Analysis Sentiment Based on IMDB Aspects from Movie Reviews using SVM

A movie is a spectacle that can be done at a relaxed time. Currently, there are many movies that can be watched via the internet or cinema. Movies that are watched on the internet are sometimes charged to watch so that potential viewers before watching a movie will read comments from users who have watched the movie. The website that is often used to view movie comments today is IMDB. Movie comments are many and varied on the IMDB website, we can see comments based on the star rating aspect. This causes users to have difficulty analyzing other users' comments. So, this study aims to analyze the sentiment of opinions from several comments from IMDB website users using the star rating aspect and will be classified using the support vector machine method (SVM). Sentiment analysis is a classification process to understand the opinions, interactions, and emotions of a document or text. SVM is very efficient for many applications in science and engineering, especially for classification (pattern recognition) problems. In addition to the SVM method, the TF-IDF technique is also used to change the shape of the document into several words. The results obtained by applying the SVM model are 79% accuracy, 75% precision, and 87% recall. The SVM classification is also superior to other methods, namely logistic regression.

Risk Evaluation and Leakage Mechanism on Runoff in Coal Mining Area—A Case Study in Jinjie Coal Mine of Tuwei River

According to the aims of the runoff protection in coal mining area, taking Jinjie coal mine as an example, the risk zonation and mechanism of runoff leakage were carried out based on the dimen-sionless multi-factor information fusion technique. Based on the analysis of field exploration and borehole data, four key factors affecting the runoff leakage from the roof were identified, which included the deposition features of aquifer in Sala Wusu Group, the distribution of overburden rock and soil mass, effective thickness of aquiclude layer and the height of water flow cracking zone. The evaluation criterion was whether the development height of the water flow cracking zone reaches or exceeds the bottom plate of the sandy phreatic aquifer and even penetrates the surface ground, which results in the complete or partial leakage of the phreatic water. According the evaluation criterion, the influence of coal mining disturbance on runoff leakage was divided into three zones: zone of seriously runoff leakage, zone of general runoff leakage and zone of slight runoff leakage. Furthermore, the influence mechanism of different zones in coal mining also been discussed preliminarily, which included drainage Sarawusu aquifer, groundwater leakage in Sarawusu aquifer, water level fluctuation in Sarawusu aquifer and so on. Finally, classification pattern diagram was drawn.

Analysis on the Effectiveness of the Input in Household Waste Classification of Residents—Taking S City in China as an Example

S city in China has implemented a waste classification system and constructed a waste classification model with government-led market and public participation. In order to explore the effectiveness of waste classification input in S city, this paper conducts analyses from the points of view of the classification facility’s construction, environmental effectiveness, social acceptability and operation sustainability, based on interviews with and questionnaire surveys completed by related parties. The results show that the current waste classification facility system in S city is basically completed; high rates of both properties and residents comply with the waste classification system. S city has established a government-led waste classification pattern that depends on social participation. This pattern has been recognized and accepted by residents and is economically sustainable. At the same time, it is pointed out that the current marginal effectiveness of the waste classification input is showing a declining trend. Future investment should shift from investment in facilities and equipment to incentives for autonomous management by residents, and the corresponding evaluation of investment and effectiveness should also change accordingly. This requires the government to guide the refined management system.

Sistem Rekomendasi Jurusan pada Sekolah Menengah Kejuruan (SMK) dengan Algoritma K-Means

The system of determining majors in SMK Negeri 02 Moswaren South Sorong Regency, is very important, because in SMK there is no good majoring system so students are often wrong in choosing a major based on their abilities. The purpose of this study is to use the recommendation system of majors in vocational high schools (SMK) using the K-Means Algorithm. The research method conducted is to conduct interviews with the school or those responsible at smk to get the data they need. The results of the classification pattern of major determination can be used by the school in determining policies in determining prospective student majors in the admission process of new learners. After conducting this research, it was found that the system had successfully implemented the K-means algorithm to determine the priority of determining vocational expertise programs based on raport junior high school value criteria, interests, student talent

Reconstructing winter climate anomalies in the Euro-Atlantic sector using circulation patterns

The efficacy of Euro-Atlantic circulation regimes for estimating wintertime climate anomalies (precipitation and surface temperature) over Europe is assessed. A comparison of seasonal climate reconstructions from two different regime frameworks (cluster analysis of the low-level zonal flow, and traditional blocking indices) is presented and contrasted with seasonal reconstructions using the North Atlantic Oscillation (NAO) index. The reconstructions are quantitatively evaluated using correlations and the coefficient of efficiency, accounting for misfit in phase and amplitude. The skill of the various classifications in reconstructing seasonal anomalies depends on the variable and region of interest. The jet and blocking regimes are found to capture more spatial structure in seasonal precipitation anomalies over Europe than the NAO, with the jet framework showing generally better skill relative to the blocking indices. The reconstructions of temperature anomalies have lower skill than those for precipitation, with the best results for temperature obtained by the NAO for high-latitude and by the blocking framework for southern Europe. All methods underestimate the magnitude of seasonal anomalies due to the large variability in precipitation and temperature within each classification pattern.

