Spectrum Sensing Using Optimized Deep Learning Techniques in Reconfigurable Embedded Systems

Internet of Things (IoT) technology has been incorporated into the majority of people’s everyday lives and places of employment due to the quick development in information technology. Modern agricultural techniques increasingly use the well-known and superior approach of managing a farm known as “smart farming”. Utilizing a variety of information and agricultural technologies, crops are observed for their general health and productivity. This requires monitoring the condition of field crops and looking at many other indicators. The goal of smart agriculture is to reduce the amount of money spent on agricultural inputs while keeping the quality of the final product constant. The Internet of Things (IoT) has made smart agriculture possible through data collection and storage techniques. For example, modern irrigation systems use effective sensor networks to collect field data for the best plant irrigation. Smart agriculture will become more susceptible to cyber-attacks as its reliance on the IoT ecosystem grows, because IoT networks have a large number of nodes but limited resources, which makes security a difficult issue. Hence, it is crucial to have an intrusion detection system (IDS) that can address such challenges. In this manuscript, an IoT-based privacy-preserving anomaly detection model for smart agriculture has been proposed. The motivation behind this work is twofold. Firstly, ensuring data privacy in IoT-based agriculture is of the utmost importance due to the large volumes of sensitive information collected by IoT devices, including on environmental conditions, crop health, and resource utilization data. Secondly, the timely detection of anomalies in smart agriculture systems is critical to enable proactive interventions, such as preventing crop damage, optimizing resource allocation, and ensuring sustainable farming practices. In this paper, we propose a privacy-encoding-based enhanced deep learning framework for the difficulty of data encryption and intrusion detection. In terms of data encoding, a novel method of a sparse capsule-auto encoder (SCAE) is proposed along with feature selection, feature mapping, and feature normalization. An SCAE is used to convert information into a new encrypted format in order to prevent deduction attacks. An attention-based gated recurrent unit neural network model is proposed to detect the intrusion. An AGRU is an advanced version of a GRU which is enhanced by an attention mechanism. In the results section, the proposed model is compared with existing deep learning models using two public datasets. Parameters such as recall, precision, accuracy, and F1-score are considered. The proposed model has accuracy, recall, precision, and F1-score of 99.9%, 99.7%, 99.9%, and 99.8%, respectively. The proposed method is compared using a variety of machine learning techniques such as the deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), and long short-term memory (LSTM).

In future wireless systems, efficient spectrum usage enabled by technologies such as cognitive radio (CR), dynamic spectrum access, non-orthogonal multiuser within licensed and unlicensed band requires knowledge of prevalence situation in a frequency band through learning. It is critical for wireless devices to identify the type and number of users and their waveforms in a frequency band at a given time. In this paper, this problem is formulated as a multi-class classification problem for accurate spectrum situation prediction under complicated coexistence scenarios. Deep learning is chosen for obtaining the statistics of the different coexisting wireless systems through learning from superimposed radio frequency (RF) data. Specifically, Deep Neural Network (DNN), Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) are adopted and designed. They are trained using real RF traces for different coexisting scenarios collected from a USRP based testbed to identify the presence of signals with varying levels of Signal to Noise Ratio, even when the signal is superimposed with other signals as sources of interference. Experimental results demonstrate the potential of deep learning for spectrum situation prediction under complicated coexistence scenarios.

Most of the existing Medium Access Control (MAC) layer protocols for the Internet of Things (IoT) model the traffic generated by each IoT device via random arrivals such as those in a Poisson process. Under this model, since it is implied that IoT device traffic cannot be predicted, only reactive MAC-layer protocols in which the network responds to the current traffic are viable. In contrast, recent work has demonstrated that the traffic generated by an individual IoT device can be predictable, thus enabling predictive network protocols at the MAC layer. In this paper, we investigate information-theoretic bounds on the predictability of IoT traffic of individual devices. To this end, first, we compare the performance achieved by the following state-of-the-art forecasters on individual IoT device traffic: Logistic Regression, Multi-Layer Perceptron (MLP), 1-Dimensional Convolutional Neural Network (1D CNN), and Long Short Term Memory (LSTM) as well as MLP under feature selection based on Analysis of Variance (ANOVA) and Auto-Correlation Function (ACF). Second, we quantify the gap between the performance of these forecasters against information-theoretic bounds as follows: For IoT devices that generate a fixed number of bits at each generation instance, we measure the gap between the forecasting accuracy and the information-theoretic bound established by Fano’s inequality on the probability of correct prediction. Our empirical results show that existing forecasting schemes perform close to the information-theoretic bound in this case. For IoT devices that generate a variable number of bits, we measure the gap between the Mean Square Error (MSE) and the estimation-theoretic counterpart to Fano’s inequality. Our empirical results show that the performance of existing forecasting schemes is far from the information-theoretic bound in this case. This work thus motivates the machine learning community to develop forecasting schemes that approach information-theoretic bounds. Furthermore, this work is expected to impact the development of predictive MAC-layer protocols that exploit these bounds.

