656 research outputs found
Opinion mining from machine translated Bangla reviews with stacked contractive auto-encoders
No full textIn the last years, online users have been sharing more and more opinions, reviews, and comments on the web. Opinion mining is the automatic process of getting the subject of such opinions, and recently it has been attracting great commercial and academic interest. Several methods were presented for performing opinion mining in Bangla language, however they reported limited performance. In the present article, we considered the only two publicly datasets available for opinion mining in the Bangla language. We machine translated the datasets into the English language and we preprocessed them by extracting textual frequency based features. Then, we designed two stacked contractive auto-encoders based architectures to perform opinion mining in Bangla language, one for each dataset. The classifiers were trained on the machine translated version on the two datasets in a stacked learning fashion. The proposed classifiers achieved improved performance, with respect to accuracy (>= 96%), precision (>= 93%), recall (>= 94%), and F1 score (>= 94%), reported in the past state of the art works. Furthermore, the experimental results showed that both the machine translation procedure and the stacked learning frameworks improved the final classification performance
Aspect extraction from bangla reviews through stacked auto-encoders
No full textInteractions between online users are growing more and more in recent years, due to the latest developments of the web. People share online comments, opinions, and reviews about many topics. Aspect extraction is the automatic process of understanding the topic (the aspect) of such comments, which has obtained huge interest from commercial and academic points of view. For instance, reviews available in webshops (like eBay, Amazon, Aliexpress, etc.) can help the customers in purchasing products and automatic analysis of reviews would be useful, as sometimes it is almost impossible to read all the available ones. In recent years, aspect extraction in the Bangla language has been regarded more and more as a task of growing importance. In the previous literature, a few methods have been introduced to classify Bangla texts according to the aspect they were focused on. This kind of research is limited mainly due to the lack of publicly available datasets for aspect extraction in the Bangla language. We take into account the only two publicly available datasets, recently published, collected for the task of aspect extraction in the Bangla language. Then, we introduce several classification methods based on stacked auto-encoders, as far as we know never exploited in the task of aspect extraction in Bangla, and we achieve better aspect classification performance with respect to the state-of-the-art: The experiments show an average improvement of 0.17, 0.31 and 0.30 (across the two datasets), respectively in precision, recall and F1-score, reported in the state-of-the-art works that tackled the problem
Will the machine like your image? Automatic assessment of beauty in images with machine learning techniques
No full textAlthough the concept of image quality has been a subject of study for the image processing community for more than forty years (where, with the term “quality”, we are referring to the accuracy with which an image processing system captures, processes, stores, compresses, transmits, and displays the signals that compose an image), notions related to aesthetics of photographs and images have only appeared for about ten years within the community. Studies devoted to aesthetics of images are multiplying today, taking advantage of the latest machine learning techniques and mostly due to the proliferation of huge communities and websites, specialized in digital photography sharing and archiving, such as Flickr, Imgur, DeviantArt, and Instagram. In this review, we examine the latest advances of computer methods that aim at computationally distinguishing high-quality from low-quality photos and images, relying on machine learning techniques. The paper is organized as follows: First, we introduce many approaches to aesthetics, studied in philosophy, neurobiology, experimental psychology, and sociology, to see what lighting they propose to researchers. Such points of view let us explain the weakness of the current consensus on the difficult aesthetics problem and the importance of the ongoing debates on it. Then, we analyze the work done in the community of pattern recognition and artificial intelligence on the task of automatic aesthetic assessment, and we both compare and critically examine the presented results. Finally, we describe many issues that have not been addressed, and starting from these, we outline some possible future directions
A Review of Facial Landmark Extraction in 2D Images and Videos Using Deep Learning
No full textThe task of facial landmark extraction is fundamental in several applications which involve facial analysis, such as facial expression analysis, identity and face recognition, facial animation, and 3D face reconstruction. Taking into account the most recent advances resulting from deep-learning techniques, the performance of methods for facial landmark extraction have been substantially improved, even on in-the-wild datasets. Thus, this article presents an updated survey on facial landmark extraction on 2D images and video, focusing on methods that make use of deep-learning techniques. An analysis of many approaches comparing the performances is provided. In summary, an analysis of common datasets, challenges, and future research directions are provided
"Nudità", "Nulla", "Nuvola": Bodini e la 'resurrezione' simbolicamente gestuale nell' 'Inutile'
No full textLettura ermeneutica delle immagini poetiche più 'oscure' della poesia di Vittorio Bodini, in particolare quelle caratterizzate da una sovrapposizione stilistica a carattere surreale ed ermetico. L'interpretazione critica 'utilizza' concetti anche teorici, sul piano del metodo, di M. Bachtin, G. Debenedetti e P. Ricoeur
Consumer Perception of Local and Organic Products: Substitution or Complementary Goods?
