Legal Judgment Elements Extraction Approach with Law Article-aware Mechanism

Legal judgment elements extraction (LJEE) aims to identify the different judgment features from the fact description in legal documents automatically, which helps to improve the accuracy and interpretability of the judgment results. In real court rulings, judges usually need to scan both the fact descriptions and the law articles repeatedly to find out the relevant information, and it is hard to acquire the key judgment features quickly, so legal judgment elements extraction is a crucial and challenging task for legal judgment prediction. However, most existing methods follow the text classification framework, which fails to model the attentive relations of the law articles and the legal judgment elements. To address this issue, we simulate the working process of human judges, and propose a legal judgment elements extraction method with a law article-aware mechanism, which captures the complex semantic correlations of the law article and the legal judgment elements. Experimental results show that our proposed method achieves significant improvements than other state-of-the-art baselines on the element recognition task dataset. Compared with the BERT-CNN model, the proposed “All labels Law Articles Embedding Model (ALEM)” improves the accuracy, recall, and F1 value by 0.5, 1.4 and 1.0, respectively.

Color-Based Feature Extraction Method for Skin Segmentation Based on SVM

Different colored digital images can be represented in a variety of color spaces. Red-Green-Blue is the most commonly used color space. That can be transformed into Luminance, Blue difference, Red difference. These color pixels' defined features provide strong information about whether they belong to human skin or not. A novel color-based feature extraction method is proposed in this paper, which makes use of both red, green, blue, luminance, hue, and saturation information. The proposed method is used on an image database that contains people of various ages, races, and genders. The obtained features are used to segment the human skin using the Support-Vector- Machine algorithm, and the promising performance results of 89.86% accuracy are then compared to the most commonly used methods in the literature. Keywords: Skin segmentation, SVM, feature extraction, digital images

Optimization of novel single-step gelatin extraction method using RSM model for valorization of surimi industry by-products

Surimi industry produces large quantity of by-products as a combination of skin, bones, and scale, which due to technical difficulty in separation, are being currently utilized for production of low- value products such as biofertilizers and fish feed. Present paper focuses on utilization of combined skin, bones, and scale from Pink Perch (Nemipterus japonicus) obtained from surimi industry for gelatin extraction using single step process. Single step extraction method with acetic acid and water was optimized using Response Surface Methodology (RSM) to maximize yield and gel strength so that the process can be applied for sustainable utilization. Parameters such as pH (A), extraction temperature (B) and extraction time (C) with respect to yield and L-hydroxyproline content were optimized. Highest gelatin yield was obtained at pH 3, 75°C extraction temperature, and 30 min extraction time. Gelatin yield and L-hydroxyproline content under optimum condition were 16.2% and 41.62 mg.g−1. The chemical composition, functional, rheological, and structural properties of gelatin were examined and compared with commercial bovine gelatin. Gelatin thus obtained at optimized condition exhibited high gel strength (793g) and higher imino acid content (18.1%) than bovine gelatin. FTIR spectra depicted high similarities between both gelatin sample. Thus, the optimized method can be utilized for gelatin extraction from Pink Perch by-products for development of high value products such as food application.

The Effectiveness of Soil Extracts from Selangor Peat Swamp and Pristine Forest Soils on the Growth of Green Microalgae sp.

Microalgae are widely utilized in commercial industries. The addition of a modified artificial medium (soil extract) could enhance their growth. Soil extract collected from the Raja Musa peat swamp and mineral soil from the Ayer Hitam Forest Reserve (AHFR), Selangor, Malaysia, were treated using various extraction methods. Carteria radiosa PHG2-A01, Neochloris conjuncta, and Nephrochlamys subsolitaria were grown in microplates at 25 °C, light intensity 33.75 µmol photons m−2s−1 for 9 days. N. conjuncta dominated the growth in 121 °C twice extraction method AFHR samples, with 47.17% increment. The highest concentrations of ammonia and nitrate were detected in the medium with soil extract treated with 121 °C twice extraction method, yielding the concentrations of 2 mg NL−1 and 35 mg NL−1 for ammonia and nitrate of RM soil and 2 mg NL−1 and 2.85 mg NL−1 for the AH soil. These extracts are proved successful as a microalgal growth stimulant, increasing revenue and the need for enriched medium. The high rate of nutrient recovery has the potential to serve as a growth promoter for microalgae.