A high-precision automatic diagnosis method of maize developmental stage based on ensemble deep learning with IoT devices

Investigation on identify the multiple issues in IoT devices using Convolutional Neural Network

The development and implementation of Internet of Things (IoT) devices have accelerated dramatically in recent years. As a result, a robust network infrastructure is required to handle the massive volumes of data collected and transmitted to these devices. Fifth-generation (5G) is a new, comprehensive wireless system with the potential to be the primary enabling technology for the IoT. However, the rapid spread of IoT devices presents significant security challenges. Consequently, new and serious security and privacy risks have emerged. Attackers often exploit IoT devices to launch large-scale attacks, such as the Distributed Denial of Service (DDoS) attack. Recent research shows that deep learning methods are effective in identifying and preventing DDoS attacks. In this paper, we applied four deep learning algorithms: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Feedforward Neural Network (FNN), and Deep Neural Network (DNN). We compared the results of these algorithms with three machine learning methods: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Stochastic Gradient Descent (SGD). These methods were used to detect DDoS attacks in a dataset specifically designed for IoT devices within 5G networks. We constructed the 5G network infrastructure using OMNeT++ with the INET and Simu5G frameworks. The dataset encompasses both normal network traffic and DDoS attacks. CNN, FNN, SVM, SGD, and KNN achieved high accuracy, with results reaching up to 99%. In contrast, LSTM and DNN showed significantly lower accuracy. These results demonstrate that deep and machine learning can improve the protection of IoT devices in 5G networks.

Anomaly-based intrusion detection system in the Internet of Things using a convolutional neural network and multi-objective enhanced Capuchin Search Algorithm

Connecting food supply chains

The growing number of Internet of Things (IoT) devices has resulted in a significant surge in network attacks, frequently causing harmful and catastrophic consequences. Malicious actors may utilize these devices to infiltrate the network infrastructure by taking advantage of hardware and software weaknesses through uninterrupted internet access. Despite significant advancements in the field of network IDS (Intrusion Detection System), there is still a lack of employing intrusion detectors in IoT environments. Hence, to address this issue, a neural network model-based intrusion detection system is introduced, which can effectively detect and classify various types of attacks on IoT devices used in intelligent applications. A feature reduction technique and a hyperparameter optimization strategy to reduce both the computing time and overhead were utilized. Important features chosen via a genetic algorithm-based feature selection model are transformed into colour images for use as input to several Convolutional Neural Network (CNN) architectures, including Xception, VGG16, and VGG19 models. The suggested ensemble model, which combines Xception, VGG16, and VGG19 classifiers using a genetic algorithm to select the most relevant features, is 98.7% accurate, which is 5% better than individual classifiers. This novel approach significantly reduces false positives while cutting computational latency when compared to existing models. By optimizing both detection speed and accuracy, the proposed system enables real-time intrusion detection, offering a scalable and efficient solution for securing IoT devices in smart environments. These advancements underscore the system’s potential to set a new standard in IoT security.

Poor road conditions play a significant role in road accidents as well as damage to the structural integrity of the vehicle. Detecting potholes on the roads is an essential step toward preventing road accidents. Pothole detection can be a challenging task due to their irregular shape and inconsistent size. With new innovations in artificial intelligence (AI), machine learning (ML), and deep learning (DL), it is possible to learn semantic features to address real-world problems in numerous applications. Internet of Thing (IoT) devices have proven to be a vital instrument for in situ measurements and source of real-time information. This chapter focuses a framework for automated detection and counting of potholes for real-time monitoring of roads using IoT devices integrated with a DL technique. The framework precisely detects and counts the potholes in real time, via video feed of the road from a vehicle-mounted dashcam connected to an IoT device. Detection of potholes is achieved using convolution neural network (CNN)-based algorithm, trained on more than 22,000 images of potholes. The study compares the efficacy of faster Region Based Convolutional Neural Networks (R-CNN) and single shot detection (SSD) MobileNet network architectures in the context of pothole detection and road monitoring under different illumination conditions. The models were compared based on their performance against accuracy and inference speed. In case of accuracy, Faster R-CNN outperformed the SSD MobileNet, with f-score averaging 93.59% under different illumination conditions, whereas SSD MobileNet depicted accuracy of 89.58%. However, SSD MobileNet could detect the potholes faster. The model is further coupled with DeepSORT tracking algorithm to track and count the potholes detected; the tracking algorithm also ensures that each pothole in the video frame is accounted only once. The model was deployed into Raspberry Pi single-board micro-computer for real-time road monitoring. In order to enhance the inference speed on the IoT device, Edge Tensor processing unit (TPU)-based machine learning acceleration is implemented using Google coral USB accelerator. The real-time inspection results show that the proposed “pothole detection” system achieves an accuracy of 89.58% at seven frames per second. The framework developed is the part of research on integration of IoT with machine learning; the framework provides scope for future researchers to enhance and carry out value addition of information on many other parameters for the benefit of research community and society.