No full textMany consumers are interested in local products because of the perceived benefits of freshness, stronger taste and higher quality. To consumers the origin attribute represents a strong purchasing criterion. With respect to organic produce, local food products may be perceived either as substitutes or as complementary. A qualitative approach to data collection (focus groups) and to data processing (content analysis) has been used to analyse Italian consumers’ perception with respect to local and organic food products. In the framework of the EU project QLIF (FP6-506358) a discussion guide to focus group interview was used in order to identify important purchase criteria, the willingness to pay, as well as the role of organic food products in purchasing criteria. Two animal – yogurt and eggs – and two non animal products – bread
and tomatoes – were taken into account. Focus groups interviews indicate that Italian consumers place much importance on the local origin of food products, especially if fresh consumed. The origin with its implication of seasonality, territoriality and localness are among the major motivating and trust factors, however not always linked to organic food products. The lack of availability of local and organic food products together with retailing issues are taken into consideration. Differentiation throughout animal and non-animal products and between processed food products and commodities is analysed. Organic seems to suffer in global markets, localness may suggest a solution. The research provides insights on substitution and complementary marketing strategies
Daily Streamflow Forecasting Using AutoML and Remote-Sensing-Estimated Rainfall Datasets in the Amazon Biomes
No full textReliable streamflow forecasting is crucial for several tasks related to water-resource management, including planning reservoir operations, power generation via Hydroelectric Power Plants (HPPs), and flood mitigation, thus resulting in relevant social implications. The present study is focused on the application of Automated Machine-Learning (AutoML) models to forecast daily streamflow in the area of the upper Teles Pires River basin, located in the region of the Amazon biomes. The latter area is characterized by extensive water-resource utilization, mostly for power generation through HPPs, and it has a limited hydrological data-monitoring network. Five different AutoML models were employed to forecast the streamflow daily, i.e., auto-sklearn, Tree-based Pipeline Optimization Tool (TPOT), H2O AutoML, AutoKeras, and MLBox. The AutoML input features were set as the time-lagged streamflow and average rainfall data sourced from four rain gauge stations and one streamflow gauge station. To overcome the lack of training data, in addition to the previous features, products estimated via remote sensing were leveraged as training data, including PERSIANN, PERSIANN-CCS, PERSIANN-CDR, and PDIR-Now. The selected AutoML models proved their effectiveness in forecasting the streamflow in the considered basin. In particular, the reliability of streamflow predictions was high both in the case when training data came from rain and streamflow gauge stations and when training data were collected by the four previously mentioned estimated remote-sensing products. Moreover, the selected AutoML models showed promising results in forecasting the streamflow up to a three-day horizon, relying on the two available kinds of input features. As a final result, the present research underscores the potential of employing AutoML models for reliable streamflow forecasting, which can significantly advance water-resource planning and management within the studied geographical area
Generative Artificial Intelligence and Regulations: Can We Plan a Resilient Journey Toward the Safe Application of Generative Artificial Intelligence?
No full textThe rapid advancements of Generative Artificial Intelligence (GenAI) technologies, such as the well-known OpenAI ChatGPT and Microsoft Copilot, have sparked significant societal, economic, and regulatory challenges. Indeed, while the latter technologies promise unprecedented productivity gains, they also raise several concerns, such as job loss and displacement, deepfakes, and intellectual property violations. The present article aims to explore the present regulatory landscape of GenAI across the major global players, highlighting the divergent approaches adopted by the United States, United Kingdom, China, and the European Union. By drawing parallels with other complex global issues such as climate change and nuclear proliferation, this paper argues that the available traditional regulatory frameworks may be insufficient to address the unique challenges posed by GenAI. As a result, this article introduces a resilience-focused regulatory approach that emphasizes aspects such as adaptability, swift incident response, and recovery mechanisms to mitigate potential harm. By analyzing the existing regulations and suggesting potential future directions, the present article aims to contribute to the ongoing discourse on how to effectively govern GenAI technologies in a rapidly evolving regulatory landscape
Threshold extinction in food webs
No full textFood web response to species loss has been investigated in several ways in the last years. In binary food webs species go secondarily extinct if no resource item remains to exploit. We considered that species can go extinct well before their remain without energy intake and we explore this issue by introducing thresholds of minimum energy requirement for species survival. According to this approach extinction would occur whenever an initial extinction event eliminates links so that certain nodes are left with an overall energy intake lower than the threshold value. We tested 18 real food webs by removing species from most to least connected and considering different scenarios defined by a progressively increasing extinction threshold. Increasing energy requirement threshold negatively affect food web robustness. We found that a very low increase of the energy requirement induces a significative increase in system fragility. In addition, above a certain value of energy requirement threshold we found no relationship between the robustness and the connectance of the web. Further, networks with more species showed higher level of fragility when energy threshold is more severe. Such discovery indicates that the shape of the robustnesscomplexity
relationship of a web depends on the sensitivity of consumers to loss of prey
Gastroesophageal reflux disease: key messages for clinicians
No full textGastroesophageal reflux disease (GERD) is a chronic common disorder for which patients often refer to specialists. In the last decades, numerous studies helped to clarify the pathophysiology and the natural history of this disease. Currently, in the clinical setting, GERD is defined by the presence of symptoms that, when endoscopic investigation is required, permit to distinguish between cases with or without associated esophageal mucosal injuries. These conditions are called erosive reflux disease and non-erosive reflux disease (NERD), respectively. The latter is the most common manifestation of GERD. Symptoms are defined typical, as heartburn and regurgitation, and atypical (also called extra-esophageal), as coughing and/or wheezing, hoarseness, sore throat, otitis media, and dental manifestations. In this context, it is crucial for clinicians to investigate the presence of features of suspected malignancy, as unexplained weight loss, anemia, dysphagia, persistent vomiting, familiar history of cancer, long history of GERD, and beginning of GERD symptoms after the age of 50 years. The presence of these risk factors should induce to perform an endoscopic examination. Particular attention should be given to functional conditions that can mimic GERD, such as functional heartburn and hypersensitive esophagus as well as, more rarely, eosinophilic esophagitis. The former ones have different pathophysiology and this explains the frequent non-response to proton pump inhibitor drugs. This narrative review provides to clinicians a useful and practical overview of the state-of-the-art on advancements in the knowledge of GERD. (Cite this article as: Saracco M, Savarino V, Bodini G, Saracco GM, Pellicano R. Gastroesophageal reflux disease: key messages for clinicians. Minerva Gastroenterol 2021;67:390-403. DOI: 10.23736/S2724-5985.20.02783-X
- …
