Experimental Evaluation Research Articles

Pneumatic Exoskeleton Joint With a Self-Supporting Air Tank and Stiffness Modulation: Design, Modeling, and Experimental Evaluation

Pneumatic Exoskeleton Joint With a Self-Supporting Air Tank and Stiffness Modulation: Design, Modeling, and Experimental Evaluation

Envelope spectrum neural network with adaptive domain weight harmonization for intelligent bearing fault diagnosis under cross-machine scenarios

Accurate bearing fault diagnosis technology is highly important for ensuring the safe operation of mechanical equipment. Fault diagnosis methods can be roughly divided into signal processing-based methods (SPM) and data-driven methods (DDMs), which rely on physical knowledge and data knowledge, respectively. However, SPM cannot adapt to large data samples and dynamic parameter variations. DDMs did not consider physical representation consistency. To address the above issues, an envelope spectrum neural network (ESNN) is proposed for cross-machine bearing fault diagnosis. First, a deep transfer convolution network (DTCN) is constructed as the basic diagnostic framework. Second, a knowledge-to-model conversion strategy (KMC) is built to create ESNN, which utilizes equivalent convolution functions to construct the first two layers of DTCN, guiding the model to learn physical knowledge. Subsequently, an adaptive domain weight harmonization (ADWH) mechanism is proposed that can dynamically combine marginal distributions and joint distributions and automatically learn hidden features contained in physical and data knowledge, thus alleviating domain shift issues. Experimental evaluations are conducted using fault datasets from three different machines. The results show that, compared to models without knowledge guidance, ESNN achieves a 6.4% improvement in diagnostic accuracy. Compared to many advanced models, ESNN can achieve a maximum diagnostic accuracy improvement of 35.94%. The code of the ESNN can be found at https://github.com/John-520/ESNN.

Pair-EGRET: Enhancing the prediction of protein-protein interaction sites through graph attention networks and protein language models.

Proteins are responsible for most biological functions, many of which require the interaction of more than one protein molecule. However, accurately predicting protein-protein interaction (PPI) sites (the interfacial residues of a protein that interact with other protein molecules) remains a challenge. The growing demand and cost associated with the reliable identification of PPI sites using conventional experimental methods call for computational tools for automated prediction and understanding of PPIs. We present Pair-EGRET, an edge-aggregated graph attention network that leverages the features extracted from pre-trained transformer-like models to accurately predict PPI sites. Pair-EGRET works on a k-nearest neighbor graph, representing the three-dimensional structure of a protein, and utilizes the cross-attention mechanism for accurate identification of interfacial residues of a pair of proteins. Through an extensive evaluation study using a diverse array of experimental data, evaluation metrics, and case studies on representative protein sequences, we demonstrate that Pair-EGRET can achieve remarkable performance in predicting PPI sites. Moreover, Pair-EGRET can provide interpretable insights from the learned cross-attention matrix. Pair-EGRET is freely available in open source form at the GitHub Repository https://github.com/1705004/Pair-EGRET. Supplementary data are available at Bioinformatics online.

Experimental Performance Evaluation of a Lightweight Additively Manufactured Hydrodynamic Thrust Bearing

In this paper, a lightweight additively manufactured (AM) fixed geometry hydrodynamic thrust bearing fabricated via laser powder bed fusion (LPBF) is experimentally compared to a traditionally manufactured cast aluminum alloy thrust bearing of similar design. The purpose of this study is to evaluate how weight-saving design features in the AM bearing affect active critical hydrodynamic performance parameters to better understand in-service viability. Under various static operating conditions, performance parameters such as hydrodynamic pressure distribution, minimum oil film thickness (MOFT), bearing temperature and increase in oil temperature are measured. Compared to the traditionally manufactured bearing, the AM bearing showed an average increase in minimum oil film thickness of 53%, an average increase in trailing edge hydrodynamic pressure of 116%, while exhibiting an average decrease in bearing temperature of 1%. Experimental results are compared to numerical simulation showing reasonably good agreement.

