Hyperspectral images (HSIs) are used in a large number of real-world applications. HSI classification (HSIC) is a challenging task due to high interclass similarity, high intraclass variability, overlapping, and nested regions. The 2-D convolutional neural network (CNN) is a viable classification approach since HSIC depends on both spectral–spatial information. The 3-D CNN is a good alternative for improving the accuracy of HSIC, but it can be computationally intensive due to the volume and spectral dimensions of HSI. Furthermore, these models may fail to extract quality feature maps and underperform over the regions having similar textures. This work proposes a 3-D CNN model that utilizes both spatial–spectral feature maps to improve the performance of HSIC. For this purpose, the HSI cube is first divided into small overlapping 3-D patches, which are processed to generate 3-D feature maps using a 3-D kernel function over multiple contiguous bands of the spectral information in a computationally efficient way. In brief, our end-to-end trained model requires fewer parameters to significantly reduce the convergence time while providing better accuracy than existing models. The results are further compared with several state-of-the-art 2-D/3-D CNN models, demonstrating remarkable performance both in terms of accuracy and computational time.

Access control mechanisms define the level of access to the resources among specified users. It distinguishes the users as authorized or unauthorized based on appropriate policies. Several traditional and hybrid access control models have been proposed in previous researches over the last few decades. In this study, we provide a detailed survey of access control models and compare the traditional and hybrid access control models based on their access control criteria. This survey focuses on the growing literature of access control models and summarizes it through comparative analysis, identifying limitations and illustrating the advantages of both traditional and hybrid models. This study will help the researchers to get a deep understanding of the traditional and hybrid access control models.

As the SQL injection attack is still at the top of the list at Open Web Application Security Project (OWASP) for more than one decade, this type of attack created too many types of issues for a web application, sensors, or any similar type of applications, such as leakage of user private data and organization intellectual property, or may cause Distributed Denial of Service (DDoS) attacks. This paper focused on the poor coding or invalidated input field which is a big cause of services unavailability for web applications. Secondly, it focused on the selection of program created issues for the WebSocket connections between sensors and the webserver. The number of users is growing to use web applications and mobile apps. These web applications or mobile apps are used for different purposes such as tracking vehicles, banking services, online stores for shopping, taxi booking, logistics, education, monitoring user activities, collecting data, or sending any instructions to sensors, and social websites. Web applications are easy to develop with less time and at a low cost. Due to that, business community or individual service provider’s first choice is to have a website and mobile app. So everyone is trying to provide 24/7 services to its users without any downtime. But there are some critical issues of web application design and development. These problems are leading to too many security loopholes for web servers, web applications, and its user’s privacy. Because of poor coding and validation of input fields, these web applications are vulnerable to SQL Injection and other security problems. Instead of using the latest third-party frameworks, language for website development, and version database server, another factor to disturb the services of a web server may be the socket programming for sensors at the production level. These sensors are installed in vehicles to track or use them for booking mobile apps.

In ad hoc networks, the communication is usually made through multiple hops by establishing an environment of cooperation and coordination among self-operated nodes. Such nodes typically operate with a set of finite and scarce energy, processing, bandwidth, and storage resources. Due to the cooperative environment in such networks, nodes may consume additional resources by giving relaying services to other nodes. This aspect in such networks coined the situation of noncooperative behavior by some or all the nodes. Moreover, nodes sometimes do not cooperate with others due to their social likeness or their mobility. Noncooperative or selfish nodes can last for a longer time by preserving their resources for their own operations. However, such nodes can degrade the network's overall performance in terms of lower data gathering and information exchange rates, unbalanced work distribution, and higher end-to-end delays. This work surveys the main roots for motivating nodes to adapt selfish behavior and the solutions for handling such nodes. Different schemes are introduced to handle selfish nodes in wireless ad hoc networks. Various types of routing techniques have been introduced to target different types of ad hoc networks having support for keeping misbehaving or selfish nodes. The major solutions for such scenarios can be trust-, punishment-, and stimulation-based mechanisms. Some key protocols are simulated and analyzed for getting their performance metrics to compare their effectiveness.

Crime is a bone of contention that can create a societal disturbance. Crime forecasting using time series is an efficient statistical tool for predicting rates of crime in many countries around the world. Crime data can be useful to determine the efficacy of crime prevention steps and the safety of cities and societies. However, it is a difficult task to predict the crime accurately because the number of crimes is increasing day by day. The objective of this study is to apply time series to predict the crime rate to facilitate practical crime prevention solutions. Machine learning can play an important role to better understand and analyze the future trend of violations. Different time-series forecasting models have been used to predict the crime. These forecasting models are trained to predict future violent crimes. The proposed approach outperforms other forecasting techniques for daily and monthly forecast.