Traders and investors are interested in accurately predicting cryptocurrency prices to increase returns minimize risk. However, due their uncertainty, volatility, dynamism, forecasting crypto is a challenging time series analysis task. Researchers have proposed predictors based on statistical, machine learning (ML), deep (DL) approaches, but the literature limited. Indeed, it narrow because focuses only of few most famous cryptos. In addition, scattered compares different models cryptos...

Short-term electricity markets are becoming more relevant due to less-predictable renewable energy sources, attracting considerable attention from the industry. The balancing market is closest real-time and most volatile among them. Its price forecasting literature limited, inconsistent outdated, with few deep learning attempts no public dataset. This work applies Irish a variety of prediction techniques proven successful in widely studied day-ahead market. We compare statistical, machine...

The integration of renewable energy into electricity markets poses significant challenges to price stability and increases the complexity market operations. Accurate reliable forecasting is crucial for effective participation, where dynamics can be significantly more challenging predict. Probabilistic forecasting, through prediction intervals, efficiently quantifies inherent uncertainties in prices, supporting better decision-making participants. This study explores enhancement probabilistic...

Diffuse reflectance spectroscopy (DRS) has been extensively studied in both preclinical and clinical settings for multiple applications, notably as a minimally invasive diagnostic tool tissue identification disease delineation. In this study, extended-wavelength DRS (EWDRS) measurements of ex vivo tissues ranging from ultraviolet through visible to the short-wave infrared region (355-1919 nm) are presented two datasets. The first dataset contains labelled EWDRS collected bone cement samples...

Pressure insoles allow for the collection of real time pressure data inside and outside a laboratory setting as they are non-intrusive can be simply integrated into industrial environments occupational health safety monitoring purposes. Activity detection is important wellbeing workers, present study aims to employ detect type industry-related task an individual performing by using random forest, artificial intelligence-based classification technique. Twenty subjects wore loadsol® performed...

Providers of cloud computing systems need to manage resources carefully meet the desired Quality Service and reduce waste due overallocation. An accurate prediction future demand is crucial allocate service requests without excessive delays. Current state-of-the-art methods such as Long Short-Term Memory-based models make only point forecasts considering uncertainty in their predictions. Forecasting a distribution would provide more comprehensive picture inform resource scheduler decisions....

A well-know control policy in stochastic inventory is the (R, s, S) policy, which raised to an order-up-to-level S at a review instant R whenever it falls below reorder-level s. To date, little or no work has been devoted developing approaches for computing parameters. In this work, we introduce hybrid approach that exploits tree search compute optimal replenishment cycles, and dynamic programming (s, levels given cycle. Up 99.8% of pruned by branch-and-bound technique with bounds generated...

Natural language processing and machine learning are gaining wide popularity in supporting judicial decision-making. Research this area is particularly active. However, a methodological issue the use of AI methods can lead to poor statistical soundness results. We consider improve work Aletras et. al. [1] for predicting outcome cases at European Court Human Rights. replicate their experiments using more statistically reliable methodology analyzed results state-of-the-art Bayesian techniques...

Drive-by road pavement monitoring, using smartphone sensing, has faced longstanding challenges in adoption due to low accuracy and limited applicability. This stems from significant uncertainties during data collection real-world scenarios, making it prohibitively difficult applying conventional machine learning models the detection of anomalies. paper presents a two-stage approach that extracts potential anomalies dataset classifies them into four typical feature categories. Unlike...

Wavelength selection from a large diffuse reflectance spectroscopy (DRS) dataset enables removal of spectral multicollinearity and thus leads to improved understanding the feature domain. Feature (FS) frameworks are essential discover optimal wavelengths for tissue differentiation in DRS-based measurements, which can facilitate development compact multispectral optical systems with suitable illumination clinical translation.

This work presents the results of a transdisciplinary analysis performed on Harward's Almanac (Dublin, 1666), an extremely rare volume currently housed in National Library Ireland. The uniqueness and historical value is related to presence nineteen handwritten poems, entered by anonymous scribe. These record textually important English clandestine satire circulating anonymously Dublin late seventeenth early eighteenth century. Following comprehensive assessment, it appeared evident that...

Predicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing provisioning cost. Modelling prediction uncertainty also desirable to better inform decision-making process, but research this field under-investigated. In paper, we propose univariate bivariate Bayesian deep learning models that provide predictions of workload its uncertainty. We run extensive experiments on Google Alibaba clusters,...

This paper introduces a new stochastic dynamic program (SDP) based heuristic to compute the (R,s,S) policy parameters for non-stationary lot-sizing problem with backlogging of excessive demand, fixed order and review costs, linear holding penalty costs. Our model combines greedy relaxation that considers replenishment cycles independent modified version Scarf's (s,S) SDP. A simple implementation requires prohibitive computational effort parameters. However, leveraging K-convexity property...

Cloud computing has seen widespread adoption because it increases the productivity and efficiency of industries allows for effective scalability their business [1]. Guaranteeing performance levels is at core cloud services requires huge computational resources, especially with latest advances in technologies such as Artificial Intelligence Internet Things [2]. Typically, customers subscribe to agreements where providers ensure specific reliability, availability responsiveness systems...

The Boolean Satisfiability Problem (SAT) was the first known NP-complete problem and has a very broad literature focusing on it. It been applied successfully to various real-world problems, such as scheduling, planning cryptography. SAT feature extraction plays an essential role in this field. solvers are complex, fine-tuned systems that exploit structure. ability represent/encode large using compact set of features practical use instance classification, algorithm portfolios, solver...

Short-term electricity markets are becoming more relevant due to less-predictable renewable energy sources, attracting considerable attention from the industry. The balancing market is closest real-time and most volatile among them. Its price forecasting literature limited, inconsistent outdated, with few deep learning attempts no public dataset. This work applies Irish a variety of prediction techniques proven successful in widely studied day-ahead market. We compare statistical, machine...

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Drive-by road pavement monitoring, using smartphone sensing, has faced longstanding challenges in adoption due to low accuracy and limited applicability. This stems from significant uncertainties during data collection real-world scenarios, making it prohibitively difficult applying conventional machine learning models the detection of anomalies. In this paper, a novel two-stage approach is proposed first extract potential anomalies dataset then classify them into four categories...

Revision total hip arthroplasty suffers from low visibility with intra-body navigation hinging primarily on auditory and tactile cues. Consequently, the risk of surgical injury increases. One proposition to increase precision is integrating an algorithm which classifies encountered tissues based their reflectance spectra into tools. Previous works have developed machine learning applications for automatic, binary, classification tissue diffuse spectroscopy (DRS) signals exploratory...

Raman spectroscopy, a non-invasive analytical method, offers insights into molecular structures and interactions in various liquid solid samples with applications ranging from material science, chemical analysis to medical diagnostics. Preprocessing of spectra is vital remove interferences like background signals calibration errors, ensuring precise data extraction. Artificial intelligence, particularly machine learning (ML), aids extracting valuable information complex datasets. However,...