Satisfy User Requirements Research Articles

Multi-interest sequential recommendation with contrastive learning and temporal analysis

Sequential recommendation systems aim to forecast the subsequent item of interest to users by analyzing their historical behaviors. While existing approaches, which employ attention mechanisms, have significantly advanced by capturing users’ multiple interests, they encounter two primary challenges. Firstly, they often fail to effectively capture the transient shifts in users’ interests across a sequence of items and neglect the interdependencies among these items, leading to a misalignment between the identified and actual interests. Secondly, conventional multi-interest models struggle to ensure that the identified interests are distinct, which results in overly similar interests that may not adequately satisfy user requirements. To address these issues, we propose a novel multi-interest recommendation method, which models the temporal features and user’s preference features from the user level. In order to capture short-term variations in interest, we introduce a time period module to encode the behavioral intervals between items and capture the periodicity of users clicking on similar items by extracting temporal information. In addition, we integrate similar types of items into the interest subgraph through preference feature extraction to capture users’ short-term changes in relevance term interests, and incorporate contrastive learning to enhance the differences between the captured interests. Extensive experiments conducted on two datasets Amazon Books and Taobao show that the model outperforms current state-of-the-art methods.

DRL-assisted task offloading in enhanced time-expanded graph (eTEG)-modeled aerial computing

Space–air–ground integrated networks (SAGINs), categorized under aerial computing (AC), are emerging as a promising hierarchical platform designed to meet the seamless connectivity demands of the forthcoming 6G era. However, efficiently offloading ground tasks to space entities via SAGINs presents unprecedented challenges, primarily due to the mobility of these networks. In response, an enhanced time-expanded graph (eTEG) is proposed to model the dynamic distribution of heterogeneous SAGIN resources, including transmission bandwidth, computation, and storage, thereby optimizing task offloading and resource allocation by employing eTEG. Specifically, this optimization challenge is addressed using a deep reinforcement learning (DRL) approach, aimed at streamlining decision-making for task offloading and resource management to significantly reduce end-to-end delay and enhance network performance. Simulation experiments conducted to evaluate the proposed DRL-based method demonstrate its effectiveness in reducing energy consumption and improving stability, thereby outperforming other methods by achieving reduced delays and satisfying user requirements.

A CFD simulation platform for surface finishing processes in advanced manufacturing

Products created by additive manufacturing often have surface imperfections that require post-processing operations to remove extraneous material in order to meet design specifications. The usage of computational fluid dynamics (CFD) simulations to predict material removal rates of components, allows practitioners to optimize the setup and usage of post-processing equipment. However, those without in-depth knowledge of CFD or the related specialized software, require an easy-to-use and cost-effective application to manage the computational workflow. The two specific surface finishing applications investigated here, are, abrasive flow machining (AFM) and robotic stream finishing (RSF). In order to satisfy user requirements, a modular, threaded, fault-tolerant and object-oriented project management application, written with the Python programming language and PyQt6 framework, has been developed to conduct surface finishing-related CFD simulations using OpenFOAM®. The advantages of the proposed software are: 1) the modern PyQt6 framework is used to develop a cross-platform and user-friendly application which employs the model-view class architectural paradigm for data management and its display, 2) step-by-step interactive project workflows have been tailored specifically for AFM and RSF simulations, 3) the developed steady-state viscoelastic flow solver for AFM and continuum-based steady-state dense granular flow solver for RSF, offer advantages over those provided by OpenFOAM® and 4) simulation results have been corroborated by experimental data to assess the improved accuracy of material removal prediction of the current software when compared to other commercial applications.

Energy performance of a residential zero energy building energy system – R-CELLS at solar decathlon China 2022

