequently embeds this information into bidding amounts, facilitating the covert transfer of sensitive data. We implemented and deployed this model on the Ethereum platform and conducted comprehensive performance evaluations. To assess the stealthiness of our approach, we employed a suite of statistical tests including the CDF, the Kolmogorov–Smirnov test, Welch’s t-test and K–L divergence. These analyses confirmed that amounts carrying concealed information were statistically indistinguishable from regular transactions, thus validating the effectiveness of our solution in maintaining the anonymity and confidentiality of information transmission within the blockchain ecosystem.

Performance-Enhanced Piezoelectric Micromachined Ultrasonic Transducers by PDMS Acoustic Lens Design.

This paper delves into enhancing the performance of ScAlN-based Piezoelectric Micromachined Ultrasonic Transducers (PMUTs) through the implementation of Polydimethylsiloxane (PDMS) acoustic lenses. The PMUT, encapsulated in PDMS, underwent thorough characterization through the utilization of an industry-standard hydrophone calibration instrument. The experimental results showed that the ScAlN-based PMUT with the PDMS lenses achieved an impressive sensitivity of -160 dB (re: 1 V/μPa), an improvement of more than 8 dB compared to the PMUT with an equivalent PDMS film. There was a noticeable improvement in the -3 dB main lobe width within the frequency response when comparing the PMUT with PDMS encapsulation, both with and without lenses. The successful fabrication of high-performance PDMS lenses proved instrumental in significantly boosting the sensitivity of the PMUT. Comprehensive performance evaluations underscored that the designed PMUT in this investigation surpassed its counterparts reported in the literature and commercially available transducers. This encouraging outcome emphasizes its substantial potential for commercial applications.