To see the other types of publications on this topic, follow the link: Classification of network devices.
Journal articles on the topic 'Classification of network devices'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Classification of network devices.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Mhetre, Nalini A., Arvind V. Deshpande, and Parikshit Narendra Mahalle. "Device Classification-Based Context Management for Ubiquitous Computing using Machine Learning." International Journal of Engineering and Advanced Technology 10, no. 5 (June 30, 2021): 135–42. http://dx.doi.org/10.35940/ijeat.e2688.0610521.
Full textAbstract:
Ubiquitous computing comprises scenarios where networks, devices within the network, and software components change frequently. Market demand and cost-effectiveness are forcing device manufacturers to introduce new-age devices. Also, the Internet of Things (IoT) is transitioning rapidly from the IoT to the Internet of Everything (IoE). Due to this enormous scale, effective management of these devices becomes vital to support trustworthy and high-quality applications. One of the key challenges of IoT device management is proactive device classification with the logically semantic type and using that as a parameter for device context management. This would enable smart security solutions. In this paper, a device classification approach is proposed for the context management of ubiquitous devices based on unsupervised machine learning. To classify unknown devices and to label them logically, a proactive device classification model is framed using a k-Means clustering algorithm. To group devices, it uses the information of network parameters such as Received Signal Strength Indicator (rssi), packet_size, number_of_nodes in the network, throughput, etc. Experimental analysis suggests that the well-formedness of clusters can be used to derive cluster labels as a logically semantic device type which would be a context for resource management and authorization of resources.
2
Ganesan, Elaiyasuriyan, I.-Shyan Hwang, Andrew Tanny Liem, and Mohammad Syuhaimi Ab-Rahman. "SDN-Enabled FiWi-IoT Smart Environment Network Traffic Classification Using Supervised ML Models." Photonics 8, no. 6 (June 4, 2021): 201. http://dx.doi.org/10.3390/photonics8060201.
Full textAbstract:
Due to the rapid growth of the Internet of Things (IoT), applications such as the Augmented Reality (AR)/Virtual Reality (VR), higher resolution media stream, automatic vehicle driving, the smart environment and intelligent e-health applications, increasing demands for high data rates, high bandwidth, low latency, and the quality of services are increasing every day (QoS). The management of network resources for IoT service provisioning is a major issue in modern communication. A possible solution to this issue is the use of the integrated fiber-wireless (FiWi) access network. In addition, dynamic and efficient network configurations can be achieved through software-defined networking (SDN), an innovative and programmable networking architecture enabling machine learning (ML) to automate networks. This paper, we propose a machine learning supervised network traffic classification scheduling model in SDN enhanced-FiWi-IoT that can intelligently learn and guarantee traffic based on its QoS requirements (QoS-Mapping). We capture the different IoT and non-IoT device network traffic trace files based on the traffic flow and analyze the traffic traces to extract statistical attributes (port source and destination, IP address, etc.). We develop a robust IoT device classification process module framework, using these network-level attributes to classify IoT and non-IoT devices. We tested the proposed classification process module in 21 IoT/Non-IoT devices with different ML algorithms and the results showed that classification can achieve a Random Forest classifier with 99% accuracy as compared to other techniques.
3
Bezerra, Vitor Hugo, Victor Guilherme Turrisi da Costa, Sylvio Barbon Junior, Rodrigo Sanches Miani, and Bruno Bogaz Zarpelão. "IoTDS: A One-Class Classification Approach to Detect Botnets in Internet of Things Devices." Sensors 19, no. 14 (July 19, 2019): 3188. http://dx.doi.org/10.3390/s19143188.
Full textAbstract:
Internet of Things (IoT) devices have become increasingly widespread. Despite their potential of improving multiple application domains, these devices have poor security, which can be explored by attackers to build large-scale botnets. In this work, we propose a host-based approach to detect botnets in IoT devices, named IoTDS (Internet of Things Detection System). It relies on one-class classifiers, which model only the legitimate device behaviour for further detection of deviations, avoiding the manual labelling process. The proposed solution is underpinned by a novel agent-manager architecture based on HTTPS, which prevents the IoT device from being overloaded by the training activities. To analyse the device’s behaviour, the approach extracts features from the device’s CPU utilisation and temperature, memory consumption, and number of running tasks, meaning that it does not make use of network traffic data. To test our approach, we used an experimental IoT setup containing a device compromised by bot malware. Multiple scenarios were made, including three different IoT device profiles and seven botnets. Four one-class algorithms (Elliptic Envelope, Isolation Forest, Local Outlier Factor, and One-class Support Vector Machine) were evaluated. The results show the proposed system has a good predictive performance for different botnets, achieving a mean F1-score of 94% for the best performing algorithm, the Local Outlier Factor. The system also presented a low impact on the device’s energy consumption, and CPU and memory utilisation.
4
Li, Xiu, Rujiao Long, Jiangpeng Yan, Kun Jin, and Jihae Lee. "TANet: A Tiny Plankton Classification Network for Mobile Devices." Mobile Information Systems 2019 (April 3, 2019): 1–8. http://dx.doi.org/10.1155/2019/6536925.
Full textAbstract:
This paper is devoted to a lightweight convolutional neural network based on the attention mechanism called the tiny attention network (TANet). The TANet consists of three main parts termed as a reduction module, self-attention operation, and group convolution. The reduction module alleviates information loss caused by the pooling operation. The new parameter-free self-attention operation makes the model to focus on learning important parts of images. The group convolution achieves model compression and multibranch fusion. Using the main parts, the proposed network enables efficient plankton classification on mobile devices. The performance of the proposed network is evaluated on the Plankton dataset collected by Oregon State University’s Hatfield Marine Science Center. The results show that TANet outperforms other deep models in speed (31.8 ms per image), size (648 kB, the size of the hard disk space occupied by the model), and accuracy (Top-1 76.5%, Top-5 96.3%).
5
Niewiadomska-Szynkiewicz, Ewa. "Localization in wireless sensor networks: Classification and evaluation of techniques." International Journal of Applied Mathematics and Computer Science 22, no. 2 (June 1, 2012): 281–97. http://dx.doi.org/10.2478/v10006-012-0021-x.
Full textAbstract:
Localization in wireless sensor networks: Classification and evaluation of techniques Recent advances in technology have enabled the development of low cost, low power and multi functional wireless sensing devices. These devices are networked through setting up a Wireless Sensor Network (WSN). Sensors that form a WSN are expected to be remotely deployed in large numbers and to self-organize to perform distributed sensing and acting tasks. WSNs are growing rapidly in both size and complexity, and it is becoming increasingly difficult to develop and investigate such large and complex systems. In this paper we provide a brief introduction to WSN applications, i.e., properties, limitations and basic issues related to WSN design and development. We focus on an important aspect of the design: accurate localization of devices that form the network. The paper presents an overview of localization strategies and attempts to classify different techniques. A set of properties by which localization systems are evaluated are examined. We then describe a number of existing localization systems, and discuss the results of performance evaluation of some of them through simulation and experiments using a testbed implementation.
6
Kim, Jiyeon, Minsun Shim, Seungah Hong, Yulim Shin, and Eunjung Choi. "Intelligent Detection of IoT Botnets Using Machine Learning and Deep Learning." Applied Sciences 10, no. 19 (October 8, 2020): 7009. http://dx.doi.org/10.3390/app10197009.
Full textAbstract:
As the number of Internet of Things (IoT) devices connected to the network rapidly increases, network attacks such as flooding and Denial of Service (DoS) are also increasing. These attacks cause network disruption and denial of service to IoT devices. However, a large number of heterogenous devices deployed in the IoT environment make it difficult to detect IoT attacks using traditional rule-based security solutions. It is challenging to develop optimal security models for each type of the device. Machine learning (ML) is an alternative technique that allows one to develop optimal security models based on empirical data from each device. We employ the ML technique for IoT attack detection. We focus on botnet attacks targeting various IoT devices and develop ML-based models for each type of device. We use the N-BaIoT dataset generated by injecting botnet attacks (Bashlite and Mirai) into various types of IoT devices, including a Doorbell, Baby Monitor, Security Camera, and Webcam. We develop a botnet detection model for each device using numerous ML models, including deep learning (DL) models. We then analyze the effective models with a high detection F1-score by carrying out multiclass classification, as well as binary classification, for each model.
