Reinforcement learning (RL) and imitation learning (IL) are quite two useful machine learning techniques that were shown to be potential in enhancing navigation performance. Basically, both of these methods try to find a policy decision function in a reinforcement learning fashion or through imitation. In this paper, we propose a novel algorithm named Reinforcement Imitation Learning (RIL) that naturally combines RL and IL together in accelerating more reliable and efficient navigation in dynamic environments. RIL is a hybrid approach that utilizes RL for policy optimization and IL as some kind of learning from expert demonstrations with the inclusion of guidance. We present the comparison of the convergence of RIL with conventional RL and IL to provide the support for our algorithm’s performance in a dynamic environment with moving obstacles. The results of the testing indicate that the RIL algorithm has better collision avoidance and navigation efficiency than traditional methods. The proposed RIL algorithm has broad application prospects in many specific areas such as an autonomous driving, unmanned aerial vehicles, and robots.

Background: The most important aspect of medical image processing and analysis is image segmentation. Fundamentally, the outcomes of segmentation have an impact on all subsequent image testing methods, including object representation and characterization, measuring of features, and even higher-level procedures. The problem with image segmentation is recognition and perceptual completion while segmenting the image. However, these issues can be resolved by multilevel optimization techniques. However, multilevel thresholding will become more computationally intensive with increasing thresholds. Optimization algorithms can resolve these issues. Therefore, hybrid optimization is used for image segmentation in this research work. Methods: The researchers propose a Multilevel Thresholding-based Segmentation using a Hybrid Optimization approach with an adaptive bilateral filter to resolve the optimization challenges in medical image segmentation. The proposed model utilizes Kapur's entropy as the objective function in the nature-inspired optimization algorithm. Results: The result is evaluated using parameters such as the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM). The researchers perform result analysis with variable thresholding levels on KAU-BCMD and mini-MIAS datasets. The highest PSNR, SSIM, and FSIM achieved were 31.9672, 0.9501, and 0.9728 respectively. The results of the hybrid model are compared with state-of-the-art models, demonstrating its efficiency. Conclusion: The research concludes that the proposed Multilevel thresholding-based segmentation using a Hybrid Optimization approach effectively solves optimization challenges in medical image segmentation. The results indicate its efficiency compared to existing models. The research work highlights the potential of the proposed hybrid model for improving image processing and analysis in the medical field.

Recently, technology like Blockchain is gaining attention all over the world today, because it provides a secure, decentralized framework for all types of commercial interactions. When choosing the optimal blockchain platform, one needs to consider its usefulness, adaptability, and compatibility with existing software. Because novice software engineers and developers are not experts in every discipline, they should seek advice from outside experts or educate themselves. As the number of decision-makers, choices, and criteria grows, the decision-making process becomes increasingly complicated. The success of Bitcoin has spiked the demand for blockchain-based solutions in different domains in the sector such as health, education, energy, etc. Organizations, researchers, government bodies, etc. are moving towards more secure and accountable technology to build trust and reliability. In this paper, we introduce a model for the prediction of blockchain development platforms (Hyperledger, Ethereum, Corda, Stellar, Bitcoin, etc.). The proposed work utilizes multiple data sets based on blockchain development platforms and applies various traditional Machine Learning classification techniques. The obtained results show that models like Decision Tree and Random Forest have outperformed other traditional classification models concerning multiple data sets with 100

Fog computing, an innovative approach building upon cloud technology, taps into local user resources to enhance services. It boasts cost-effectiveness, improved security, and reduced network delays, making it a popular choice for real-time applications. However, due to the heterogeneity of fog devices, resource allocation and scheduling pose challenges. This paper introduces a novel solution using a crow-inspired search mechanism and a multi-objective evolutionary approach for fog computing environments. The primary objectives are to optimize security and success rates simultaneously. A local search method enhances the performance of the crow search algorithm (CSA). The proposed method utilizes evolutionary techniques to allocate and schedule resources effectively. We compared our hybrid CSA with the original CSA and Genetic Algorithm (GA) across seven scenarios with varying parameters. Our hybrid CSA consistently outperformed existing methods, demonstrating its effectiveness in achieving the desired objectives.

Today, technology has become a basic necessity for every individual in society. There were times when the internet was used only to send digital mail. We never imagined that technology would be at the tip of our fingers someday, with no long queues and no waiting times. The solution is just a few clicks away on your smartphone. The COVID-19 pandemic outbreak pushed many services online, and the need for an online voting mechanism became the need of the hour. Blockchain innovation is an approach to putting away information that makes it troublesome or difficult to change, switch, or delude the system. It eliminates the need for third-party approval by making the transaction between two parties. The existing electronic voting (e-voting) system failed to build trust among voters due to several security vulnerabilities. We offer a different model that addresses the shortcomings of both the electronic and traditional voting systems with the use of blockchain technology. It will make the voting mechanism more secure and impenetrable to tampering. In this article, we provide an improved environment for unbiased voting. The Ethereum platform is utilized along with Ganache and Metamask to set up a local blockchain network and transaction records.