IOT NETWORK INTRUSION DETECTION USING MACHINE LEARNING ON UNSW-NB15 DATASET

This research presents a comprehensive investigation into the application of machine learning techniques for addressing the pervasive security challenges within Internet of Things (IoT) networks. With the exponential growth of interconnected devices, ensuring the integrity and confidentiality of data transmissions has become increasingly critical. In this study, we deploy and evaluate seven distinct machine learning methods tailored to the IoT network intrusion detection problem. Leveraging the rich and diverse UNSW-NB15 dataset, encompassing real-world network traffic scenarios, our analysis encompasses a thorough examination of both traditional and state-of-the-art algorithms. Through rigorous experimentation and performance evaluation, we assess the efficacy of these methods in accurately detecting and classifying various forms of network intrusions. Our findings provide valuable insights into the strengths and limitations of different machine learning approaches for enhancing the security posture of IoT environments, thereby facilitating informed decision-making for network administrators and cybersecurity practitioners.

Enhanced decomposition of H2S to H2 via iron sulfide nanoparticles: A comprehensive experimental and theoretical evaluation

Hydrogen sulfide (H2S), a common pollutant in both fossil and bio-based fuels, can be transformed into valuable hydrogen (H2) through a two-step thermochemical process known as sulfur looping. This scheme, derived from the chemical looping approach, employs a metal-sulfide-based sulfur carrier as a solid intermediate. Iron sulfide, a benign and abundant material, is a promising candidate as the sulfur carrier; however, it faces challenges related to its poor kinetic activity. In this study, we demonstrate the exceptional performance of nano-sized sulfur carriers for the sulfur looping scheme through comprehensive experimental and theoretical analyses. We synthesized iron sulfide nanoparticles that exhibit a remarkable ∼69% enhancement in reactivity over the bulk-sized sulfur carrier. This enhancement is attributed to the high surface area and the nanoscale effects that enhance intrinsic activity. Furthermore, for the first time, we evaluated the effect of co-feeding carbon dioxide (CO2), a prevalent component in industrial acid gas streams alongside H2S. Our combined thermodynamic, atomistic density functional theory (DFT), and experimental studies indicate that the presence of CO2 enhances the conversion of H2S. Additionally, to gauge the sulfur looping process’s superiority at a larger scale, we conducted comprehensive thermodynamic analyses under industrial acid gas conditions. These analyses reveal an improvement of ∼22 percentage points in energy efficiency and ∼8 percentage points in exergy efficiency over the state-of-the-art Claus process. This study, integrating experiments, atomistic DFT studies, and process simulations, provides valuable guidance in the design of high-performance sulfur carriers for efficient H2S splitting to H2.

Scheduling of Earth observing satellites using distributed constraint optimization

Earth observation satellites (EOS) are satellites equipped with optical sensors that orbit the Earth to take photographs of particular areas at the request of users. With the development of space technology, the number of satellites has increased continuously. Yet still, the number of satellites cannot meet the explosive growth of applications. Thus, scheduling solutions are required to satisfy requests and obtain high observation efficiency. While the literature on multi-satellite scheduling is rich, most solutions are centralized algorithms. However, due to their cost, EOS systems are often co-funded by several agents (e.g., countries, companies, or research institutes). Central solutions require that these agents share their requests for observations with others. To date, there has yet to be a solution for EOS scheduling that protects the private information of the interested parties. In this study, we model the EOS scheduling problem as a distributed constraint optimization problem (DCOP). This modeling enables the generation of timetables for the satellites in a distributed manner without a priori sharing users’ private information with some central authority. For solving the resulting DCOP, we use and compare the results of two different local search algorithms—Distributed Stochastic Algorithm and Maximum Gain Message—which are known to produce efficient solutions in a timely manner. The modeling and solving of the resulting DCOP constitute our new solution method, which we term Distributed Satellite Timetable Solver (DSTS). Experimental evaluation reveals that the DSTS method provides solutions of higher quality than a commonly used centralized greedy algorithm and is comparable to an additional centralized algorithm that we propose.

