Deep Learning Methods In Predicting Indonesia Composite Stock Price Index (IHSG)

The stock price changes at any time within seconds. The stock price is a time series data. Thus, it is necessary to have the best analysis model in predicting the stock price to make decisions to avoid losses in investing. In this research, the method used two models Deep Learning namely Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) in predicting Indonesia Composite Stock Price Index (IHSG). The dataset used is historical data from the Jakarta Composite Index (^JKSE) stock price in 2013-2020 obtained through Yahoo Finance. The results suggest that Deep learning methods with LSTM and GRU models can predict Indonesia Composite Stock Price Index (IHSG). Based on the test results obtained RMSE value of 71.28959454502723 with an accuracy rate of 92.39% for LSTM models and obtained RMSE value of 70.61870739073838 with an accuracy rate of 96.77% on GRU models.

A Survey of Deep Learning Solutions for Anomaly Detection in Surveillance Videos

Deep learning has proven to be a landmark computing approach to the computer vision domain. Hence, it has been widely applied to solve complex cognitive tasks like the detection of anomalies in surveillance videos. Anomaly detection in this case is the identification of abnormal events in the surveillance videos which can be deemed as security incidents or threats. Deep learning solutions for anomaly detection has outperformed other traditional machine learning solutions. This review attempts to provide holistic benchmarking of the published deep learning solutions for videos anomaly detection since 2016. The paper identifies, the learning technique, datasets used and the overall model accuracy. Reviewed papers were organised into five deep learning methods namely; autoencoders, continual learning, transfer learning, reinforcement learning and ensemble learning. Current and emerging trends are discussed as well.

Neutrosophic Triangular Fuzzy Travelling Salesman Problem Based on Dhouib-Matrix-TSP1 Heuristic

In this paper, the Travelling Salesman Problem is considered in neutrosophic environment which is more realistic in real-world industries. In fact, the distances between cities in the Travelling Salesman Problem are presented as neutrosophic triangular fuzzy number. This problem is solved in two steps: At first, the Yager’s ranking function is applied to convert the neutrosophic triangular fuzzy number to neutrosophic number then to generate the crisp number. At second, the heuristic Dhouib-Matrix-TSP1 is used to solve this problem. A numerical test example on neutrosophic triangular fuzzy environment shows that, by the use of Dhouib-Matrix-TSP1 heuristic, the optimal or a near optimal solution as well as the crisp and fuzzy total cost can be reached.

A Computer Model of the Spread of the Pandemic and its Analysis

The paper describes and analyzes a mathematical model of the variable state of the incidence of epidemic diseases, which is of great importance for determining the quantity of vaccines and antiviral drugs to be produced. The information model according to the system of differential equations of the spread of the pandemic is illustrated in a structural diagram. The model is presented in a vector-matrix form and the state of equilibrium of the model in the spatial state is proved.The model of the spread of the pandemic was developed, whose implementation with a Matlab software package resulted in obtaining the curves of variation of the state. The developed computer model of the incidence of epidemic diseases can be used to make a projection of the number of infected people, as well as intensity of the process of disseminating information and ideas in the community.

Object Tracking in Video Using the TLD and CMT Fusion Model

Object tracking has been an attractive study topic in computer vision in recent years, thanks to the development of video monitoring systems. Tracking-Learning Detection (TLD), Compressive Tracking (CT), and Clustering of Static-Adaptive Correspondences for Deformable Object Tracking are some of the state-of-the-art methods for motion object tracking (CMT). We present a fusion model that combines TLD and CMT in this study. To restrict the calculation time of the CMT technique, the fusion TLD CMT model enhanced the TLD benefits of computation time and accuracy on t no deformable objects. The experimental results on the Vojir dataset for three techniques (TLD, CMT, and TLD CMT) demonstrated that our fusion proposal successfully trades off CMT accuracy for computing time.

Digital Video Watermarking for Copyright Labelling

Penggunaan konten multimedia di internet kini semakin berkembang, terutama dalam video digital. Pemalsuan, penipuan, dan penjarahan konten video menyebabkan masalah karena pasokan sumber daya untuk berbagi konten. Hak cipta menjadi hal yang krusial dalam video digital untuk menghindari manipulasi dari pihak yang tidak bertanggung jawab. Ada banyak cara yang bisa dilakukan untuk melabeli hak cipta ke dalam sebuah video. Salah satunya adalah digital watermarking. Pembuatan air digital digunakan untuk mencegah replikasi ilegal atau eksploitasi konten digital, melindungi konten digital, dan menghindari manipulasi multimedia secara ilegal. Penggunaan beberapa metode seperti Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), dan Discrete Fourier Transform (DFT) untuk pelabelan hak cipta video akan dibandingkan berdasarkan imperceptibility dan robustness setelah beberapa manipulasi diterapkan ke dalam video yang disisipkan-watermark. Dari segi imperceptibility, metode DWT menghasilkan nilai PSNR sebesar 45,62435 dB, metode DCT menghasilkan nilai PSNR sebesar 45.89422 dB, dan metode DFT menghasilkan nilai PSNR sebesar 45.77747 dB. Rerata PSNR dari ketiga metode tersebut adalah 45.76535 dB. Artinya, video yang disisipkan tanda air tampak mirip dengan yang disisipkan. Dengan demikian, dari percobaan dapat disimpulkan bahwa metode DWT, DCT, dan DFT yang diterapkan menunjukkan bahwa video yang diberi watermark masih dalam kualitas yang baik yaitu wajar dan memenuhi imperceptibility. Dari segi kekokohan, NC mean metode DCT adalah 0,63974, metode DCT adalah 0,755839, dan metode DFT adalah 0,745442. Hal ini menunjukkan bahwa hasil ekstraksi watermark dari ketiga metode tersebut sama dengan hasil watermark aslinya. Dengan kata lain, semua tanda air pada ketiga metode ini dapat diekstraksi dengan baik meskipun serangan dikirimkan kepada mereka. Dari tingkat uji imperceptibility dan robustness pada metode DWT, DCT, dan DFT, dapat dikatakan bahwa metode DCT lebih baik daripada metode DWT dan DFT karena performansinya yang tinggi pada PSNR dan NC.

