Search Results (8)

The refractive index (RI) of liquids is a key physical property of molecular compounds and materials. In addition to its ubiquitous role in physics, it is also exploited to impart specific optical properties (transparency, opacity, and gloss) to materials and various end-use products. Since few methods exist to accurately estimate this property, we have designed a graph machine model (GMM) capable of predicting the RI of liquid organic compounds containing up to 16 different types of atoms and effective in discriminating between stereoisomers. Using 8267 carefully checked RI values from the literature and the corresponding 2D organic structures, the GMM provides a training root mean square relative error of less than 0.5%, i.e., an RMSE of 0.004 for the estimation of the refractive index of the 8267 compounds. The GMM predictive ability is also compared to that obtained by several fragment-based approaches. Finally, a Docker-based tool is proposed to predict the RI of organic compounds solely from their SMILES code. The GMM developed is easy to apply, as shown by the video tutorials provided on YouTube. Full article

The long-term endurance of building stones must be assured since their longevity has repercussions for their economic and social value. Frequently, slabs for flooring and cladding are installed with polished finishing in outdoor environments for technical and ornamental purposes in cultural heritage sites and modern civil architecture. Compared to any other finishing, glossy surfaces are rather vulnerable to wear, particularly when they interact with slightly acidic rainwater. Several hydrophobic treatments are applied to prevent this damage by preventing contact between rain and stone; such treatments are efficient but sometimes non-durable. Stakeholders and conservation scientists need better methods to anticipate the future behaviour of this building material and hydrophobic solutions. Complying with this demand, a comparison is made between outdoor natural ageing and artificial weathering, reproduced by UVA radiation, moisture and spray accelerated weathering. Artificial weathering is applied to predict the behaviour of stones over time in the real environment. Data obtained through the measurement of gloss and colour parameters, the detection of micro-textures through SEM, and the calculation of micro-roughness using a digital rugosimeter demonstrate that weakly acidic rainwater is the main cause of superficial decay of stone finishing over just six months of outdoor exposure. This period corresponds to 7–14 days of artificial weathering. Furthermore, the loss of efficiency and durability of the hydrophobic coatings is detected by measuring the static contact angle. This highlights that even if a protective treatment was proficient, it could easily deteriorate in normal weathering conditions if applied on polished, low-porosity stone. Additionally, water vapour permeability indicates variations of regular vapour transmission through the stones due to ageing. The first solution to threats is the prevention of pathologies, including aesthetic ones. A careful choice of the most suitable lithotype finish and an environmental study represent an existing solution to the problem. It must be highlighted that aesthetic requirements should not be prioritised to detriment of the technical requirements of architectural quality, performance, durability, and safety. Full article

Word-level sign language recognition (WSLR) is the backbone for continuous sign language recognition (CSLR) that infers glosses from sign videos. Finding the relevant gloss from the sign sequence and detecting explicit boundaries of the glosses from sign videos is a persistent challenge. In this paper, we propose a systematic approach for gloss prediction in WLSR using the Sign2Pose Gloss prediction transformer model. The primary goal of this work is to enhance WLSR’s gloss prediction accuracy with reduced time and computational overhead. The proposed approach uses hand-crafted features rather than automated feature extraction, which is computationally expensive and less accurate. A modified key frame extraction technique is proposed that uses histogram difference and Euclidean distance metrics to select and drop redundant frames. To enhance the model’s generalization ability, pose vector augmentation using perspective transformation along with joint angle rotation is performed. Further, for normalization, we employed YOLOv3 (You Only Look Once) to detect the signing space and track the hand gestures of the signers in the frames. The proposed model experiments on WLASL datasets achieved the top 1% recognition accuracy of 80.9% in WLASL100 and 64.21% in WLASL300. The performance of the proposed model surpasses state-of-the-art approaches. The integration of key frame extraction, augmentation, and pose estimation improved the performance of the proposed gloss prediction model by increasing the model’s precision in locating minor variations in their body posture. We observed that introducing YOLOv3 improved gloss prediction accuracy and helped prevent model overfitting. Overall, the proposed model showed 17% improved performance in the WLASL 100 dataset. Full article

Continuous sign language recognition is a weakly supervised task dealing with the identification of continuous sign gestures from video sequences, without any prior knowledge about the temporal boundaries between consecutive signs. Most of the existing methods focus mainly on the extraction of spatio-temporal visual features without exploiting text or contextual information to further improve the recognition accuracy. Moreover, the ability of deep generative models to effectively model data distribution has not been investigated yet in the field of sign language recognition. To this end, a novel approach for context-aware continuous sign language recognition using a generative adversarial network architecture, named as Sign Language Recognition Generative Adversarial Network (SLRGAN), is introduced. The proposed network architecture consists of a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator’s predictions by modeling text information at the sentence and gloss levels. The paper also investigates the importance of contextual information on sign language conversations for both Deaf-to-Deaf and Deaf-to-hearing communication. Contextual information, in the form of hidden states extracted from the previous sentence, is fed into the bidirectional long short-term memory module of the generator to improve the recognition accuracy of the network. At the final stage, sign language translation is performed by a transformer network, which converts sign language glosses to natural language text. Our proposed method achieved word error rates of 23.4%, 2.1% and 2.26% on the RWTH-Phoenix-Weather-2014 and the Chinese Sign Language (CSL) and Greek Sign Language (GSL) Signer Independent (SI) datasets, respectively. Full article