Abstract Fog computing is a new way of using computers that builds on standard cloud technology by taking advantage of the resources at the user's location to improve services. Because of its advantages, which include cheaper operational costs, better security, and lower network latency, it is the most often used option for many real-time applications. However, since each fog device is different, it is hard to figure out how to divide up and schedule resources. This paper proposes a novel approach for resource allocation and scheduling in a fog computing environment using a crow search mechanism and a multi-objective population-based evolutionary mechanism. The proposed work considers two goals: the security hit rate and the success rate. These two aims must be met to the greatest extent possible. A local search method improves how well the crow search algorithm (CSA) works. The suggested work uses the evolutionary method to figure out how to schedule and divide resources in a fog computing environment. We have contrasted the effectiveness of our suggested hybrid CSA with two other approaches, the original CSA and the Genetic Algorithm (GA), based on two metrics: success rate and security hit ratio. We have used seven different scenarios with different values for the parameters. We found that our proposed hybrid CSA outperformed other currently employed methods. The study's outcome also shows how well the suggested algorithm accomplishes its objectives.

Artificial intelligence and Blockchain are two of the most important forces driving innovation today. At the point when Blockchain and AI join their assets, this gives a more significant investigation of the viability of the details of the agreement, and the work processes it manages. Consequently, the requirement for human investigation, intercession and check, is enormously diminished. Man-made intelligence alludes to the capacity of machines to grasp, think, and learn likewise to people, demonstrating the chance of utilizing PCs to mimic human knowledge. A smart contract is computer code running on a blockchain that contains a set of norms by which the smart contract’s parties’ consent to communication between one another. Examining AI integration with smart contracts that are enabled by blockchain in the enhancing finance system operations is the main objective of this endeavor. AI is added to well-established smart contracts, their efficiency increases exponentially. This article presumes that AI and blockchain enabled smart contract will have an enormous effect in future for Finance industry and Digital trading.

The outrageous demand for file sharing among peers has become a significant development of the Peer-to-Peer (P2P) communication system during the past few years. The essence of recent P2P file-sharing systems has been driven mainly by their architectures’ scalability and the simplicity of their search capabilities. To increase data transmission and reduce the network overhead, we need an optimal resource searching algorithm. For the heterogeneous and complex potential of peers, it is challenging to pick an ideal peer for an algorithm. Implementing an effective lookup algorithm is, therefore, an essential challenge for the unstructured P2P mobile network. This paper has suggested an Optimal and Secure Resource Searching Algorithm (OSRSA) for the highly secure and most trusted P2P system. We have used Particle Swarm Optimization (PSO) to pick a peer in this optimal resource searching algorithm. This algorithm reduces the query delay and increases the success rate of searching files in the P2P network system. This algorithm also decreases network overhead and increases search efficiency in the P2P network system. This suggested algorithm’s efficiency is determined and equated with pre-existing approaches such as Flooding, Partial Indexed Search (PIS), and P2P Resource Organization by Social Acquaintances (PROSA). Our findings are that our proposed algorithm OSRSA is better than Flooding in terms of network overhead. Query delay of OSRSA is less than PIS and PROSA. The success rate of OSRSA is relatively better than PIS and PROSA.

In this paper, biorthogonal wavelet transform is used for compression of high resolution aerial images. Biorthogonal wavelets enlarge the family of orthogonal wavelets and can be subjected to inversion. The Biorthogonal wavelet family uses distinct wavelet and scaling functions for the decomposition and reconstruction of images and signals. Biorthogonal wavelets also demonstrates the feature of linear phase by using two wavelets for decomposition and reconstruction. This basically means that images are decomposed by one family and reconstructed by another.A methodology is designed using bi-orthogonal wavelets, preserving 8% of the wavelet coefficients after image compression. Even though there is a significant reduction in both the dimensions and size of the selected images, there is almost negligible damage to the visual properties of the images. The originality of the selected images remains unhindered throughout the course of action which conveys how efficient biorthogonal wavelets are in compression of high resolution images.