7
Lu, Peng, Yang Gao, Hao Xi, Yabin Zhang, Chao Gao, Bing Zhou, Hongpo Zhang, Liwei Chen, and Xiaobo Mao. "KecNet: A Light Neural Network for Arrhythmia Classification Based on Knowledge Reinforcement." Journal of Healthcare Engineering 2021 (April 24, 2021): 1–10. http://dx.doi.org/10.1155/2021/6684954.
Full textAbstract:
Acquiring electrocardiographic (ECG) signals and performing arrhythmia classification in mobile device scenarios have the advantages of short response time, almost no network bandwidth consumption, and human resource savings. In recent years, deep neural networks have become a popular method to efficiently and accurately simulate nonlinear patterns of ECG data in a data-driven manner but require more resources. Therefore, it is crucial to design deep learning (DL) algorithms that are more suitable for resource-constrained mobile devices. In this paper, KecNet, a lightweight neural network construction scheme based on domain knowledge, is proposed to model ECG data by effectively leveraging signal analysis and medical knowledge. To evaluate the performance of KecNet, we use the Association for the Advancement of Medical Instrumentation (AAMI) protocol and the MIT-BIH arrhythmia database to classify five arrhythmia categories. The result shows that the ACC, SEN, and PRE achieve 99.31%, 99.45%, and 98.78%, respectively. In addition, it also possesses high robustness to noisy environments, low memory usage, and physical interpretability advantages. Benefiting from these advantages, KecNet can be applied in practice, especially wearable and lightweight mobile devices for arrhythmia classification.
8
Feng, Kai, Xitian Pi, Hongying Liu, and Kai Sun. "Myocardial Infarction Classification Based on Convolutional Neural Network and Recurrent Neural Network." Applied Sciences 9, no. 9 (May 7, 2019): 1879. http://dx.doi.org/10.3390/app9091879.
Full textAbstract:
Myocardial infarction is one of the most threatening cardiovascular diseases for human beings. With the rapid development of wearable devices and portable electrocardiogram (ECG) medical devices, it is possible and conceivable to detect and monitor myocardial infarction ECG signals in time. This paper proposed a multi-channel automatic classification algorithm combining a 16-layer convolutional neural network (CNN) and long-short term memory network (LSTM) for I-lead myocardial infarction ECG. The algorithm preprocessed the raw data to first extract the heartbeat segments; then it was trained in the multi-channel CNN and LSTM to automatically learn the acquired features and complete the myocardial infarction ECG classification. We utilized the Physikalisch-Technische Bundesanstalt (PTB) database for algorithm verification, and obtained an accuracy rate of 95.4%, a sensitivity of 98.2%, a specificity of 86.5%, and an F1 score of 96.8%, indicating that the model can achieve good classification performance without complex handcrafted features.
9
Et. al., Gopal Patil,. "REVIEW THE DEEP LEARNING TECHNIQUE FOR MISSING DATA CLASSIFICATION IN IOT APPLICATIONS FOR NETWORK PERFORMANCE IMPROVEMENT." INFORMATION TECHNOLOGY IN INDUSTRY 9, no. 2 (March 25, 2021): 365–69. http://dx.doi.org/10.17762/itii.v9i2.356.
Full textAbstract:
In order to ensure product safety and increase production quality, The construction of mine Internet of Things networks continues to accelerate mining enterprises. Given the large increase in the number of networked devices connectivity capability in the mine, there is considerable strain on the mine network communication facilities. We suggest an Innovative Solution Using Deep Learning for Missing Data Classification in IoT Network Performance Enhancement System Market Classifier based on neural networks to improve the quality of service in the connectivity infrastructure of mine networks. The classifier uses a transformation wavelet to delete the data flow and to build compliance characteristics to identify the market categories of the system.Owing to the findings of the classification, the system changes the specifications of the network services given to the terminal equipment in a versatile manner. In this way, the system's network capacity can be fairly distributed. We assess the output of the classifier model using the test data collection. We review the deep learning technique in IoT applications for Network Improvement for missing data classification
10
Cotrim, Jeferson Rodrigues, and João Henrique Kleinschmidt. "LoRaWAN Mesh Networks: A Review and Classification of Multihop Communication." Sensors 20, no. 15 (July 31, 2020): 4273. http://dx.doi.org/10.3390/s20154273.
Full textAbstract:
The growth of the Internet of Things (IoT) led to the deployment of many applications that use wireless networks, like smart cities and smart agriculture. Low Power Wide Area Networks (LPWANs) meet many requirements of IoT, such as energy efficiency, low cost, large coverage area, and large-scale deployment. Long Range Wide Area Network (LoRaWAN) networks are one of the most studied and implemented LPWAN technologies, due to the facility to build private networks with an open standard. Typical LoRaWAN networks are single-hop in a star topology, composed of end-devices that transmit data directly to gateways. Recently, several studies proposed multihop LoRaWAN networks, thus forming wireless mesh networks. This article provides a review of the state-of-the-art multihop proposals for LoRaWAN. In addition, we carried out a comparative analysis and classification, considering technical characteristics, intermediate devices function, and network topologies. This paper also discusses open issues and future directions to realize the full potential of multihop networking. We hope to encourage other researchers to work on improving the performance of LoRaWAN mesh networks, with more theoretical and simulation analysis, as well as practical deployments.
11
Li, Wenwen, Zheng Dou, and Lin Qi. "Wavelet transform and cyclic cumulant based modulation classification in wireless network." International Journal of Distributed Sensor Networks 15, no. 12 (December 2019): 155014771989545. http://dx.doi.org/10.1177/1550147719895459.
Full textAbstract:
With the development of Internet of things, a large number of embedded devices are interconnected by ad hoc and wireless network. The embedded devices can work correctly, only by ensuring correct communication between them. Identifying modulation scheme is the precondition to ensure the correct communication between embedded devices. However, in the multipath channel, ensuring the correct communication between embedded devices is a great challenge. Multipath channel always exists in the wireless network. However, most of the available modulation classification algorithms are based on ideal channel. It leads to the low-modulation classification probability in multipath channel. To resolve this problem, we propose a novel modulation classification algorithm. The proposed algorithm can classify signal without prior information about multipath channel. We calculate feature by high-order cyclic cumulant and wavelet transform. The feature is robust to multipath channel. The simulation results show that the proposed algorithm can achieve the much better classification accuracy than the available method in multipath channel.
12
Cvitić, Ivan, Dragan Peraković, Marko Periša, and Mirjana D. Stojanović. "Novel Classification of IoT Devices Based on Traffic Flow Features." Journal of Organizational and End User Computing 33, no. 6 (November 2021): 1–20. http://dx.doi.org/10.4018/joeuc.20211101.oa12.
Full textAbstract:
The concept of IoT (Internet of Things) assumes a continuous increase in the number of devices, which raises the problem of classifying them for different purposes. Based on their semantic characteristics, meaning, functionality or domain of usage, the system classes have been identified so far. This research purpose is to identify devices classes based on traffic flow characteristics such as the coefficient of variation of the received and sent data ratio. Such specified classes can combine devices based on behavior predictability and can serve as the basis for the creation of network management or network anomaly detection classification models. Four generic classes of IoT devices where defined by using the classification of the coefficient of variation method.
13
He, Hui, Chi Xin Li, and Cheng Ying Gong. "Network Topology Discovery Algorithm Based on MIB." Applied Mechanics and Materials 496-500 (January 2014): 2134–37. http://dx.doi.org/10.4028/www.scientific.net/amm.496-500.2134.
