Wildfires are one of the most destructive natural disasters that cause significant harm to both humans and the environment. Predicting their spread is critical for disaster management and preparedness. In this study, ...
Wildfires are one of the most destructive natural disasters that cause significant harm to both humans and the environment. Predicting their spread is critical for disaster management and preparedness. In this study, we have utilized machine learning algorithms, including Decision Tree Regression, XG Boost Regression, and Artificial Neural Networks, to predict the spread of wildfires using the Next Day Wildfire dataset. The dataset includes satellite images, weather, and geography conditions aggregated across the United States from 2012 to 2020. We preprocessed and engineered the dataset which includes the features such as elevation, wind direction and speed, temperature, humidity, precipitation, drought index, vegetation index, energy release component, and population density. We evaluated the models using the Root Mean Squared Error (RMSE) metric and found that the Decision Tree Regression algorithm performed the best with the lowest RMSE score. Our study highlights the potential of machine learning algorithms in predicting the spread of wildfires, which can aid in better disaster management and preparedness efforts.
A compact size nature-inspired, petal shaped two-port MIMO antenna is proposed to operate at V- and E-band. Initially, a single-element antenna is designed to resonate for quad-band. The proposed antenna resonates at ...
详细信息
Few-shot learning is a challenging task in which a classifier needs to quickly adapt to new classes. These new classes are unseen in the training stage, and there are only very few samples (e.g., five images) provided...
Few-shot learning is a challenging task in which a classifier needs to quickly adapt to new classes. These new classes are unseen in the training stage, and there are only very few samples (e.g., five images) provided for learning each new class in the testing stage. When the existing methods learn with such a small amount of samples, they could easily be affected by the outliers. Moreover, the category center calculated from those few samples may deviate from the true center. To address these issues, we propose a novel approach called Current Task Variational Auto-Encoder (CTVAE) for few-shot learning. In our framework, a trained feature extractor first produces the features of the current task, and these features are used to repeatedly train the generator in CTVAE. After that, we can use CTVAE to generate additional features of samples, and then find a new center of the category based on these newly generated features. Compared with the original center, the new center tends to be closer to the true center in vector space. CTVAE can break the limitation of traditional few-shot learning methods, which can only fine-tune the model with very few samples in the testing stage. Moreover, by generating the features directly without producing the images first, the training process of the generator in CTVAE is simplified and becomes more efficient, and the features can be generated faster and more precisely. According to the experiments on benchmark datasets (i.e., Mini-ImageNet, CUB, and CIFAR-FS), our proposed framework is able to outperform the state-of-the-art methods and improves the accuracy by 1–4%. We also conduct experiments on the cross-domain tasks, and the results show that the proposed framework can bring 1-5% accuracy improvements.
Debugging microservices in complex cloud-native deployments can be a daunting task due to interaction-based problems and challenges in reproducing such environments. Traditional fault localization approaches may be in...
Debugging microservices in complex cloud-native deployments can be a daunting task due to interaction-based problems and challenges in reproducing such environments. Traditional fault localization approaches may be ineffective, leading to longer debugging times. To address these challenges, we propose utilizing checkpoint/restart (C/R) techniques to replicate buggy environments across different hardware configurations without code instrumentation or specialized kernels. Our approach integrates with existing debugging practices, making it adaptable and user-friendly. However, since C/R requires some downtime, we assess our approach’s practicality by analyzing data from 13,000 observations and estimating the time required to capture a service’s state. The minimal downtime introduced by our approach minimizes service interruption. This can be leveraged by operators to plan deployments, live debugging, maintenance, and game-day operations. By combining the power of C/R techniques with existing debugging practices, we aim to facilitate environment reproduction and reduce the iterative nature of the debugging process in complex cloud-native deployments.
The debt market is a substantial industry, estimated to be of significant value and projected to grow further in the near future. However, its size is marred by inefficiencies due to a lack of transparency and trust. ...
The debt market is a substantial industry, estimated to be of significant value and projected to grow further in the near future. However, its size is marred by inefficiencies due to a lack of transparency and trust. To address these issues, DeFy, a blockchain-based system, offers loans to borrowers using their cryptocurrency assets as collateral. Leveraging smart contract technology and a decentralized network, DeFy creates a secure and transparent lending environment that operates globally without intermediaries. Empowering users with autonomy to select preferred lenders through a robust bidding system, DeFy enhances transparency in the borrowing process and empowers borrowers to make informed decisions. This user-driven lending approach provides an efficient and secure means for borrowers to access capital without liquidating their cryptocurrency holdings, while allowing lenders to earn interest on their capital through the lending process.
