The proliferation of Internet of Things (IoT) devices has exponentially increased the attack surface for cyber threats, necessitating lightweight yet effective Network Intrusion Detection Systems (NIDS). This paper proposes a novel hybrid deep learning architecture that combines Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and an attention mechanism to detect intrusions in IoT environments. The CNN component captures spatial dependencies from raw traffic flows, while the BiLSTM layers learn temporal patterns in both forward and backward directions. An integrated attention mechanism further refines these temporal features by selectively focusing on the most salient time steps. To ensure robustness and generalizability, the model is rigorously evaluated across two benchmark datasets, UNSW-NB15 and BoT-IoT, under multi-class and binary classification settings. The proposed framework achieves a near-perfect Area Under Curve (AUC) of 1.00, with F1-scores reaching 1.00 even under class imbalance, all while maintaining low false alarm rates. Notably, the model converges rapidly and demonstrates excellent generalization across heterogeneous traffic distributions, confirming its adaptability for real-world deployment in resource-constrained IoT networks. Results highlight the effectiveness of hybrid attention-based architectures in enhancing detection fidelity and interpretability, offering a promising pathway for next-generation, edge-deployable, and scalable IoT security solutions.

In this study, we propose an innovative iterative methodology employing Generative Adversarial Networks (GANs) to achieve two primary objectives: (i) develop a comprehensive knowledge base termed TAG (Training-set for Architecture Generation) to facilitate the automated training of GANs for creating architecture configurations of Network Intrusion Detection Systems (NIDS) without manual intervention, and (ii) utilize the iterative framework with TAG to derive optimal deep learning-based intrusion classifier architecture. Our proposed method overcomes the limitations inherent in traditional Neural Architecture Search (NAS), which is often restricted by a predefined search space and incurs high computational overhead. To the best of our knowledge, this study represents the first effort to create a dedicated knowledge base for training GANs, which serves as a training dataset to produce NIDS architecture configurations. The proposed approach not only enhances the efficiency of generating NIDS configurations by reducing computational costs and accelerating convergence but also introduces a novel strategy for developing a structured knowledge base to direct GAN training. Experimental evaluations demonstrate that employing TAG to guide GAN training results in the generation of deep learning-based intrusion classifier architecture with a reported accuracy of 99%, an optimal False Alarm Rate (FAR) of 0.01, precision of 97%, and recall of 99%.

The unprecedented proliferation of Internet of Things (IoT) devices has significantly widened the cyber-attack surface, creating a critical need for diverse, scalable intrusion datasets. Traditional physical testbeds are costly and inflexible, motivating the development of synthetic alternatives. In this paper, we introduce a knowledge-enhanced Dual-Generator Generative Adversarial Network (GAN) framework capable of synthesizing high-quality IoT intrusion traffic directly from PCAP captures without physical infrastructure. Our proposed methodology encompasses a novel knowledge extraction mechanism, utilizing introduced attack-traffic-categorization mechanism and key-value (k,v) aggregation method to guide the conditional generation mechanism. Building on this foundation we introduce a conditional generation mechanism that embeds extracted knowledge into two specialized generators— one specializes in crafting realistic intrusion categories while the other focuses on synthesizing corresponding payload features, preserving temporal dependencies through residual-learning and dynamic-attention mechanism. Experimental results demonstrate optimal convergence around 3,200 epochs, with generated samples exhibiting 97% clustering around the mean. Pearson Correlation analysis confirms statistically significant (ρ < 0.05) correlations in 96% of generated features, while Spearman Rank analysis indicates both positive and negative correlations, highlighting the emergence of novel attack patterns. Machine-Learning tests on the benchmark CIC_IoT-23 [16] dataset validate that classifiers trained on our synthetic data outperforms baselines in accuracy, precision, recall, F1-score, and False Alarm Rate (FAR), underscoring the proposed model’s resource-efficiency, scalability, and effectiveness for advancing Deep-Learning-based Network Intrusion Detection System (NIDS) research.

In this study, we introduce the IoT Intrusion Detector Architecture Generator (IoT-IDAG), a novel approach utilizing Generative Adversarial Networks (GANs) to generate optimal Deep Learning-based Network Intrusion Detection System (NIDS) architecture configurations without relying on prior knowledge. IoT-IDAG addresses the limitations of traditional Neural Architecture Search (NAS) methods, which are constrained by predefined search spaces, high computational costs, and produce a single architecture per training session. Our approach enhances the generation efficiency of NIDS architecture configurations by reducing computational cost and convergence time, while producing multiple NIDS architecture configurations in a single training session. The proposed model includes a generator that creates architecture descriptors and a discriminator that ensures these descriptors fit within a given distribution. Original methodologies for neuron mapping and hyperparameter computation have also been introduced to convert architecture descriptors into a feasible and implementable NIDS. Experimental results show that IoT-IDAG generates intrusion classifier architecture configurations that outperform hand-crafted DL-based NIDS in terms of detection accuracy, recall, and F-1 score.