Experimental study on flow and heat transfer characteristics of three types of finned tube bundle heat exchangers applied in aero-engines

This study outlines the design and manufacture of three types of finned tube bundle heat exchangers (HX) for advanced aero-engines followed by a series of experimental evaluations on flow and heat transfer characteristics. Considering the compactness and reliability, the finned tube bundle HX is more suitable for aero-engines when the heat transfer unit is small-diameter serpentine tubes with the enhanced heat transfer area provided by fins. In this paper, the Logarithmic Mean Temperature Difference method (LMTD) was utilized for the design of a small-diameter (OD: 3.6 mm with 0.3 mm thickness) finned tube bundle HX. Mass reduction was achieved by perforating the fins and removing the support devices, respectively. The flow and heat transfer characteristics of HXs and the impact of the mass reduction schemes were evaluated based on a series of comparative experiments. Among them, the connectionless scheme can significantly improve the power-to-mass ratio, providing it certain application value despite causing considerable flow resistance. Subsequently, empirical correlations for the flow and heat transfer outside the tubes suitable for small-diameter finned tube bundle HXs were proposed based on the experimental results, with over 95 % of the data falling within a 10 % error margin. These correlations have substantially modified the previous one for large-diameter straight tubes, providing an important reference for the future design of HXs in aero-engine.

Experimental evaluation of green nanofluids in heat exchanger made oF PDMS

Conventional methods for synthesizing metallic nanoparticles face challenges such as instability and environmental concerns. Therefore, new, simpler, and more eco-friendly methods are being explored. In this context, the study reports a green synthesis process to produce magnetic iron oxide nanoparticles using an aqueous extract of the alga Chlorella vulgaris. This process leverages natural resources to create a sustainable nanofluid known as green nanofluid. To evaluate the characteristics of this nanofluid, experimental measurements of wettability, viscosity, thermal conductivity, and qualitative stability analysis were conducted. An experimental setup consisting of a heat exchanger made of polydimethylsiloxane (PDMS) was used to assess the thermal performance and the results were compared to theoretical equations and numerical simulation. Additionally, thermographic imaging of temperature gradients as the fluids passed over the heated surface of the serpentine channel were made. The main findings confirmed that the nanofluid was more stable than that obtained by traditional methods and had a more uniform temperature distribution over the heat exchanger. The higher concentration exhibited superior thermal performance compared to DI-Water. Moreover, the green nanofluid was used at a weight concentration of 0.1 wt%, provided thermal performance results of nearly 4.5% superior to those estimated by the numerical model and 6.4% higher than those experimentally obtained with the base fluid, respectively. Finally, the results obtained for the nanofluid also showed an average increase of around 5% in the viscosity of the base fluid, with a more significant sedimentation at a concentration of 0.1 wt%.

Marine remote target signal extraction based on 128 line-array single photon LiDAR

LiDAR technology has garnered significant attention in recent years due to its superior directivity, high resolution, and precise 3D information acquisition capabilities, making it indispensable in navigation systems. Among its variants, single-photon LiDAR stands out for maritime applications, owing to its reduced power consumption and extended detection range. However, the high sensitivity of single-photon detectors often results in substantial noise, necessitating effective denoising before data can be utilized for identification, tracking, and other purposes. In this study, we present a novel 128-line, 1550 nm shipborne long-range single-photon LiDAR system, with data collected and analyzed in maritime environments. This system contends with challenges such as a large dynamic range, abundant noise photons, and the complexity of sea surface conditions. To address these issues, we propose an efficient and adaptive denoising algorithm based on the k-th nearest neighbor (KNN) methodology. By examining the distribution characteristics of signal and noise photons, our approach enables target extraction even under conditions of intense noise and sparse signals. Our method exhibits robust adaptability across various detection scenarios. Experimental evaluations demonstrate its efficacy, accurately identifying targets at distances of 3.2 km in clear weather and 1.6 km in foggy conditions.

