Search

Maize (Zea mays) is a critical crop for global food security and economic stability. However, it is highly vulnerable to various diseases such as northern leaf blight, common rust, and maize lethal necrosis, which can lead to significant crop losses if not detected early. Traditional CNN-based models, while effective in extracting spatial features, often fail to capture subtle multi-scale variations necessary for distinguishing between disease symptoms. These models also suffer from high computational complexity when deeper layers are introduced to handle fine-grained details. Transformer-based models, on the other hand, provide long-range dependencies but come with significant computational overhead, limiting their use in real-time agricultural applications. To overcome these challenges, we propose MSCPNet, a novel architecture that combines a truncated MobileNetV2 backbone with a Multi-Scale Convolutional PoolFormer block. The truncated backbone ensures that only essential layers for general feature extraction are retained, enhancing the model’s adaptability across domains. The Multi-Scale Convolutional PoolFormer block captures both local and global dependencies through parallel convolutional branches of varying kernel sizes, while the PoolFormer module efficiently handles feature aggregation without the heavy computational cost associated with traditional attention mechanisms. This design allows the model to balance computational efficiency and high accuracy, making it highly suitable for real-time maize disease detection. Extensive evaluations on the maize leaf disease classification task yielded outstanding results, with the proposed MSCPNet achieving an accuracy of 97.44%, precision of 96.76%, recall of 97.37%, F1-score of 97.04%, and an MCC of 0.9653, with a model size of 998,084 parameters and 315,258,752 FLOPs. Furthermore, the model was evaluated on the PlantVillage dataset for tomato leaf disease classification, where it achieved an accuracy of 99.32%, precision of 99.32%, recall of 99.33%, F1-score of 99.32%, and an MCC of 0.9925. These results demonstrate the effectiveness and efficiency of MSCPNet in disease classification across different domains.

Vehicular Edge-Cloud Computing (VECC) paradigm has emerged as a viable approach to overcome the inherent resource limitations of vehicles by offloading computationally demanding tasks to remote servers. Despite its potential, existing offloading strategies often result in increased latency and sub-optimal performance due to the concentration of workloads on a limited number of connected Roadside Units (RSUs). Moreover, ensuring data security and optimizing energy usage within this framework remain significant challenges. To address these concerns, this paper proposes a comprehensive framework for VECC systems. A novel load-balancing algorithm is proposed to effectively redistribute vehicles among RSUs, considering factors such as RSUs load, computational capacity, and data rate. Additionally, a robust security mechanism is incorporated using the Advanced Encryption Standard (AES) in conjunction with Electrocardiogram (ECG) signals as encryption keys to enhance data protection during transmission. To further improve system efficiency, a novel caching strategy is introduced, enabling edge servers to store completed tasks, which in turn reduces both latency and energy consumption. An optimization model is also proposed to minimize energy expenditure while ensuring that latency constraints are satisfied during computation offloading. Given the complexity of this problem in large-scale vehicular networks, the study formulates an equivalent reinforcement learning model and employs a deep learning algorithm to derive optimal solutions. Simulation results conclusively demonstrate that the proposed model significantly outperforms existing benchmark techniques in terms of energy savings.

The emergence of Industrial Internet of Things (IIoT) networks has sparked a demand for reliable and efficient communication systems. One promising strategy to overcome interference and coverage issues in IIoT setups is leveraging massive multiple-input multiple-output (MIMO) technology in a cell-free configuration. However, implementing large antenna arrays for such systems can be impractical and expensive, especially in remote or dynamic environments. Unmanned aerial vehicles (UAVs) have emerged as a versatile solution, including for communication relays. This study investigates the integration of UAV swarms into cell-free massive MIMO systems for IIoT networks. The proposed approach involves deploying a swarm of UAVs equipped with multiple antennas as aerial base stations to serve ground-based IIoT devices. It examines the benefits of employing UAV swarms, such as expanded coverage, better interference management, and increased flexibility. Additionally, it addresses challenges like UAV mobility, resource allocation, and power consumption. To address these challenges, an algorithm for resource allocation is proposed. This algorithm considers factors like UAV mobility, quality-of-service requirements for IIoT devices, and interference among UAVs. It aims to optimize transmit power and antenna selection for each UAV, ensuring QoS satisfaction and enhancing overall system capacity. Simulation results demonstrate the effectiveness of the algorithm, indicating improvements in system capacity, coverage, and interference management. Moreover, the findings highlight the trade-offs between system performance and power consumption within the UAV swarm. In essence, this study contributes to understanding the potential of utilizing UAV swarms in cell-free massive MIMO systems for IIoT networks. The proposed resource allocation algorithm offers insights for planning and enhancing such nodes, paving the way for further research and development in this promising field.