This paper introduces the Leaky Generative Adversarial Network for Synthetic Dataset Generation (L-GANSDG) framework employing Leaky ReLU activation function with a specific negative slope $\boldsymbol{(\alpha)}$ value of 0.2. This design improves the training convergence and prevents the issue of dying neurons. The proposed approach optimizes the process of generating synthetic intrusion dataset which is scalable, reproducible, and consisting of diverse attack and benign footprints. Results show that L-GANSDG achieves an optimal Discriminator accuracy of 1.0 and loss of 0.001 within 100 epochs. The intrusion dataset generated by our proposed formulation, named GenMix, is crafted in a tabular format and does not require any physical infrastructure or specialized domain expertise. Additionally, GenMix has been validated through comprehensive statistical and machine learning efficacy analysis. Statistical evaluation confirms that 93% of the GenMix data points closely cluster around the mean, and 100% of the features maintain acceptable correlations with the training set. Machine learning efficacy evaluations indicates that GenMix demonstrates an optimal replica of performance compared to the benchmark UNSW_NB15 [1] dataset. This is evidenced across several key performance metrics, including accuracy, F1-score, precision, recall and False Alarm Rate (FAR). Additionally, proposed L-GANSDG significantly reduces resource demands in terms of cost, time, and operational effort highlighting GenMix's robustness and efficiency. Furthermore, our proposed framework eliminates the need for infrastructure deployment or expert knowledge, ensuring scalability and reproducibility.

Falls among the elderly are a major worry for both the elderly and their care-takers, as falls frequently result in severe physical injury. Detecting falls using Internet of Things (IoT) devices can give elderly persons and their care-takers peace of mind in case of emergency. However, due to usability and intrusive nature of wearable and vision-based fall detection has limited acceptability and applicability in washroom and privacy sensitive locations as well as older adults with mental health condition. Privacy-aware infrared array sensors have great potential to identify fall in a non-intrusive way preserving privacy of the subject. Using a secondary dataset, we have utilised and tuned time series based deep learning network to identify fall. Experiments indicate that the time-series based deep learning network offers accuracy of 96.4% using 6 infrared sensors. This result provides encouraging evidence that low-cost privacy-aware infrared array sensor-based fall monitoring can enhance safety and well-being of older adults in self-care or aged care environment.

Wayfinding and navigation can present substantial challenges to visually impaired (VI) people. Some of the significant aspects of these challenges arise from the difficulty of knowing the location of a moving person with enough accuracy. Positioning and localization in indoor environments require unique solutions. Furthermore, positioning is one of the critical aspects of any navigation system that can assist a VI person with their independent movement. The other essential features of a typical indoor navigation system include pathfinding, obstacle avoidance, and capabilities for user interaction. This work focuses on the positioning of a VI person with enough precision for their use in indoor navigation. We aim to achieve this by utilizing only the capabilities of a typical smartphone. More specifically, our proposed approach is based on the use of the accelerometer, gyroscope, and magnetometer of a smartphone. We consider the indoor environment to be divided into microcells, with the vertex of each microcell being assigned two-dimensional local coordinates. A regression-based analysis is used to train a multilayer perceptron neural network to map the inertial sensor measurements to the coordinates of the vertex of the microcell corresponding to the position of the smartphone. In order to test our proposed solution, we used IPIN2016, a publicly-available multivariate dataset that divides the indoor environment into cells tagged with the inertial sensor data of a smartphone, in order to generate the training and validating sets. Our experiments show that our proposed approach can achieve a remarkable prediction accuracy of more than 94%, with a 0.65 m positioning error.

Identifying the symptoms of the early stages of dementia is a difficult task, particularly for older adults living in residential care. Internet of Things (IoT) and smart environments can assist with the early detection of dementia, by nonintrusive monitoring of the daily activities of the older adults. In this work, we focus on the daily life activities of adults in a smart home setting to discover their potential cognitive anomalies using a public dataset. After analysing the dataset, extracting the features, and selecting distinctive features based on dynamic ranking, a classification model is built. We compare and contrast several machine learning approaches for developing a reliable and efficient model to identify the cognitive status of monitored adults. Using our predictive model and our approach of distinctive feature selection, we have achieved 90.74% accuracy in detecting the onset of dementia.

