Cloud Network Research Articles

LatentPCN: latent space-constrained point cloud network for reconstruction of 3D patient-specific bone surface models from calibrated biplanar X-ray images.

Accurate three-dimensional (3D) models play crucial roles in computer assisted planning and interventions. MR or CT images are frequently used to derive 3D models but have the disadvantages that they are expensive or involving ionizing radiation (e.g., CT acquisition). An alternative method based on calibrated 2D biplanar X-ray images is highly desired. A point cloud network, referred as LatentPCN, is developed for reconstruction of 3D surface models from calibrated biplanar X-ray images. LatentPCN consists of three components: an encoder, a predictor, and a decoder. During training, a latent space is learned to represent shape features. After training, LatentPCN maps sparse silhouettes generated from 2D images to a latent representation, which is taken as the input to the decoder to derive a 3D bone surface model. Additionally, LatentPCN allows for estimation of a patient-specific reconstruction uncertainty. We designed and conducted comprehensive experiments on datasets of 25 simulated cases and 10 cadaveric cases to evaluate the performance of LatentLCN. On these two datasets, the mean reconstruction errors achieved by LatentLCN were 0.83mm and 0.92mm, respectively. A correlation between large reconstruction errors and high uncertainty in the reconstruction results was observed. LatentPCN can reconstruct patient-specific 3D surface models from calibrated 2D biplanar X-ray images with high accuracy and uncertainty estimation. The sub-millimeter reconstruction accuracy on cadaveric cases demonstrates its potential for surgical navigation applications.

A Novel Security Model for Strong Confidentiality and Authentication in Public Cloud Networks

A Novel Security Model for Strong Confidentiality and Authentication in Public Cloud Networks

An Intelligent Optimal Secure Framework for Malicious Events Prevention in IOT Cloud Networks

The intrusion is considered a significant problematic parameter in Cloud networks. Thus, an efficient mechanism is required to avoid intrusion and provide more security to the cloud system. Therefore, the novel Artificial Bee-based Elman Neural Security Framework (ABENSF) is developed in this article. The developed model rescales the raw dataset using the pre-processing function. Moreover, the artificial bee's optimal fitness function is integrated into the feature extraction phase to track and extract the attack features. In addition, the monitoring mechanism in the developed model provides high security to the network by preventing attacks. Thus, the tracking and monitoring functions avoid intrusion by eliminating known and unknown attacks. The presented work was designed and validated with an NSL-KDD dataset in python software. Finally, the performance parameters of the presented work are estimated and verified with the existing techniques in a comparative analysis. The comparative performance shows that the developed model has earned better outcomes than others.

IoT-based Secure Data Transmission Prediction using Deep Learning Model in Cloud Computing

The security of Internet of Things (IoT) networks has become highly significant due to the growing number of IoT devices and the rise in data transfer across cloud networks. Here, we propose Generative Adversarial Networks (GANs) method for predicting secure data transmission in IoT-based systems using cloud computing. We evaluated our model’s attainment on the UNSW-NB15 dataset and contrasted it with other machine-learning (ML) methods, comprising decision trees (DT), random forests, and support vector machines (SVM). The outcomes demonstrate that our suggested GANs model performed better than expected in terms of precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC-ROC). The GANs model generates a 98.07% accuracy rate for the testing dataset with a precision score of 98.45%, a recall score of 98.19%, an F1 score of 98.32%, and an AUC-ROC value of 0.998. These outcomes show how well our suggested GANs model predicts secure data transmission in cloud-based IoT-based systems, which is a crucial step in guaranteeing the confidentiality of IoT networks.