Instant pose extraction based on mask transformer for occluded person re-identification

Re-Identification (Re-ID) of obscured pedestrians is a daunting task, primarily due to the frequent occlusion caused by various obstacles like buildings, vehicles, and even other pedestrians. To address this challenge, we propose a novel approach named Instant Pose Extraction based on Mask Transformer (MTIPE), tailored specifically for occluded person Re-ID. MTIPE consists of several new modules: a Mask Aware Module (MAM) for alignment between the overall prototype and the occluded image; a Multi-headed Attention Constraint Module (MACM) to enrich the feature representation; a Pose Aggregation Module (PAM) to separate useful human information from the occlusion noise; a Feature Matching Module (FMM) in matching non-occluded parts; introduction of learnable local prototypes in the defined local prototype-based transformer decoder; a Pooling Attention Module (PAM) instead of traditional self-attention module to better extract and propagate local contextual information; and Pose Key-points Loss to better match non-occluded body parts. Through comprehensive experimental evaluations and comparisons, MTIPE demonstrates encouraging performance improvements in both occluded and holistic person Re-ID tasks. Its results surpass or at least match those of current state-of-the-art methods in various aspects, highlighting its potential advantages and promising application prospects.

Photovoltaic to electrolysis off-grid green hydrogen production with DC-DC conversion

Green hydrogen (H2), being the product of water electrolysis powered by renewable energy sources, is expected to be an energetic vector of major importance toward a more sustainable energy mix. In this context, photovoltaic (PV) -based H2 production is a key element, where power electronics technologies are critical to enable its development. In off-grid applications, designing DC-DC power electronics converters with high efficiency and high power density is really important since it can impact significantly the global performance of the H2 production system. In this work, a two-stage DC-DC power conversion system composed by an unregulated DCX converter and a regulated partial power converter is considered to increase the H2 production system efficiency. The DCX converter works in open-loop at resonant frequency with a high DC-DC conversion ratio. A partial power converter (PPC), which regulates only a fraction of the total power between its input and output terminals, represents a improvement in PV-to-H2 direct conversion, particularly since the PV panels do not require regulation from zero to nominal voltage, and in this work, is introduced for regulation of the DCX-based system, by optimizing the PV produced power through a maximum power point tracking (MPPT) algorithm along with the current control of the electrolyzer. A comparison with state-of-the-art converters show an important improvement of the proposed DCX with PPC regulated system. Compared to the solution with classical interleaved-buck pre-regulator, significant improvements in terms of efficiency for the whole range of operation are obtained, up to 2.5% higher with the proposed system. Experimental evaluation of the proposed PPC and DCX two stage converter for PV-powered electrolysis system is provided, validating its feasibility and interest for off-grid green hydrogen production application.

TECHNOLOGY FOR THE PRODUCTION OF COMPOSITE MATERIAL-SULFUR CONCRETE PRODUCTS FROM MODIFIED SULFUR

Due to the increase in the processing of sulfur-containing hydrocarbon raw materials (oil and gas), sulfur is released as one of the large - tonnage waste. Long-term storage of large sulfur reserves has a negative impact on the environment. Composite material of sulfur modification-characterized by environmental efficiency, economic efficiency in construction. This review examines the sources of sulfur origin, properties, technology for making sulfur concrete from it and the use of sulfur-based concrete in the construction industry today. Experimental evaluation of modified sulfur concrete, other methods of preparation of mixtures were identified, and the importance of adaptation to foreign experience in the development of sulfur concrete production was shown. One of the most promising projects is the production of concrete containing sulfur binder in order to reduce the load on the environment. After all, sulfur concrete has such advantages as resistance to acid and radiation, frost resistance and the ability to recycle. The aim of the work was to study a new composition of sulfur concrete based on a bitumen composition. To conduct the study, samples of sulfur concrete with different percentage contents of the constituent components were prepared.

BGFlow: Brightness-guided normalizing flow for low-light image enhancement

Low-light image enhancement poses significant challenges due to its ill-posed nature. Recently, deep learning-based methods have attempted to establish a unified mapping relationship between normal-light images and their low-light versions but frequently struggle to capture the intricate variations in brightness conditions. As a result, these methods often suffer from overexposure, underexposure, amplified noise, and distorted colors. To tackle these issues, we propose a brightness-guided normalizing flow framework, dubbed BGFlow, for low-light image enhancement. Specifically, we recognize that low-frequency sub-bands in the wavelet domain carry significant brightness information. To effectively capture the intricate variations in brightness within an image, we design a transformer-based multi-scale wavelet-domain encoder to extract brightness information from the multi-scale features of the low-frequency sub-bands. The extracted brightness feature maps, at different scales, are then injected into the brightness-guided affine coupling layer to guide the training of the conditional normalizing flow module. Extensive experimental evaluations demonstrate the superiority of BGFlow over existing deep learning-based approaches in both qualitative and quantitative assessments. Moreover, we also showcase the exceptional performance of BGFlow on the underwater image enhancement task.