Congestion in the world’s traffic systems is a major issue that has far-reaching repercussions, including wasted time and money due to longer commutes and more frequent stops for gas. The incorporation of contemporary technologies into transportation systems creates opportunities to significantly improve traffic prediction alongside modern academic challenges. Various techniques have been utilized for the purpose of traffic flow prediction, including statistical, machine learning, and deep neural networks. In this paper, a deep neural network architecture based on long short-term memory (LSTM), bi-directional version, and gated recurrent units (GRUs) layers has been structured to build the deep neural network in order to predict the performance of the traffic flow in four distinct junctions, which has a great impact on the Internet of vehicles’ applications. The structure is composed of sixteen layers, five of which are GRU layers and one is a bi-directional LSTM layer. The dataset employed in this work involved four congested junctions. The dataset extended from November 1, 2016, to June 30, 2017. Cleaning and preprocessing operations were performed on the dataset before feeding it to the designed deep neural network in this paper. Results show that the suggested method produced comparable performance with respect to state-of-the-art approaches.

The presence of various maize plant leaf diseases has significantly decreased both the quality and quantity of crop production. In order to take the appropriate steps to prevent the occurrence of plant leaf diseases, it is essential to track and recognize such infections during the planting period. However, correct recognition of numerous maize diseases is difficult to achieve because the currently employed automated solutions are operationally complicated or only effective on samples with plain backgrounds. While real-world scenarios are suffering from huge sample distortions like the effect of noise, clutter in the background, and blurring of the leaf regions that increase the complexity of the recognition procedure. To alleviate the above-listed problems, a deep learning (DL) approach called the MaizeNet is proposed for the correct localization and classification of various maize crop leaf disorders. We have presented an improved Faster-RCNN approach that utilizes the ResNet-50 model with spatial-channel attention as its base network for the computation of deep keypoints which are then localized and categorized into various classes. The proposed work is tested on a standard database named Corn Disease and Severity that contains samples from three different classes of maize plant diseases which are captured under diverse conditions such as complex background, brightness, and color and size variations. The MaizeNet model attains an average accuracy score of 97.89% along with mAP value of 0.94, which is showing the effectiveness of our approach for locating and classifying the numerous types of maize leaf infections.

Agriculture plays the vigorous role in economy as well as it is contemplated to be the mainstay of economic system in emerging countries. Furthermore, it influences the society in huge ways including ancillary livelihoods, anyhow occurring of plant diseases impacts many farmers. Henceforth, erroneous leaf disease identification inclines to menacing effects on plants thereby curtailing product quality, productivity or quantity. To overcome these issues, we have designed Multi-agent DRL and EfficientNet assisted 3D plant leaf disease identification and severity estimation (MULTINET) framework. The main aim of this study is to effectively identify plant leaf diseases and quatify the severity of the disease. The proposed work comprehends of following four consecutive processes. At first, we have performed image pre-treatment for data cleansing using Adaptable LoW Pass Weiner (AWW) filter and then EMbellished Manta-Ray Optimization Algorithm (EMMARO) based data augmentation for enhancing image quality and balance the classes. After that, we have adopted Block Divider Model (BDM) for transfiguring 2D to 3D image which sustenance to navigate the information from multiple perceptive and bargains superior viewpoints from miscellaneous angles. Following that, we have executed dual effective segmentation on 3D image by utilizing Enhanced Deep Q-Network (EnDeep) that embrace of Haar-U-Net (HUNT) Algorithm for appropriate feature extraction and Convolution Feature Attention (CFA) Mechanism for dimensionality reduction. Here, the Multiple Deep Reinforcement Learning (DRL) agents are employed for segmentation and ensuring its accuracy through segmentation reliability checker which accommodates rewards entrenched on its actions. Based on those segmented regions, we have accomplished species detection and disease classification by the proposed Lightweight EfficientNet and Di-attention aided Bilinear-VGG (EBBI) Algorithm. At last, the severity enumeration is performed by contemplating lesions counts and its density. The proposed MULTINET framework is conducted in MATLAB R2020a simulation tool and the performance of proposed work is evaluated in terms of accuracy, precision, sensitivity, F1-score and ROC curve where the proposed work outperforms existing works. The accuracy of the proposed work increases from 19%-29%, precision increases from 19%-28%, sensitivity increases from 31%-38%, F1-score increases from 31%-38%, and ROC curve increases about 0.15–0.22 when compared with the existing works.