The Potential of Deep Learning for Satellite Rainfall Detection over Data-Scarce Regions, the West African Savanna

Food and economic security in West Africa rely heavily on rainfed agriculture and are threatened by climate change and demographic growth. Accurate rainfall information is therefore crucial to tackling these challenges. Particularly, information about the occurrence and length of droughts as well as the onset date of the rainy season is essential for agricultural planning. However, existing rainfall models fail to accurately represent the highly variable and sparsely monitored West African rainfall patterns. In this paper, we show the potential of deep learning (DL) to model rainfall in the region and propose a methodology to develop DL models in data-scarce areas. We built two DL models for satellite rainfall (rain/no-rain) detection over northern Ghana from Meteosat TIR data based on standard DL architectures: Convolutional neural networks (CNNs) and convolutional long short-term memory neural networks (ConvLSTM). The Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) and Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System (PERSIANN-CCS) products are used as benchmarks. We use rain gauge data from the Trans-African Hydro-Meteorological Observatory (TAHMO) for model development and performance evaluation. We show that our models compare well against existing products despite being considerably simpler, developed with a small training dataset—i.e., 8 stations covering 2.5 years with 20.4% of the data missing—and using TIR data alone. Concretely, our models consistently outperform PERSIANN-CCS for rain/no-rain detection at a sub-daily timescale. While IMERG is the overall best performer, the DL models perform better in the second half of the rainy season despite their simplicity (i.e., up to 120 k parameters). Our results suggest that DL-based regional models are a promising alternative to state-of-the-art global products for providing regional rainfall information, especially in meteorologically complex regions such as the (sub)tropics, which are poorly covered by ground-based rainfall observations.

Precipitation Estimation Based on Infrared Data with a Spherical Convolutional Neural Network

Abstract Precipitation is a vital process in the water cycle. Accurate estimation of the precipitation rate underpins the success of hydrological simulations, flood predictions, and water resource management. Satellite infrared (IR) data, with high temporal resolution and wide coverages, have been commonly used in precipitation inversion. However, existing IR-based precipitation retrieval algorithms suffer from various problems such as overestimation in dry regions, poor performance in extreme rainfall events, and reliance on an empirical cloud-top brightness–rain rate relationship. To resolve these problems, we construct a deep learning model using a spherical convolutional neural network to properly represent Earth’s spherical surface. With data input directly from IR bands 3, 4, and 6 of the operational Geostationary Operational Environmental Satellite (GOES), our new model of Precipitation Estimation based on IR data with Spherical Convolutional Neural Network (PEISCNN) was first trained and tested with a 3-month-long dataset, and then validated in a 2-yr period. Compared to the commonly used IR-based precipitation product PERSIANN-CCS (Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Cloud Classification System), PEISCNN showed significant improvement in the metrics of POD, CSI, RMSE, and CC, especially in the dry region and for extreme rainfall events. Decomposed with the four-component error decomposition (4CED) method, the overestimation of PEISCNN was averaged 47.66% lower than the CCS at the hourly scale. The PEISCNN model may provide a promising way to produce an improved IR-based precipitation product to benefit a wide range of hydrological applications. Significance Statement An IR-based precipitation algorithm is irreplaceable in satellite precipitation inversion, since an IR sensor can provide observations of high frequency, fine temporal resolution, and wide coverage. Considering the spherical nature of Earth’s surface which has been overlooked in previous IR-based precipitation retrieval algorithms, we proposed a new deep learning model PEISCNN, which can address the problems that exist in IR-based precipitation estimations such as overestimation in dry regions, deficiency in extreme rainfall events, and reliance on the empirical cloud-top brightness–rain rate relationship. PEISCNN provides a new insight to improve the accuracy of the satellite IR-based or multisensor-based precipitation estimation, and it has great potential to benefit a range of related hydrological research, applications in water resource management, and flood predictions.

Public attitudes toward cloud computing and willingness to share personal health records (PHRs) and genome data for health care research in Japan

Japan’s government aims to promote the linkage of medical records, including medical genomic testing data and personal health records (PHRs), via cloud computing (the cloud). However, linking national medical records and using them for health care research can be controversial. Additionally, many ethical issues with using cloud networks with health care and genome data have been noted. However, no research has yet explored the Japanese public’s opinions about their PHRs, including genome data, being shared for health care research or the use of the cloud for storing and analyzing such data. Therefore, we conducted a survey in March 2021 to clarify the public’s attitudes toward sharing their PHRs, including genome data and using the cloud for health care research. We analyzed data to experimentally create digital health basic literacy scores (BLSs). Our results showed that the Japanese public had concerns about data sharing that overlapped with structural cloud computing issues. The effect of incentives on changes in participants’ willingness to share data (WTSD) was limited. Instead, there could be a correlation between WTSD and BLSs. Finally, we argue that it is vital to consider not only researchers but also research participants as value cocreators in health care research conducted through the cloud to overcome both parties’ vulnerability.

