Similitude Based Segment Graph Construction and Segment Ranking for Automatic Summarization of Text Document

With the increase in the amount of data and documents on the web, text summarization has become one of the significant fields which cannot be avoided in today’s digital era. Automatic text summarization provides a quick summary to the user based on the information presented in the text documents. This paper presents the automated single document summarization by constructing similitude graphs from the extracted text segments. On extracting the text segments, the feature values are computed for all the segments by comparing them with the title and the entire document and by computing segment significance using the information gain ratio. Based on the computed features, the similarity between the segments is evaluated to construct the graph in which the vertices are the segments and the edges specify the similarity between them. The segments are ranked for including them in the extractive summary by computing the graph score and the sentence segment score. The experimental analysis has been performed using ROUGE metrics and the results are analyzed for the proposed model. The proposed model has been compared with the various existing models using 4 different datasets in which the proposed model acquired top 2 positions with the average rank computed on various metrics such as precision, recall, F-score. HIGHLIGHTS Paper presents the automated single document summarization by constructing similitude graphs from the extracted text segments It utilizes information gain ratio, graph construction, graph score and the sentence segment score computation Results analysis has been performed using ROUGE metrics with 4 popular datasets in the document summarization domain The model acquired top 2 positions with the average rank computed on various metrics such as precision, recall, F-score GRAPHICAL ABSTRACT

Effect of Supplementary Levels of Rumen-Protected Lysine and Methionine on Growth Performance, Carcass Traits, and Meat Quality in Feedlot Yaks (Bos grunniens)

Yak, a unique bovine species on the Qinghai-Tibetan Plateau, has provided pastoralists with the basic materials of production and life for thousands of years. Existing literature showed that yak meat is of high nutritional value for humans whereas the growth performance is relatively low. As it has been demonstrated, lysine and methionine are the two key limiting amino acids in ruminants. Therefore, this study was conducted to investigate the effect of supplementary levels of rumen-protected lysine (RPL) and methionine (RPM) on growth performance, carcass traits, and meat quality in feedlot yaks. Thirty-two male yaks, with initial body weight (IBW) of 237.5 ± 13.99 kg were randomly assigned to four dietary treatments (n = 8), including control group (CON; basal diet without adding rumen-protected amino acid (RPAA)), low RPAA supplementation group (Group Low; basal diet supplemented with RPL (30.0 g/animal/day) and RPM (7.5 g/animal/day)), medium RPAA supplementation group (Group Medium; basal diet supplemented with RPL (50.0 g/animal/day) and RPM (12.5 g/animal/day)), and high RPAA supplementation group (Group High; basal diet supplemented with RPL (70.0 g/animal/day) and RPM (17.5 g/animal/day)). The average daily gain was increased linearly (p < 0.001) and quadratically (p < 0.01) while feed to gain ratio was decreased linearly (p < 0.001) and quadratically (p < 0.001) with the increasing RPAA supplementation, and the average daily gain was higher while feed to gain ratio was lower in RPAA than CON (p < 0.001). Meat color L* values and b* were decreased linearly (p < 0.01) with the increase of RPAA supplementation, and b* was lower in RPAA than CON (p < 0.05). Meat color a* value was increased linearly (p < 0.05) with the increasing RPAA supplementation, and a* was higher in RPAA than CON (p < 0.05). The 24 h drip loss and shear force were decreased quadratically (p < 0.01) with the increasing RPAA supplementation, and drip loss and shear force values were lower in RPAA than CON (p < 0.05). The glycine concentration in longissimus dorsi (LD) increased linearly (p < 0.05) with the increasing RPAA supplementation. These results demonstrated that both the growth performance and meat quality characteristics were improved in feedlot yaks as an effect of the dietary supplementation with RPL and RPM, and the medium supplementary level is recommended, since it showed the most promising results.

