Detection of aerial vehicles is a challenging task. Over time, the significance of developing such vehicles has increased rapidly. However, an utmost concern arises from the potential misuse of these small-sized vehic...
详细信息
ISBN:
(数字)9798350349719
ISBN:
(纸本)9798350349726
Detection of aerial vehicles is a challenging task. Over time, the significance of developing such vehicles has increased rapidly. However, an utmost concern arises from the potential misuse of these small-sized vehicles in illicit activities such as unauthorized surveillance, smuggling contraband, or disrupting critical infrastructure significant security threats. Recognizing the gravity of this issue, we have opted to introduce an innovative approach to automate the detection processes for aerial vehicles. This initiative aims to deploy effective drone detection systems to mitigate risks and safeguard against illegal activities. We put use to two datasets from GitHub depot. Cepstral, spectral, and time domain features were extracted from the data, followed by classification. We conducted two experiments, with the first (Drone, No-Drone) yielding 98.6% accuracy, using the Ensemble (Bagged Trees) classifier. The second set of experimentation addressed five classes: Background Noises, Bebop Drone, Drone, Helicopter, and Mambo Drone. Ensemble (Bagged trees) again outperformed all other classifiers and achieved 98.3% accuracy. The results highlight that our proposed framework gives effective results based on audio signals of different aerial vehicles.
There are many different types of exergaming, but one of the most engaging one is the one with virtual reality. This type of gaming allows you to immerse yourself in a completely different world, and it can be a lot o...
详细信息
This article discusses the problems of optimizing computing power by improving the performance of web applications. The shared responsibility model for the Azure cloud is considered and the area of responsibility of t...
详细信息
ISBN:
(数字)9781665498043
ISBN:
(纸本)9781665498050
This article discusses the problems of optimizing computing power by improving the performance of web applications. The shared responsibility model for the Azure cloud is considered and the area of responsibility of the user and the provider of cloud services for such models as IaaS, PaaS and SaaS is shown. The article discusses methods for optimizing loops and provides the results of performance tests in Microsoft Visual Studio using Performance Profiler and C# language. Methods for optimizing such constructs as algebraic expressions are described and ways to increase performance from caching are considered. Optimization methods are described when using the String type. The article also looks at how boxing/unboxing objects of reference and value types improve application performance. The practical steps given in the article are aimed at writing safe and efficient code. Please, note that the tests and optimization designs carried out and described in the article will help to write code that will not cause poor application performance in the future. These steps will help to avoid buying software to detect optimization problems and, accordingly, significantly reduce material costs for the entire project as a whole.
Researchers in the discipline of Data Mining (DM) occasionally disregard the need of ensuring a dataset is evenly distributed. As such, it may have a major impact on how things are ultimately sorted. Most classifiers ...
详细信息
Researchers in the discipline of Data Mining (DM) occasionally disregard the need of ensuring a dataset is evenly distributed. As such, it may have a major impact on how things are ultimately sorted. Most classifiers function on the concept that the data is roughly normally distributed. Therefore, the categorization approach is no longer as successful as it once was and fixing this is essential. This research aims to construct an evaluation of several methods for producing labels for minority classes to prevent the model from developing bias toward protected attributes. In this study, different researcher’s work learned to determine the most effective method for disseminating the data. There will be a discussion of ways to enhance categorization abilities in the conclusion. The future of data-balancing research is determined by weighing the relative merits of the several possible methodological amalgamations.
Blockchain Technology is gaining popularity throughout various industry verticals due to its data decentralization and tamper-evident nature. Machine Learning (ML) is all about embedding a learning capability to compu...
详细信息
In the current global scenario, marked by the COVID-19 pandemic, it has become imperative for healthcare systems around the globe to swiftly and accurately diagnose the disease. This is where cutting-edge approaches s...