Smart objects have grown in popularity and acceptance over the past period due to their decreasing size, greater intelligence, and lower costs. The Internet of Things (IoT) connects physical devices, including actuators, sensors, and cameras, to a network via the Internet. The widespread use of IoT devices has led to an exponential rise in network traffic volume and complexity, creating new challenges for real-time network security and threat detection. This study attempts to design an intrusion detection system which is scalable and capable of handling the vast number and variety of IoT traffic. It is based on improving the scalability and precision of the detection of threats by employing machine learning (ML) and deep learning (DL) techniques and hybrid model. The model is trained and tested on the CIC IoT DIAD 2024 dataset, a large high-volume dataset consisting of diversified IoT traffic, benign and malicious activity. It includes extensive data preprocessing, feature selection, and training of various models. Features were selected using an Analysis of Variance (ANOVA)–based feature selection technique to reduce computational overhead and time complexity while mitigating the curse of dimensionality and enhancing model accuracy. The resulting optimal feature subset was then used to train and evaluate several classifiers, including Decision Trees, K-Nearest Neighbors (KNN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and a hybrid CNN–LSTM model. The models are compared using typical measures of performance such as accuracy, precision, recall, F1-score, and confusion matrix. The results indicate that hybrid deep learning models specifically the CNN-LSTM outperformed the other models in recognizing binary attacks achieving the highest performance with accuracy of 94.08% followed by CNN and LSTM with accuracies of 93.37% and 93.24% respectively. In contrast, the traditional machine learning model, Decision trees demonstrated superior performance in multi-class classification, achieving an accuracy of 98.25% defeating KNN (90%) as well as the hybrid deep learning model (CNN-LSTM – 88.30%). This, work paves the foundation for the implementation of scalable intrusion detection models in real IoT infrastructures. The future of the work is to integrate the developed models using massive data streaming infrastructures in support of real-time intrusion detection in large-scale, dynamic IoT infrastructures.

Maxout neurons for deep convolutional and LSTM neural networks in speech recognition

Nowadays, traffic accidents are caused due to the distracted behaviors of drivers that have been noticed with the emergence of smartphones. Due to distracted drivers, more accidents have been reported in recent years. Therefore, there is a need to recognize whether the driver is in a distracted driving state, so essential alerts can be given to the driver to avoid possible safety risks. For supporting safe driving, several approaches for identifying distraction have been suggested based on specific gaze behavior and driving contexts. Thus, in this paper, a new Internet of Things (IoT)-assisted driver distraction detection model is suggested. Initially, the images from IoT devices are gathered for feature tuning. The set of convolutional neural network (CNN) methods like ResNet, LeNet, VGG 16, AlexNet GoogleNet, Inception-ResNet, DenseNet, Xception, and mobilenet are used, in which the best model is selected using Self Adaptive Grass Fibrous Root Optimization (SA-GFRO) algorithm. The optimal feature tuning CNN model processes the input images for obtaining the optimal features. These optimal features are fed into the long short-term memory (LSTM) for getting the classified distraction behaviors of the drivers. From the validation of the outcomes, the accuracy of the proposed technique is 95.89%. Accordingly, the accuracy of the existing techniques like SMO-LSTM, PSO-LSTM, JA-LSTM, and GFRO-LSTM is attained as 92.62%, 91.08%, 90.99%, and 89.87%, respectively, for dataset 1. Thus, the suggested model achieves better classification accuracy while detecting distracted behaviors of drivers and this model can support the drivers to continue with safe driving habits.