Energy-Aware and Secure Task Offloading for Multi-Tier Edge-Cloud Computing Systems

Nowadays, Unmanned Aerial Vehicle (UAV) devices and their services and applications are gaining popularity and attracting considerable attention in different fields of our daily life. Nevertheless, most of these applications and services require more powerful computational resources and energy, and their limited battery capacity and processing power make it difficult to run them on a single device. Edge-Cloud Computing (ECC) is emerging as a new paradigm to cope with the challenges of these applications, which moves computing resources to the edge of the network and remote cloud, thereby alleviating the overhead through task offloading. Even though ECC offers substantial benefits for these devices, the limited bandwidth condition in the case of simultaneous offloading via the same channel with increasing data transmission of these applications has not been adequately addressed. Moreover, protecting the data through transmission remains a significant concern that still needs to be addressed. Therefore, in this paper, to bypass the limited bandwidth and address the potential security threats challenge, a new compression, security, and energy-aware task offloading framework is proposed for the ECC system environment. Specifically, we first introduce an efficient layer of compression to smartly reduce the transmission data over the channel. In addition, to address the security issue, a new layer of security based on an Advanced Encryption Standard (AES) cryptographic technique is presented to protect offloaded and sensitive data from different vulnerabilities. Subsequently, task offloading, data compression, and security are jointly formulated as a mixed integer problem whose objective is to reduce the overall energy of the system under latency constraints. Finally, simulation results reveal that our model is scalable and can cause a significant reduction in energy consumption (i.e., 19%, 18%, 21%, 14.5%, 13.1% and 12%) with respect to other benchmarks (i.e., local, edge, cloud and further benchmark models).

Intrusion Detection on AWS Cloud through Hybrid Deep Learning Algorithm

The network security and cloud environment have been playing vital roles in today’s era due to increased network data transmission, the cloud’s elasticity, pay as you go and global distributed resources. A recent survey for the cloud environment involving 300 organizations in North America with 500 or more employees who had spent a minimum of USD 1 million on cloud infrastructure, as per March 2022 statistics, stated that 79% of organizations experienced at least one cloud data breach. In the year 2022, the AWS cloud provider leads the market share with 34% and a USD 200 billion cloud market, proving important and producing the motivation to improve the detection of intrusion with respect to network security on the basis of the AWS cloud dataset. The chosen CSE-CIC-IDS-2018 dataset had network attack details based on the real time attack carried out on the AWS cloud infrastructure. The proposed method here is the hybrid deep learning based approach, which uses the raw data first to do the pre-processing and then for normalization. The normalized data have been feature extracted from seventy-six fields to seven bottlenecks using Principal Component Analysis (PCA); those seven extracted features of every packet have been categorized as two-way soft-clustered (attack and non-attack) using the Smart Monkey Optimized Fuzzy C-Means algorithm (SMO-FCM). The attack cluster data have been further provided as inputs for the deep learning based AutoEncoder algorithm, which provides the outputs as attack classifications. Finally, the accuracy of the results in intrusion detection using the proposed technique (PCA + SMO-FCM + AE) is achieved as 95% over the CSE-CIC-IDS-2018 dataset, which is the highest known for state-of-the-art protocols compared with 11 existing techniques.

Correlation Anomaly Detection With Multiple Primary Attributes in Collaborative Device–Edge–Cloud Network

Anomaly detection is playing an increasingly important role in Internet of Things applications since anomalous events may cause some damage to the physical–social environment monitored by different kinds of smart object devices. In some cases, the occurrence of an anomalous event is caused by the fusion impact derived from several primary monitoring factors. Considering this, we propose a novel anomaly detection mechanism for the events with multiple decisive primary attributes in a collaborative device–edge–cloud architecture, in which a propagation and influence-based correlation is further explored in the edge layer for improving the detection efficiency. During the detection process, multiple primary attributes first cooperate to detect an anomaly in the edge layer in advance. If an anomaly occurs in the subregion managed by an edge device, social-aware interaction relationships between edge devices are further integrated to give a guidance on the detection of correlative anomaly in neighbor subregions. The cloud further analyzes the primary attributes information and the interaction relationship to determine the secondary attributes that are helpful in identifying the final anomaly. A large number of experiments show that our method is superior to the alternative methods in terms of energy consumption, detection time, and accuracy.

