Sentiment analysis on film review in Gujarati language using machine learning

<span>Opinion analysis is by a long shot most basic zone of characteristic language handling. It manages the portrayal of information to choose the motivation behind the wellspring of the content. The reason might be of a type of gratefulness (positive) or study (negative). This paper offers a correlation between the outcomes accomplished by applying the calculation arrangement using various classifiers for instance K-nearest neighbor and multinomial naive Bayes. These techniques are utilized to assess a significant assessment with either a positive remark or negative remark. The gathered information considered on the grounds of the extremity film datasets and an association with the results accessible proof has been created for a careful assessment. This paper investigates the word level count vectorizer and term frequency inverse document frequency (TF-IDF) influence on film sentiment analysis. We concluded that multinomial Naive Bayes (MNB) classier generate more accurate result using TF-IDF vectorizer compared to CountVectorizer, K-nearest-neighbors (KNN) classifier has the same accuracy result in case of TF-IDF and CountVectorizer.</span>

Eye Blink Classification for Assisting Disability to Communicate Using Bagging and Boosting

Disability is a physical or mental impairment. People with disability have more barriers to do certain activity than those without disability. Moreover, several conditions make them having difficulty to communicate with other people. Currently, researchers have helped people with disabilities by developing brain-computer interface (BCI) technology, which uses artifact on electroencephalograph (EEG) as a communication tool using blinks. Research on eye blinks has only focused on the threshold and peak amplitude, while the difference in how many blinks can be detected using peak amplitude has not been the focus yet. This study used primary data taken using a Muse headband on 15 subjects. This data was used as a dataset classified using bagging (random forest) and boosting (XGBoost) methods with python; 80% of the data was allocated for learning and 20% was for testing. The classified data was divided into ten times of testing, which were then averaged. The number of eye blinks’ classification results showed that the accuracy value using random forest was 77.55%, and the accuracy result with the XGBoost method was 90.39%. The result suggests that the experimental model is successful and can be used as a reference for making applications that help people to communicate by differentiating the number of eye blinks. This research focused on developing the number of eye blinks. However, in this study, only three blinking were used so that further research could increase these number.

Analisis Sentimen Berbasis Emoticon pada Komentar Instagram Bahasa Indonesia Menggunakan Naïve Bayes

The usage of social media growing rapidly, especially after the smartphone was invented. Because the number of social media users was quite a lot, companies prefer to promote their products through social media like Instagram. But, unlike TV or radio, social media is a two-way communication media, that makes users can respond directly to the content created by the company. Comments given by users have various types of sentiment, like positive or negative comments. In addition to using text, comments also often contain emoticons to support the message. This study tries to analyzing sentiment based on the usage of emoticons inside them using the Naïve Bayes algorithm. Based on the test results, the accuracy result is quite good, it is about 96.3% correct in sentiment classification.

Efficient Intrusion Detection System for SDN Orchestrated Internet of Things

Internet of Things (IoT) can simply be defined as an extension of the current Internet system. It extends the human to human interconnection and intercommunication scenario of the Internet by including things, to bring anytime, anywhere, and anything communication. A discipline in networking evolving in parallel with IoT is Software Defined Networking (SDN). It is an important technology that is aimed to solve the different problems existing in the traditional network systems. It provides a new convenient home to address the different challenges existing in different network-based systems including IoT. One important security challenge prevailing in such SDN-based IoT (SDIoT) systems is guarantying service availability. The ever-increasing denial of service (DoS) attacks are responsible for such service denials. A centralized signature-based intrusion detection system (IDS) is proposed and developed in this work. Random Forest (RF) classifier is used for training the model. A very popular and recent benchmark dataset, CICIDS2017, has been used for training and validating the machine learning (ML) models. An accuracy result of 99.968% has been achieved by using only 12 features on Wednesday’s release of the dataset. This result is higher than the achieved accuracy results of related works considering the original CICIDS2017 dataset. A maximum cross-validated accuracy result of 99.713% has been achieved on the same release of the dataset. These developed models meet the basic requirement of a supervised IDS system developed for smart environments and can effectively be used in different IoT service scenarios.