The energy system and its energy performance of R-CELLS, a residential zero energy building from team Tianjin U+ in the Solar Decathlon China 2022, is introduced in this paper. When designing and constructing the R-CELLS energy system, two sets of challenges are encountered. Firstly, from an architectural perspective, the limited construction timeframe (only 21 days) and constrained space for housing the equipment, also ease of maintenance should be taken into account. Secondly, from an operational perspective, a constrained period for tests before the competition, a large number of devices dependent on electricity, heat and hot water supply should be considered. In consideration of the ease of assembly and maintenance of the energy system components and the aesthetic requirements of R-CELLS, an improved “photovoltaics, energy storage, direct current, flexibility” based energy system is utilized in R-CELLS. The R-CELLS energy system integrates various renewable energy sources (building integrated photovoltaics, photovoltaic-thermal, and building integrated wind turbines). Furthermore, it incorporates energy storage systems such as battery energy storage system, hot water tank, and phase change material thermal storage. In order to satisfy user requirements in grid-connected, off-grid and outage scenarios, including electricity, heat and domestic hot water, a tri-period energy management strategy based on optimized scheduling and rule-based control is proposed to achieve weekly, daily, and hourly net zero goals. Furthermore, the energy performance of R-CELLS is simulated for a whole year, including typical days in winter and summer, as well as the competition period. During the Solar Decathlon China 2022 competition, R-CELLS was subjected to testing by the committee. The results demonstrated that R-CELLS can be operated off-grid and with zero energy consumption, while meeting the test requirements for indoor environment, heating and cooling, and home life.

Development and Usability Evaluation of Transitional Cross-Reality Interfaces

The concept of Transitional Cross-Reality Interfaces where a user can seamlessly transition across the Reality-Virtuality-Continuum dates back to the introduction of the Magic Book in 2001 but recently gained new research momentum since head-mounted displays advanced by combining the former distinctive concepts of augmented reality and virtual reality into a single device. New technological capabilities require new ways of developing applications to satisfy user requirements. Especially in the context of operating in multiple realities, developing AR/VR applications is not a trivial task. In this context, the development of Transitional Cross-Reality Interfaces remains a complex engineering problem that requires specific methods, concepts, and tools. To address this problem and provide a systematic development approach, we propose a conceptual framework for both developing and evaluating Transitional Cross-Reality Interfaces. To evaluate our solution, we implemented a Transitional Cross-Reality Interface based on our framework and evaluated it with both the measurements provided by the framework and additional questionnaires. We found high usability and interesting transitional behavior of users indicating the usefulness of the proposed framework as an underlying software architecture for Transitional Cross-Reality Interfaces.

CRAMP: Clustering-based RANs association and MEC placement for delay-sensitive applications

With advancements in networking technology and ubiquitous computing, there has been a significant increase in the number of edge devices and delay-sensitive applications. To facilitate efficient processing, mobile edge computing (MEC) technology provides resources through MEC servers, which are deployed at the radio access networks (RANs) of 5G networks. However, these MEC servers possess a limited amount of resources, making their effective management of these resources a critical challenge. This is due to the uneven distribution of resource utilization, where some resources become overutilized while others remain underutilized. Addressing the issue above while simultaneously satisfying user requirements for delay-sensitive applications poses a significant challenge at the edge. In this paper, we propose a clustering-based efficient RANs association and MEC server placement model to tackle this challenge. Our primary objective is to minimize MEC server deployment costs while ensuring that the delays of these applications are effectively managed. We propose a greedy algorithm called the clustering-based radio access networks association and mobile edge computing placement (CRAMP) algorithm, which determines the optimal location of MEC servers to associate with RANs. Simulation results demonstrate that our proposed algorithm outperforms existing approaches regarding cost efficiency and delay management.

A dynamic pricing scheme for secure offloading and resource allocation based on the internet of vehicles

With the development of sixth-generation (6G) wireless communication technology, billions of vehicles will access the network in the future, and the number of vehicle applications and user data will also increase dramatically. Traditional cloud computing faces serious problems of latency and energy consumption in handling massive data. Mobile edge computing (MEC) has emerged to dramatically improve computing efficiency and reduce energy consumption by placing computing servers at network edge locations close to vehicles. However, the service range of MEC servers is limited and cannot fully satisfy user requirements. In addition, the task offloading process has security risks. The current research focuses on how to reduce the energy consumption and latency overhead of task offloading and neglects the economic cost or data transmission security of vehicles. To solve the above problems, we propose a cooperative security offloading (CSO) scheme for auxiliary vehicles and MEC servers. Firstly, we propose a dynamic pricing mechanism for computing resources by considering the credibility of MEC servers and auxiliary vehicles, the urgency of the task, and the number of users competing for auxiliary vehicles. Secondly, to prevent malicious MEC servers and eavesdroppers from attacking, we employ homomorphic encryption to protect user privacy. Meanwhile, efficient and secure computing services are achieved by optimizing user selection decisions, offloading decisions, and resource allocation decisions. Finally, the optimal decisions are obtained by the dueling DQN-based resource allocation and pricing strategy (DDRP) and the cost-minimizing security offloading (CMSO) algorithm, which minimizes the economic cost of users while maximizing security. Simulation results show that, compared with some existing schemes, the CSO scheme effectively reduces the economic cost of users while ensuring the security of data transmission.