Application of improved deep learning algorithm in obstacle avoidance of UAV

Abstract To enhance the intelligent obstacle avoidance capabilities of unmanned aerial vehicles (UAVs), we introduce a refined version of the You Only Look Once (YOLO) algorithm, termed Improved YOLO (I-YOLO). This novel algorithm not only maintains the swift detection speed inherent in the original YOLO but also augments its feature enhancement network. Specifically, we propose a three-branch parallel feature pyramid network (TBPFP) to capture richer semantic information pertaining to the context of small obstacles. Furthermore, we incorporate a generative adversarial network (GAN) in a cascaded manner to synthesize more realistic super-resolution images, thereby bolstering detection accuracy. Experimental evaluations demonstrate that, in comparison to the baseline YOLO algorithm, our I-YOLO variant exhibits superior detection precision and feature extraction capabilities in the perception of intricate environmental targets. While there is a modest decrement in detection speed, it remains adequate to fulfill real-time requirements, particularly in the context of video stream processing.

Privacy-preserving and verifiable convolution neural network inference and training in cloud computing

With the rapid development of cloud computing, outsourcing massive data and complex deep learning model to cloud servers (CSs) has become a popular trend, which also brings some security problems. One is that the model stored in the CSs may be corrupted, leading to incorrect inference and training results. The other is that the privacy of outsourced data and model may be compromised. However, existing privacy-preserving and verifiable inference schemes suffer from low detection probability, high communication overhead and substantial computational time. To solve the above problems, we propose a privacy-preserving and verifiable scheme for convolutional neural network inference and training in cloud computing. In our scheme, the model owner generates the authenticators for model parameters before uploading the model to CSs. In the phase of model integrity verification, model owner and user can utilize these authenticators to check model integrity with high detection probability. Furthermore, we design a set of privacy-preserving protocols based on replicated secret sharing for both the inference and training phases, significantly reducing communication overhead and computational time. Through security analysis, we demonstrate that our scheme is secure. Experimental evaluations show that the proposed scheme outperforms existing schemes in privacy-preserving inference and model integrity verification.

Improving quaternion neural networks with quaternionic activation functions

In this paper, we propose novel quaternion activation functions where we modify either the quaternion magnitude or the phase, as an alternative to the commonly used split activation functions. We define criteria that are relevant for quaternion activation functions, and subsequently we propose our novel activation functions based on this analysis. Instead of applying a known activation function like the ReLU or Tanh on the quaternion elements separately, these activation functions consider the quaternion properties and respect the quaternion space H. In particular, all quaternion components are utilized to calculate all output components, carrying out the benefit of the Hamilton product in e.g. the quaternion convolution to the activation functions. The proposed activation functions can be incorporated in arbitrary quaternion valued neural networks trained with gradient descent techniques. We further discuss the derivatives of the proposed activation functions where we observe beneficial properties for the activation functions affecting the phase. Specifically, they prove to be sensitive on basically the whole input range, thus improved gradient flow can be expected. We provide an elaborate experimental evaluation of our proposed quaternion activation functions including comparison with the split ReLU and split Tanh on two image classification tasks using the CIFAR-10 and SVHN dataset. There, especially the quaternion activation functions affecting the phase consistently prove to provide better performance.

Summation-based Private Segmented Membership Test from Threshold-Fully Homomorphic Encryption