The security and reliability of cellular-based wireless IoT networks are often hindered by eavesdropping attacks. Existing approaches have limitations such as ineffective relay selection, untrusted relay nodes, and improper UAV positioning. This article discusses secure and reliable communication in blockchain-enabled cellular-based IoT networks. In this article, we propose a novel approach that ensures the initial level of security to the UAV relays by enrolling the UAV relay nodes to the edge-assisted base stations for initial security and enhances the optimal UAV relay selection using dual-phase optimal relay selection mechanisms. This article performs authentication of UAV relay nodes to enhance security against active eavesdroppers and mitigates the effects of passive eavesdroppers by jointly optimizing power and position based on their actions. This enables eavesdropping to resist secure communication. The proposed approach beats the state-of-the-art algorithm in terms of decreased deployment time and gradually rising efficiency with increasing UEs. The deployment time for the previously presented algorithm is fast expanding, while the proposed integrated deployment algorithm is progressively increasing. The proposed eavesdropping resisted integration technique harvests an overlay complexity tendency due to its hybrid solution, enhancing system stability and minimizing system complexity. We further integrate the blockchain with UAVs in the system and perform authentication and appropriate relay selection in the networks. We will also demonstrate secure and reliable communication in healthcare, transportation, and industry. This paper emphasizes the significance of safe and dependable IoT connectivity and how blockchain technology and appropriate relay selection techniques might be helpful. The results show that the recommended algorithm is superior in terms of both reliability and complexity. When iteration count is minimal, the proposed method and the completely distributed have a comparable but lowest complexity as they outperform one another in different scenarios. Our proposed approach provides a possible solution to existing issues and contributes to the progress of secure and reliable communication in cellular-based wireless IoT networks.

The Internet of Things (IoT) has established itself as a multibillion-dollar business in recent years. Despite its obvious advantages, the widespread nature of IoT renders it insecure and a potential target for cyber-attacks. Furthermore, these devices broad connectivity and dynamic heterogeneous nature can open up a new surface of attack for refined malware attacks. There is a critical need to protect the IoT environment from such attacks and malware. Therefore this research aims to propose an intelligent, SDN-enabled hybrid framework leveraging Cuda Long Short Term Memory Gated Recurrent Unit (cuLSTMGRU) for efficient threat detection in IoT environments. To properly assess the proposed system, a state-of-the-art IoT-based dataset and standard evaluation metrics were used. The proposed model achieved 99.23 % detection accuracy with a low false-positive rate. For further verification, we compare the proposed model results with two of our constructed models (i.e., cuBLSTM and cuGRUDNN) and current benchmark algorithms. The proposed model outclassed the other models regarding speed efficiency, detection accuracy, precision, and other standard evaluation metrics. Finally, the proposed work employed 10-fold cross-validation to ensure that the results were completely unbiased.

Malware attacks have become very common in recent years. The variety and continuous improvement of malware capabilities threaten any network. Wi-Fi is also not an exception in that context. This paper proposes a model describing the spreading of malware in Wi-Fi networks using an epidemiological mathematical model. This model is built on the characteristics of encryption and authentication in Wi-Fi networks. In addition, we also consider state transitions of devices based on some assumptions about modern malware capabilities. We calculate the basic reproduction number $\boldsymbol {R}_{0}$ and thereby indicate the condition to limit the spread of malware. This spreading model is analyzed through numerical simulation. Besides, for the readers to have an overview of the main threats and the security capabilities of the Wi-Fi devices, we also briefly present security threats and encryption methods used in Wi-Fi.