Hybrid Multi Kernel Polar Code Construction and Optimized Decoding Algorithm for 5G Mobile Communications

5G mobile communications faces difficulty in channel coding to satisfy user requirements. This paper evaluates flexibility, reliability and complexity for different channel coding schemes(Turbo codes, Low Density Parity check codes, mother polar codes, Multi Kernel-polar codes) on regular channel AWGN with BPSK modulation of code rate R=1/2. The proposed hybrid Multi Kernel-polar codes will have greater flexibility and reliability for short and large code words. The optimized decoding of Multi Kernel polar codes reduces the number of computations by using repeated LLR’s of sub-kernel matrices.

Accelerating a consensus-based EV smart charging algorithm by user priority clustering

The rapid increase in Electric Vehicle (EV) adoption leads to significant challenges for charging station operators due to the unbalance between the growing demand for charging services and their limited power capacity connected to the grid. To tackle the challenge, this paper applies a two-step architecture in which an energy management system (EMS) in the first step determines the available capacity to charge the present fleet of EVs, after which in the second step this capacity is distributed over the individual EVs. To optimally allocate available power and satisfy user requirements, a user priority-based charging management strategy is proposed. Such priority can optimally order the set of EVs to be charged based on user input. However, relying solely on user-estimated input can be prone to incorrect priority due to inaccurate estimations. Therefore, we introduced a clustering of charging sessions based on the user-provided estimated information in the proposed priority function. These clusters relax the effect of inaccurately estimated user input by grouping charging sessions with similar behavior. Our proposed priority can increase user satisfaction by up to 30%, as measured by the percentage of requested energy that is delivered to users, compared to scenarios without priority, 10% more than priority based solely on estimation information, and 8% more than first-come-first-serve. To avoid exposing the personal behavior of the user, we introduce a decentralized approach, applying a consensus-based method that allows local control per EV charging station and only requires minimal communication of a consensus variable with neighboring charging stations. By introducing the priority in the communication weight matrix of the consensus-based algorithm, we accelerate the convergence rate more than 10 times. Simulation results based on real-world data sets in Belgium demonstrate the proposed method scales well with growing fleet sizes.

Sustainability assessment of faecal sludge treatment technologies for resource recovery in Phnom Penh, Cambodia

Selection of appropriate sustainable treatment technologies involves satisfying user requirements, quality standards on treatment and products, and specific socio-technical constraints in the intended context. Using locally adapted multi-criteria assessment (MCA), this study investigated faecal sludge treatment technologies that enable resource recovery in Phnom Penh. A four-step structured approach was applied, involving i) identification of available options, ii) prerequisite screening, iii) MCA and iv) stakeholder discussions and ranking. Data were collected in a literature review, stakeholder interviews and an online survey. Lists of suitable primary (n = 7) and secondary (n = 13) treatment technologies were compiled based on the literature. Four secondary treatment technologies (solar drying, co-composting, vermicomposting, black soldier fly larvae (BSFL) composting) were retained after prerequisite screening and subjected to MCA. Co-composting was ranked highest in MCA, since it performed well in multiple aspects, especially for health criteria. However, when economic return on investment was prioritised and a lower treatment class was accepted, e.g. USEPA Class B biosolids, the highest ranking was achieved by vermicomposting or BSFL composting. If institutional criteria were included in the assessment, solar drying would likely be the highest-ranked option, since this simple technology requires less logistically complex stakeholder arrangements than co-composting. These results show that the ranking obtained for different sludge treatment options depends on criteria weighting and trade-offs. Considering secondary treatment options is crucial during early planning for faecal sludge management in a city of low-and-middle income countries, as the primary treatment must yield appropriate feedstock quality for the secondary treatment step.

