We consider, in this paper, the NP-hard problem of finding the minimum connected domination metric dimension of graphs. A vertex set B of a connected graph G = (V, E) resolves G if every vertex of G is uniquely identified by its vector of distances to the vertices in B. A resolving set B of G is connected if the subgraph induced by B is a nontrivial connected subgraph of G. A resolving set is dominating if every vertex of G that does not belong to B is a neighbor to some vertices in B. The cardinality of the smallest resolving set of G, the cardinality of the minimal connected resolving set, and the cardinality of the minimal connected domination resolving set are the metric dimension of G, connected metric dimension of G, and connected domination metric dimension of G, respectively. We present the first attempt to compute heuristically the minimum connected dominant resolving set of graphs by a binary version of the equilibrium optimization algorithm (BEOA). The particles of BEOA are binary-encoded and used to represent which one of the vertices of the graph belongs to the connected domination resolving set. The feasibility is enforced by repairing particles such that an additional vertex generated from vertices of G is added to B, and this repairing process is iterated until B becomes the connected domination resolving set. The proposed BEOA is tested using graph results that are computed theoretically and compared to competitive algorithms. Computational results and their analysis show that BEOA outperforms the binary Grey Wolf Optimizer (BGWO), the binary Particle Swarm Optimizer (BPSO), the binary Whale Optimizer (BWO), the binary Slime Mould Optimizer (BSMO), the binary Grasshopper Optimizer (BGO), the binary Artificial Ecosystem Optimizer (BAEO), and the binary Elephant Herding Optimizer (BEHO).

Nowadays, the Internet of Things (IoT) has become immensely popular in various fields like healthcare, smart cities, and industrial automation. IoT networks are expanding rapidly, including different IoT devices with limited capabilities in terms of power and storage which make the IoT security a crucial issue. IoT Network Intrusion Detection System is one of the most famous solutions that used to identify different types of attack and extract their features (e.g. IP addresses of attackers). The IP address is a valuable feature that can identify malicious traffic of an attacker who attempts to access the IoT network. However, IoT Network Intrusion Detection Systems has different limitations: centralization and scalability which easily allow attackers to access the IoT network. Accordingly, this paper aims to address these issues by proposing a novel collaborative framework called Blockchain-based Collaborative Intrusion Detection Systems (BC-IDSs) that utilizes Blockchain technology to connect several IDSs. The BC-IDSs framework (1) creates a list of malicious IP addresses using IDSs; (2) utilizes Blockchain to share and store the Blacklist; (3) creates a function for duplication check in the Blockchain layer. Further, the implementation of a proof of concept for BC-IDSs framework is presented by using Ethereum Blockchain simulators. Compared to previous works, this paper discusses several types of performance metrics that prove BC-IDSs is able to secure IoT networks. BC-IDSs also increases the scalability by 50% when compared to one of the previous defence work.

Frame duplication forgery is the most common inter-frame video forgery type to alter the contents of digital video sequences. It can be used for removing or duplicating some events within the same video sequences. Most of the existing frame duplication forgery detection methods fail to detect highly similar frames in the surveillance videos. In this paper, we propose a frame duplication forgery detection method based on textural feature analysis of video frames for digital video sequences. Firstly, we compute the single-level 2-D wavelet decomposition for each frame in the forged video sequences. Secondly, textural features of each frame are extracted using the Gray Level of the Co-Occurrence Matrix (GLCM). Four second-order statistical descriptors, Contrast, Correlation, Energy, and Homogeneity, are computed for the extracted textural features of GLCM. Furthermore, we calculate four statistical features from each frame (standard deviation, entropy, Root-Mean-Square RMS, and variance). Finally, the combination of GLCM’s parameters and the other statistical features are then used to detect and localize the duplicated frames in the video sequences using the correlation between features. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art (SOTA) methods in terms of $Precision$, $Recall$, and $F1Score$ rates. Furthermore, the use of statistical features combined with GLCM features improves the performance of frame duplication forgery detection.

