The article reflects on the classification of brain tumors where several deep learning (DL) approaches are used. Both primary and secondary brain tumors reduce the patient’s quality of life, and therefore, any sign of the tumor should be treated immediately for adequate response and survival rates. DL, especially in the diagnosis of brain tumors using MRI and CT scans, has applied its abilities to identify excellent patterns. The proposed ensemble framework begins with the image preprocessing of the brain MRI to enhance the quality of images. These images are then utilized to train seven DL models and all of these models recognize the features related to the tumor. There are four models which are General, Glioma, Meningioma, and Pituitary tumors or No Tumor model, which helps in reaching a joint profitable prediction and concentrating solely on the strength of the estimation and outcome. This is a significant improvement over all the individual models, attaining a 99. 43% accuracy. The data used in this research was gotten from Kaggle website and comprised of 7023 images belonging to four classes. The further works will be to increase the data size more investigate other DL architectures, further enhance real time detection to enhance on the diagnostic scans’ accuracy and overall relevancy to clinical practice.
There will be nine billion people on the planet by the year 2050, according to most estimates, thus agricultural output must rise steadily. In order to deal with the increasing population, agricultural chores must be mechanized and automated. The autonomous and safe navigation of ground robots has been one of the most difficult challenges in their development over the past decade. With the emergence of the “smart city” movement, automated vehicles have become a hot issue. Authorities and administrators are unprepared to deal with the anticipated disruption of autonomous vehicles, which might potentially replace traditional transportation. We don't yet know how new capabilities will disrupt existing systems and what policy solutions will be necessary to counteract this disruption. Autonomous vehicles have a variety of advantages and disadvantages that must be considered. One such challenge is its path planning. Autonomous vehicle path planning in dynamic situations is a critical yet difficult issue because of the limitations imposed by vehicle dynamics and the presence of other vehicles. Vehicle trajectories include a variety of operations, including lane holding, lane shift, ramp merging, and crossing the street at an intersection. In order to operate autonomously, a mobile platform must perform a variety of tasks such as localization and mapping, as well as motion control and path planning. We 'II look at a bunch of different ways path planning may be put to use in farming in this post. This paper, proposed a Voronoi based partitioning algorithm which is used to find the optimal path for the intelligent vehicles. The Minimum Spanning Tree is computed and the problem is posed as a Travelling Salesperson Problem. The solution for the problem is obtained by solving using various greedy approaches. The results are compared while using various algorithms for the results obtained through the proposed partitioning algorithm.
SQL (Structured Query Language) injection is one of the most prevalent and dangerous forms of cyber-attacks, posing significant threats to database management systems and the overall security of web applications. By exploiting vulnerabilities in web applications, attackers can execute malicious SQL statements, potentially compromising the integrity and confidentiality of critical data. To combat these threats, in this study, we introduce two novel CNN models, SIDNet-1 (SQL Injection-attack Detection Network-1) and SIDNet-2 (SQL Injection-attack Detection Network-2), specifically designed for the classification of SQL injection attacks to bolster web application security. Our comprehensive evaluation includes a comparison of the performance of these customized CNN models against traditional machine learning approaches, highlighting improvements in classification accuracy and reductions in false alarm rates. The proposed models have been experimented with two publicly available dataset SQLI (SQL-Injection) and SQLV2 (SQL-Injection version2). Specifically, SIDNet-1 achieves an impressive accuracy of 98.02% on the SQLI dataset, while SIDNet-2 closely follows with 97.54%. Furthermore, on the SQLIV2 dataset, SIDNet-1 attains 97.77%, and SIDNet-2 achieves 97.83% accuracy respectively.
The Internet of Things (IoT) has become a fundamental and omnipresent component of modern life, such as the infrastructure of intelligent transport systems and smart cities. All the next-generation IoT systems necessitate cognitive data processing that could be accomplished promptly through satellite communication. The edge server performs data processing in satellite communication, which is predicted to minimize service delay. However, in prevailing satellite technology, substantial transmission latency, significant route loss, and the resource, as well as energy limitations of IoT devices, all pose challenges to the rigorous service demands for latency and throughput in the upcoming 6G age. To tackle these challenges, 6G IoT will rely heavily on technologies such as space-air-ground integrated networks (SAGINs), edge computing, deep learning, machine learning, blockchain, and energy harvesting. Combining communication technology with Unmanned Aerial Vehicle (UAV) has recently been identified as one of the potential strategies in the future network. UAVs may provide a variety of services; however, the UAV’s onboard computational resources and battery backup are constrained. The Researchers in this article examine satellites as well as UAVs to deliver wireless IoT device cloud computing and edge computing services, respectively. Grounded IoT devices can conduct operations locally or offload them to UAV-based edge servers as well as distant cloud servers via satellites. The major emphasis is on the computational offloading dilemma and considering deep learning methods to optimize the task success rate considering energy dynamics and channel circumstances. The suggested AI-based offloading approach outperformed conventional methods, indicating that it can determine the most energy-efficient offloading policy.