Detection and filling of functional holes in microservice systems: Method and infrastructure support

With the widespread use of microservices technology, a growing number of Microservice Systems (MSS) have emerged. Monolithic applications are divided into several small and independent microservices that provide functions through APIs. These microservices can be orchestrated by service composition to satisfy various user requirements: microservice functionalities are aggregated into coarse-grained solutions to provide composite functions to users. However, although various service composition approaches have been presented in many works of literature, they failed to solve the situation that no feasible solutions can be found because of missing functions in MSS, named Functional Hole (FH). As a result, the system cannot satisfy user requirements and faces Quality of Service (QoS) declines. In this paper, to reduce the impact of missing functions, we defined the FH to describe the absence of functions for MSS when it cannot satisfy user requirements. Moreover, for the first time, we proposed the Detection and Filling Problem of FH (DFPFH) in a running MSS. A three-phase algorithm with supporting infrastructure was developed to solve DFPFH. It detects FHs based on hypergraphs, fills FHs with services from an external service system at runtime, and generates suggestions for thoroughly filling FH to developers. Plenty of experiments were conducted, and the results validate our approaches’ usability, effectiveness, and performance.

A directional spatial active noise control system with a sound field separation algorithm

Spatial active noise control (ANC) systems aim to control noise fields within the entire region of interest. However, current spatial ANC systems commonly lack the spatial selectivity to target a specific noise field from the whole noise fields, which cannot satisfy user requirements in some cases. This paper designs a directional spatial ANC system to control noise fields selectively based on the direction of arrival (DOA). The key idea is to introduce a DOA-informed sound field separation (SFS) algorithm to design the directional spatial ANC system. In detail, the directional spatial ANC system is designed to control noise fields selectively, with the ability to select the target sound field introduced by the SFS algorithm. Simulation results demonstrate that the designed directional spatial ANC system can control noise fields selectively within the region of interest in a noisy environment.

Data-driven implicit design preference prediction model for product concept evaluation via BP neural network and EEG

Customer preference-involved product concept evaluation is a vital stage for developing new products. One of the key factors in this stage is to mine the potential relationships between customers’ needs and technical requirements. In most new product development (NPD), design characteristics (DCs) are employed as performance indicators to describe the technical requirements of a scheme. Previous studies have focused on evaluating the degree to which a scheme meets the performance value of DCs, disregarding the relationship between DCs and potential user preferences. This oversight leads to an inability to accurately predict customer satisfaction with the candidate schemes based on their preferences. Previous research, which was aimed at ensuring the preference value of schemes by utilizing mapping data between design preference (DP) and DCs, overlooked users' psychological states and thus failed to accurately capture their cognitive preferences for the schemes. To address these issues, an electroencephalogram (EEG) data-driven, implicit DP prediction approach is proposed. The method characterizes the implicit cognitive relationship between DP and DCs by mining EEG data and utilizes a back propagation (BP) neural network to predict DP. First, a user's DP word pairs were constructed based on the approach of statistical analysis, and the best-worst method (BWM) was introduced to obtain the importance of DCs. Second, an experiment was designed based on the extracted preference word pairs to collect EEG data that reflect a user's DC preference, record the user's stimulation state toward the DCs, and label their DP based on the segmentation results of preference evaluation. Third, a BP neural network was employed to construct a preference prediction model for DCs, and the reliability of the proposed preference prediction model was validated by using the forklift design example. The prediction results further exhibited the potential association between user preferences and DCs that can be acquired by EEG data mining. The results also provide support for designers to promptly acquire design concepts that satisfy user requirements (URs), thereby enhancing the efficiency and quality of product development in a highly competitive market.

Analysis of quality standards for industrial collaborative robots based on user‐centered design framework

AbstractIndustrial collaborative robots have become increasingly important in recent years due to their ability to work safely and efficiently alongside humans. As a result, there is a growing need for evaluation standards to ensure the quality of collaborative robots. However, existing studies only consider system‐centered and technical aspects of collaborative robots, and there is a lack of research on user‐centered quality evaluation. In this study, we identified 21 user requirements based on a user‐centered design framework and confirmed the limitations of existing quality standards by reviewing the standard clauses for collaborative robots. It was found that user needs to be related to performance, safety, and even usability and enjoyment are already being expressed according to the user‐centered design framework, but the quality standards for these needs only present design principles or do not consider them at all. This study provides information on the quality attributes that need to be fulfilled to satisfy user requirements and suggests the need and direction for further research on the user‐centered evaluation of collaborative robots. Accordingly, the user's perception and experience of collaborative robots are expected to improve.