Full textAbstract:
Network topology is the core of configuration management and the infrastructure of resource management.And it is based on the detection of a network failure and the analysis of network performance.This requires the network topology complete, accurate and friendly interface with visualization.This article describes the classification of the physical network topology discovery.Based on Bridge-MIB and MIB-II of SNMP devices, designed topology discovery algorithm in data link layer and network layer.Test results show that the algorithm can accurately find the device and connection on the network layer and the data link layer.
14
Solomon, Akinboro, Emmanuel Olajubu, Ibrahim Ogundoyin, and Ganiyu Aderounmu. "A Trust Model for Detecting Device Attacks in Mobile Ad Hoc Ambient Home Network." International Journal of Advanced Pervasive and Ubiquitous Computing 8, no. 2 (April 2016): 16–37. http://dx.doi.org/10.4018/ijapuc.2016040102.
Full textAbstract:
This study designed, simulated and evaluated the performance of a conceptual framework for ambient ad hoc home network. This was with a view to detecting malicious nodes and securing the home devices against attacks. The proposed framework, called mobile ambient social trust consists of mobile devices and mobile ad hoc network as communication channel. The trust model for the device attacks is Adaptive Neuro Fuzzy (ANF) that considered global reputation of the direct and indirect communication of home devices and remote devices. The model was simulated using Matlab 7.0. In the simulation, NSL-KDD dataset was used as input packets, the artificial neural network for packet classification and ANF system for the global trust computation. The proposed model was benchmarked with an existing Eigen Trust (ET) model using detection accuracy and convergence time as performance metrics. The simulation results using the above parameters revealed a better performance of the ANF over ET model. The framework will secure the home network against unforeseen network disruption and node misbehavior.
15
Sheets, Gregory, Philip Bingham, Mark B. Adams, David Bolme, and Scott L. Stewart. "Preprocessing for Unintended Conducted Emissions Classification with ResNet." Applied Sciences 11, no. 19 (September 22, 2021): 8808. http://dx.doi.org/10.3390/app11198808.
Full textAbstract:
Characterization of Unintended Conducted Emissions (UCE) from electronic devices is important when diagnosing electromagnetic interference, performing nonintrusive load monitoring (NILM) of power systems, and monitoring electronic device health, among other applications. Prior work has demonstrated that UCE analysis can serve as a diagnostic tool for energy efficiency investigations and detailed load analysis. While explaining the feature selection of deep networks with certainty is often not fully comprehensive, or in other applications, quite lacking, additional tools/methods for further corroboration and confirmation can help further the understanding of the researcher. This is true especially in the subject application of the study in this paper. Often the focus of such efforts is the selected features themselves, and there is not as much understanding gained about the noise in the collected data. If selected feature and noise characteristics are known, it can be used to further shape the design of the deep network or associated preprocessing. This is additionally difficult when the available data are limited, as in the case which the authors investigated in this study. Here, the authors present a novel work (which is a proposed complementary portion of the overall solution to the deep network classification explainability problem for this application) by applying a systematic progression of preprocessing and a deep neural network (ResNet architecture) to classify UCE data obtained via current transformers. By using a methodical application of preprocessing techniques prior to a deep classifier, hypotheses can be produced concerning what features the deep network deems important relative to what it perceives as noise. For instance, it is hypothesized in this particular study as a result of execution of the proposed method and periodic inspection of the classifier output that the UCE spectral features are relatively close to each other or to the interferers, as systematically reducing the beta parameter of the Kaiser window produced progressively better classification performance, but only to a point, as going below the Beta of eight produced decreased classifier performance, as well as the hypothesis that further spectral feature resolution was not as important to the classifier as rejection of the leakage from a spectrally distant interference. This can be very important in unpredictable low-FNR applications, where knowing the difference between features and noise is difficult. As a side-benefit, much was learned regarding the best preprocessing to use with the selected deep network for the UCE collected from these low power consumer devices obtained via current transformers. Baseline rectangular windowed FFT preprocessing provided a 62% classification increase versus using raw samples. After performing a more optimal preprocessing, more than 90% classification accuracy was achieved across 18 low-power consumer devices for scenarios in which the in-band features-to-noise ratio (FNR) was very poor.
16
Sousa, Jose Vigno Moura, Vilson Rosa de Almeida, Aratã Andrade Saraiva, Domingos Bruno Sousa Santos, Pedro Mateus Cunha Pimentel, and Luciano Lopes de Sousa. "Classification of Pneumonia images on mobile devices with Quantized Neural Network." Research, Society and Development 9, no. 10 (September 19, 2020): e889108382. http://dx.doi.org/10.33448/rsd-v9i10.8382.
Full textAbstract:
This paper presents an approach for the classification of child chest X-ray images into two classes: pneumonia and normal. We employ Convolutional Neural Networks, from pre-trained networks together with a quantization process, using the platform TensorFlow Lite method. This reduces the processing requirement and computational cost. Results have shown accuracy up to 95.4% and 94.2% for MobileNetV1 and MobileNetV2, respectively. The resulting mobile app also presents a simple and intuitive user interface.
17
Piat, Sebastien, Nairi Usher, Simone Severini, Mark Herbster, Tommaso Mansi, and Peter Mountney. "Image classification with quantum pre-training and auto-encoders." International Journal of Quantum Information 16, no. 08 (December 2018): 1840009. http://dx.doi.org/10.1142/s0219749918400099.
Full textAbstract:
Computer vision has a wide range of applications from medical image analysis to robotics. Over the past few years, the field has been transformed by machine learning and stands to benefit from potential advances in quantum computing. The main challenge for processing images on current and near-term quantum devices is the size of the data such devices can process. Images can be large, multidimensional and have multiple color channels. Current machine learning approaches to computer vision that exploit quantum resources require a significant amount of manual pre-processing of the images in order to be able to fit them onto the device. This paper proposes a framework to address the problem of processing large scale data on small quantum devices. This framework does not require any dataset-specific processing or information and works on large, grayscale and RGB images. Furthermore, it is capable of scaling to larger quantum hardware architectures as they become available. In the proposed approach, a classical autoencoder is trained to compress the image data to a size that can be loaded onto a quantum device. Then, a Restricted Boltzmann Machine (RBM) is trained on the D-Wave device using the compressed data, and the weights from the RBM are then used to initialize a neural network for image classification. Results are demonstrated on two MNIST datasets and two medical imaging datasets.
18
Chheepa, Tarun Kumar, and Tanuj Manglani. "Power Quality Events Classification using ANN with Hilbert Transform." International Journal of Emerging Research in Management and Technology 6, no. 6 (June 29, 2018): 227. http://dx.doi.org/10.23956/ijermt.v6i6.274.
Full textAbstract:
With the evolution of Smart Grid, Power Quality issues have become prominent. The urban development involves usage of computers, microprocessor controlled electronic loads and power electronic devices. These devices are the source of power quality disturbances. PQ problems are characterized by the variations in the magnitude and frequency in the system voltages and currents from their nominal values. To decide a control action, a proper classification mechanism is required to classify different PQ events. In this paper we propose a hybrid approach to perform this task. Different Neural topologies namely Cascade Forward Backprop Neural Network (CFBNN), Elman Backprop Neural Network (EBPNN), Feed Forward Backprop Neural Network (FFBPNN), Feed Forward Distributed Time Delay Neural Network (FFDTDNN) , Layer Recurrent Neural Network (LRNN), Nonlinear Autoregressive Exogenous Neural Network (NARX), Radial Basis Function Neural Network (RBFNN) along with the application of Hilbert Transform are employed to classify the PQ events. A meaningful comparison of these neural topologies is presented and it is found that Radial Basis Function Neural Network (RBFNN) is the most efficient topology to perform the classification task. Different levels of Additive White Gaussian Noise (AWGN) are added in the input features to present the comparison of classifiers.
19
Campbell, Colin, and C. Perez Vicente. "The Target Switch Algorithm: A Constructive Learning Procedure for Feed-Forward Neural Networks." Neural Computation 7, no. 6 (November 1995): 1245–64. http://dx.doi.org/10.1162/neco.1995.7.6.1245.