Machine learning approach on road accidents analysis in Calabarzon, Philippines: an input to road safety management

This research was conducted to help the traffic policy makers and general public in preventing road incidents using the collected traffic accident dataset between the years 2016 and 2019. Data mining using classification algorithm was utilized to develop a predictive model for predicting occurrences of traffic accidents. Classification algorithms such as decision tree, k-nn, naïve bayes and neural network have been compared in identifying better classification capability in classifying stage of felony. Neural network shows a very promising result in classifying road accident with a total accuracy result of 87.63%. Nonetheless, k-nn and naïve bayes both acquired a higher than 80% accuracy which shows that this classification algorithms were also good in predicting road accidents. Moreover, public vehicle is more prone in accident rather than private vehicle in both stage of felony and accident may occur between or on 3:00pm and 6:00pm.

Pengembangan Aplikasi Asisten Pintar Pembuka Al Qur’an 30 Juz dengan Perintah Voice Command

Many developers of digital Qur'an applications today still use tap to scrolling to run applications, although the features are interesting. This makes it less effective and efficient in opening the Qur'an. As is the case during the taklim assembly, some da'i are very interactive with jama'ah, asking to open certain surahs and verses so that there are some who have difficulty in searching. Therefore, the need for the Qur'anic application with voice command command to facilitate users. This research is the development of the Qur'an application with voice recognition feature. Using the waterfall method in development, voice command with google speech API as a voice command of surah and verse calling in the Qur'an application 30 juz. Conducted 10 randomized experiments with calls in the form of play or open surahs and certain verses give a 90% accuracy result. Commands can be given when online or offline. Then the use of google speech API can be very useful for use in the development of other applications.

Peramalan Pencemaran Udara Di Kota Surabaya Menggunakan Metode DSARIMA dengan Pendekatan Percentile Error Bootstrap (PEB)

<p>Peramalan pencemaran udara yang akurat diperlukan untuk mengurangi dampak pencemaran udara. Peramalan yang belum akurat akan berdampak kurang efektifnya tindakan yang dilakukan untuk mengantisipasi dampak pencemaran udara. Sehingga diperlukan sebuah pendekatan yang dapat mengetahui keakuratan plot data hasil peramalan. Penelitian ini dilakukan dengan tujuan melakukan peramalan pencemaran udara berdasarkan parameter PM₁₀, NO₂, CO, SO₂, dan O₃dengan metode DSARIMA. Data dalam penelitian ini sebanyak 8.760 data yang berasal dari Dinas Lingkungan Hidup Kota Surabaya. Berdasarkan hasil peramalan selama 168 jam kadar parameter PM₁₀, NO₂, SO₂ dan O₃ cenderung menurun. Hasil peramalan selama 168 jam dengan menggunakan DSARIMA memberikan hasil peramalan yang nilainya mendekati data aktual terbukti dari polanya yang sesuai atau mirip dengan grafik plot data aktual dengan hasil ramalan. Dengan pendekatan PEB, selisih antara data aktual dan data ramalan kecil dan plot grafik PEB mengikuti plot grafik di data aktual, sehingga dapat dikatakan bahwa model sudah sesuai. Hasil akurasi terbaik yang dihasilkan adalah model DSARIMA dengan RMSE terkecil 0,59 didapatkan dari parameter CO yaitu ARIMA(0,1,[1,2,3])(0,1,1)²⁴(0,1,1)¹⁶⁸.</p><p> </p><p><em><strong>Abstract</strong></em></p><p class="Judul2"><em>Accurate air pollution forecasting is needed to reduce the impact of air pollution. Inaccurate forecasting will result in less effective actions taken to anticipate the impact of air pollution. So we need an approach that can determine the accuracy of the forecast data plot. This research was conducted with the aim of forecasting air pollution based on the PM₁₀, NO₂, CO, _SO2, and O₃ parameters using the DSARIMA method. The data in this study were 8.760 data from the Surabaya City Environmental Service. Based on the results of forecasting for 168 hours, the levels of PM₁₀, NO_2,SO₂, and O₃ parameters tend to decrease. Forecasting results for 168 hours using DSARIMA provide forecasting results whose values are close to the actual data as evidenced by the pattern that matches or is similar to the actual data plot graph with the forecast results. With the PEB approach, the difference between the actual data and the forecast data is small and the PEB graph plot follows the graph plot in the actual data, so it can be said that the model is appropriate. The best accuracy result is DSARIMA with the smallest RMSE 0,59 obtained from the CO parameter, namely </em>ARIMA(0,1,[1,2,3])(0,1,1)²⁴(0,1,1)¹⁶⁸.</p><p> </p><p> </p>

Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes

Approximately 4% of the world’s population suffers from rare diseases. A vast majority of these disorders have a genetic background. The number of genes that have been linked to human diseases is constantly growing, but there are still genetic syndromes that remain to be discovered. The diagnostic yield of genetic testing is continuously developing, and the need for testing is becoming more significant. Due to limited resources, including trained clinical geneticists, patients referred to clinical genetics units must be accurately selected. Around 30–40% of genetic disorders are associated with specific facial characteristics called dysmorphic features. As part of our research, we analyzed the performance of classifiers based on deep learning face recognition models in detecting dysmorphic features. We tested two classification problems: a multiclass problem (15 genetic disorders vs. controls) and a two-class problem (disease vs. controls). In the multiclass task, the best result reached an accuracy level of 84%. The best accuracy result in the two-class problem reached 96%. More importantly, the binary classifier detected disease features in patients with diseases that were not previously present in the training dataset. The classifier was able to generalize differences between patients and controls, and to detect abnormalities without information about the specific disorder. This indicates that a screening tool based on deep learning and facial recognition could not only detect known diseases, but also detect patients with diseases that were not previously known. In the future, this tool could help in screening patients before they are referred to the genetic unit.

Melanoma Detection from Lesion Images using Optimized Features Selected by Metaheuristic Algorithms

This paper deals with a simple but efficient method for detection of deadly malignant melanoma with optimized hand-crafted feature sets selected by three alternative metaheuristic algorithms, namely Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and Simulated Annealing (SA). Total 1898 number of features relating to lesion shapes, colors and textures are extracted from each of the 170 non-dermoscopy camera images of the popular MED-NODE dataset. This large feature set is then optimized and the number of features is reduced to up-to the range of single digit using metaheuristic algorithms as feature selector. Two well-known supervised classifiers, i.e. Support Vector Machine (SVM) and Artificial Neural Network (ANN) are used to classify malignant and benign lesions. The best classification accuracy result found by this method is 87.69% with only 7 features selected by PSO using ANN classifier which is far better than the results found in the literature so far.

Pengenalan Jamur Yang Dapat Dikonsumsi Menggunakan Metode Transfer Learning Pada Convolutional Neural Network

Not all mushrooms are edible because some are poisonous. The edible or poisonous mushrooms can be identified by paying attention to the morphological characteristics of mushrooms, such as shape, color, and texture. There is an issue: some poisonous mushrooms have morphological features that are very similar to edible mushrooms. It can lead to the misidentification of mushrooms. This work aims to recognize edible or poisonous mushrooms using a Deep Learning approach, typically Convolutional Neural Networks. Because the training process will take a long time, Transfer Learning was applied to accelerate the learning process. Transfer learning uses an existing model as a base model in our neural network by transferring information from the related domain. There are Four base models are used, namely MobileNets, MobileNetV2, ResNet50, and VGG19. Each base model will be subjected to several experimental scenarios, such as setting the different learning rate values for pre-training and fine-tuning. The results show that the Convolutional Neural Network with transfer learning method can recognize edible or poisonous mushrooms with more than 86% accuracy. Moreover, the best accuracy result is 92.19% obtained from the base model of MobileNetsV2 with a learning rate of 0,00001 at the pre-training stage and 0,0001 at the fine-tuning stage.