This paper proposes a condition monitoring method for the early defect detection in a chain sprocket drive (CSD) system and classification of fault types before a catastrophic failure occurs. In the operation of a CSD system, early defect detection is very useful in preventing system failure. In this work, eight fault types associated with the CSD system components, such as the gear tooth, bearings, and drive motor shaft, were arbitrarily damaged and incorporated into the CSD system. To detect the fault signals during the CSD system operation, the vibration was measured using an Internet of Things (IoT) device, which features a wireless MEMS accelerometer, Bluetooth function, Wi-Fi function, and battery. The IoT device was mounted on the gearbox housing. The measured one-dimensional vibration time-series was transformed into time-scale images using continuous wavelet transform (CWT). A convolution neural network (CNN) was employed to extract deep features embedded in the images, which are closely related to fault types. To update the learning parameters of the CNN, the RMSprop learning algorithm was applied, and the CNN was trained using 500 image samples. Multiple-classification performance of the trained network was tested using 100 image samples. Feature maps for different fault types were obtained from the final CNN convolution layer. For the visualization of fault types, t-stochastic neighbor embedding was employed and applied to the feature maps to convert high-dimensional data into two-dimensional data. Two-dimensional features enabled excellent classification of the eight fault types and one normal type.

MicroNets: A multi-phase pruning pipeline to deep ensemble learning in IoT devices

Security, privacy, and interoperability challenges have arisen as the Internet of Things (IoT) devices proliferate and become increasingly connected. IoT devices have resource constraints such as computational capabilities, power consumption, onboard storage, and network bandwidth, which limit the implementation of cryptographic solutions. The heterogeneous nature of IoT devices makes them an avenue for attackers to exploit threats like spoofing, routing, MITM, and DoS attacks. With the current sophistication of threats IoT devices are subjected to, an Intrusion Detection System (IDS) is the preferred solution for IoT devices. An IDS continuously monitors incoming traffic and discovers potential threats in incoming and outgoing traffic. This research proposes a novel intelligent ensemble-based IDS that will reside in the IoT gateway. The uniqueness of our approach lies in an ensemble learning approach that combines multiple machine learning methods to improve prediction performance and detection accuracy. Ensemble learning has been studied to increase the detection rate while obtaining better generalization performance due to combining several Machine Learning (ML) models, also known as base learners. Three popularly known ensemble models (i.e., boosting, stacking, and voting) are employed to assess our proposed IDS performance. The proposed method use algorithms such as Naïve Bayes (NB), Support Vector Classification (SVC), and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> -Nearest Neighbors ( <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> NN). Lastly, the proposed approach will be evaluated on two publicly available datasets; Intrusion Detection Evaluation Dataset (CIC-IDS2017) and N-BaIoT.

The challenge of authenticating Internet of Things (IoT) devices, particularly in low-cost deployments with constrained nodes that struggle with dynamic re-keying solutions, renders these devices susceptible to various attacks. This paper introduces a robust alternative mitigation strategy based on Physical-Layer Authentication (PLA), which leverages the intrinsic physical layer characteristics of IoT devices. These unique imperfections, stemming from the manufacturing process of IoT electronic integrated circuits (ICs), are difficult to replicate or falsify and vary with each function executed by the IoT device. We propose a novel lightweight authentication scheme, MAG-PUFs, that uses the unintentional Electromagnetic (EM) emissions from IoT devices as Physical Unclonable Functions (PUFs). MAG-PUFs operate by collecting these unintentional EM emissions during the execution of pre-defined reference functions by the IoT devices. The authentication is achieved by matching these emissions with profiles recorded at the time of enrollment, using state-of-the-art Deep Learning (DL) approaches such as Neural Networks (NN) and Autoencoders. Notably, MAG-PUFs offer compelling advantages: (i) it preserves privacy, as it does not require direct access to the IoT devices; and, (ii) it provides unique flexibility, permitting the selection of numerous and varied reference functions. We rigorously evaluated MAG-PUFs using 25 Arduino devices and a diverse set of 325 reference function classes. Employing a DL framework, we achieved a minimum authentication F1-Score of 0.99. Furthermore, the scheme’s efficacy in detecting impostor EM emissions was also affirmed, achieving a minimum F1-Score of 0.99. We also compared our solution to other solutions in the literature, showing its remarkable performance. Finally, we discussed code obfuscation techniques and the impact of Radio Frequency (RF) interference on the IoT authentication process.