Falls of older adults is a significant concern for themselves and caregivers as most of the times a fall leads to serious physical injuries. In the age of the Internet of things (IoT), connected smart homes and monitoring services have opened up opportunities for quality of life for the older adults. Detecting falls with wearable IoT devices can provide peace of mind for older adults and caregivers. Accelerometer based fall detection is investigated in this paper. Feed Forward Neural Network (FFNN) and Long Short Term Memory (LSTM) based Deep Learning network is applied to detect fall. LSTM network provides good accuracy based on the experiment. This experiment provides a promising indication that IoT-based fall monitoring can assure post-fall procedures to older adults and caregivers and this can increase the safety level and well-being of the older adults.

Pedestrians have a variety of tools that can assist them in travelling, including maps, kiosks, and signage. However, these facilities are inaccessible to visually impaired users. Moreover, voice aided feature with Global Positioning System (GPS) cannot be adopted in indoor applications due to signal strength attenuation and multipath effects. Internet of Things (IoT) has become a backbone for such navigation applications that can assist in locating a user within IoT equipped smart buildings. Despite the growing use of Wi-Fi and beacon technologies, smartphones are uniquely positioned to be a critical part of a localization solution. The popularity of smartphone is increased by the diverse array of microelectromechanical (MEMS) inertial sensors. This paper discusses the adaptive distance estimation algorithm for visually impaired people. It represents the use of a smartphone in a situation where external proximity sensors fail to share location information to supplement an indoor navigation system in dark areas. An improved fusion algorithm is presented that adapts the walking style of a user detecting right turns and headings. The proposed fusion algorithm depends on inertial sensors to detect the relative position of the moving user with the absolute initial position using ibeacon. Tests were carried out to determine the accuracy of steps travelled, orientation and heading information for a user holding a smartphone. Our approach estimates heading and orientation from 3-axis inertial sensors (gyroscope, accelerometer and magnetometer) have shown accuracy more than 95%. The positioning root-mean-square error (RMSE) calculation results have demonstrated that the hybrid fusion algorithm can achieve a real-time positioning and reduce the error of indoor positioning.

To overcome the limitation of Global positioning system (GPS) in indoor environments, various indoor positioning system have been developed using Wi-Fi, Bluetooth, Ultrawideband (UWB) and radio-frequency identification (RFID). Amongst them, Wi-Fi technologies are most commonly used for indoor navigation. Wi-Fi signals may be unavailable in some areas due to obstacles and unreachable coverages. Despite of it, the accuracy achieved by Wi-Fi is between 5-15 m that is unfavorable for visually impaired people. The popularity of beacons for positioning and smartphones with built-in inertial sensors plays a vital role in developing potential indoor navigation system. This paper presents a framework for visually impaired person (VIP) based on inertial sensors of smartphones and Bluetooth beacons. Beacons/proximity sensors in a building can help a pedestrian to navigate between two landmarks/points of interest via turn-by-turn navigation. However, there are certain areas in the building where external sensing is absent in a big hallway or dark alley. This model demonstrates that inertial sensors are useful to track a VIP in dark areas. Also. minimizes the use of external sensors between two landmarks/beacons. The performance of the proposed framework with the fusion algorithm in an android application is examined by conducting trajectory test on a smartphone. The experimental results of the walking traces show that the system has high accuracy with almost 1.5-2 m mean position error which could be improved further by implementing magnetometer based position learning techniques.

Detecting early onset dementia can reduce the rate of deterioration of cognitive ability in the elderly. By collecting data of daily life in older adults using smart devices, machine learning can detect anomalies in the daily or weekly routine. Additionally, smart connected devices can help to identify dementia symptoms in the behaviour of older adults who live independently. This can alleviate the fear and concerns of the older adults and caregiver, and through selfmanagement, can gradually increase their overall quality of life. This paper develops these ideas.

Traditionally, pathfinding is solved using classical search algorithms such as the Dijkstra's, A*, probabilistic roadmaps and jump point search. These algorithms are still more practical in a familiar environment that has minimum changes. However, these generated navigation path may lose their appropriateness as they cannot handle dynamic changes in the complex environment, restricting independent living of visually impaired people. Nowadays, a network of smart physical devices called Internet of Things has become a foundation infrastructure for indoor navigation and pathfinding. Although, variations in the environment are identified and stored by sensors, there is absence of a reasonable system that adapts to the variable circumstances and learns to react to the changes. In this paper, we introduce a learning based autonomous system DynaPATH that classifies events of dynamic environments and adapts to the changes. We have performed simulation in order to evaluate the effectiveness of our approach. The results of our approach are compared with performance of different pathfinding algorithms for VIP people. The simulation results display strong conclusion that our proposed system has high stability and is VIP friendly for navigation in a complex environment.

