Comparison of Machine Learning and Sentiment Analysis in Detection of Suspicious Online Reviewers on Different Type of Data

The article focuses on solving an important problem of detecting suspicious reviewers in online discussions on social networks. We have concentrated on a special type of suspicious authors, on trolls. We have used methods of machine learning for generation of detection models to discriminate a troll reviewer from a common reviewer, but also methods of sentiment analysis to recognize the sentiment typical for troll’s comments. The sentiment analysis can be provided also using machine learning or lexicon-based approach. We have used lexicon-based sentiment analysis for its better ability to detect a dictionary typical for troll authors. We have achieved Accuracy = 0.95 and F1 = 0.80 using sentiment analysis. The best results using machine learning methods were achieved by support vector machine, Accuracy = 0.986 and F1 = 0.988, using a dataset with the set of all selected attributes. We can conclude that detection model based on machine learning is more successful than lexicon-based sentiment analysis, but the difference in accuracy is not so large as in F1 measure.

COMPARISON OF METHODS FOR CONTROLLED THERMAL DEFORMATIONS IN MACHINE TOOLS

Progress in improving the accuracy of metal-cutting machines is inextricably linked and driven by deeper knowledge gained through the study of thermal processes and effects occurring in machines, which can be used to manage them. This led to the dominance of temperature errors in the balance of machine accuracy, the share of which changed from 20-30% to 70% during the period from 1950 to 2020, which is determined by the absolute value of the achievable machine accuracy. Types and forms of compensation methods were formed (1990-2020), which were based on the use of linear and nonlinear regression or correlation methods. Performing experiments can establish the functional relationship between the measured temperature in the machine nodes and the amount of displacement. With good repeatability and stable reproducibility of the result, an equation expresses this functional relationship. Applying this equation to a program, a control device compensates the thermal deformations. However, in all cases, it is necessary to determine the number and location of temperature measurements on the machine, determining the compensation accuracy. The proposed sensorless model is based on a thermal behavior model and does not require temperature measurements. A method is presented and justified for estimating the number of temperature measurement locations based on thermophysical analysis by applying the finite element method in comparison with the analytical method in order to achieve the required compensation accuracy. For several machine tool types, a comparison is given regarding the control method of the TCP spindle displacement without sensors and with temperature sensors. The limits of their rational use are presented.

Automating Accuracy Evaluation of 5-Axis Machine Tools

A wireless non-contact 3D measuring head is used to determine the accuracy of 5-axis machine tools. The measuring head is inserted in the spindle by the tool exchanger automating the measurement routine used. For checking the linear machine axes, a cross shaped artefact containing 13 precision balls is introduced, named Position Inspector, enabling the determination of positioning and straightness errors of two linear axes in one setup. The squareness error between both axes is also determined in this setup. This artefact can be mounted on a pallet system for automatic loading and is measured in a bi-directional run. This artefact can be measured in different orientations (i.e., horizontal, inclined, vertical) and is pre-calibrated with a CMM. The measurement sequence using this artefact is executed in eight minutes and its design and support system is addressed in this paper. The location errors and orientation errors of the axis average line (or pivot line) of both rotary axes are determined with the Rotary Inspector using the same measuring head with a single precision ball. For this, kinematic tests are used from ISO10791-6, e.g., the BK1 test, BK2 test which apply for trunnion or swivel table machines. Derived parameters can be used for machine correction resulting in a significantly improved machine accuracy. An example is given where this correction is performed automatically by implementing this measurement system in the machine’s controller. Finally the machine tool is tested using the BK4 test. For this test all 5-axes are moved simultaneously and the measured displacements between the machine’s spindle and table in X-, Y-, and Z-directions are compared to tolerance levels. This final test reveals the machine’s overall accuracy and dynamic behavior.

Coordinate Measuring Machine Retrofit and Technological Upgradation

Planned To Import Axis Motors and Air Bearing From U.S. •Planned To Import 5axis Probe Head, Probe Head & Machine Controller, 5 Axis Measurement Software From U.K. •Machine Axis X-900mm, Y-1200mm, Z-800mm, A -115°To 115°, B- Infinity Position. •Being Five Axis Technologies We Can Minimize the Measurement Time By 70%, So Throughput Of The Machine Can Be Increased. •Being Five Axis Technologies We Can Rotate The Probe Head With Infinite Positions Which Can Minimize The Stylus Calibration & Increases Machine Accuracy. •CMM Retrofit, Technological Upgradation & Calibration Cost Will Come Around 80 Lakhs.

Emotion recognition from posed and spontaneous dynamic expressions: Human observers vs. machine analysis

The majority of research on the judgment of emotion from facial expressions has focused on deliberately posed displays, often sampled from single stimulus sets. Herein, we investigate emotion recognition from posed and spontaneous expressions, comparing classification performance between humans and machine in a cross-corpora investigation. For this, dynamic facial stimuli portraying the six basic emotions were sampled from a broad range of different databases, and then presented to human observers and a machine classifier. Recognition performance by the machine was found to be superior for posed expressions containing prototypical facial patterns, and comparable to humans when classifying emotions from spontaneous displays. In both humans and machine, accuracy rates were generally higher for posed compared to spontaneous stimuli. The findings suggest that automated systems rely on expression prototypicality for emotion classification, and may perform just as well as humans when tested in a cross-corpora context.

Bacterial and Virus affected Citrus Leaf Disease Classification using Smartphone and SVM

Automatic detection of citrus leaves disease is very much essential for the better productivity of citrus. Citrus leaves are affected by bacteria, fungus and virus respectively. Farmer detects the diseases of the plant using laboratory, naked eyes or using expert’s view. The rural farmers often face difficulties to detect these diseases due to the non availability of the laboratories in their area. Here in this paper, a computer automation system is proposed to detect the diseases of citrus leaves on an early stage. Citrus leaves images are captured using Smartphone. Captured images are used to extract the different features of the citrus leaves samples using Gray Level Co-occurrence Matrix. Finally, citrus greening and citrus CTV images are classified from citrus healthy images using Gaussian kernel based support vector machine. Accuracy of the kernel is evaluated for the different values of Gamma parameter of kernel. The Gaussian kernel gives maximum accuracy (95.5%) with Gamma value 1.

Support Vector Machine Accuracy Assessment for Extracting Green Urban Areas in Towns

The most commonly used model for analyzing satellite imagery is the Support Vector Machine (SVM). Since there are a large number of possible variables for use in SVM, this paper will provide a combination of parameters that fit best for extracting green urban areas from Copernicus mission satellite images. This paper aims to provide a combination of parameters to extract green urban areas with the highest degree of accuracy, in order to speed up urban planning and ultimately improve town environments. Two different towns in Croatia were investigated, and the results provide an optimal combination of parameters for green urban areas extraction with an overall kappa index of 0.87 and 0.89, which demonstrates a very high classification accuracy.