In many real-world scenarios, there are cases where a client wishes to check if a data element they hold is included in a set segmented across a large number of data holders. To protect user privacy, the client's query and the data holders' sets should remain encrypted throughout the whole process. Prior work on Private Set Intersection (PSI), Multi-Party PSI (MPSI), Private Membership Test (PMT), and Oblivious RAM (ORAM) falls short in this scenario in many ways. They either require data holders to possess the sets in plaintext, incur prohibitively high latency for aggregating results from a large number of data holders, leak the information about the party holding the intersection element, or induce a high false positive. This paper introduces the primitive of a Private Segmented Membership Test (PSMT). We give a basic construction of a protocol to solve PSMT using a threshold variant of approximate-arithmetic homomorphic encryption and show how to overcome existing challenges to construct a PSMT protocol without leaking information about the party holding the intersection element or false positives for a large number of data holders ensuring IND-CPA^D security. Our novel approach is superior to existing state-of-the-art approaches in scalability with regard to the number of supported data holders. This is enabled by a novel summation-based homomorphic membership check rather than a product-based one, as well as various novel ideas addressing technical challenges. Our PSMT protocol supports many more parties (up to 4096 in experiments) compared to prior related work that supports only around 100 parties efficiently. Our experimental evaluation shows that our method's aggregation of results from data holders can run in 92.5s for 1024 data holders and a set size of 2^25, and our method's overhead increases very slowly with the increasing number of senders. We also compare our PSMT protocol to other state-of-the-art PSI and MPSI protocols and discuss our improvements in usability with a better privacy model and a larger number of parties.

Are continuous stop-and-go mixnets provably secure?

This work formally analyzes the anonymity guarantees of continuous stop-and-go mixnets and attempts to answer the titular question. Existing mixnet based anonymous communication protocols that aim to provide provable anonymity guarantees rely on round-based communication models, which requires synchronization among all the nodes and clients that is difficult to achieve in practice. Continuous stop-and-go mixnets (e.g., Loopix and Nym) provide a nice alternative by adding a random delay for each message on every hop independent of all other hops and all other messages. The core anonymization technique of continuous mixnets combined with the fact that the messages are sent by the clients to the mixnet at different times makes it a difficult problem to formally prove security for such mixnet protocols; existing end-to-end analyses for such designs provide only experimental evaluations for anonymity and were lacking a comprehensive formal treatment. We are the first to close that gap and provide a formal analysis. We provide two indistinguishability based definitions (of sender anonymity), namely pairwise unlinkability and user unlinkability, tuned specifically for continuous stop-and-go mixnets. We derive the adversarial advantage as a function of the protocol parameters for the two definitions. We show that there is a fundamental lower bound on the adversarial advantage $\delta$ for pairwise unlinkability; however, strong user unlinkability (negligible adversarial advantage) can be achieved if the users message rate ($\lambda_u$) is proportional to message processing rate ($\lambda$) on the nodes.

Design, development and experimental evaluation of a concentrator agrivoltaic system with integrated spectrally splitting Fresnel lens

The main aim of this research is to develop and evaluate a cost-effective, innovative agrivoltaic system that optimizes land use by simultaneously producing agricultural products and generating electricity on the same land. In this regard, a highly transparent concentrator agrivoltaic system that utilizes the spectral splitting property is developed. The system consists of a Fresnel lens coated with a dichroic thin film and a receiver made of silicon solar cells. In this system, the sunlight is first focused by a Fresnel lens and then split into two spectral ranges by the dichroic film: (i) photosynthetically active radiation (PAR), which passes through the film and can be utilized by the plants, and (ii) the remaining spectrum, which is reflected to the receiver to generate electricity. Cherry tomatoes and mint were planted under the system. The results showed that the receiver reduces the intensity of the focused radiation by almost 3.28 times. The optical efficiency of the receiver is 83.1% and the electricity generated is up to 18.1 watts. The photosynthetic photon flux density (PPFD) under the agrivoltaic system ranges from 229 to 778 μmol/m2. s, while the daily light integral (DLI) varies between 13.5 and 27 mol/m2.d. Cherry tomatoes grown in the shade of the agrivoltaic system are larger, heavier and have a deeper red hue, while the mint plants have larger, greener, and longer leaves. In addition, the agrivoltaic system provides cooler soil temperatures, ranging from 3.66°C to 9.53°C, and retains 5.7% to 8.4% more moisture, resulting in less water consumption. The total initial cost of the system was USD 587 and included the agricultural and photovoltaic components and maintenance. Over a period of ten years, the cumulative costs are likely to amount to USD 1,165. However, the system has strong economic potential, starting at an annual income of USD 27 and expected to exceed USD 15,000. This analysis indicates a favorable return on investment that should pay for itself within six years.