Full textAbstract:
We propose an efficient procedure for constructing and training a feedforward neural network. The network can perform binary classification for binary or analogue input data. We show that the procedure can also be used to construct feedforward neural networks with binary-valued weights. Neural networks with binary-valued weights are potentially straightforward to implement using microelectronic or optical devices and they can also exhibit good generalization.
20
Lotz, W. A., M. Vountas, T. Dinter, and J. P. Burrows. "Cloud and surface classification using SCIAMACHY polarization measurement devices." Atmospheric Chemistry and Physics 9, no. 4 (February 18, 2009): 1279–88. http://dx.doi.org/10.5194/acp-9-1279-2009.
Full textAbstract:
Abstract. A simple scheme has been developed to discriminate surface, sun glint and cloud properties in satellite based spectrometer data utilizing visible and near infrared information. It has been designed for the use with data measured by SCIAMACHY's (SCanning Imaging Absorption SpectroMeter for Atmospheric CHartographY) Polarization Measurement Devices (PMD) but the applicability is not strictly limited to this instrument. The scheme is governed by a set of constraints and thresholds developed by using satellite imagery and meteorological data. Classification targets are ice, water and generic clouds, sun glint and surface parameters, such as water, land, snow/ice, desert and vegetation. The validation has been done using MERIS (MEdium Resolution Imaging Spectrometer) and meteorological data from METAR (MÉTéorologique Aviation Régulière – a network for the provision of meteorological data for aviation). Qualitative validation using MERIS satellite imagery shows good agreement. However, the quantitative agreement is hampered by the heterogeneity of MERIS classifications within each SCIAMACHY PMD ground pixel. The comparison with METAR data shows good agreement. The comparison for sun glint classifications and MERIS results exhibits excellent agreement.
21
Churcher, Andrew, Rehmat Ullah, Jawad Ahmad, Sadaqat ur Rehman, Fawad Masood, Mandar Gogate, Fehaid Alqahtani, Boubakr Nour, and William J. Buchanan. "An Experimental Analysis of Attack Classification Using Machine Learning in IoT Networks." Sensors 21, no. 2 (January 10, 2021): 446. http://dx.doi.org/10.3390/s21020446.
Full textAbstract:
In recent years, there has been a massive increase in the amount of Internet of Things (IoT) devices as well as the data generated by such devices. The participating devices in IoT networks can be problematic due to their resource-constrained nature, and integrating security on these devices is often overlooked. This has resulted in attackers having an increased incentive to target IoT devices. As the number of attacks possible on a network increases, it becomes more difficult for traditional intrusion detection systems (IDS) to cope with these attacks efficiently. In this paper, we highlight several machine learning (ML) methods such as k-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), naive Bayes (NB), random forest (RF), artificial neural network (ANN), and logistic regression (LR) that can be used in IDS. In this work, ML algorithms are compared for both binary and multi-class classification on Bot-IoT dataset. Based on several parameters such as accuracy, precision, recall, F1 score, and log loss, we experimentally compared the aforementioned ML algorithms. In the case of HTTP distributed denial-of-service (DDoS) attack, the accuracy of RF is 99%. Furthermore, other simulation results-based precision, recall, F1 score, and log loss metric reveal that RF outperforms on all types of attacks in binary classification. However, in multi-class classification, KNN outperforms other ML algorithms with an accuracy of 99%, which is 4% higher than RF.
22
Churcher, Andrew, Rehmat Ullah, Jawad Ahmad, Sadaqat ur Rehman, Fawad Masood, Mandar Gogate, Fehaid Alqahtani, Boubakr Nour, and William J. Buchanan. "An Experimental Analysis of Attack Classification Using Machine Learning in IoT Networks." Sensors 21, no. 2 (January 10, 2021): 446. http://dx.doi.org/10.3390/s21020446.
Full textAbstract:
In recent years, there has been a massive increase in the amount of Internet of Things (IoT) devices as well as the data generated by such devices. The participating devices in IoT networks can be problematic due to their resource-constrained nature, and integrating security on these devices is often overlooked. This has resulted in attackers having an increased incentive to target IoT devices. As the number of attacks possible on a network increases, it becomes more difficult for traditional intrusion detection systems (IDS) to cope with these attacks efficiently. In this paper, we highlight several machine learning (ML) methods such as k-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), naive Bayes (NB), random forest (RF), artificial neural network (ANN), and logistic regression (LR) that can be used in IDS. In this work, ML algorithms are compared for both binary and multi-class classification on Bot-IoT dataset. Based on several parameters such as accuracy, precision, recall, F1 score, and log loss, we experimentally compared the aforementioned ML algorithms. In the case of HTTP distributed denial-of-service (DDoS) attack, the accuracy of RF is 99%. Furthermore, other simulation results-based precision, recall, F1 score, and log loss metric reveal that RF outperforms on all types of attacks in binary classification. However, in multi-class classification, KNN outperforms other ML algorithms with an accuracy of 99%, which is 4% higher than RF.
23
Chen, Dan. "Multiple Linear Regression of Multi-class Images in Devices of Internet of Things." Traitement du Signal 37, no. 6 (December 31, 2020): 965–73. http://dx.doi.org/10.18280/ts.370609.
Full textAbstract:
The correct classification of images is an important application in the monitoring of Internet of things (IoT). In the research of IoT images, a key issue is to recognize multi-class images at a high accuracy. As a result, this paper puts forward a classification method for multi-class images based on multiple linear regression (MLR). Firstly, the convolutional neural network (CNN) was improved to automatically generate a network from the IoT terminals, and used to classify images into disjoint class sets (clusters), which were processed by the subsequently constructed expert network. After that, the MLR was introduced to evaluate the accuracy and robustness of the classification of multi-class images. Finally, the proposed method has been verified on CIFAR-10, CIfar-100 and MNIST, etc. benchmark data sets. Our method was found to outperform other methods in classification, and improve the accuracy of the classic AlexNet by 2%. The research results provide theoretical evidence and lay practical basis for the classification of multi-class IoT images.
24
Lokhande, Meghana P., Dipti Durgesh Patil, Lalit V. Patil, and Mohammad Shabaz. "Machine-to-Machine Communication for Device Identification and Classification in Secure Telerobotics Surgery." Security and Communication Networks 2021 (August 27, 2021): 1–16. http://dx.doi.org/10.1155/2021/5287514.
Full textAbstract:
The capacity of machine objects to communicate autonomously is seen as the future of the Internet of Things (IoT), but machine-to-machine communication (M2M) is also gaining traction. In everyday life, security, transportation, industry, and healthcare all employ this paradigm. Smart devices have the ability to detect, handle, store, and analyze data, resulting in major network issues such as security and reliability. There are numerous vulnerabilities linked with IoT devices, according to security experts. Prior to performing any activities, it is necessary to identify and classify the device. Device identification and classification in M2M for secure telerobotic surgery are presented in this study. Telerobotics is an important aspect of the telemedicine industry. The major purpose is to provide remote medical care, which eliminates the requirement for both doctors and patients to be in the same location. This paper aims to propose a security and energy-efficient protocol for telerobotic surgeries, which is the primary concern at present. For secure telerobotic surgery, the author presents an Efficient Device type Detection and Classification (EDDC) protocol for device identification and classification in M2M communication. The periodic trust score is calculated using three factors from each sensor node. It demonstrates that the EDDC protocol is more effective and secure in detecting and categorizing rogue devices.
25
Kikuchi, Satoru, Kota Kadama, and Shintaro Sengoku. "Characteristics and Classification of Technology Sector Companies in Digital Health for Diabetes." Sustainability 13, no. 9 (April 26, 2021): 4839. http://dx.doi.org/10.3390/su13094839.
