Search results for "CLASSIFICATION"
showing 10 items of 29475 documents
The Truth is Out There : Focusing on Smaller to Guess Bigger in Image Classification
2023
In Artificial Intelligence (AI) in general and in Machine Learning (ML) in particular, which are important and integral components of modern Industry 4.0, we often deal with uncertainty, e.g., lack of complete information about the objects we are classifying, recognizing, diagnosing, etc. Traditionally, uncertainty is considered to be a problem especially in the responsible use of AI and ML tools in the smart manufacturing domain. However, in this study, we aim not to fight with but rather to benefit from the uncertainty to improve the classification performance in supervised ML. Our objective is a kind of uncertainty-driven technique to improve the performance of Convolutional Neural Netwo…
Semantics of Voids within Data: Ignorance-Aware Machine Learning
2021
Operating with ignorance is an important concern of geographical information science when the objective is to discover knowledge from the imperfect spatial data. Data mining (driven by knowledge discovery tools) is about processing available (observed, known, and understood) samples of data aiming to build a model (e.g., a classifier) to handle data samples that are not yet observed, known, or understood. These tools traditionally take semantically labeled samples of the available data (known facts) as an input for learning. We want to challenge the indispensability of this approach, and we suggest considering the things the other way around. What if the task would be as follows: how to buil…
Multitask deep learning for native language identification
2020
Identifying the native language of a person by their text written in English (L1 identification) plays an important role in such tasks as authorship profiling and identification. With the current proliferation of misinformation in social media, these methods are especially topical. Most studies in this field have focused on the development of supervised classification algorithms, that are trained on a single L1 dataset. Although multiple labeled datasets are available for L1 identification, they contain texts authored by speakers of different languages and do not completely overlap. Current approaches achieve high accuracy on available datasets, but this is attained by training an individua…
Bioactivity of Carlina acaulis essential oil and its main component to the olive fruit fly, Bactrocera oleae: ingestion toxicity, electrophysiologica…
2021
In recent years, botanical insecticides based on essential oils (EOs), or their main components, have received much attention as promising tools for Integrated Pest Management, due to their environmental safety and low side effects on non-target organisms. In this study, Carlina acaulis EO and its main component, carlina oxide, recently proven to be effective larvicidal and adulticidal agents against some insect pests, were analyzed for their toxicity, electroantennographic (EAG), and behavioral responses to adult olive fruit fly (Bactrocera oleae). The C. acaulis EO was more toxic to the tephritid than the carlina oxide, and both were more toxic to the same insect pest than EOs from other …
Diuron mobility through vineyard soils contaminated with copper
2005
International audience; The herbicide diuron is frequently applied to vineyard soils in Burgundy, along with repeated treatments with Bordeaux mixture (a blend of copper sulfate and calcium hydroxide) that result in elevated copper concentrations. Cu could in principle affect the fate and transport of diuron or its metabolites in the soil either directly by complexation or indirectly by altering the populations or activity of microbes involved in their degradation. To assess the effect of high Cu concentrations on diuron transport, an experiment was designed with ten undisturbed columns of calcareous and acidic soils contaminated with 17–509 mg kg−1 total Cu (field-applied). Grass was plant…
Xrn1 influence on gene transcription results from the combination of general effects on elongating RNA pol II and gene-specific chromatin configurati…
2020
mRNA homoeostasis is favoured by crosstalk between transcription and degradation machineries. Both the Ccr4-Not and the Xrn1-decaysome complexes have been described to influence transcription. While Ccr4-Not has been shown to directly stimulate transcription elongation, the information available on how Xrn1 influences transcription is scarce and contradictory. In this study we have addressed this issue by mapping RNA polymerase II (RNA pol II) at high resolution, using CRAC and BioGRO-seq techniques in Saccharomyces cerevisiae. We found significant effects of Xrn1 perturbation on RNA pol II profiles across the genome. RNA pol II profiles at 5ʹ exhibited significant alterations that were com…
Glottal Source Features for Automatic Speech-Based Depression Assessment
2017
Depression is one of the most prominent mental disorders, with an increasing rate that makes it the fourth cause of disability worldwide. The field of automated depression assessment has emerged to aid clinicians in the form of a decision support system. Such a system could assist as a pre-screening tool, or even for monitoring high risk populations. Related work most commonly involves multimodal approaches, typically combining audio and visual signals to identify depression presence and/or severity. The current study explores categorical assessment of depression using audio features alone. Specifically, since depression-related vocal characteristics impact the glottal source signal, we exa…
Exploring relationships between audio features and emotion in music
2009
In this paper, we present an analysis of the associations between emotion categories and audio features automatically extracted from raw audio data. This work is based on 110 excerpts from film soundtracks evaluated by 116 listeners. This data is annotated with 5 basic emotions (fear, anger, happiness, sadness, tenderness) on a 7 points scale. Exploiting state-of-the-art Music Information Retrieval (MIR) techniques, we extract audio features of different kind: timbral, rhythmic and tonal. Among others we also compute estimations of dissonance, mode, onset rate and loudness. We study statistical relations between audio descriptors and emotion categories confirming results from psychological …
Multilayer perceptron training with multiobjective memetic optimization
2016
Machine learning tasks usually come with several mutually conflicting objectives. One example is the simplicity of the learning device contrasted with the accuracy of its performance after learning. Another common example is the trade-off that must often be made between the rate of false positive and false negative predictions in diagnostic applications. For computer programs that learn from data, these objectives are formulated as mathematical functions, each of which describes one facet of the desired learning outcome. Even functions that intend to optimize the same facet may behave in a subtly different and mutually conflicting way, depending on the task and the dataset being examined. Mul…
Antioxidant Potential of Extracts Obtained from Macro- (Ascophyllum nodosum, Fucus vesiculosus and Bifurcaria bifurcata) and Micro-Algae (Chlorella v…
2018
Background: Natural antioxidants, which can replace synthetic ones due to their potential implications for health problems in children, have gained significant popularity. Therefore, the antioxidant potential of extracts obtained from three brown macroalgae (Ascophyllum nodosum, Fucus vesiculosus and Bifurcaria bifurcata) and two microalgae (Chlorella vulgaris and Spirulina platensis) using ultrasound-extraction as an innovative and green approach was evaluated. Methods: Algal extracts were obtained by ultrasound-assisted extraction using water/ethanol (50:50, v:v) as the extraction solvent. The different extracts were compared based on their antioxidant potential, measuring the extraction …