Key Technologies Research Articles

An Efficient Homomorphic Argmax Approximation for Privacy-Preserving Neural Networks

Privacy-preserving neural networks offer a promising solution to train and predict without user privacy leakage, and fully homomorphic encryption (FHE) stands out as one of the key technologies, as it enables homomorphic operations over encrypted data. However, only addition and multiplication homomorphisms are supported by FHE, and thus, it faces huge challenges when implementing non-linear functions with ciphertext inputs. Among the non-linear functions in neural networks, one may refer to the activation function, the argmax function, and maximum pooling. Inspired by using a composition of low-degree minimax polynomials to approximate sign and argmax functions, this study focused on optimizing the homomorphic argmax approximation, where argmax is a mathematical operation that identifies the index of the maximum value within a given set of values. For the method that uses compositions of low-degree minimax polynomials to approximate argmax, in order to further reduce approximation errors and improve computational efficiency, we propose an improved homomorphic argmax approximation algorithm that includes rotation accumulation, tree-structured comparison, normalization, and finalization phases. And then, the proposed homomorphic argmax algorithm was integrated into a neural network structure. Comparative experiments indicate that the network with our proposed argmax algorithm achieved a slight increase in accuracy while significantly reducing the inference latency by 58%, as the homomorphic sign and rotation operations were rapidly reduced.

Research on asymmetric spatial heterodyne spectroscopy for velocimetry navigation

The further development of deep space exploration contributes to the exploration of the universe and the origin and evolution of life on Earth, and is a prerequisite and foundation for the development and utilization of space resources. Autonomous navigation of deep space probes, one of the key technologies for deep space exploration, can significantly reduce ground support costs and improve the autonomous operation, management, and on-orbit survivability of deep space probes. Among them, autonomous astronomical navigation methods based on velocity measurements directly measure velocity information, effectively avoiding the impact of using calculus to solve velocity on response time and navigation accuracy in navigation methods based on angle and distance measurements. The passive radial velocity measurement technique of asymmetric spatial heterodyne spectroscopy has the advantages of compact structure, large luminous flux, and multiple spectra detected simultaneously. Taking the Sun as the navigation target source, we carried out the selection of observational spectral lines and the parameter design of the velocimetry navigation system, designed the calculation of phases for the absorption characteristic line under the complex polychromatic strong background, carried out the simulation analysis of velocimetry under the typical relative velocimetry.

Design of High-Precision Driving Control System for Charge Management

Due to the interaction of accumulated charges on the surface of a test mass with the surrounding electric and magnetic fields, the performance of inertial sensors is affected, necessitating charge management for the test mass. Discharge technology based on Ultraviolet LEDs is internationally recognized as the optimal solution for charge management. Precision driving of Ultraviolet LEDs is considered a key technology in charge management. This paper presents the driving control system used for Ultraviolet LEDs, achieving precision pulse-width-modulation-type current output with controllable pulse width and amplitude. The system generates the pulse-width-controllable pulse voltage signal via analog pulse-width modulation, and subsequently regulates the amplitude of the PWM signal through range switching. To convert the voltage into the pulse-width-modulation-type driving current, the improved Howland current source is employed. The test results demonstrate that the driving control system can output controllable current in the range of 0.01 mA to 10 mA, with a minimum step of 0.01 mA. The accuracy of the current reaches 1%, the stability within 1 h is better than 1%, and the load regulation is better than 2%. The driving control system provides an important reference for the integration of charge management system and the precision drive control method for LEDs.

High heat flux components with beryllium armour: From the small-scale mock-ups to the full-scale prototype of the ITER first wall panel

The Russian Federation shall supply 179 enhanced heat flux First Wall Panels (FWP) to the ITER construction site. These panels have about 30 types and consist of a steel supporting structure (FW Beam) with multilayer plasma-facing units (PFU) attached onto it. To start the production of the panels, the manufacturing readiness must be confirmed by the ITER Organization (IO). The JSC “NIIEFA” responsible for manufacturing of a part of the components, final assembly and testing of the panels has come a long way from the experimental work on small-scale mock-ups, through the development of the design and key manufacturing technologies to the production and testing of the full-scale prototype (FSP) which is the final step before the confirmation for the manufacture. The manufactured FSP has successfully passed most of the acceptance tests including hydraulic pressure and leak tightness tests. The high heat flux tests have been successfully carried out on the PFUs with beryllium armour. In parallel to the tests of the beryllium prototype, the tungsten armour has been analyzed and tested which is due to the IO's intention to change the armour material.