Word Sense Disambiguation (WSD) aims to predict the correct sense of a word given its context. This problem is of extreme importance in Arabic, as written words can be highly ambiguous; 43% of diacritized words have multiple interpretations and the percentage increases to 72% for non-diacritized words. Nevertheless, most Arabic written text does not have diacritical marks. Gloss-based WSD methods measure the semantic similarity or the overlap between the context of a target word that needs to be disambiguated and the dictionary definition of that word (gloss of the word). Arabic gloss WSD suffers from a lack of context-gloss datasets. In this paper, we present an Arabic gloss-based WSD technique. We utilize the celebrated Bidirectional Encoder Representation from Transformers (BERT) to build two models that can efficiently perform Arabic WSD. These models can be trained with few training samples since they utilize BERT models that were pretrained on a large Arabic corpus. Our experimental results show that our models outperform two of the most recent gloss-based WSDs when we test them against the same test data used to evaluate our model. Additionally, our model achieves an F1-score of 89% compared to the best-reported F1-score of 85% for knowledge-based Arabic WSD. Another contribution of this paper is introducing a context-gloss benchmark that may help to overcome the lack of a standardized benchmark for Arabic gloss-based WSD. Full article

Many natural exposure sites have been developed to ensure the reliability of materials intended for outdoor use. However, the effects of local climate on aging have not been completely understood. This study aimed to elucidate the regional characteristics of natural aging. Non-stabilized and stabilized polycarbonates were monitored in terms of their appearance (yellowing and loss of gloss) during natural weathering at five exposure sites (Tokyo, Kagoshima, Okinawa, Florida, and Arizona) in conjunction with climate fluctuation for up to 24 months. Three approaches were employed to characterize the natural aging behaviors: (i) modeling the rate function of degradation, (ii) evaluating the contribution ratio of individual degradational factors, and (iii) estimating the “synchronicity” by cross-correlation analysis with the climate dataset. The aging rates were the highest in Arizona and lowest in Kagoshima among the five exposure sites. First, prediction curves were constructed from the degradation rate function (variables: UV irradiation, temperature, and humidity), and these curves were found to agree well with the measured aging behaviors. Second, the exposure data in Arizona demonstrated strong temperature dependence, while those in Okinawa and Florida had stronger dependence on UV irradiation compared to other sites. Lastly, the synchronicity between UV irradiation and temperature was the highest in Arizona and lowest in Kagoshima, which can explain the significantly faster deterioration in Arizona and the slow deterioration in Kagoshima. Full article

Recently, artificial intelligence (AI) technologies have been employed to predict construction and demolition (C&D) waste generation. However, most studies have used machine learning models with continuous data input variables, applying algorithms, such as artificial neural networks, adaptive neuro-fuzzy inference systems, support vector machines, linear regression analysis, decision trees, and genetic algorithms. Therefore, machine learning algorithms may not perform as well when applied to categorical data. This article uses machine learning algorithms to predict C&D waste generation from a dataset, as a way to improve the accuracy of waste management in C&D facilities. These datasets include categorical (e.g., region, building structure, building use, wall material, and roofing material), and continuous data (particularly, gloss floor area), and a random forest (RF) algorithm was used. Results indicate that RF is an adequate machine learning algorithm for a small dataset consisting of categorical data, and even with a small dataset, an adequate prediction model can be developed. Despite the small dataset, the predictive performance according to the demolition waste (DW) type was R (Pearson’s correlation coefficient) = 0.691–0.871, R² (coefficient of determination) = 0.554–0.800, showing stable prediction performance. High prediction performance was observed using three (for mortar), five (for other DW types), or six (for concrete) input variables. This study is significant because the proposed RF model can predict DW generation using a small amount of data. Additionally, it demonstrates the possibility of applying AI to multi-purpose DW management. Full article

The process of preparing anti-glare thin films by spray-coating silica sol-gel to soda-lime glass was exclusively and statistically studied in this paper. The effects of sol-gel deliver pressure, air transport pressure, and spray gun displacement speed on the gloss, haze, arithmetic mean surface roughness, and total transmittance light were analyzed. The experimental results indicate that the factors of sol-gel deliver pressure, air transport pressure, and displacement speed exhibit a significant effect on the haze, gloss, and Ra. In contrast, the variation of total transmittance light with these three factors are insignificant. Because the anti-glare property is predominantly determined by low gloss and high haze, we therefore aim to minimize gloss and maximize haze to achieve high anti-glare. Central composite design and response surface methodology are employed to analyze the main and interaction effects of the three factors through quadratic polynomial equations, which are confirmed by the analysis of variance and R². The response surface methodology predict the lowest gloss and highest haze are 9.2 GU and 57.0%, corresponding to the sol-gel deliver pressure, air-transport pressure, and displacement speed of 250 kPa, 560 kPa, and 140 mm/s, and 340 kPa, 620 kPa, and 20 mm/s, respectively. Comparing the predicted optimal data with the real experimental results validates the applicability of the mathematical model. This study provides an important basis for the subsequent production of anti-glare glass with different specifications to satisfy the market demand. Full article