A cascaded federated deep learning based framework for detecting wormhole attacks in IoT networks

Online leakage current classification using convolutional neural network long short-term memory for high voltage insulators on web-based service

Extensive internet of things (IoT) devices being in-fected by malware are an increasingly important viable objective in IoT cyberattacks e.g., botnet, virus, trojan, etc. The botnets got leverage from unsecured IoT devices (e.g., CCTV, Raspberry Pi, Arduino Uno, ESP8266, etc) that operates by using the Internet traffic. In recent year, the high-profile IoT device’s vendor and the researcher from all over universities are exploring the robustness of IoT devices against botnet attacks. This research uses a deep learning approach to prevent botnet attacks on IoT networks. The deep residual one-dimensional CNN (1DCNN) model as the proposed method is used for botnet traffic detection. Two algorithms are provided: data processing for the N-BaIoT dataset and IoT botnet detection training and testing. For data processing, training, and testing, the datasets were evaluated, and the model was optimized with different optimizers. This research used RMS Prop, ADaDelta, AdaGrad, AdaMax, and Adam as optimizers and the CNN was compared with LSTM, CNN with RNN, and Deep residual 1DCNN, respectively. The results showed that Deep Residual 1DCNN with Adam has the highest training accuracy of 88.67%, 88.67% for validation accuracy, and 88.53%for test accuracy.

Security for IoT gadgets is an undertaking that has been made more troublesome by the far-reaching utilization of network safety in different applications, including wise modern frameworks, homes, individual devices, and vehicles. The fact that has been introduced makes deep learning for interruption recognition one productive security method. I thought about a few relevant systematic reviews that had already been written. Recent systematic reviews may include older and more recent works on the subject. For better IoT security, late exploration has focused on improving deep learning calculations. The ideal methodology for carrying out interruption recognition in the Internet of Things is determined by looking at the exhibition of different deep learning executions and investigating interruption location techniques that utilise them. Convolutional neural networks (CNNs), long short-term memory (LSTM), and gated recurrent units (GRUs) are the deep learning models used in this review. A standard dataset for IoT interruption identification is considered to evaluate the proposed model. The practical information is then investigated and diverged from current IoT interruption discovery strategies. In contrast with currently utilized approaches, the recommended strategy seems to have the best precision.

Semiconductor optical amplifier (SOA) is a promising solution for future O-band optical amplification. However, the SOA-induced nonlinearity will affect the quality of the signals and cause bit errors. Nowadays, the neural network is a hot topic in communication networks and has been considered a practical algorithm for signals equalization. In this paper, we investigate the performance of the three types of neural networks: deep neural networks (DNN), convolutional neural network (CNN), and long short term memory (LSTM) neural networks for the compensation of the SOA-induced nonlinearity. We first compare the fitting ability of the three neural networks on the saturated response of SOA. Based on the simulation result, LSTM has the best nonlinear expressiveness for the SOA-induced nonlinearity. Subsequently, we do some experimental validations in an intensity modulation and direct-detection (IM/DD) system, where the 100 Gbit/s pulse-amplitude-modulation-4 (PAM4) signals are transmitted over 80 km at O-band using an 18 GHz electro-absorption modulated laser (EML). The bit-error-ratio (BER) results show that the cell states in LSTM play a crucial role in nonlinearity compensation. Furthermore, LSTM offers the best equalization performance and can achieve a receiver sensitivity of −18.0 dBm.

In the realm of water resource management, meticulous monitoring and control methodologies are quintessential to the refinement of wastewater treatment processes. This research elucidates an avant-garde methodology for forecasting the Chemical Oxygen Demand (COD), an instrumental indicator of water quality, by harnessing the capabilities of long short-term memory (LSTM) neural networks in conjunction with Internet of Things (IoT) paradigms. The efficacy of the LSTM model is juxtaposed with that of an advanced Deep Belief Network (DBN), as well as contemporary models like a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) hybrid model and a Transformer-based model, employing data sourced from a wastewater treatment facility located in Changsha. The empirical findings show that notwithstanding the comparable training durations used, the LSTM model exhibits a preeminent error rate of merely 7%, thus surpassing the DBN model (which has an error rate of 35%), the CNN-LSTM model (registering a 22% error rate), and the Transformer-based model (with a 17% error rate) in its predictive precision. This research underscores the potential of integrating an astute wastewater control system with IoT and LSTM models, thereby hinting at prospective enhancements in the sustainability and operational efficacy of wastewater treatment installations.