An Intelligent Task Scheduling Model for Hybrid Internet of Things and Cloud Environment for Big Data Applications

One of the most significant issues in Internet of Things (IoT) cloud computing is scheduling tasks. Recent developments in IoT-based technologies have led to a meteoric rise in the demand for cloud storage. In order to load the IoT services onto cloud resources efficiently even while satisfying the requirements of the applications, sophisticated planning methodologies are required. This is important because several processes must be well prepared on different virtual machines to maximize resource usage and minimize waiting times. Different IoT application tasks can be difficult to schedule in a cloud-based computing architecture due to the heterogeneous features of IoT. With the rise in IoT sensors and the need to access information quickly and reliably, fog cloud computing is proposed for the integration of fog and cloud networks to meet these demands. One of the most important necessities in a fog cloud setting is efficient task scheduling, as this can help to lessen the time it takes for data to be processed and improve QoS (quality of service). The overall processing time of IoT programs should be kept as short as possible by effectively planning and managing their workloads, taking into account limitations such as task scheduling. Finding the ideal approach is challenging, especially for big data systems, because task scheduling is a complex issue. This research provides a Deep Learning Algorithm for Big data Task Scheduling System (DLA-BDTSS) for the Internet of Things (IoT) and cloud computing applications. When it comes to reducing energy costs and end-to-end delay, an optimized scheduling model based on deep learning is used to analyze and process various tasks. The method employs a multi-objective strategy to shorten the makespan and maximize resource consumption. A regional exploration search technique improves the optimization algorithm’s capacity to exploit data and avoid becoming stuck in local optimization. DLA-BDTSS was compared to other well-known task allocation methods in accurate trace information and the CloudSim tools. The investigation showed that DLA-BDTSS performed better than other well-known algorithms. It converged faster than different approaches, making it beneficial for big data task scheduling scenarios, and it obtained an 8.43 percent improvement in the outcomes. DLA-BDTSS obtained an 8.43% improvement in the outcomes with an execution time of 34 s and fitness value evaluation of 76.8%.

Securing and managing healthcare data generated by intelligent blockchain systems on cloud networks through DNA cryptography

PurposeThe purpose of this paper is to ensure the anonymity and security of health data and improve the integrity and authenticity among patients, doctors and insurance providers. Simulation and validation algorithms are proposed in this work to ensure the proper implementation of the distributed system to secure and manage healthcare data. The author also aims to examine the methodology of Wireless Body Area Networks and how it contributes to the health monitoring system.Design/methodology/approachWireless Body Area Network (WBAN) plays an important role in patient health data monitoring. In this paper, a novel framework is designed and proposed to generate data by the sensor machines and be stored in the cloud, and the transactions can be secured by blockchain. DNA cryptography is used in the framework to encrypt the hashes of the blocks. The proposed framework will ensure the anonymity and security of the health data and improve the integrity and authenticity among the patients, doctors and insurance providers.FindingsCloud Computing and Distributed Networking have transformed the IT industry and their amalgamation with intelligent systems would revolutionize the Healthcare Industry. The data being generated by devices is huge and storing it in the cloud environment would be a better decision. However, the privacy and security of healthcare data are still a concern because medical data is very confidential and desires to be safe and secure. The blockchain is a promising distributed network that ensures the security aspect of the data and makes the transactions authentic and transparent. In this work, the data is collected using various sensor devices and is transmitted to the cloud through the WBAN via the blockchain network.Research limitations/implicationsIn this paper, a framework for securing and managing the healthcare data generated by intelligent systems is proposed. As the data generated by these devices are heterogeneous and huge in nature, the cloud environment is chosen for its storage and analysis. Therefore, the transactions to and from the cloud are secured by using the blockchain-based distributed network.Practical implicationsThe target end-users of our system are the patients to keep themselves informed and healthy, healthcare providers to monitor the conditions of their patients virtually, and the health insurance providers to have a track of the history of the patients, so that no fraudulent claims can be made.Originality/valueThe target end-users of our system are the patients for keeping themselves informed and healthy, healthcare providers for monitoring the conditions of their patients virtually and the health insurance providers to have a track of the history of the patients, so that no fraudulent claims can be made.