Hyperspectral imaging is a valuable technique for accurately classifying materials because of the abundance of spectral information and high resolution it provides. However, the characteristics of Hyperspectral Imaging, such as high-dimensional features and information redundancy, pose significant challenges to data processing. Traditional dimensionality reduction methods often have information loss, high computational complexity, and easy to ignore the strong correlation between HSI bands when dealing with the HSI data. Although other methods can achieve satisfactory classification performance, they do not consider the dimensionality reduction of HSI, and they focus on the model performance, which limits further improvement in classification performance. This article proposes a transformer-based framework called “SpectrumRecombineFormer” (SRF), which is composed of two key modules, namely “Spatial–Spectral Recombination” (SSRC) and “Cross-Layer Fusion” (CF). The SSRC is capable of utilizing both adjacent and non-adjacent spectrums to generate the spatial-sequential perceptive representations, which alleviate the effect of the strong correlation between HSI bands. The CF can avoid the loss of information during the feed-forward procedure among layers. Extensive experiments on five existing datasets (widely adopted Indian Pines, Houston2013, Pavia University, Salinas, and KSC) demonstrate the capability of our proposed method to address the above-mentioned challenges. Both quantitative and qualitative experimental ablation studies, including visualization results, reveal that the proposed SRF method can successfully and efficiently classify HSIs and surpass the other state-of-the-art methods. For access to the source code, please visit https://github.com/kangpeilun/SRF-HSI-Classification-master .

Forest height is a key forest parameter which is of great significance for monitoring forest resources, calculating forest biomass, and observing the global carbon cycle. Because the PolInSAR system could provide various object information including height, shape and direction sensitivity, and spatial distribution, it becomes a powerful means for measuring forest height. The proposed framework utilizes deep learning and builds upon traditional DEM differencing and coherence amplitude inversion algorithms. By using L band PolInSAR data, a new CNN model is established in which the estimated results of DEM differencing and coherence amplitude inversion are used as labels. Furthermore, the PCGrad optimization strategy is used for updating the gradient automatically in the training stage. This model could not only builds a relationship between complex coherences and forest height but also makes full use of the spatial context information by using the CNN layers. Experiments are carried out based on the simulated data and real data, named Lope forest site, which are collected by UAVSAR in the NASA AfriSAR campaign. Compared to the classic forest height inversion algorithms, the proposed framework has achieved a higher level of accuracy and performance on RMSE (10.15 m) and $R^{2}$ (0.87). Overall, the proposed framework does not require LiDAR data as prior knowledge and can be performed on various forest scenes. Consequently, it will hopefully serve as a useful approach for improvements in forest height inversion based on PolInSAR data. Codes, trained model, and data will be available for public access.

Vehicular Ad Hoc Networks (VANETs) are increasingly playing a fundamental role in improving driving safety. However, VANETs in a sparse environment may add risk to driving safety. The probability of a low density of vehicles in a rural area at midnight is very high. Consequently, the packet will be lost due to the lack of other vehicles, and the arrival of the following vehicles in the accident area is unavoidable. To overcome this problem, VANET is integrated with Wireless Sensor Network (WSN). The most challenging features of VANETs are their high mobility. This high mobility causes sensor nodes to consume most of their energy during communication with other nodes, leading to frequent network disconnectivity. With the evolution of VANET and WSN, the Store/Carry-Forward (SCF) paradigm has emerged as an exciting research area in the Delay Tolerant Networks (DTNs) to solve network disconnectivity. This paper proposes the Energy-Mobility-Connectivity aware routing protocol (EMCR) for a hybrid network of VANET-WSN. A comprehensive performance analysis that considers realistic propagation models and real city scenario traffic is performed in NS3. The simulation results show that the SCF mechanism is essential in the EMCR protocol to maximize the delivery ratio and minimize energy consumption and overhead.