Uptime Monitoring and Reporting Strategies: A Case Study

Abstract: In today's digital landscape, the uninterrupted availability of services is critical for businesses to uphold customer satisfaction and maintain their competitive edge. This paper presents a comprehensive methodology for constructing an Uptime Monitoring System tailored specifically for a leading enterprise. By harnessing technologies such as Angular.js, Node.js, Express.js, and MSSQL, the system ensures real-time monitoring of service availability, drawing on data from Zabbix production servers. This proactive approach not only minimizes downtime but also optimizes operational efficiency, enabling businesses to make informed decisions swiftly, thereby enhancing overall reliability and service excellence. Through the integration of cuttingedge technologies and proactive monitoring strategies, this paper offers a transformative solution for businesses seeking to elevate their service reliability. This abstract serves as a concise summary of the paper's content, highlighting the key technologies employed, methodological approaches adopted, and the resultant benefits achieved in terms of reliability and operational efficiency.

Incremental high average-utility itemset mining: survey and challenges

The High Average Utility Itemset Mining (HAUIM) technique, a variation of High Utility Itemset Mining (HUIM), uses the average utility of the itemsets. Historically, most HAUIM algorithms were designed for static databases. However, practical applications like market basket analysis and business decision-making necessitate regular updates of the database with new transactions. As a result, researchers have developed incremental HAUIM (iHAUIM) algorithms to identify HAUIs in a dynamically updated database. Contrary to conventional methods that begin from scratch, the iHAUIM algorithm facilitates incremental changes and outputs, thereby reducing the cost of discovery. This paper provides a comprehensive review of the state-of-the-art iHAUIM algorithms, analyzing their unique characteristics and advantages. First, we explain the concept of iHAUIM, providing formulas and real-world examples for a more in-depth understanding. Subsequently, we categorize and discuss the key technologies used by varying types of iHAUIM algorithms, encompassing Apriori-based, Tree-based, and Utility-list-based techniques. Moreover, we conduct a critical analysis of each mining method's advantages and disadvantages. In conclusion, we explore potential future directions, research opportunities, and various extensions of the iHAUIM algorithm.

Advancements in Intelligent Video Surveillance for Public Safety: A Comprehensive Review

Abstract: Intelligent video surveillance systems have emerged as invaluable tools for ensuring public safety in a variety of settings, from essential infrastructure to urban environments. These systems, which are driven by state-of-the-art technology like computer vision, machine learning, and artificial intelligence, provide unmatched real-time threat detection, analysis, and response capabilities. This study provides an in-depth analysis of the most recent developments in intelligent video surveillance for public safety, covering key technology, useful uses, enduring difficulties, and potential directions. This paper aims to provide a thorough knowledge of the significant implications and emerging opportunities of intelligent video surveillance in protecting public places from potential dangers through an examination of recent research insights and industry advancements. This article seeks to offer a guide for researchers, practitioners, policymakers, and stakeholders navigating the ever-changing field of intelligent video surveillance for public safety by exploring the evolving trends, emerging technologies, and practical applications.