Research on the implementation status and improvement strategies of cloud classroom personality teaching in elementary schools

Currently, the development of students' personality and the cultivation of innovative talents are regarded as an important task of education for each country, the personalized teaching has become the goal of the new curriculum reform in China. With the continuous development of cloud computing technology, network cloud platform education resources are being used more and more in the teaching process, the " personalized teaching of the cloud classroom" in primary schools has gradually become the highlight for the reform and research of the basic education in Nanjing. Since it was officially launched in 2010, Nanjing has 1380 high-quality courses in the cloud classroom, trained 775 backbone teachers, explored new teaching models, accumulated a wealth of teaching cases. At the same time, in the implementation process, it also faces many problems and challenges related to educational concept, technology and application. This study use the literature design and case study method to define the relevant conceptss in analyze the teaching. The result of this study shown that the use of cloud classroom teaching can provide teachers visual expression tools for the smooth implementation of teaching, reduce the teaching burden of teachers, and provide students with a teaching environment rich in pictures and texts, stimulate learning interest and improve learning efficiency.

Evidence in the fog – Triage in fog computing systems

Fog computing promises improved service scalability and lower latency for IoT systems. The concept closes the gap between full computing capabilities at the network's edge and cloud systems' centrally located processing infrastructure. The drawback of the former is the high power requirements at the edge nodes, and the latter is the high latency for the data being transmitted from the edge to the cloud and back. One of the challenges for a digital forensic investigator facing a fog is the number of possible data locations, as the node functioning as the server processing data can be selected among several nodes in the network. An investigator typically has limited resources for an investigation; the more possible evidence locations, the more resources are required to collect and examine the data locations. A triage is thus needed to prioritize collecting and examining the evidence. This work analyzes measures that can identify which fog nodes are more likely to contain data, and it uses simulations to test the measures' precision and sensitivity. It aims for digital forensic investigators to maximize the utility of the available investigation resources, such that all relevant evidence is found on time.

Enhancing Network Performance Tomography in Software-Defined Cloud Network

For cloud network performance profiling, network tomography based on end-to-end measurement is often used in deducing the network performance for its efficiency. However, most tomography problems are under-constrained, which require additional assumptions or probing monitors planted among network switches, which are often unavailable in software-defined networking (SDN) environment. On the other hand, SDN-based flow mirroring could provide accurate flow information, but the cost of both gathering and analysing the packet traces is tremendous that it is impossible to cover the whole network. We propose ScoutFlow, a method combining SDN flow measurement and end-to-end performance tomography, to achieve accurate performance profiling for cloud network while keeping low monitoring overhead. We evaluate ScoutFlow in our campus data center cloud, and the experiment shows good scalability and accuracy.

A High-Performantal and Server-Centric Based Data Center Network

With the increasing demand of data center interconnection in the network cloud era, data center networks (DCNs) play key roles in computing and communication, becoming the center of a great deal of resources and business. Therefore, how to design a DCN with good performance has been a significant issue in networks. The hypercube is a popular interconnection network topology with low diameter, symmetry and recursive structure, and scalability. As a variant of the hypercube, the crossed cube not only retains the excellent properties of the hypercube, but also performs better in terms of Hamiltonian-connectivity, embeddability, diameter, etc. In this paper, we first propose a novel and server-centric DCN, called CSDC, which is based on the crossed cube network. The performance of CSDC can be characterized by the properties of its logical structure, so we then give its logical structure <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$C_{n}$</tex-math></inline-formula> , and determine the connectivity and edge-connectivity of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$C_{n}$</tex-math></inline-formula> . Furthermore, we explore the fault-tolerant paths and disjoint paths between any two distinct nodes in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$C_{n}$</tex-math></inline-formula> , and obtain the diameter of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$C_{n}$</tex-math></inline-formula> . Moreover, we propose a method to construct two completely independent spanning trees (CISTs) in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$C_{n}$</tex-math></inline-formula> . Extensive evaluations demonstrate that CSDC is a magnetic DCN for building large-scale data centers.