The Accuracy Improvement of Text Mining Classification on Hospital Review through The Alteration in The Preprocessing Stage

Sentiment analysis is a part of text mining used to dig up information from a sentence or document. This study focuses on text classification for the purpose of a sentiment analysis on hospital review by customers through criticism and suggestion on Google Maps Review. The data of texts collected still contain a lot of nonstandard words. These nonstandard words cause problem in the preprocessing stage. Thus, the selection and combination of techniques in the preprocessing stage emerge as something crucial for the accuracy improvement in the computation of machine learning. However, not all of the techniques in the preprocessing stage can contribute to improve the accuracy on classification machine. The objective of this study is to improve the accuracy of classification model on hospital review by customers for a sentiment analysis modeling. Through the implementation of the preprocessing technique combination, it can produce a highly accurate classification model. This study experimented with several preprocessing techniques: (1) tokenization, (2) case folding, (3) stop words removal, (4) stemming, and (5) removing punctuation and number. The experiment was done by adding the preprocessing methods: (1) spelling correction and (2) Slang. The result shows that spelling correction and Slang method can assist for improving the accuracy value. Furthermore, the selection of suitable preprocessing technique combination can fasten the training process to produce the more ideal text classification model.

A Systematic Literature Review of Hausa Natural Language Processing

The processing of natural languages is an area of computer science that has gained growing attention recently. NLP helps computers recognize, in other words, the ways in which people use their language. NLP research, however, has been performed predominantly on languages with abundant quantities of annotated data, such as English, French, German and Arabic. While the Hausa Language is Africa's second most commonly used language, only a few studies have so far focused on Hausa Natural Language Processing (HNLP). In this research paper, using a keyword index and article title search, we present a systematic analysis of the current literature applicable to HNLP in the Google Scholar database from 2015 to June 2020. A very few research papers on HNLP research, especially in areas such as part-of-speech tagging (POS), Name Entity Recognition (NER), Words Embedding, Speech Recognition and Machine Translation, have just recently been released. This is due to the fact that for training intelligent models, NLP depends on a huge amount of human-annotated data. HNLP is now attracting researchers' attention after extensive research on NLP in English and other languages has been performed. The key objectives of this paper are to promote research, to define likely areas for future studies in the HNLP, and to assist in the creation of further examinations by researchers for relevant studies.

A Comparative Study of Gameplay of Different Sets of Players in an Engineering Mapping Game

Educators in the STEM (science, technology, engineering, and mathematics) field are constantly employing different tools to make the process of education streamlined and fun. The digital gaming platform also called e-gaming platform has evolved as one of the key tools to make STEM education more accessible to students. UNTANGLED III is such an e-gaming platform that is based on STEM concepts and aims to bring in players from all educational backgrounds under a common platform. The data obtained from the game gave us insights on how males and females play the game. It has answered whether there are any significant differences in the gameplay strategies between males and females. The data pertaining to the types of puzzles that players, from both genders, chose and played, was also obtained. Males and females had no stark differences in the strategies that they used in solving the puzzles. They used similar kinds of moves and in fact solved similar kinds of puzzles of similar difficulty levels. During their gameplay sessions, both the males and the females visualized similar patterns in the puzzles as evident in their final solution. The performance of players from both the genders, based on the gameplay data was at par. Suggestions obtained from the current players and outreach events hold the key to increasing the overall participation in the game.

A Vision of the Internet of Things: A Review of Critical Challenges

Today, Information Communication Technology has brought many benefits to have a better life. Meanwhile, the concept of the Internet of Things (IoT), which has transformed the traditional lifestyle into a modern lifestyle and is growing rapidly, is of great importance. This research deals with the critical challenges of IoT. Although not much time has passed since the advent of the concept of the IoT, today the Internet of Things has faced a great deal of complexity in the industry, which requires in-depth studies to realise its potential and challenges. This study introduces and examines IoT challenges including security and privacy, scalability, interoperability, mobility, protocol & standardisation, and energy consumption. In this study, the relationship between these challenges has been clearly defined. Finally, based on the research, some main challenges or sub-challenges considered for these challenges.