PREDIKSI PENERIMAAN KARYAWAN BAGIAN DESAIN PADA EVENT ORGANIZER PT. SEIRAH WISATA MENGGUNAKAN ALGORITMA C4.5

ABSTRACT Human resources design section at an Event Organizer is a vital part considering that the design will be seen by the event participants in addition to the technical events. The selection of employees who understand design and have extensive experience is important. The process of selecting employees in the design field can sometimes be difficult to predict if there are several prospective employees with balanced abilities. From the calculation results of the dataset as many as 14 applicants using the C4.5 algorithm, the highest Gain Ratio value obtained in the design Ability and Experience = 0.7172, Origin of Schools = 0.0511 and Age = 0.0205. Keywords : event organizer, C4.5 algorithm, prospective employees, Gain Ratio

Effect of feeding buttermilk coated diets on growth, carcass characteristics and production cost of crossbred chicken

Growth performance, carcass characteristics and production costs associated with feeding crossbred indigenous chicken on traditional buttermilk coated diets were evaluated. Three batches of day-old Indigenous x Kuroiler crossbred chicks were raised on a commercial diet for one month. At one month, chicken in each of the three batches were weighed and randomly divided into 3 equal groups. Each group comprised of 20 birds. Chicken in each group were either fed coated (dry buttermilk coated maize-bran), combined (buttermilk coated maize bran + commercial diet) or a commercial (control) diet. Average final live weight and feed intake were similar across the three dietary treatments (P>0.05). Feed to gain ratio significantly varied (P<0.05) across dietary treatments with buttermilk coated diets having the highest feed to gain ratio (7.27) compared to combined (4.38) and commercial (3.88) diets. Coated and combined diets yielded similar dressing percentage of 60.2 and 62 compared to 65% obtained with commercial diets. Carcass and organ yield was similar (P>0.05) across dietary treatments. On a 5 point hedonic scale, chicken meat produced using coated diets was more acceptable (2.0), compared to combined (2.1) and commercial (3.1) diets (P<0.05). The highest gross margins accrued from feeding combined and commercial diets. Over-all, results provide evidence of the potential of the combined diet to attain similar growth performance, carcass yield and gross margins as the commercial diet at lower cost. Bang. J. Anim. Sci. 2021. 50 (1):57-63

Application of a MOGA Algorithm and ANN in the Optimization of Apple Drying and Rehydration Processes

The aim of the study was to estimate the optimal parameters of apple drying and the rehydration temperature of the obtained dried apple. Conducting both processes under such conditions is aimed at restoring the rehydrated apple to the raw material properties. The obtained drying parameters allow the drying process to be carried out in a short drying time (DT) and at low energy consumption (EC). The effect of air velocity (vd), drying temperature (Td), characteristic dimension (CD), and rehydration temperature (Tr) on rehydrated apple quality was studied. Quality parameters of the rehydrated apple as: color change (CC), mass gain ratio (MG), solid loss ratio (SL), volume gain ratio (VG) together with DT and EC were taken into consideration. The artificial neural network was used for modeling of rehydrated apple quality parameters, DT, and EC. A multi-objective genetic algorithm was developed in order to optimize parameters of the drying and rehydration processes. The simultaneous minimization of CC, SL, DT, EC, and the maximization of MG and VG were considered with the following drying and rehydration processes parameters: Td: 50–70 °C, vd: 0.01–2 m/s, Tr: 20–70 °C. The best solution has been found at drying temperature 56.1 °C, air velocity 1.3 m/s, characteristic dimension 2.0 mm, and rehydration temperature 59.2 °C. This apple drying and rehydration resulted in MG = 3.51, SL = 0.57, VG = 4.77, CC = 11.2, DT = 5.4 h, EC = 159.8 GJ/kg. The parameters of apple drying and rehydration processes can be recommended for the industry application.

KLASIFIKASI KELANCARAN PEMBAYARAN PINJAMAN KOPERASI DENGAN METODE DECISION TREE

Salah isatu ipenyebab ikredit ibermasalah iadalah ikurang itelitinya ipihak ikoperasi idalam isurvei idan ianalisis ipemberian ipeminjaman. iOleh ikarena iitu, ianalisis ikredit idengan iteknik idata imining iperlu idilakukan isehingga idapat imeminimalisir inasabah iterlambat imembayar ipinjaman iserta imempersingkat iwaktu ianalisis ipemberian ipinjaman. iPenelitian iini ibertujuan iuntuk membuat sistem decision tree yang dapat digunakan sebagai klasifikasi nasabah peminjaman berdasarkan nilai kelancaran pembayaran pinjamannya. Pada penelitian ini atribut yang yang digunakan sebagai acuan untuk menganalisis kelacancaran pembayaran pinjaman koperasi adalah status keanggotaan, status pernikahan, pekerjaan, pendapatan, pengeluaran, jaminan, keperluan, jumlah pinjaman dan lama pinjman. Algotitma C4.5 digunakan untuk membentu decision tree dengan cara mencari nilai entropy, gain info, split info, dan gain ratio pada setiap atribut untuk menentukan atribut akar dan cabangnya.