Efficient and secure content-based image retrieval with deep neural networks in the mobile cloud computing

Smart devices offer a variety of more convenient forms to help us record our lives and generate a large amount of data in this process. Limited by the local storage capacity, many users outsource their image data directly to the cloud server. However, images stored in plaintext on the cloud server are very insecure, resulting in image privacy information can be easily leaked. Therefore, users will encrypt the images and outsource them to the cloud server, but the encrypted images cannot be retrieved. Therefore, we proposed a secure and efficient ciphertext image retrieval scheme based on image content retrieval (CBIR) and approximate homomorphic encryption (HE). First, we used approximate homomorphic encryption to encrypt images after resizing and uploaded the ciphertext images to the cloud for feature extraction of ciphertext. At the same time, the large images (size, dimension, and resolution) would generate data inflation after using homomorphic encryption. Therefore, the original images are encrypted using the chaotic image encryption scheme to reduce ciphertext size and computation costs. Second, we proposed two deepening network depth optimization strategies that address the problem of insufficient neural network depth. Finally, reducing the dimensionality of the ciphertext feature vector using locally sensitive hashing (LSH) can accelerate the retrieval of ciphertext images. Compared with other literature, our ciphertext image retrieval scheme can significantly reduce the rounds of user-server communication.

Correction to: FPSO-GA: A Fuzzy Metaheuristic Load Balancing Algorithm to Reduce Energy Consumption in Cloud Networks

Correction to: FPSO-GA: A Fuzzy Metaheuristic Load Balancing Algorithm to Reduce Energy Consumption in Cloud Networks

Real-Time Reliability Access Control Based on Rail Traffic Data Platform

With the introduction of the industrial internet, Internet of Things, and big data technology, the interconnection degree of the industrial control cloud network is getting higher and higher, the data interface needs to be gradually standardized, and there are more and more open interface components. Data-based attacks will continue to emerge. The real-time and reliability of access control are essential for trust value updating between network participants. This paper proposes a fine-grained dynamic real-time credibility access control method based on zero trust. Continuous authentication and trust evaluation should be carried out throughout the access control process. The zero-trust evaluation indicators of a rail transit data platform that conforms to the requirements of grade protection 2.0 are established. According to the risk feedback, the current trust level is dynamically updated in real time, and the results are used in the access control model. It can reject unauthorized access, reduce the occurrence of illegal intrusion data leakage and data loss events, and has great value in rail transit data security.

Kernel-based feature aggregation framework in point cloud networks

Various effective deep networks have been developed for analysis of 3D point clouds. One key step in these networks is to aggregate the features of orderless points into a compact representation for the cloud. As a typical order-invariant aggregation method, max-pooling has been widely applied. However, while enjoying simplicity and high efficiency, max-pooling does not fully exploit the feature information since it not only ignores the non-maximum elements in each feature dimension but also neglects the interactions between different dimensions. These drawbacks of max-pooling motivate us to explore advanced feature aggregation methods for 3D point cloud analysis. The desired advanced method should be capable of modeling richer information between the point features than max-pooling, and, at the same time, it can readily replace max-pooling without the need to modify other parts of the existing network architecture. To this end, this paper proposes a novel kernel-based feature aggregation framework for 3D point cloud analysis for the first time. The proposed method effectively considers all the elements in each dimension and models the nonlinear interactions between feature dimensions as complementary information to max-pooling. In addition, it is a plug-in module that can be integrated to many common networks as a replacement of max-pooling. Comprehensive experiments are conducted to demonstrate the consistently superior performance and high generality of the proposed method over max-pooling. Specifically, the proposed kernel-based feature aggregation framework consistently improves the max-pooling with three representative backbones of PointNet, DGCNN and PCT across four 3D point cloud based analysis tasks, including supervised 3D object classification, 3D part segmentation, indoor semantic segmentation and one additional unsupervised place retrieval task. Especially, it shows remarkable performance improvement over max-pooling in the unsupervised retrieval task, demonstrating its advantage in forming 3D point cloud representation.