Research on Key Technologies for Text Similarity Calculation Based on Small Datasets

Research on Key Technologies for Text Similarity Calculation Based on Small Datasets

Demand and key technology for a LEO constellation as augmentation of satellite navigation systems

A Low Earth Orbit (LEO) constellation augmenting satellite navigation is important in the future development of Global Navigation Satellite System (GNSS). GNSS augmented by LEO constellations can improve not only the accuracy of Positioning, Navigation, and Timing (PNT), but also the consistency and reliability of secure PNT system. This paper mainly analyzes the diverse demands of different PNT users for LEO augmented GNSS, including the precision demand in real-time, the availability demand in special areas, the navigation signal enhancement demand in complex electromagnetic environments, and the integrity demand with high security. Correspondingly, the possible contributions of LEO constellations to PNT performance are analyzed from multiple aspects. A particular attention is paid to the special PNT user requirements that cannot be fulfilled with existing GNSS, such as the PNT service demand in the polar regions and the onboard GNSS orbit determination demand of some LEO satellites. The key technologies to be considered in the constellation design, function realization, and payload development of the LEO-augmented navigation system are summarized.

Temperature scaling unmixing framework based on convolutional autoencoder

Hyperspectral unmixing is a key technology in the development of remote sensing applications. However, since both endmembers and abundances are unknown, unmixing is a non-convex problem with a large solution space. To solve this, existing methods usually impose the same strength of sparsity constraint. However, this often does not hold in practice. Because the abundances of purer regions are generally sparse, while the abundances distribution of more mixed regions should be smoother. Temperature scaling is a technique of introducing a temperature parameter T into softmax activation function to adjust the sparsity of the output. Inspired by this, we propose a temperature scaling unmixing (TSU) framework based on convolutional autoencoder (CAE). In this framework, sparse constraints of different intensities are applied to diverse regions by considering spatial similarity of ground objects distribution while preserving the ability of CAE to extract spatial features. What is more, equal-frequency binning is adopted to guide the division of regions by similarity matrix to realize the automatic temperature parameter setting. In addition, a CAE network is designed under the TSU framework in this paper, called TSUCAE. The TSUCAE method exhibits superior accuracy compared to state-of-the-art approaches, as demonstrated through extensive comparative experiments. Furthermore, the TSU framework can be transferred to other CAE-based unmixing methods directly while keeping the network structure of these methods unchanged. Sufficient ablation experiments also prove that the transfer of framework can improve the performance of unmixing. The code is publicly available at https://github.com/UPCGIT/TSUCAE.

CSL-SFNet for Cooperative Spectrum Sensing in Cognitive Satellite Network with GEO and LEO Satellites

In a cognitive satellite network (CSN) with GEO and LEO satellites, there is a large propagation losses between the sensing satellite and the ground station. The results of spectrum sensing from a single satellite may be inaccurate, which will create serious interference in the primary satellite system. Cooperative spectrum sensing (CSS) has become the key technology for solving the above problems in recent years. However, most of the current CSS techniques are model-driven. They are difficult to model and implement in CSNs since their detection performance is strongly dependent on an assumed statistical model. Thus, we propose a novel CSS scheme, which uses convolutional neural networks (CNNs), self-attention (SA) modules, long short-term memory networks (LSTMs), and soft fusion networks, called CSL-SFNet. This scheme combines the advantages of CNNs, SA modules, and LSTMs to extract the features of the input signals from the spatial and temporal domains. Additionally, the CSL-SFNet makes use of a novel soft fusion technique that improves detection performance while also considerably reducing communication overhead. The simulation results demonstrate that the proposed algorithm can achieve a detection probability of 90% when the signal-to-noise ratio is −20 dB; it has a shorter running time and always outperforms the other CSS algorithms.

Design and Experiment of an Autonomous Navigation System for a Cattle Barn Feed-Pushing Robot Based on UWB Positioning