As digital infrastructure continues to expand, networks, web services, and Internet of Things (IoT) devices become increasingly vulnerable to distributed denial of service (DDoS) attacks. Remarkably, IoT devices have become attracted to DDoS attacks due to their common deployment and limited applied security measures. Therefore, attackers take advantage of the growing number of unsecured IoT devices to reflect massive traffic that overwhelms networks and disrupts necessary services, making protection of IoT devices against DDoS attacks a major concern for organizations and administrators. In this paper, the effectiveness of supervised machine learning (ML) classification and deep learning (DL) algorithms in detecting DDoS attacks on IoT networks was investigated by conducting an extensive analysis of network traffic dataset (legitimate and malicious). The performance of the models and data quality improved when emphasizing the impact of feature selection and data pre-processing approaches. Five machine learning models were evaluated by utilizing the Edge-IIoTset dataset: Random Forest (RF), Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and K-Nearest Neighbors (KNN) with multiple K values, and Convolutional Neural Network (CNN). Findings revealed that the RF model outperformed other models by delivering optimal detection speed and remarkable performance across all evaluation metrics, while KNN (K = 7) emerged as the most efficient model in terms of training time.

DeL-IoT: A deep ensemble learning approach to uncover anomalies in IoT

Smart home consists of various Internet of things (IoT) devices. These IoT devices are designed to help and simplify people’s lives. The technical progress of the IoT field is aimed at simplifying human life, thereby creating new cyber threats. Different scientific papers are mentioned that number of IoT devices is growing constantly by 15% per year. As a result, around 1.6 billion IoT devices will be used globally over the internet. It means that IoT devices will be accessed over internet by consumers. Nowadays, Internet is accessible easily by everyone, so they can afford freely the ecosystem of IoT devices at home. Within this development of IoT ecosystem, consumers can face serious problems of transmission and storage of information by IoT devices. These problems might be data theft from IoT devices, using such IoT devices for Denial of Service (DoS) attacks, user tracking and so on. Local cyber threats provide an opportunity for an attacker to gain access to a home network and take advantages of it. Global cyber threats are dangerous because IoT devices can be controlled remotely from anywhere in the world without the knowledge of the user. One of the risks is that the user’s home network of IoT devices could be controlled by botnets to carry out cyber-attacks. The article describes and analyzes current threats to IoT smart home devices and provides examples of data collected and processed by smart devices. Collecting information about users through IoT devices is a novelty of this work.

This paper proposes and analyses a lightweight Convolutional Neural Network (CNN) based anomaly detection framework for Internet of Things (IoT) devices. IoT security has become a massive concern in recent years. IoT devices form the backbone of much of the critical infrastructure we have today. From power stations to biomedical devices, there is the potential of heavy financial damage and loss of human life if they become compromised. As IoT adoption accelerates, the amount of cyberattacks on IoT devices increases substantially. Due to the resource constrained nature of IoT devices, no security solution addresses all concerns in the IoT field. By training models based on normal power consumption behaviour, a wide range of anomalies can be detected in the power time series data of the IoT device. The methodology proposed in this paper is generic in nature, making it applicable to every IoT device on the market. The work in this paper is implemented at the edge, on an ultra-low-power microcontroller.

With the improvement of intelligence and interconnection, Internet of Things (IoT) devices tend to become more vulnerable and exposed to many threats. Device identification is the foundation of many cybersecurity operations, such as asset management, vulnerability reaction, and situational awareness, which are important for enhancing the security of IoT devices. The more information sources and the more angles of view we have, the more precise identification results we obtain. This study proposes a novel and alternative method for IoT device identification, which introduces commonly available WebUI login pages with distinctive characteristics specific to vendors as the data source and uses an ensemble learning model based on a combination of Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) for device vendor identification and develops an Optical Character Recognition (OCR) based method for device type and model identification. The experimental results show that the ensemble learning model can achieve 99.1% accuracy and 99.5% F1-Score in the determination of whether a device is from a vendor that appeared in the training dataset, and if the answer is positive, 98% accuracy and 98.3% F1-Score in identifying which vendor it is from. The OCR-based method can identify fine-grained attributes of the device and achieve an accuracy of 99.46% in device model identification, which is higher than the results of the Shodan cyber search engine by a considerable margin of 11.39%.