Full textAbstract:
In recent years, technological progress in smart devices and artificial intelligence has also led to advancements in digital health. Digital health tools are especially prevalent in diabetes treatment and improving lifestyle. In digital health’s innovation ecosystem, new alliance networks are formed not only by medical device companies and pharmaceutical companies but also by information and communications technology (ICT) companies and start-ups. Therefore, while focusing on digital health for diabetes, this study explored the characteristics of companies with high network centralities. Our analysis of the changes in degree, betweenness, and eigenvector centralities of the sample companies from 2011 to 2020 found drastic changes in the company rankings of those with high network centrality during this period. Accordingly, the following eight companies were identified and investigated as the top-ranking technology sector companies: IBM Watson Health, Glooko, DarioHealth, Welldoc, OneDrop, Fitbit, Voluntis, and Noom. Lastly, we characterized these cases into three business models: (i) intermediary model, (ii) substitute model, and (iii) direct-to-consumer model, and we analyzed their customer value.
26
Arivudainambi D., Varun Kumar K.A., Vinoth Kumar R., and Visu P. "Ransomware Traffic Classification Using Deep Learning Models." International Journal of Web Portals 12, no. 1 (January 2020): 1–11. http://dx.doi.org/10.4018/ijwp.2020010101.
Full textAbstract:
Ransomware is a malware which affects the systems data with modern encryption techniques, and the data is recovered once a ransom amount is paid. In this research, the authors show how ransomware propagates and infects devices. Live traffic classifications of ransomware have been meticulously analyzed. Further, a novel method for the classification of ransomware traffic by using deep learning methods is presented. Based on classification, the detection of ransomware is approached with the characteristics of the network traffic and its communications. In more detail, the behavior of popular ransomware, Crypto Wall, is analyzed and based on this knowledge, a real-time ransomware live traffic classification model is proposed.
27
Ndichu, Samuel, Sylvester McOyowo, Henry Okoyo, and Cyrus Wekesa. "A Remote Access Security Model based on Vulnerability Management." International Journal of Information Technology and Computer Science 12, no. 5 (October 8, 2020): 38–51. http://dx.doi.org/10.5815/ijitcs.2020.05.03.
Full textAbstract:
Information security threats exploit vulnerabilities in communication networks. Remote access vulnerabilities are evident from the point of communication initialization following the communication channel to data or resources being accessed. These threats differ depending on the type of device used to procure remote access. One kind of these remote access devices can be considered as safe as the organization probably issues it to provide for remote access. The other type is risky and unsafe, as they are beyond the organization’s control and monitoring. The myriad of devices is, however, a necessary evil, be it employees on public networks like cyber cafes, wireless networks, vendors support, or telecommuting. Virtual Private Network (VPN) securely connects a remote user or device to an internal or private network using the internet and other public networks. However, this conventional remote access security approach has several vulnerabilities, which can take advantage of encryption. The significant threats are malware, botnets, and Distributed Denial of Service (DDoS). Because of the nature of a VPN, encryption will prevent traditional security devices such as a firewall, Intrusion Detection System (IDS), and antivirus software from detecting compromised traffic. These vulnerabilities have been exploited over time by attackers using evasive techniques to avoid detection leading to costly security breaches and compromises. We highlight numerous shortcomings for several conventional approaches to remote access security. We then adopt network tiers to facilitate vulnerability management (VM) in remote access domains. We perform regular traffic simulation using Network Security Simulator (NeSSi2) to set bandwidth baseline and use this as a benchmark to investigate malware spreading capabilities and DDoS attacks by continuous flooding in remote access. Finally, we propose a novel approach to remote access security by passive learning of packet capture file features using machine learning and classification using a classifier model.
28
Mook KANG, Jang, Choel Hee YOON, and Jiho SHIN. "A Study on Development of IoT Software Vulnerability (Using Fake Information) Response System based on Artificial Intelligence." International Journal of Engineering & Technology 7, no. 3.33 (August 29, 2018): 157. http://dx.doi.org/10.14419/ijet.v7i3.33.18598.
Full textAbstract:
The use of IoT devices such as wearable digital devices based on mobile devices is increasingly evident. In IoT-based environment, communication protocol of IoT category and lightweight special environment software are used instead of universal network configuration. Due to the operating structure of IoT, preparation of countermeasures to automatically analyze IoT software vulnerabilities based on artificial intelligence should be considered. Because of the rapid growth of IoT equipment and the expectation that there will be a sharp increase in the need to identify facts about vulnerabilities and improper use associated with IoT services naturally. It is necessary to apply artificial intelligence technology for classification and automatic collection and analysis of IoT vulnerabilities for wearable devices and smart home devices through artificial intelligence analysis technology. Sequentially, To acquire the data from the device, internal data and network data of the specified device after searching the protocol of the IoT device, it is possible to cope with IoT software vulnerability applying AI intelligence analysis method to related data. In this paper, we investigate software vulnerabilities in IoT environment and propose a technique to cope with ioT vulnerabilities through artificial intelligence.
29
Copiaco, Abigail, Christian Ritz, Nidhal Abdulaziz, and Stefano Fasciani. "A Study of Features and Deep Neural Network Architectures and Hyper-Parameters for Domestic Audio Classification." Applied Sciences 11, no. 11 (May 26, 2021): 4880. http://dx.doi.org/10.3390/app11114880.
Full textAbstract:
Recent methodologies for audio classification frequently involve cepstral and spectral features, applied to single channel recordings of acoustic scenes and events. Further, the concept of transfer learning has been widely used over the years, and has proven to provide an efficient alternative to training neural networks from scratch. The lower time and resource requirements when using pre-trained models allows for more versatility in developing system classification approaches. However, information on classification performance when using different features for multi-channel recordings is often limited. Furthermore, pre-trained networks are initially trained on bigger databases and are often unnecessarily large. This poses a challenge when developing systems for devices with limited computational resources, such as mobile or embedded devices. This paper presents a detailed study of the most apparent and widely-used cepstral and spectral features for multi-channel audio applications. Accordingly, we propose the use of spectro-temporal features. Additionally, the paper details the development of a compact version of the AlexNet model for computationally-limited platforms through studies of performances against various architectural and parameter modifications of the original network. The aim is to minimize the network size while maintaining the series network architecture and preserving the classification accuracy. Considering that other state-of-the-art compact networks present complex directed acyclic graphs, a series architecture proposes an advantage in customizability. Experimentation was carried out through Matlab, using a database that we have generated for this task, which composes of four-channel synthetic recordings of both sound events and scenes. The top performing methodology resulted in a weighted F1-score of 87.92% for scalogram features classified via the modified AlexNet-33 network, which has a size of 14.33 MB. The AlexNet network returned 86.24% at a size of 222.71 MB.
30
Ma, Fengying, Jingyao Zhang, Wei Liang, and Jingyu Xue. "Automated Classification of Atrial Fibrillation Using Artificial Neural Network for Wearable Devices." Mathematical Problems in Engineering 2020 (April 25, 2020): 1–6. http://dx.doi.org/10.1155/2020/9159158.
Full textAbstract:
Atrial fibrillation (AF), as one of the most common arrhythmia diseases in clinic, is a malignant threat to human health. However, AF is difficult to monitor in real time due to its intermittent nature. Wearable electrocardiogram (ECG) monitoring equipment has flourished in the context of telemedicine due to its real-time monitoring and simple operation in recent years, providing new ideas and methods for the detection of AF. In this paper, we propose a low computational cost classification model for robust detection of AF episodes in ECG signals, using RR intervals of the ECG signals and feeding them into artificial neural network (ANN) for classification, to compensate the defect of the computational complexity in traditional wearable ECG monitoring devices. In addition, we compared our proposed classifier with other popular classifiers. The model was trained and tested on the AF Termination Challenge Database and MIT-BIH Arrhythmia Database. Experimental results achieve the highest sensitivity of 99.3%, specificity of 97.4%, and accuracy of 98.3%, outperforming most of the others in the recent literature. Accordingly, we observe that ANN using RR intervals as an input feature can be a suitable candidate for automatic classification of AF.
31
You, Shingchern D. "Classification of Relaxation and Concentration Mental States with EEG." Information 12, no. 5 (April 26, 2021): 187. http://dx.doi.org/10.3390/info12050187.