The rapidly growing number of wireless devices running applications that require high bandwidths, has resulted in increasing demands for the unlicensed frequency spectrum.Given the scarcity of allocated unlicensed frequencies, meeting such demands can become a serious concern.Cognitive Radio (CR) technology opens the door for the opportunistic use of the licensed spectrum to partially address the issues relevant to the limited availability of unlicensed frequencies.Combining CR and Wi-Fi to form the socalled White-Fi networks, has been proposed for achieving higher spectrum utilization.This article discusses the spectrum sensing in White-Fi networks and the impacts that it has on the QoS of typical applications.It also reports the analysis of such impacts through various simulation studies.Our results demonstrate the advantages of an adaptive sensing strategy that is capable of changing the related parameters based on QoS requirements.We also propose such a sensing strategy that can adapt to the IEEE 802.11e requirements.The goal of the proposed strategy is the enhancement of the overall QoS of the applications while maintaining efficient sensing of the spectrum.Simulation results of the scenarios that implement the proposed mechanisms demonstrate noticeable QoS improvements compared to cases where common sensing methods are utilized in IEEE802.11networks.

Internet of Things (IoT) is one of the most rapidly evolving technologies nowadays. It has its impact in various industrial sectors including logistics tracking, medical fields, automobiles and smart cities. With its immense potentiality, IoT comes with crucial security concerns that need to be addressed. In this paper, we present a novel deep learning technique for detecting attacks within the IoT network using Bi-directional Long Short-Term Memory Recurrent Neural Network (BLSTM RNN). A multi-layer Deep Learning Neural Network is trained using a novel benchmark data set: UNSWNB15. This paper focuses on the binary classification of normal and attack patterns on the IoT network. The experimental outcomes show the efficiency of our proposed model with regard to precision, recall, f-1 score and FAR. Our proposed BLSTM model achieves over 95% accuracy in attack detection. The experimental outcome shows that BLSTM RNN is highly efficient for building high accuracy intrusion detection model and offers a novel research methodology.

Cognitive Radio (CR) technology opens the door for the opportunistic use of the licensed spectrum to partially address the issues relevant to the limited availability of unlicensed frequencies.Combining CR and Wi-Fi to form the so called White-Fi networks, has been proposed for achieving higher spectrum utilization.This paper discusses the spectrum sensing in White-Fi networks and the impacts that they have on the QoS of typical applications.It also reports the analysis of such impacts through various simulation studies.We also propose such a sensing strategy that can adapt to the IEEE 802.11e requirements.The proposed strategy aims to enhance overall QoS while maintaining efficient sensing.Simulation results of the proposed mechanism demonstrate a noticeable improvement in QoS.

The Internet of Things (IoT) promises to revolute communications on the Internet. The IoT enables numerous business opportunities in fields as diverse as e-health, smart cities, smart homes, among many others. It incorporates multiple long-range, short-range, and personal area wireless networks and technologies into the designs of IoT applications. This will result in the IoT being pervasive in many areas which raise many challenges. This chapter reviews the major research issues challenging the IoT with regard to security, privacy, and management.

The upcoming communication paradigms, in particular, 5G and the Internet of things (IoT) networks, will infer an enormous number of smart objects to join the global network, mostly through wireless communications technologies. Consequentially, considerable wireless traffic density and radio spectrum scarcity are expected. Cognitive radio (CR) technology is a promising solution for improving spectrum utilization to handle the potential increasing traffic of future wireless networks. This chapter explains the concept of this new technology and its various proposed definitions. The primary CR functions are explained, and their related challenges are identified. Spectrum sensing is the most important function in CR. Among several sensing methods proposed for spectrum sensing, there is no single optimized method. In this chapter, the factors that should be considered when choosing the proper sensing method are investigated. The critical issue that hinders the wide adaptation of CR technology is the noticeable QoS degradation caused by an imperfect sensing operation. The authors of this chapter have suggested that a future CR device has to be designed to support various sensing methods so it can switch between them, based on the investigated factors, for better sensing performance and QoS provisioning.

Indoor navigation is an active area to tackle the problems related to locate an object or person and to explore several domains ranging from emergency response to improving marketing strategies in micro indoor spaces. This paper aims to provide the review of emerging indoor technologies explored to resolve indoor navigation for Visually Impaired people. This paper discusses various positioning enabled wireless technologies and algorithms used in real-world scenarios for providing indoor navigation with a comprehensive study about their advantages and disadvantages.

The Internet of Things (IoT) brings connectivity to about every objects found in the physical space.It extends connectivity to everyday objects.From connected fridges, cars and cities, the IoT creates opportunities in numerous domains.However, this increase in connectivity creates many prominent challenges.This paper provides a survey of some of the major issues challenging the widespread adoption of the IoT.Particularly, it focuses on the interoperability, management, security and privacy issues in the IoT.It is concluded that there is a need to develop a multifaceted technology approach to IoT security, management, and privacy.