MEMS: An automated multi-energy management system for smart residences using the DD-LSTM approach

The increasing popularity of home automation and the rising global electricity costs have emphasized the importance of energy conservation for consumers. With smart meters, machine learning models can anticipate equipment behavior by monitoring and recording residential power use. Multi-Energy Management Systems, which allow smart grid flexibility, have garnered interest. Smart meters and smart energy gadgets in homes require autonomous multi-energy management systems. These systems should efficiently utilize real-time data to plan device consumption, reducing costs for end users. The model incorporates two Long Short-Term Memory networks, capturing short-term and long-term dependencies in energy consumption patterns. This enables the Multi-Energy Management Systems to make accurate predictions and manage energy resources in real-time. The primary objectives are to minimize reliance on the grid and maximize the utilization of renewable energy sources. The proposed Deep Dual- Long Short-Term Memory model achieves impressive accuracy rates, with scores ranging from 97% to 99% for recall, F1-score, and precision. Numerical findings demonstrate the superior performance of the proposed method compared to existing approaches, showcasing its ability to lower energy consumption and meet operational constraints. The results indicate that the proposed strategy optimizes energy use, providing cost savings and satisfying user requirements.

뉴로모픽 환경에서 QoS를 고려한 최적의 SNN 모델 파라미터 생성 기법

IoT edge services utilizing neuromorphic hardware architectures are suitable for autonomous IoT applications as they perform intelligent processing on the device itself. However, spiking neural networks applied to neuromorphic hardware are difficult for IoT developers to comprehend due to their complex structures and various hyper-parameters. In this paper, we propose a method for generating spiking neural network (SNN) models that satisfy user performance requirements while considering the constraints of neuromorphic hardware. Our proposed method utilizes previously trained models from pre-processed data to find optimal SNN model parameters from profiling data. Comparing our method to a naive search method, both methods satisfy user requirements, but our proposed method shows better performance in terms of runtime. Additionally, even if the constraints of new hardware are not clearly known, the proposed method can provide high scalability by utilizing the profiled data of the hardware.

Validation of Simplified Level 2 Prototype Processor Sentinel-2 fraction of canopy cover, fraction of absorbed photosynthetically active radiation and leaf area index products over North American forests

Canopy biophysical variables such as the fraction of canopy cover (fCOVER), fraction of absorbed photosynthetically active radiation (fAPAR), and leaf area index (LAI) are widely used for ecosystem modelling and monitoring. The Sentinel-2 mission was designed for systematic global mapping of these variables at 20 m resolution using imagery from the MultiSpectral Instrument. The Simplified Level 2 Prototype Processor (SL2P) is available as a baseline mapping solution. Previous validation over limited sites indicates that SL2P generally satisfies user requirements for all three variables over crops, but underestimates LAI over forests. In this study, Sentinel-2 fAPAR, fCOVER, and LAI products, from SL2P, were validated over 281 sites representative of most North American forest ecozones and also compared to Moderate Resolution Imaging Spectrometer (MODIS) and Copernicus Global Land Service (CGLS) products. In addition to meeting the Committee on Earth Observation Satellites Stage 3 validation requirements for these areas, our study also explores the relationship between bias in SL2P products and canopy clumping and provides empirical bias correction functions for each variable.SL2P was implemented within the Landscape Evolution and Forecasting Toolbox in Google Earth Engine both for efficiency and due to bugs in the Sentinel Application Platform implementation. SL2P was found to underestimate LAI by 20% to 50% over forests with LAI > 2; in agreement with other studies and with comparisons to MODIS and CGLS products. SL2P bias for fCOVER and fAPAR transitions from ∼0.1 at low values to ∼ − 0.1 at high values. Precision error, at one standard deviation, was ∼0.5 for LAI and slightly less than ∼0.1 for fCOVER and fAPAR. Total uncertainty was dominated by bias for LAI and was slightly greater than precision error for fCOVER and fAPAR. Target user requirements were satisfied for 51% of LAI, 37% of fCOVER and 31% of fAPAR comparisons to in-situ measurements. For all variables, accuracy exhibited weak to moderate linear relationships to clumping (r2 ≤0.52), but scatter plots indicated larger negative LAI biases over northern latitude sites where canopies exhibited greater clumping. With the exception of evergreen broadleaf forests, empirical bias correction using in-situ data reduced accuracy error by 40% for fCOVER, 57% for fAPAR and, 92% for LAI and increased the agreement rate with uncertainty requirements by up to 8%. Users of SL2P LAI over forests are recommended to apply bias correction or consider recalibrating SL2P with spatially heterogenous radiative transfer model simulations.