Full textAbstract:
In this paper, we study the use of EEG (Electroencephalography) to classify between concentrated and relaxed mental states. In the literature, most EEG recording systems are expensive, medical-graded devices. The expensive devices limit the availability in a consumer market. The EEG signals are obtained from a toy-grade EEG device with one channel of output data. The experiments are conducted in two runs, with 7 and 10 subjects, respectively. Each subject is asked to silently recite a five-digit number backwards given by the tester. The recorded EEG signals are converted to time-frequency representations by the software accompanying the device. A simple average is used to aggregate multiple spectral components into EEG bands, such as α, β, and γ bands. The chosen classifiers are SVM (support vector machine) and multi-layer feedforward network trained individually for each subject. Experimental results show that features, with α+β+γ bands and bandwidth 4 Hz, the average accuracy over all subjects in both runs can reach more than 80% and some subjects up to 90+% with the SVM classifier. The results suggest that a brain machine interface could be implemented based on the mental states of the user even with the use of a cheap EEG device.
32
Dube, Swaraj, Yee Wan Wong, and Hermawan Nugroho. "Dynamic sampling of images from various categories for classification based incremental deep learning in fog computing." PeerJ Computer Science 7 (July 15, 2021): e633. http://dx.doi.org/10.7717/peerj-cs.633.
Full textAbstract:
Incremental learning evolves deep neural network knowledge over time by learning continuously from new data instead of training a model just once with all data present before the training starts. However, in incremental learning, new samples are always streaming in whereby the model to be trained needs to continuously adapt to new samples. Images are considered to be high dimensional data and thus training deep neural networks on such data is very time-consuming. Fog computing is a paradigm that uses fog devices to carry out computation near data sources to reduce the computational load on the server. Fog computing allows democracy in deep learning by enabling intelligence at the fog devices, however, one of the main challenges is the high communication costs between fog devices and the centralized servers especially in incremental learning where data samples are continuously arriving and need to be transmitted to the server for training. While working with Convolutional Neural Networks (CNN), we demonstrate a novel data sampling algorithm that discards certain training images per class before training even starts which reduces the transmission cost from the fog device to the server and the model training time while maintaining model learning performance both for static and incremental learning. Results show that our proposed method can effectively perform data sampling regardless of the model architecture, dataset, and learning settings.
33
Bausch, Johannes. "Classifying data using near-term quantum devices." International Journal of Quantum Information 16, no. 08 (December 2018): 1840001. http://dx.doi.org/10.1142/s0219749918400014.
Full textAbstract:
The goal of this work is to define a notion of a “quantum neural network” to classify data, which exploits the low-energy spectrum of a local Hamiltonian. As a concrete application, we build a binary classifier, train it on some actual data and then test its performance on a simple classification task. More specifically, we use Microsoft’s quantum simulator, LIQ[Formula: see text][Formula: see text], to construct local Hamiltonians that can encode trained classifier functions in their ground space, and which can be probed by measuring the overlap with test states corresponding to the data to be classified. To obtain such a classifier Hamiltonian, we further propose a training scheme based on quantum annealing which is completely closed-off to the environment and which does not depend on external measurements until the very end, avoiding unnecessary decoherence during the annealing procedure. For a network of size [Formula: see text], the trained network can be stored as a list of [Formula: see text] coupling strengths. We address the question of which interactions are most suitable for a given classification task, and develop a qubit-saving optimization for the training procedure on a simulated annealing device. Furthermore, a small neural network to classify colors into red versus blue is trained and tested, and benchmarked against the annealing parameters.
34
Shin, Changho, Sunghwan Joo, Jaeryun Yim, Hyoseop Lee, Taesup Moon, and Wonjong Rhee. "Subtask Gated Networks for Non-Intrusive Load Monitoring." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 1150–57. http://dx.doi.org/10.1609/aaai.v33i01.33011150.
Full textAbstract:
Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a household’s aggregate electricity consumption is broken down into electricity usages of individual appliances. In this way, the cost and trouble of installing many measurement devices over numerous household appliances can be avoided, and only one device needs to be installed. The problem has been well-known since Hart’s seminal paper in 1992, and recently significant performance improvements have been achieved by adopting deep networks. In this work, we focus on the idea that appliances have on/off states, and develop a deep network for further performance improvements. Specifically, we propose a subtask gated network that combines the main regression network with an on/off classification subtask network. Unlike typical multitask learning algorithms where multiple tasks simply share the network parameters to take advantage of the relevance among tasks, the subtask gated network multiply the main network’s regression output with the subtask’s classification probability. When standby-power is additionally learned, the proposed solution surpasses the state-of-the-art performance for most of the benchmark cases. The subtask gated network can be very effective for any problem that inherently has on/off states.
35
Peppas, Konstantinos, Apostolos C. Tsolakis, Stelios Krinidis, and Dimitrios Tzovaras. "Real-Time Physical Activity Recognition on Smart Mobile Devices Using Convolutional Neural Networks." Applied Sciences 10, no. 23 (November 27, 2020): 8482. http://dx.doi.org/10.3390/app10238482.
Full textAbstract:
Given the ubiquity of mobile devices, understanding the context of human activity with non-intrusive solutions is of great value. A novel deep neural network model is proposed, which combines feature extraction and convolutional layers, able to recognize human physical activity in real-time from tri-axial accelerometer data when run on a mobile device. It uses a two-layer convolutional neural network to extract local features, which are combined with 40 statistical features and are fed to a fully-connected layer. It improves the classification performance, while it takes up 5–8 times less storage space and outputs more than double the throughput of the current state-of-the-art user-independent implementation on the Wireless Sensor Data Mining (WISDM) dataset. It achieves 94.18% classification accuracy on a 10-fold user-independent cross-validation of the WISDM dataset. The model is further tested on the Actitracker dataset, achieving 79.12% accuracy, while the size and throughput of the model are evaluated on a mobile device.
36
Abu Al-Haija, Qasem, and Saleh Zein-Sabatto. "An Efficient Deep-Learning-Based Detection and Classification System for Cyber-Attacks in IoT Communication Networks." Electronics 9, no. 12 (December 15, 2020): 2152. http://dx.doi.org/10.3390/electronics9122152.
Full textAbstract:
With the rapid expansion of intelligent resource-constrained devices and high-speed communication technologies, the Internet of Things (IoT) has earned wide recognition as the primary standard for low-power lossy networks (LLNs). Nevertheless, IoT infrastructures are vulnerable to cyber-attacks due to the constraints in computation, storage, and communication capacity of the endpoint devices. From one side, the majority of newly developed cyber-attacks are formed by slightly mutating formerly established cyber-attacks to produce a new attack that tends to be treated as normal traffic through the IoT network. From the other side, the influence of coupling the deep learning techniques with the cybersecurity field has become a recent inclination of many security applications due to their impressive performance. In this paper, we provide the comprehensive development of a new intelligent and autonomous deep-learning-based detection and classification system for cyber-attacks in IoT communication networks that leverage the power of convolutional neural networks, abbreviated as IoT-IDCS-CNN (IoT based Intrusion Detection and Classification System using Convolutional Neural Network). The proposed IoT-IDCS-CNN makes use of high-performance computing that employs the robust Compute Unified Device Architectures (CUDA) based Nvidia GPUs (Graphical Processing Units) and parallel processing that employs high-speed I9-core-based Intel CPUs. In particular, the proposed system is composed of three subsystems: a feature engineering subsystem, a feature learning subsystem, and a traffic classification subsystem. All subsystems were developed, verified, integrated, and validated in this research. To evaluate the developed system, we employed the Network Security Laboratory-Knowledge Discovery Databases (NSL-KDD) dataset, which includes all the key attacks in IoT computing. The simulation results demonstrated a greater than 99.3% and 98.2% cyber-attack classification accuracy for the binary-class classifier (normal vs. anomaly) and the multiclass classifier (five categories), respectively. The proposed system was validated using a K-fold cross-validation method and was evaluated using the confusion matrix parameters (i.e., true negative (TN), true positive (TP), false negative (FN), false positive (FP)), along with other classification performance metrics, including precision, recall, F1-score, and false alarm rate. The test and evaluation results of the IoT-IDCS-CNN system outperformed many recent machine-learning-based IDCS systems in the same area of study.