Peer-to-Peer (P2P) networks are less expensive, simple to use, and do not require the traditional client–server model. It has particular advantages in data sharing and resource utilization, so it is recommended to use it for various applications. P2P networks have been used in many applications, especially in data sharing and resource utilization. Load balancing and security is an essential task to improve the performance of P2P networks. Hence, in this paper, probability-based load balancing control and security enhancement is developed in P2P networks. The probability of peer can be computed with chicken swarm optimization (CSO), which selects the best peer in P2P networks to achieve load balancing and resource utilization. The proposed method is developed to attain two main objective functions: load balancing control and security enhancement. A probability-based CSO algorithm is used to control load balancing. The security is achieved with Enhanced Rumour Riding protocol (ERR) and SXOR (Split XOR) operation. The proposed method is implemented in the NS2 platform, and the performance of the proposed method is analysed with performance metrics such as delay, delivery ratio, packet loss, encryption time, decryption time, and throughput. The proposed method is compared with existing methods such as Biased Contribution Index based Rumour Riding protocol (BCIRR), Ant Colony Optimization (ACO), and Catching Algorithms (CA). The proposed technique achieves a 98.75% packet delivery ratio, with a minimum 3.8 s delay. Ultimately the performance suggests that the proposed system can perform better for load balancing and security in the P2P network.

The progressive growth of wireless mechanisms and the wide popularity of intelligent devices are attracting particular attention to peer-to-peer mobile ad hoc networks (P2P MANET). Increasing the efficiency to search the resources became an important research topic in the P2P MANETs. Most existing research gives more emphasis on position-based clustering techniques and does not give preference to time. Due to not giving any preference to time, the existing approaches are not so appropriate to improve the efficiency to search the resources in P2P MANETs. This paper suggests a navel resource search approach that first uses position-aware peer clustering strategy. Then, using an ant colony optimisation method with pheromones, it chooses the preeminent neighbour's peer that is of time-aware neighbouring peer's resource preferences and the time-aware neighbouring peer's availability. Based on the results of the experiment, this approach outweighs other approaches in terms of search delay, overhead traffic, and search success rate.

Breast cancer strikes women more frequently than it strikes males, which is a major factor in the rising mortality rate for women. Breast cancer, which predominantly concerns women (roughly 1% of cases include non-females), will impact one in eight women in their lifetime. Breast carcinoma, one of the deadliest malignancies, is the main cause of cancer-related deaths in women. Today, early diagnosis and prognosis are crucial to increase survival rates and finally bring them down. Cancer researchers have a number of difficulties when attempting to differentiate between benign and malignant tumors as well as when attempting to make judgments about mild and metastatic breast cancer. Research has turned its attention to machine learning techniques, which have been shown to be successful in the early identification and prognostication of breast cancer. In proposed article, we utilized eight machine learning techniques to the Breast Cancer Wisconsin Diagnostic dataset: Support Vector Machine, Logistic Regression, XGBoost, CatBoost, Random Forest, Artificial Neural Network, Decision Tree, K-Nearest Neighbours. After getting the data, a performance assessment and comparison of these different classifiers is done. The foremost goal of this study is to detect and utilize machine learning to detect breast cancer and determine which method is more efficient in terms of confusion matrices, accuracy, and precision. The Support Vector Machine and Artificial Neural Network have demonstrated superior performance than all other classifiers, with an accurate result of 98.08%.

Data sharing in the Peer to Peer (P2P) networks became an important function in the trustworthy computing. Secure and load balancing control in file sharing is vital to enhance the overall performance of P2P file sharing system. In literature many methods of load balancing control and security control have been used but it is not able to attain the best results in P2P networks. Hence, in this paper, Biased Contribution Index Based Rumour Riding Protocol (BCIRR) is developed to attain the load balancing control and security enhancement of P2P networks. The proposed method is concentrated to achieve two main objective function such as load balancing control and security enhancement. The proposed protocol is a combination of Biased Contribution Index (BCI) and Enhanced Rumour Riding protocol (ERR). Here, load balancing control of the P2P network is attained with the utilization of the BCI and security enhancement of the P2P network is attained with the utilization of the ERR. The proposed protocol will be implemented in the Matlab platform and the performance of the proposed protocol is analysed with different performance metrics such as Packet loss, Delivery ratio, Average end to end delay and Throughput. To analysis the effectiveness of proposed method, it will be compared with the existing method of Catching Algorithms (CA).

In recent years, the size of databases has increased enormously. This has led the world to grow interest in the development of tools that can extract knowledge automatically from data. Here, data mining proves to be the useful tool to discover the knowledge from huge data repositories. This requires proper classification methods and algorithms. In a particular dataset, we require minimal set of features that can lead us to the proper classification of instances of the dataset. Here, the need of the good feature selection algorithm comes to existence. In this paper, we perform a comparative study of the two most popular methods used for the feature selection: Wrapper and Filtering method. A number of algorithms exist that fall under these two categories. In this paper relative merits of the respective algorithms and their performance on a number of datasets is analyzed and depicted graphically also.