The autonomous navigation system of feed-pushing robots is one of the key technologies for the intelligent breeding of dairy cows, and its accuracy has a significant influence on the quality of feed-pushing operations. Currently, the navigation methods of feed-pushing robots in the complex environment of cattle barns mainly include visual, LiDAR, and geomagnetic navigation, but there are still problems relating to low navigation accuracy. An autonomous navigation system based on ultra-wideband (UWB) positioning utilizing the dynamic forward-looking distance pure pursuit algorithm is proposed in this paper. First, six anchor nodes were arranged in the corners and central feeding aisle of a 30 × 86 m rectangular standard barn to form a rectangular positioning area. Then, utilizing the 9ITL-650 feed-pushing robot as a platform and integrating UWB wireless positioning technology, a global coordinate system for the cattle barn was established, and the expected path was planned. Finally, the pure pursuit model was improved based on the robot’s two-wheel differential kinematics model, and a dynamic forward-looking distance pure pursuit controller based on PID regulation was designed to construct a comprehensive autonomous navigation control system. Subsequently, field experiments were conducted in the cattle barn. The experimental results show that the static positioning accuracy of the UWB system for the feed-pushing robot was less than 16 cm under no-line-of-sight conditions in the cattle barn. At low speeds, the robot was subjected to linear tracking comparative experiments with forward-looking distances of 50, 100, 150, and 200 cm. The minimum upper-line distance of the dynamic forward-looking distance model was 205.43 cm. In the steady-state phase, the average lateral deviation was 3.31 cm, with an average standard deviation of 2.58 cm and the average root mean square error (RMSE) of 4.22 cm. Compared with the fixed forward-looking distance model, the average lateral deviation, the standard deviation, and the RMSE were reduced by 42.83%, 37.07%, and 42.90%, respectively. The autonomous navigation experiments conducted on the feed-pushing robot at travel speeds of 6, 8, and 10 m/min demonstrated that the maximum average lateral deviation was 7.58 cm, the maximum standard deviation was 8.22 cm, and the maximum RMSE was 11.07 cm, meeting the autonomous navigation requirements for feed-pushing operations in complex barn environments. This study provides support for achieving high-precision autonomous navigation control technology in complex environments.

Synthesis of Co0·52Cu0·48/Cu@S–C arrays for the enhanced performance of hydrazine-assisted hydrogen production

The development of efficient bifunctional catalysts is the key technology to replace oxygen evolution reaction (OER) with hydrazine oxidation reaction (HzOR) with lower theoretical potential to achieve high efficiency and energy-saving hydrogen production. In this work, the Co0·52Cu0·48/Cu@S–C (−1.3 V) composite with flower-like array was prepared by two-step electrodeposition coupled pyrolysis method. The electrochemical measurements showed that the driving voltages of the optimal composite for HzOR and hydrogen evolution reaction (HER) are respectively −118 mV and 47 mV at a current density (j) of 10 mA cm−2. The excellent performance of Co0·52Cu0·48/Cu@S–C (−1.3 V) composite is attributed to the fact that the flower-like structure exposes more active areas and facilitates the diffusion of electrolyte, the strong electron interaction between Co0·52Cu0·48/Cu and S–C substrate, which can be verified by X-ray photoelectron spectroscopy (XPS), enhances the electrical conductivity, the Co0·52Cu0·48/Cu heterogeneous interface reduces the water dissociation barrier and facilitates the dehydrogenation kinetics of N2H4 determined by density functional theory (DFT) calculations. Due to the excellent performance of Co0·52Cu0·48/Cu@S–C (−1.3 V), the overall hydrazine splitting (OHzS) electrolytic cell was constructed with Co0·52Cu0·48/Cu@S–C (−1.3 V) as electrodes. The results showed the voltages required by the cell are 36, 210 and 282 mV at the current density values of 10, 100 and 200 mA cm−2 respectively, showing that Co0·52Cu0·48/Cu@S–C (−1.3 V) can be used for energy-saving hydrogen production by hydrazine assisted water electrolysis.

Efficient Absorption of CO2 by Protic-Ionic-Liquid Based Deep Eutectic Solvents.