37
Tran, Ky, Sid Keene, Erik Fretheim, and Michail Tsikerdekis. "Marine Network Protocols and Security Risks." Journal of Cybersecurity and Privacy 1, no. 2 (April 14, 2021): 239–51. http://dx.doi.org/10.3390/jcp1020013.
Full textAbstract:
Marine network protocols are domain-specific network protocols that aim to incorporate particular features within the specialized marine context that devices are implemented in. Devices implemented in such vessels involve critical equipment; however, limited research exists for marine network protocol security. In this paper, we provide an analysis of several marine network protocols used in today’s vessels and provide a classification of attack risks. Several protocols involve known security limitations, such as Automated Identification System (AIS) and National Marine Electronic Association (NMEA) 0183, while newer protocols, such as OneNet provide more security hardiness. We further identify several challenges and opportunities for future implementations of such protocols.
38
Umadevi, K. S., Arpita Ghosh, and Shalu Achamma Sam. "A Classification Algorithm to Reduce Data Redundancy in Wireless Sensor Networks." Advanced Science Letters 24, no. 8 (August 1, 2018): 6020–24. http://dx.doi.org/10.1166/asl.2018.12239.
Full textAbstract:
Middleware acts in between the application level and the lower level constructs which solve many wireless sensor network challenges. Still, middleware poses a number of issues such as energy constraint of devices, scalability, mobility, heterogeneity, data aggregation, data redundancy, dynamic networking requirements, security and Quality of Service. If data redundancy is reduced, then data aggregation and energy-related issues in middleware can be solved. An efficient middleware must have the ability to aggregate data from devices in such a way that data redundancy is reduced and hence, the amount of data transmitted to the sink is decreased. Classification algorithms can be used in middleware to reduce the duplication of data. Here, we use k-nearest neighbour algorithm for classification in order to prevent data redundancy in wireless sensor networks.
39
Cai, Yu. "Mobile Agent Based Network Defense System in Enterprise Network." International Journal of Handheld Computing Research 2, no. 1 (January 2011): 41–54. http://dx.doi.org/10.4018/jhcr.2011010103.
Full textAbstract:
Security has become the Achilles’ heel of many organizations in today’s computer-dominated society. In this paper, a configurable intrusion detection and response framework named Mobile Agents based Distributed (MAD) security system was proposed for enterprise network consisting of a large number of mobile and handheld devices. The key idea of MAD is to use autonomous mobile agents as lightweight entities to provide unified interfaces for intrusion detection, intrusion response, information fusion, and dynamic reconfiguration. These lightweight agents can be easily installed and managed on mobile and handheld devices. The MAD framework includes a family of autonomous agents, servers and software modules. An Object-based intrusion modeling language (mLanguage) is proposed to allow easy data sharing and system control. A data fusion engine (mEngine) is used to provide fused results for traffic classification and intrusion identification. To ensure Quality-of-Service (QoS) requirements for end users, adaptive resource allocation scheme is also presented. It is hoped that this project will advance the understanding of complex, interactive, and collaborative distributed systems.
40
Civelek, Muhsin, and Adnan Yazici. "Object Extraction and Classification in Video Surveillance Applications." European Review 25, no. 2 (December 19, 2016): 246–59. http://dx.doi.org/10.1017/s1062798716000582.
Full textAbstract:
In this paper we review a number of methods used in video surveillance applications in order to detect and classify threats. Moreover, the use of those methods in wireless surveillance networks contributes to decreasing the energy consumption of the devices because it reduces the amount of information transferred through the network. In this paper we focus on the most popular object extraction and classification methods that are used in both wired and wireless surveillance applications. We also develop an application for identification of objects from video data by implementing the selected methods and demonstrate the performance of these methods on pre-recorded videos using the outputs of this application.
41
Velichko, Andrei. "Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map." Electronics 9, no. 9 (September 2, 2020): 1432. http://dx.doi.org/10.3390/electronics9091432.
Full textAbstract:
This study presents a neural network which uses filters based on logistic mapping (LogNNet). LogNNet has a feedforward network structure, but possesses the properties of reservoir neural networks. The input weight matrix, set by a recurrent logistic mapping, forms the kernels that transform the input space to the higher-dimensional feature space. The most effective recognition of a handwritten digit from MNIST-10 occurs under chaotic behavior of the logistic map. The correlation of classification accuracy with the value of the Lyapunov exponent was obtained. An advantage of LogNNet implementation on IoT devices is the significant savings in memory used. At the same time, LogNNet has a simple algorithm and performance indicators comparable to those of the best resource-efficient algorithms available at the moment. The presented network architecture uses an array of weights with a total memory size from 1 to 29 kB and achieves a classification accuracy of 80.3–96.3%. Memory is saved due to the processor, which sequentially calculates the required weight coefficients during the network operation using the analytical equation of the logistic mapping. The proposed neural network can be used in implementations of artificial intelligence based on constrained devices with limited memory, which are integral blocks for creating ambient intelligence in modern IoT environments. From a research perspective, LogNNet can contribute to the understanding of the fundamental issues of the influence of chaos on the behavior of reservoir-type neural networks.
42
Subahi, Alanoud, and George Theodorakopoulos. "Detecting IoT User Behavior and Sensitive Information in Encrypted IoT-App Traffic." Sensors 19, no. 21 (November 3, 2019): 4777. http://dx.doi.org/10.3390/s19214777.
Full textAbstract:
Many people use smart-home devices, also known as the Internet of Things (IoT), in their daily lives. Most IoT devices come with a companion mobile application that users need to install on their smartphone or tablet to control, configure, and interface with the IoT device. IoT devices send information about their users from their app directly to the IoT manufacturer’s cloud; we call this the ”app-to-cloud way”. In this research, we invent a tool called IoT-app privacy inspector that can automatically infer the following from the IoT network traffic: the packet that reveals user interaction type with the IoT device via its app (e.g., login), the packets that carry sensitive Personal Identifiable Information (PII), the content type of such sensitive information (e.g., user’s location). We use Random Forest classifier as a supervised machine learning algorithm to extract features from network traffic. To train and test the three different multi-class classifiers, we collect and label network traffic from different IoT devices via their apps. We obtain the following classification accuracy values for the three aforementioned types of information: 99.4%, 99.8%, and 99.8%. This tool can help IoT users take an active role in protecting their privacy.
43
He, Yan, Bin Fu, Jian Yu, Renfa Li, and Rucheng Jiang. "Efficient Learning of Healthcare Data from IoT Devices by Edge Convolution Neural Networks." Applied Sciences 10, no. 24 (December 15, 2020): 8934. http://dx.doi.org/10.3390/app10248934.
Full textAbstract:
Wireless and mobile health applications promote the development of smart healthcare. Effective diagnosis and feedbacks of remote health data pose significant challenges due to streaming data, high noise, network latency and user privacy. Therefore, we explore efficient edge and cloud design to maintain electrocardiogram classification performance while reducing the communication cost. These contributions include: (1) We introduce a hybrid smart medical architecture named edge convolutional neural networks (EdgeCNN) that balances the capability of edge and cloud computing to address the issue for agile learning of healthcare data from IoT devices. (2) We present an effective deep learning model for electrocardiogram (ECG) inference, which can be deployed to run on edge smart devices for low-latency diagnosis. (3) We design a data enhancement method for ECG based on deep convolutional generative adversarial network to expand ECG data volume. (4) We carried out experiments on two representative datasets to evaluate the effectiveness of the deep learning model of ECG classification based on EdgeCNN. EdgeCNN shows superior to traditional cloud medical systems in terms of network Input/Output (I/O) pressure, architecture cost and system high availability. The deep learning model not only ensures high diagnostic accuracy, but also has advantages in aspect of inference time, storage, running memory and power consumption.