The Internet of Things (IoT) holds transformative potential in fields such as power grid optimization, defense networks, and healthcare. However, the constrained processing capacities and resource limitations of IoT networks make them especially susceptible to cyber threats. This study addresses the problem of detecting intrusions in IoT environments by evaluating the performance of deep learning (DL) models under different data and algorithmic conditions. We conducted a comparative analysis of three widely used DL models—Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Bidirectional LSTM (biLSTM)—across four benchmark IoT intrusion detection datasets: BoTIoT, CiCIoT, ToNIoT, and WUSTL-IIoT-2021. Each model was assessed under balanced and imbalanced dataset configurations and evaluated using three loss functions (cross-entropy, focal loss, and dual focal loss). By analyzing model efficacy across these datasets, we highlight the importance of generalizability and adaptability to varied data characteristics that are essential for real-world applications. The results demonstrate that the CNN trained using the cross-entropy loss function consistently outperforms the other models, particularly on balanced datasets. On the other hand, LSTM and biLSTM show strong potential in temporal modeling, but their performance is highly dependent on the characteristics of the dataset. By analyzing the performance of multiple DL models under diverse datasets, this research provides actionable insights for developing secure, interpretable IoT systems that can meet the challenges of designing a secure IoT system.

Over the past few decades, research has focused heavily on automatic speech recognition (ASR). Although ASR for a few languages is close to reality; ASR for the low resource languages like Malayalam is still in its infancy. Here, in this work, the authors discuss the experiment conducted on accented data of Malayalam speech using two approaches. One approach uses the spectral features for modeling using deep convolutional neural network and the other uses the influential features of speech signals for modeling using LSTM-RNN approach. The proposed methodology comprises three distinct stages; dataset preparation, feature extraction, classification, and hence the construction of deep learning models that recognize the accent-based spoken sentences in the Malayalam language. Mel-frequency cepstral coefficient (MFCC) algorithm, short-term Fourier transform (STFT), and mel spectrogram methodologies are used for feature engineering and hence the features that represent the speech signals are used for constructing the accented ASR system for the Malayalam language using long short-term memory (LSTM) a recurrent neural network (RNN). The spectrogram dataset has been constructed for the speech dataset and used for constructing the ASR model with deep convolutional neural network (DCNN). The result of the experiment shows that LSTM-based RNN outperforms DCNN for the proposed dataset that has been constructed for the experiment in the natural recording environment.

The ability to deploy such systems throughout a region, or perhaps a nation, will increase as IoT infrastructure develops. Although Internet of Things (IoT) devices are capable of offering intelligent services, the massive amounts of data they gather and analyze pose a severe security threat. Researchers have spent a lot of work building sophisticated NIDS to prevent the exploitation of IoT data in smart applications. However, present methods may be vulnerable to attack, particularly new attacks, due to a lack of sufficient and evenly distributed attack data used to train the detection strategy. This study introduces a original hierarchical adversarial attack (HAA) generation strategy, which in turn targets the convolutional neural network-based intrusion detection in IoT devices with a limited budget, and therefore realizes the level-aware black-box adversarial attack approach. To generate adversarial instances with little disturbance, an intelligent approach is developed that relies on a saliency map methodology. To do this, a shadow CNN framework has been constructed. Using a random walk having restart based hierarchical node selection approach, a subset of the targeted IoT network's nodes with the lowest structural strength are selected. The proposed HAA generation technique is evaluated in comparison to three reference methods using the publicly available data set UNSW-SOSR2019. In a comparison of the two most sophisticated convolutional neural network (CNN) designs, GCN and JK-Net, it was shown that the classification accuracy for NIDS in IoT settings may be reduced by more than 30%.