Carbon capture, utilization, and storage (CCUS) are among the key technologies to achieve large-scale carbon emission reduction globally. Deep eutectic solvents (DESs) are considered as designable solvents, which has attracted intensive attention for CO2 capture. Here, a series of binary DESs are synthesized through one-step mixing with the starting materials of protic ionic liquid (PIL) and amine. The eutectic behavior was investigated by measuring the melting point of PILs and amine. The saturated vapor of these DESs and industrial MDEA solution were measured and compared. These DESs are investigated to have high absorption capacity (0.1 g ⋅ g-1 at 1.0 bar and 25 °C), superior apparent absorption rate constant (0.381 min-1 vs 0.012 min-1 of 70 wt.% MDEA), moderate interaction with CO2 (the enthalpy change is as low as -34.8 kJ ⋅ mol-1). The absorption mechanism is also investigated by NMR analysis. Eight absorption/desorption regeneration experiments are carried out to show their reversibility. Considering the advantages, including convenience of synthesis, large absorption capacity, fast absorption rate, and moderate interaction energy as well as good regeneration, these DESs are believed to be as potential CO2 absorbent in practical applications.

Digital Twins for Discrete Manufacturing Lines: A Review

Along with the development of new-generation information technology, digital twins (DTs) have become the most promising enabling technology for smart manufacturing. This article presents a statistical analysis of the literature related to the applications of DTs for discrete manufacturing lines, researches their development status in the areas of the design and improvement of manufacturing lines, the scheduling and control of manufacturing line, and predicting faults in critical equipment. The deployment frameworks of DTs in different applications are summarized. In addition, this article discusses the three key technologies of high-fidelity modeling, real-time information interaction methods, and iterative optimization algorithms. The current issues, such as fine-grained sculpting of twin models, the adaptivity of the models, delay issues, and the development of efficient modeling tools are raised. This study provides a reference for the design, modification, and optimization of discrete manufacturing lines.

Design Method for Travel E-commerce Platform Based on HHO imparoved K-means Clustering Algorithm

Convenient and intelligent tourism product recommendation method, as the key technology of tourism E-commerce platform design, not only provides academic value to the research of tourism E-commerce platform, but also improves the efficiency of personalized recommendation of tourism products. In order to improve the quality of tourism recommendation, this paper proposes a tourism E-commerce platform design method based on HHO improved K-means clustering algorithm. Firstly, the Harris optimization algorithm is used to improve the K-means algorithm to construct a user-oriented tourism product recommendation strategy; then, combined with the XGBoost algorithm, an item-oriented tourism product recommendation strategy is proposed; secondly, the two strategies are mixed to construct a personalized tourism product recommendation model. Finally, the effectiveness of the proposed method is verified by simulation experiment analysis. The results show that the recommendation accuracy of the tourism E-commerce platform design method proposed in this paper reaches more than 90%, and the recommendation response time meets the real-time requirements, which can provide personalized tourism product recommendation for platform users and enhance the purchase of tourism products.

Recent Progress on Digital Twins in Intelligent Connected Vehicles: A Review

As an important enabling technology in the era of Industry 4.0, the intelligent connected vehicle (ICV) facilitates robust data interaction with the outside through sensors and communication technologies, ultimately making scientific decisions based on environmental perception information. However, due to constraints such as limited communication bandwidth and computing resources, the influx of data simultaneously impedes the sustainable optimisation of the vehicle decision making process at the same time. As a novel technology that effectively connects physical and virtual space, the special ability of the digital twin (DT) is to identify characteristics within a certain lifecycle, thereby garnering widespread attention across various industries. The purpose of this paper is to review the contribution of digital twins in the application field of intelligent vehicles and explore its potential for development. First, the key technologies of ICV provide a basis for the embedding of digital twins. Then, by analysing the development process and technical composition of digital twins, readers can better understand the concept of digital twins. Finally, the application of DTs in ICV is reviewed from the perspective of vehicles, traffic facilities, and occupants. Future challenges and opportunities in this direction are described at the same time.