44
Bachratá, Katarína, Katarína Buzáková, Michal Chovanec, Hynek Bachratý, Monika Smiešková, and Alžbeta Bohiniková. "Classification of Red Blood Cell Rigidity from Sequence Data of Blood Flow Simulations Using Neural Networks." Symmetry 13, no. 6 (May 26, 2021): 938. http://dx.doi.org/10.3390/sym13060938.
Full textAbstract:
Numerical models for the flow of blood and other fluids can be used to design and optimize microfluidic devices computationally and thus to save time and resources needed for production, testing, and redesigning of the physical microfluidic devices. Like biological experiments, computer simulations have their limitations. Data from both the biological and the computational experiments can be processed by machine learning methods to obtain new insights which then can be used for the optimization of the microfluidic devices and also for diagnostic purposes. In this work, we propose a method for identifying red blood cells in flow by their stiffness based on their movement data processed by neural networks. We describe the performed classification experiments and evaluate their accuracy in various modifications of the neural network model. We outline other uses of the model for processing data from video recordings of blood flow. The proposed model and neural network methodology classify healthy and more rigid (diseased) red blood cells with the accuracy of about 99.5% depending on the selected dataset that represents the flow of a suspension of blood cells of various levels of stiffness.
45
Lotz, W. A., M. Vountas, T. Dinter, and J. P. Burrows. "Cloud and surface classification using SCIAMACHY polarization measurement devices." Atmospheric Chemistry and Physics Discussions 8, no. 3 (May 28, 2008): 9855–81. http://dx.doi.org/10.5194/acpd-8-9855-2008.
Full textAbstract:
Abstract. A simple scheme has been developed to discriminate surface, sun glint and cloud properties in satellite based spectrometer data utilizing visible and near infrared information. It has been designed for the use with data measured by SCIAMACHY's (SCanning Imaging Absorption SpectroMeter for Atmospheric CHartographY) Polarization Measurement Devices but the applicability is not strictly limited to this instrument. The scheme is governed by a set of constraints and thresholds developed by using satellite imagery and meteorological data. Classification targets are ice, water and generic clouds, sun glint and surface parameters, such as water, snow/ice, desert and vegetation. The validation is done using MERIS (MEdium Resolution Imaging Spectrometer) and meteorological data from METAR (MÉTéorologique Aviation Régulière – a network for the provision of meteorological data for aviation). Qualitative and quantitative validation using MERIS satellite imagery shows good agreement. The comparison with METAR data exhibits very good agreement.
46
Nachiappan, V. Alagammai, Raj esh, and Rajalakshmi Devaraj. "Remote Diagnosis of the Patient through IOT and Virtual Reality, Classification of the Cloud Data Using ANN." Revista Gestão Inovação e Tecnologias 11, no. 1 (June 29, 2021): 6025–34. http://dx.doi.org/10.47059/revistageintec.v11i1.1876.
Full textAbstract:
Telemedicine was an existing field, but the current situation its becoming a more important necessity in the health care industry.my major aim is To increase the reliability of the online diagnosis using IoT and virtual Reality for the future with help of advanced technologies. Bridge between the patients and doctors. Patients may have wearable devices with AR glass, the measured data will be send to the raspberry pi based router device which is having the Node Red Software for connecting N- no of patients easily and also control the devices remotely based on the self-learning algorithms. All the information can be classified based on type of diseases and classified based on artificial neural network-based algorithms, the information is passed to doctors. Doctor may also have device with wearable Glass, with patient information and details will be displayed on the AR glass. So, we can connect N- of Patients and N- doctors with this technology also sharing the information through the cloud and IOT devices, which will help for the current trend and future technology for the society.
47
Marinucci, Daniele, Agnese Sbrollini, Ilaria Marcantoni, Micaela Morettini, Cees A. Swenne, and Laura Burattini. "Artificial Neural Network for Atrial Fibrillation Identification in Portable Devices." Sensors 20, no. 12 (June 24, 2020): 3570. http://dx.doi.org/10.3390/s20123570.
Full textAbstract:
Atrial fibrillation (AF) is a common cardiac disorder that can cause severe complications. AF diagnosis is typically based on the electrocardiogram (ECG) evaluation in hospitals or in clinical facilities. The aim of the present work is to propose a new artificial neural network for reliable AF identification in ECGs acquired through portable devices. A supervised fully connected artificial neural network (RSL_ANN), receiving 19 ECG features (11 morphological, 4 on F waves and 4 on heart-rate variability (HRV)) in input and discriminating between AF and non-AF classes in output, was created using the repeated structuring and learning (RSL) procedure. RSL_ANN was created and tested on 8028 (training: 4493; validation: 1125; testing: 2410) annotated ECGs belonging to the “AF Classification from a Short Single Lead ECG Recording” database and acquired with the portable KARDIA device by AliveCor. RSL_ANN performance was evaluated in terms of area under the curve (AUC) and confidence intervals (CIs) of the received operating characteristic. RSL_ANN performance was very good and very similar in training, validation and testing datasets. AUC was 91.1% (CI: 89.1–93.0%), 90.2% (CI: 86.2–94.3%) and 90.8% (CI: 88.1–93.5%) for the training, validation and testing datasets, respectively. Thus, RSL_ANN is a promising tool for reliable identification of AF in ECGs acquired by portable devices.
48
Lin, Yun, Ya Tu, and Zheng Dou. "An Improved Neural Network Pruning Technology for Automatic Modulation Classification in Edge Devices." IEEE Transactions on Vehicular Technology 69, no. 5 (May 2020): 5703–6. http://dx.doi.org/10.1109/tvt.2020.2983143.
Full text
49
Browne, David, Michael Giering, and Steven Prestwich. "PulseNetOne: Fast Unsupervised Pruning of Convolutional Neural Networks for Remote Sensing." Remote Sensing 12, no. 7 (March 29, 2020): 1092. http://dx.doi.org/10.3390/rs12071092.
Full textAbstract:
Scene classification is an important aspect of image/video understanding and segmentation. However, remote-sensing scene classification is a challenging image recognition task, partly due to the limited training data, which causes deep-learning Convolutional Neural Networks (CNNs) to overfit. Another difficulty is that images often have very different scales and orientation (viewing angle). Yet another is that the resulting networks may be very large, again making them prone to overfitting and unsuitable for deployment on memory- and energy-limited devices. We propose an efficient deep-learning approach to tackle these problems. We use transfer learning to compensate for the lack of data, and data augmentation to tackle varying scale and orientation. To reduce network size, we use a novel unsupervised learning approach based on k-means clustering, applied to all parts of the network: most network reduction methods use computationally expensive supervised learning methods, and apply only to the convolutional or fully connected layers, but not both. In experiments, we set new standards in classification accuracy on four remote-sensing and two scene-recognition image datasets.
50
Sun, Baofeng, and Wanzhong Chen. "CLASSIFICATION OF sEMG SIGNALS USING INTEGRATED NEURAL NETWORK WITH SMALL SIZED TRAINING DATA." Biomedical Engineering: Applications, Basis and Communications 24, no. 04 (August 2012): 365–76. http://dx.doi.org/10.4015/s1016237212500329.
Full textAbstract:
The sEMG (Surface electromyography) signals detected from activated muscles can be used as a control source for prosthesis. So an efficient and accurate method for the classification of sEMG signal patterns has become a hot research in recent years. Artificial neural network is a popular used method in this field, however, most neural networks require large numbers of samples in the training stage to obtain the potential relationships between input feature vectors and the outputs. In this paper, Integrated back propagation neural network (IBPNN) is used to classify sEMG signals acquired during five different hand motions. The correct classification rates of IBPNN for the five hand movements are significantly higher than that of BPNN and Elman neural network. This reveals that IBPNN achieves the best performance with a small sized training data and can be used in control systems on prosthetic hands and other robotic devices based on electromyography pattern recognition.