A meta-learning configuration framework for graph-based similarity search indexes

Similarity searches retrieve elements in a dataset with similar characteristics to the input query element. Recent works show that graph-based methods have outperformed others in the literature, such as tree-based and hash-based methods. However, graphs are highly parameter-sensitive for indexing and searching, which usually demands extra time for finding a suitable trade-off for specific user requirements. Current approaches to select parameters rely on observing published experimental results or Grid Search procedures. While the former has no guarantees that good settings for a dataset will also perform well on a different one, the latter is computationally expensive and limited to a small range of values. In this work, we propose a meta-learning-based recommender framework capable of providing a suitable graph configuration according to the characteristics of the input dataset. We present two instantiations of the framework: a global instantiation that uses the whole meta-database to train meta-models and a dataset-similarity-based instantiation that relies on clustering to generate meta-models tailored to datasets with similar characteristics. We also developed generic and tuned versions of the instantiations. The generic versions can satisfy user requirements in orders of magnitude faster than the traditional Grid Search. The tuned versions provide more accurate predictions at a higher cost. Our results show that the tuned methods outperform the Grid Search for most cases, providing recommendations close to the optimal one and being a suitable alternative, particularly for more challenging datasets.

SDBlockEdge: SDN-Blockchain Enabled Multihop Task Offloading in Collaborative Edge Computing

In recent years, the Internet of Things (IoT) has gained tremendous attention and exponential growth in every domain of life. However, these devices face many challenges due to the limited resources in terms of storage and computation. Collaborative Edge Computing (CEC) is an emerging paradigm that solves these issues where multiple edge devices share computational resources to collaborate and satisfy user requirements. The fundamental issues in CEC are to make an offloading decision while considering the flow scheduling and balancing the load over multiple edge devices. Moreover, the efficient resource allocation of edge nodes is challenging, particularly when IoT devices are more vulnerable and become resource-hungry. The combination of Software Defined Networking (SDN) and Blockchain (BC) can play a vital role in solving the issues mentioned above. This paper presents a token-based resource management mechanism as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SDBlockEdge</i> by integrating these two technologies. The programming abstractions and global view of the SDN can help offload decision and flow scheduling, whereas the smart contract mechanism of BC can help control the abnormal behavior of IoT devices. We design the Resource Management Controller (RMC), which collaborates with the SDN controller to keep the record of available resources. It helps for offloading decisions and balancing the load over edge servers, whereas the SDN controller helps consider the less loaded path, while offloading reduces the task completion time. Moreover, the resources are allocated against tokens, and smart contracts are used to pay the cost of these resources. The proposed approach is implemented in Mininet_WiFi and Containernet, where docker hosts act as edge nodes with different IoT devices. The results after the extensive simulation show the effectiveness of the proposed approach.

TripleBrain: A Compact Neuromorphic Hardware Core With Fast On-Chip Self-Organizing and Reinforcement Spike-Timing Dependent Plasticity.

Human brain cortex acts as a rich inspiration source for constructing efficient artificial cognitive systems. In this paper, we investigate to incorporate multiple brain-inspired computing paradigms for compact, fast and high-accuracy neuromorphic hardware implementation. We propose the TripleBrain hardware core that tightly combines three common brain-inspired factors: the spike-based processing and plasticity, the self-organizing map (SOM) mechanism and the reinforcement learning scheme, to improve object recognition accuracy and processing throughput, while keeping low resource costs. The proposed hardware core is fully event-driven to mitigate unnecessary operations, and enables various on-chip learning rules (including the proposed SOM-STDP & R-STDP rule and the R-SOM-STDP rule regarded as the two variants of our TripleBrain learning rule) with different accuracy-latency tradeoffs to satisfy user requirements. An FPGA prototype of the neuromorphic core was implemented and elaborately tested. It realized high-speed learning (1349 frame/s) and inference (2698 frame/s), and obtained comparably high recognition accuracies of 95.10%, 80.89%, 100%, 94.94%, 82.32%, 100% and 97.93% on the MNIST, ETH-80, ORL-10, Yale-10, N-MNIST, Poker-DVS and Posture-DVS datasets, respectively, while only consuming 4146 (7.59%) slices, 32 (3.56%) DSPs and 131 (24.04%) Block RAMs on a Xilinx Zynq-7045 FPGA chip. Our neuromorphic core is very attractive for real-time resource-limited edge intelligent systems.