Bibliometric analysis of China's high standard farmland construction research based on CNKI

Carrying out the construction of high-standard farmland is an important way to implement the principle of "storing grain in the land and storing grain in the technology", and it is an important practice to implement General Secretary Xi Jinping's principle of food security. The construction of high-standard farmland can speed up the modernization of agriculture, help urbanization development, and realize the efficient use of arable land, scientific management, and guarantee the increase of farmers' incomes. The construction of high-standard farmland is beneficial to the country and the people. Using CNKI database publication year, institutions, authors, publications, journals, cited frequency, keywords and other elements, we systematically sorted out the overview of the research field of high-standard farmland construction in China from 1996 to 2024, and comprehensively analyzed the research dynamics and hotspots in this field. The results show that: at present, China's high standard farmland construction research mainly focuses on the theoretical policy, implementation effect and engineering technology; the organization with the most publications in this field is the newspaper, and the two documents with the highest total citation frequency are Research on the Construction Standards and Models of High-standard Farmland in Chongqing Municipality and Construction Standards of High-standard Farmland, respectively, and Comprehensive Agricultural Development of China is the periodical that publishes the most related documents; in the future, the research hotspots will gradually tend to be zoning construction and high standard farmland construction. The research hotspot gradually tends to zoning construction, ecological construction and other aspects, need to accelerate the research of scientific research institutions on this aspect of the research and key technology integration.

Variable Universe Fuzzy-Proportional-Integral-Differential-Based Braking Force Control of Electro-Mechanical Brakes for Mine Underground Electric Trackless Rubber-Tired Vehicles.

Currently, the main solution for braking systems for underground electric trackless rubber-tired vehicles (UETRVs) is traditional hydraulic braking systems, which have the disadvantages of hydraulic pressure crawling, the risk of oil leakage and a high maintenance cost. An electro-mechanical-braking (EMB) system, as a type of novel brake-by-wire (BBW) system, can eliminate the above shortcomings and play a significant role in enhancing the intelligence level of the braking system in order to meet the motion control requirements of unmanned UETRVs. Among these requirements, the accurate control of clamping force is a key technology in controlling performance and the practical implementation of EMB systems. In order to achieve an adaptive clamping force control performance of an EMB system, an optimized fuzzy proportional-integral-differential (PID) controller is proposed, where the improved fuzzy algorithm is utilized to adaptively adjust the gain parameters of classic PID. In order to compensate for the deficiency of single-close-loop control and adjusting the brake gap automatically, a cascaded three-closed-loop control architecture with force/position switch technology is established, where a contact point detection method utilizing motor rotor angle displacement is proposed via experiments. The results of the simulation and experiments indicate that the clamping force response of the proposed multi-close-loop Variable Universe Fuzzy-PID (VUF-PID) controller is faster than the multi-closed-loop Fuzzy-PID and cascaded three-close-loop PID controllers. In addition, the chattering of braking force can be suppressed by 17%. This EMB system may rapidly and automatically finish the operation of the overall braking process, including gap elimination, clamping force tracking and gap recovery, which can obviously enhance the precision of the longitudinal motion control of UETRVs. It can thus serve as a BBW actuator of mine autonomous driving electric vehicles, especially in the stage of braking control.

A comprehensive overview of core modules in visual SLAM framework

Visual Simultaneous Localization and Mapping (VSLAM) technology has become a key technology in autonomous driving and robot navigation. Relying on camera sensors, VSLAM can provide a richer and more precise perception means, and its advancement has accelerated in recent years. However, current review studies are often limited to in-depth analysis of a specific module and lack a comprehensive review of the entire VSLAM framework. The VSLAM system consists of five core components: (1) The camera sensor module is responsible for capturing visual information about the surrounding environment. (2) The front-end module uses image data to roughly estimate the camera’s position and orientation. (3) The back-end module optimizes and processes the pose information estimated by the front-end. (4) The loop detection module is used to correct accumulated errors in the system. (5) The mapping module is responsible for generating environmental maps. This review provides a systematic and comprehensive analysis of the SLAM framework by taking the core components of VSLAM as the entry point. Deep learning brings new development opportunities for VSLAM, but it still needs to solve the problems of data dependence, cost and real-time in practical application. We deeply explore the challenges of combining VSLAM with deep learning and feasible solutions. This review provides a valuable reference for the development of VSLAM. This will help push VSLAM technology to become smarter and more efficient. Thus, it can better meet the needs of future intelligent autonomous systems in multiple fields.