Internet of Things (IoT) is an instantly exacerbated communication technology that is manifesting miraculous effectuation to revolutionize conventional means of network communication. The applications of IoT are compendiously encompassing our prevalent lifestyle and the integration of IoT with other technologies makes this application spectrum even more latitudinous. However, this admissibility also introduces IoT with a pervasive array of imperative security hazards that demands noteworthy solutions to be swamped. In this scientific study, we proposed Deep Learning (DL) driven Software Defined Networking (SDN) enabled Intrusion Detection System (IDS) to combat emerging cyber threats in IoT. Our proposed model (DNNLSTM) is capable to encounter a tremendous class of common as well as less frequently occurring cyber threats in IoT communications. The proposed model is trained on CICIDS 2018 dataset, and its performance is evaluated on several decisive parameters i.e Accuracy, Precision, Recall, and F1-Score. Furthermore, the designed framework is analytically compared with relevant classifiers, i.e., DNNGRU, and BLSTM for appropriate validation. An exhaustive performance comparison is also conducted between the proposed system and a few preeminent solutions from the literature. The proposed design has circumvented the existing literature with unprecedented performance repercussions such as 99.55% accuracy, 99.36% precision, 99.44% recall, and 99.42% F1-score.

There exist several performance criteria for cryptographically-strong substitution boxes (S-boxes), which are often conflicting with each other. Constructing S-boxes that satisfy multiple criteria with optimal tradeoffs is one of the challenging tasks for cryptographers. In practice, the existing S-box design algorithms are used to optimize performance according to a single performance criterion, mainly the nonlinearity, which usually results in weak scores for other equally-significant criteria. To overcome this problem, a multi-objective optimization-based method is presented in this paper. In this method, $8 \times 8$ S-boxes are constructed satisfying multiple criteria of balancedness, high nonlinearity, low differential uniformity, and low auto-correlation. Multiple objectives are fulfilled by applying the chaos-assisted non-dominated sorting genetic algorithm-II to introduce the S-boxes. The performance assessment of the proposed method and the comparative analysis with available optimization tools and other state-of-the-art algorithms demonstrate its proficiency in generating significantly-better S-box solutions with good Pareto-optimal security features. Eventually, the S-boxes with minimum nonlinearity (NL) of 110, differential uniformity (DU) as low as 8, and auto-correlation function (ACF) as low as 80 are obtained after the optimization. Furthermore, the obtained Pareto-optimal S-box is utilized to put forward a medical image encryption algorithm for secure telemedicine services. The suggested encryption algorithm uses an S-box to perform the required permutation and diffusion of images. The encryption performance assessment and comparison analyses validate its effectiveness for securing medical imagery data in telemedicine networks.

In this paper, the effective end-to-end secure communication of N-pair cellular network is studied. Promising multiple access scheme known as non-orthogonal multiple access (NOMA) and physical layer network coding (PLNC) scheme are employed to improve the spectral and the temporal efficiency respectively. Also, this proposed model uses the physical layer security to ensure the secure wireless communication. It is assumed that the eavesdropper (Eve) tries to trace the confidential message from the legitimate user’s. Hence, they generates the artificial noise (AN) to confuse the Eve. Closed form expression for the end-to-end outage probability of the proposed N-pair NOMA-PLNC wireless network is derived. Further, a closed form expression for the secrecy outage probability of the proposed network is derived using homogeneous Poisson point process (HPPP) and Gaussian -Laguerre quadrature. Numerical results are presented to validate theoretical findings. It is noteworthy that uplink performance of the proposed network is better than the network without PLNC scheme.

The accurate estimation of underwater Visible Light Communication (VLC) channel conditions is challenging due to its widespread attenuation and scattering effects. The channel attenuation is a linear function of frequency and causes exponential signal power loss whereas due to the scattering effect, numerous photons are statistically generated as light beams strike water molecules and there arise security concerns. Assuming realistic underwater conditions, this paper investigates the security performance of a typical Non-Orthogonal Multiple Access (NOMA)-assisted underwater VLC system. It consists of a Floating Vehicle Transmitter (FVT), equipped with multiple Light Emitting Diodes (LEDs) to transmit the signal to two legitimate near-end and far-end Underwater Vehicles (UVs) in presence of an active/passive eavesdropper. The Channel State Information (CSI) of each transmitting link is estimated with the use of a Minimum Mean Square Error (MMSE) technique. Furthermore, we propose a LED selection mechanism to select an LED that can achieve the highest secrecy rate defined under the constraints of known and unknown CSI of legitimate and/or eavesdropping links. Using the Successive Interference Cancellation (SIC) technique, a novel closed-form secrecy outage probability expressions for the conventional single-LED and multi-LED NOMA-VLC links for both known and unknown CSI scenarios is derived. The security performance of the proposed multi-LED NOMA-VLC system is compared with the conventional single-LED NOMA-VLC system under the effect of air bubbles for both fresh and salty water. Finally, we verify the validity of the numerical results through Monte-carlo simulation analysis.