Quantification of the Geranium Essential Oil, Palmarosa Essential Oil and Phenylethyl Alcohol in Rosa damascena Essential Oil Using ATR-FTIR Spectroscopy Combined with Chemometrics

Rosa damascena essential oil is an essential oil that has the greatest industrial importance due to its unique quality properties. The study used ATR-FTIR (attenuated total reflectance-Fourier transform infrared) spectroscopy coupled with chemometrics of PLSR (partial least squares regression) and PCR (principal component regression) for quantification of probable adulterants of geranium essential oil (GEO), palmarosa essential oil (PEO) and phenyl ethyl alcohol (PEOH). Hierarchical cluster analysis was performed to observe the classification pattern of Rosa damascena essential oil, spiked samples and adulterants. Rosa damascena essential oil was spiked with each adulterant at concentrations of 0–100% (v/v). Excellent R2 (regression coefficient) values (≥0.96) were obtained in all PLSR and PCR cross-validation models. The SECV (standard error of cross-validation) values ranged between 0.43 and 4.15. The lowest SECV and bias values were observed in the PLSR and PCR models, which were built by using the raw FTIR spectra of all samples. Hierarchical cluster analysis through Ward’s algorithm and Euclidian distance had high potential to observe the classification pattern of all adulterated and authentic samples. In conclusion, the combination of ATR-FTIR spectroscopy with multivariate analysis can be used for rapid, cost-effective, easy, reliable and high-throughput detection of GEO, PEO and PEOH in Rosa damascena essential oil.

POETS: A Parallel Cluster Architecture for Spiking Neural Network

Spiking Neural Networks (SNNs) are known as a branch of neuromorphic computing and are currently used in neuroscience applications to understand and model the biological brain. SNNs could also potentially be used in many other application domains such as classification, pattern recognition, and autonomous control. This work presents a highly-scalable hardware platform called POETS, and uses it to implement SNN on a very large number of parallel and reconfigurable FPGA-based processors. The current system consists of 48 FPGAs, providing 3072 processing cores and 49152 threads. We use this hardware to implement up to four million neurons with one thousand synapses. Comparison to other similar platforms shows that the current POETS system is twenty times faster than the Brian simulator, and at least two times faster than SpiNNaker.

INFORMATION TECHNOLOGY FOR SYNTHESIS AND OPTIMIZATION OF FUZZY SYSTEMS RULE BASES

In the last two decades, intelligent computer systems based on fuzzy set theory, fuzzy logic and soft computing are widely used in various fields of science and technology to solve problems of control, identification, modeling of complex physical and economic phenomena, classification, pattern recognition, etc. Modern research in the field of creation and development of fuzzy systems (FS) of control and decision-making is conducted mainly in the direction of development of highly effective methods and information technologies of their synthesis and structural-parametric optimization. This paper is devoted to the development and research of information technology for the synthesis and optimization of highly efficient rule bases (RB) with the optimal set of consequences and optimal number of rules for Mamdani-type FSs in terms of incomplete source information. The developed information technology allows to conduct iterative search of the optimal vector of RB consequences based on a sequential search of the consequences of each rule, as well as to identify and exclude rules from RB, that do not affect the system operation, to reduce the total number of rules to optimal. To study the effectiveness of the proposed information technology in this work, the synthesis and optimization of the fuzzy automatic control system (ACS) for the multi-purpose mobile robot (MR), which is able to move on inclined and vertical ferromagnetic surfaces, is carried out. The obtained results of computer simulation showed that the fuzzy ACS of MR with optimized RB based on the developed information technology has higher quality indicators of control compared to the ACS with a similar RB developed on the basis of experts knowledge. Also, the optimized RB by means of the proposed information technology has fewer rules than the full RB, which is synthesized on the basis of experts knowledge, which, in turn, significantly simplifies the further software and hardware implementation of the developed fuzzy ACS of MR. In addition, in the process of synthesis and optimization of the RB for the fuzzy ACS of MR, presented information technology did not require significant computational costs, which generally confirms its high efficiency and feasibility of application to design rule bases of control and decision making FSs of different types.

Functional Autonomy Evaluation Levels in Middle-Aged and Older Spanish Women: On Behalf of the Healthy-Age Network

Aging is associated with a progressive loss of functional capacity that affects the health and quality of life of middle-aged and older people. The purpose of this study was to report functional autonomy evaluation levels in middle-aged and older women in the Spanish context. A total of 709 middle-aged and older women, between 50 and 90 years old, were selected to participate in the study. The sample was divided by age category every five years. The functional autonomy levels were determined by the Latin American Group for Maturity (GDLAM) protocol and we developed a classification pattern for middle-aged and older women living in Spain. The GDLAM Index (GI) was then calculated to assess functional autonomy. The classification of the tests and the GI followed the percentile rank (P) Very Good (p < 0.15), Good (p 0.16–p 0.50), Regular (p 0.51–p 0.85), and Poor (p > 0.85). It was considered that the lower the value found for the percentile, the better the result. The GDLAM protocol showed strong reliability with intraclass correlation coefficient (ICC) values greater than 0.92 in all tests. It is observed that all variables of the GDLAM protocol presented a positive and significant correlation with age (p < 0.001). The Roc Curve showed that GI values higher than 26 (CI95% = 0.97–1.00; p < 0.001) and 32 (CI95% = 0.98–1.00; p < 0.001) for middle-aged and elderly women, respectively, can predict and indicate low functional autonomy. The normative values hereby provided will enable evaluation and adequate interpretation of Spanish middle-aged and older women’s functional autonomy.