Breathing difficulties, such as shortness of breath or rapid breathing, can significantly harm health and diminish the quality of life. Breathing exercises are widely recognized for their effectiveness in resolving su...
Breathing difficulties, such as shortness of breath or rapid breathing, can significantly harm health and diminish the quality of life. Breathing exercises are widely recognized for their effectiveness in resolving such difficulties. They increase lung function, ease discomfort, and alleviate stress. However, current breathing-assisted methods, such as the incentive spirometer, do not accurately track the duration and frequency of training despite their advantages. Furthermore, the process of performing breathing exercises is tedious over time, making users feel bored and reducing their motivation. Thus, we presented Breathing+, a breathing video game designed to address these limitations by providing a series of game challenges. Breathing+ incorporated sensors to detect breathing signals and provided users with real-time feedback on a screen. According to the experimental results, Breathing+ achieved a breathing recognition accuracy of 95%. In addition, the response time to the user’s breathing was around 0.23 s.
This paper describes a 24.8 μm2 on-chip CMOS digital temperature sensor core operable on 95 nW at the 200mV supply voltage. The target of this sensor is IoT devices powered by energy harvesters with ultra-low output ...
详细信息
DNA-based encryption with bioinformatics has emerged as a promising field for secure data storage and transfer. This study analyzes the bioinformatics aspects of DNA cryptography, focusing on important advancements an...
详细信息
ISBN:
(数字)9798331520762
ISBN:
(纸本)9798331520779
DNA-based encryption with bioinformatics has emerged as a promising field for secure data storage and transfer. This study analyzes the bioinformatics aspects of DNA cryptography, focusing on important advancements and challenges. We look at techniques like DNA origami, enzymatic reactions, and DNA strand displacement that use DNA sequences to encode and decode data. Additionally discussed are the security implications of DNA-based cryptography, including privacy issues, data integrity issues, and the potential for DNA-based attacks. Finally, we outline some possible directions for further review, such as developing more robust error-correction systems, looking at cutting-edge DNA-based encryption methods using bioinformatics, and addressing the ethical and societal implications of this emerging technology.
Text classification is a fundamental activity in natural language processing (NLP), that includes classifying text resources into predetermined groups. With the growing concerns over data privacy and confidentiality, ...
Text classification is a fundamental activity in natural language processing (NLP), that includes classifying text resources into predetermined groups. With the growing concerns over data privacy and confidentiality, there is a need to perform text classification on encrypted data to protect sensitive information. In recent years, homomorphic encryption has emerged as a powerful technique that makes computations possible on encrypted data without compromising its confidentiality. This paper provides an overview of text classification using machine learning algorithms on encrypted data. In this research work, we have taken a data set of movie reviews. The data set is cleaned by removing stop words and performing stemming, lemmatization, and tokenization. We utilized a semantic model with inverse document frequency weighting and term frequency weighting to represent the data (TF-IDF). For the classification of the data set, we have applied six machine learning algorithms Logistic Regression, Naïve Bayes, KNN, Support Vector Machine, Random Forest, and Decision Tree. The plain text is encrypted using a somewhat homomorphic encryption technique called the RSA method. The ciphertext is subjected to the machine learning algorithms mentioned above. We have compared the results for accuracy. The Random Forest algorithm was found to give 75.56% accuracy compared to other algorithms on encrypted data. In this work, we have calculated the time taken by each algorithm for execution on plain text and ciphertext. It was observed that the Random Forest method took more time and the KNN method took less time comparatively.
Modern network administration desires to have early detection of DDoS traffic before damages occur. Nevertheless, as Internet traffic grows over years, it becomes more challenging to detect DDoS traffic in an efficien...
Modern network administration desires to have early detection of DDoS traffic before damages occur. Nevertheless, as Internet traffic grows over years, it becomes more challenging to detect DDoS traffic in an efficient and effective manner. The survey of existing literature shows that random forest classifier, when applied to DDoS detection, yields great performance at low learning costs. This work is devoted to a case study of implementing and using random forest classifier to detect DDoS traffic generated by a well-known DDoS tool named HULK. Our result indicates that when used with a good feature selection mechanism, random forest classifier can achieve a high detection accuracy with fast training time.
暂无评论