In the current global scenario, marked by the COVID-19 pandemic, it has become imperative for healthcare systems around the globe to swiftly and accurately diagnose the disease. This is where cutting-edge approaches such as machine learning (ML) come into play, specifically, ML-based identification of COVID-19 from chest X-ray and CT-Scan imagery. Our research collective is devotedly working towards devising a robust, accurate ML model capable of deciphering these images to identify COVID-19 effectively. This involves the application of a variety of AI algorithms and vast data resources. Our work is grounded on a large, annotated image dataset that aids in training and refining the model. Our findings indicate that ML methodologies can discern COVID-19 from chest X-ray and CT scan images with a mean accuracy of 90%. Such a tool holds promise in aiding medical practitioners in prompt and precise patient diagnosis, thereby improving patient prognosis. The most notable contribution of our study lies in the creation of an ML model that can accurately detect COVID-19 in chest X-ray and CT-Scan images, potentially aiding in early disease detection and management.
Data aggregation is an important approach in IoT sensor networks since it reduces data transfer while also preserving energy and bandwidth. This research investigates the challenge of time-efficient data aggregation i...
详细信息
ISBN:
(数字)9798350327939
ISBN:
(纸本)9798350327946
Data aggregation is an important approach in IoT sensor networks since it reduces data transfer while also preserving energy and bandwidth. This research investigates the challenge of time-efficient data aggregation in wireless sensor networks, which is critical in military, civilian, and industrial applications. Effective data aggregation algorithm design and optimization are required for quick and interference-free data collection. Machine learning has received attention for outperforming classical heuristic techniques. The research presents the first Graph Neural Network (GNN) model for data aggregation in IoT sensor networks, which incorporates Graph Attention Networks (GATs) and fully connected layers. The GNN-based model learns network topology and node attributes, creating node embeddings and correcting sensor node transmitting time slots. With a centralized training procedure and adapted execution for network size change, the proposed approach achieves satisfactory performance compared to the heuristic algorithm.
BERT and other pre-trained language models (PLMs) are ubiquitous in modern NLP. Even though PLMs are the state-of-the-art (SOTA) models for almost every NLP task (Qiu et al., 2020), the significant latency during infe...
详细信息
Human activity recognition (HAR) research using smartphone sensor technology has changed people's daily lives and opened the door for numerous exciting applications due to its extensive applications in addressing ...
Human activity recognition (HAR) research using smartphone sensor technology has changed people's daily lives and opened the door for numerous exciting applications due to its extensive applications in addressing real-world humancentric issues. These studies, however, mostly concentrated on a woman's daily activities and behaviours when she is attacked, such as running, walking, sleeping,eating,drinking,lying, straight punching, front kicking, and so forth. The article offers a method to foresee human behaviour using a deep learning model and evaluates the efficiency of the approach using real-world data in response to this. We offer an LSTM structure for detecting the intensity of HAR in order to track activity patterns and build a neural network with binary classification skills to evaluate the situation of women. The proposed model uses the dataset to identify human activity, which records 30 volunteers' body movements while they engage in 18 physical activities. Feature engineering is used to extract additional variables from the data in addition to that. Our proposed model achieves a 90.89% accuracy.
This paper evaluates the uplink spectral efficiency (SE) achieved by a reconfigurable intelligent surface (RIS)-aided cell-free massive MIMO system with max-min fairness (MMF) power allocation. We provide an exact clo...
This paper evaluates the uplink spectral efficiency (SE) achieved by a reconfigurable intelligent surface (RIS)-aided cell-free massive MIMO system with max-min fairness (MMF) power allocation. We provide an exact closed-form expression for an achievable SE expression which assumes maximum ratio receive combining at the access points (APs) and centralized large-scale fading decoding at the central processing unit. The derived SE expression also accounts for imperfect channel estimation and spatially correlated Ricean fading channels for both direct (APs-users) and cascaded (APs-RISs-users) links. Alongside this, we provide a generalized SE expression and evaluate the performance achieved by local partial minimum mean-squared error combining. Finally, we optimally solve the RIS phase-shift selection problem in order to maximize the aggregate channel gains, and derive a closed-form solution to the MMF power allocation problem. Simulation results validate the effectiveness of the proposed framework in enhancing the unlink SE with resnect to various benchmarks.
暂无评论