Wavelet-based automated localization and classification of peaks in streamflow data series

Pellegrini, Maurizio; Sini, Francesca; Taramasso, Angela Celeste

doi:10.1016/j.cageo.2011.08.005

Cited by 8 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such analysis could therefore be a fair amount of work, dealing with decades-long time series or dam releases. Discrete wavelet transform (DWT) combined with artificial intelligence (AI) has been employed in order to develop an unsupervised method for fast detecting, localizing, and classifying flood events in real-world stage-discharge data time series [7]. The method, tested on a discharge dataset obtained through the SOL system, does not require any a priori information such as catchment characteristics or alert flood thresholds.…”

Section: Discussionmentioning

confidence: 99%

Dissemination and Exploitation of Regional Meteo-Hydrological Datasets through Web-based Interactive Applications: The SOL System Case Study

Pellegrini

2021

OJES

View full text Add to dashboard Cite

The effects of climate change are already being felt in several parts of the World. Variability of changing rainfall intensity, drought and weather patterns contribute to determining the vulnerability of many human activities such as agriculture. In the next future, climate change considerations will depend on having appropriate strategies such as strengthen implementation agencies working in a coordinated manner and with a data-driven approach in order to ensure monitoring, reporting and data verification. In this context, national and regional meteorological Services are facing with high demand for timely and quality information, services and products. A web-based interactive application with the aim of disseminating meteo-hydrological information at regional scale is described in this paper. The web application is built on a relational database and client-side programming has been used for implementing the user interface and controlling the web page behavior. The combination of PHP (Hypertext Preprocessor, a general-purpose scripting language, especially suited to server-side web development) and JavaScript (high-level object-oriented scripting language, nowadays the dominant client-side scripting language of the Web) has been chosen for this reason, since such software is free to use for everyone. The SOL system, developed on behalf of Marche region, Italy, was chosen as a case study, due to its multi-source data framework and because of the processing and public dissemination of several ad-hoc data elaborations.

show abstract

Section: Discussionmentioning

confidence: 99%

Dissemination and Exploitation of Regional Meteo-Hydrological Datasets through Web-based Interactive Applications: The SOL System Case Study

Pellegrini

2021

OJES

View full text Add to dashboard Cite

show abstract

“…The Contrast Limited Adaptive Histogram Equalization (CLAHE) equalization technique is used to reduce noise and localize the contrast values of pixels in the images [19,20]. The wavelet transform [21][22][23] is used to compress the images without losing the essential features for levels 1 and 2 that provide two versions of the dataset of images, consisting of images containing 112 pixels and 56 pixels. Finally, both versions of the dataset are fed into machine learning classifiers for training and testing.…”

Section: Introductionmentioning

confidence: 99%

Memory Forensics-Based Malware Detection Using Computer Vision and Machine Learning

et al. 2022

View full text Add to dashboard Cite

Malware has recently grown exponentially in recent years and poses a serious threat to individual users, corporations, banks, and government agencies. This can be seen from the growth of Advanced Persistent Threats (APTs) that make use of advance and sophisticated malware. With the wide availability of computer-automated tools such as constructors, email flooders, and spoofers. Thus, it is now easy for users who are not technically inclined to create variations in existing malware. Researchers have developed various defense techniques in response to these threats, such as static and dynamic malware analyses. These techniques are ineffective at detecting new malware in the main memory of the computer and otherwise require considerable effort and domain-specific expertise. Moreover, recent techniques of malware detection require a long time for training and occupy a large amount of memory due to their reliance on multiple factors. In this paper, we propose a computer vision-based technique for detecting malware that resides in the main computer memory in which our technique is faster or memory efficient. It works by taking portable executables in a virtual environment to extract memory dump files from the volatile memory and transform them into a particular image format. The computer vision-based contrast-limited adaptive histogram equalization and the wavelet transform are used to improve the contrast of neighboring pixel and to reduce the entropy. We then use the support vector machine, random forest, decision tree, and XGBOOST machine learning classifiers to train the model on the transformed images with dimensions of 112 × 112 and 56 × 56. The proposed technique was able to detect and classify malware with an accuracy rate of 97.01%. Its precision, recall, and F1-score were 97.36%, 95.65%, and 96.36%, respectively. Our finding shows that our technique in preparing dataset with more efficient features to be trained by the Machine Learning classifiers has resulted in significant performance in terms of accuracy, precision, recall, F1-score, speed and memory consumption. The performance has superseded most of the existing techniques in its unique approach.

show abstract

“…Wavelet method is a powerful tool to detect multiscale and localized features of time-series data for transient processes. Wavelet coherence has been used to distinguish the localized and scale-specific relationship embedded in nonstationary time-series data sets observed in various scientific disciplines such as geochemistry (Chen and Cheng 2016), geophysics (Heidary and Javaherian 2013), and hydrology (Pellegrini et al 2012;Carey et al 2013;Graf et al 2014;Song et al 2018). These studies usually considered only one influencing factor on the dynamic process, although the combination of influencing factors may exist.…”

Section: Introductionmentioning

confidence: 99%

Multiple Wavelet Coherence to Evaluate Local Multivariate Relationships in a Groundwater System

Sun

Zhang

et al. 2021

Groundwater

View full text Add to dashboard Cite

Groundwater level fluctuations are affected by surface properties due to complex correlations of groundwatersurface water interaction and/or other surface processes, which are usually hard to be accurately quantified. Previous studies have assessed the relationship between groundwater level fluctuations and specific controlling factors. However, few studies have been conducted to explore the impact of the combination of multiple factors on the groundwater system. Hence, this paper tries to explore the localized and scale-specific multivariate relationships between the groundwater level and controlling factors (such as hydrologic and meteorological factors) using bivariate wavelet coherence and multiple wavelet coherence. The groundwater level fluctuations of two wells in areas covered by different plant densities (i.e., the riparian zone of the Colorado River, USA) are analyzed. Main findings include three parts. First, barometric pressure and river stage are the best factors to interpret the groundwater level fluctuations at small scales (<1 day) and large scales (>1 day) at the well of low-density plants stand, respectively. Second, at the well of high-density plants stand, the best predictors to control the groundwater level fluctuations include barometric pressure (<1 day), the combination of barometric pressure and temperature (1-7 days), temperature (7-30 days), and the combination of barometric pressure, temperature, and river stage (>30 days). The best predictor of groundwater head fluctuations depends on the variance of the vegetation coverage and hydrological processes. Third, these results provide a suite of factors to explain the groundwater level variations, which is an important topic in water-resource prediction and management.

show abstract

Wavelet-based automated localization and classification of peaks in streamflow data series

Cited by 8 publications

References 10 publications

Dissemination and Exploitation of Regional Meteo-Hydrological Datasets through Web-based Interactive Applications: The SOL System Case Study

Dissemination and Exploitation of Regional Meteo-Hydrological Datasets through Web-based Interactive Applications: The SOL System Case Study

Memory Forensics-Based Malware Detection Using Computer Vision and Machine Learning

Multiple Wavelet Coherence to Evaluate Local Multivariate Relationships in a Groundwater System

Contact Info

Product

Resources

About