Search

There are currently more than 10.000 cryptocurrencies available to buy from the online market, with a vast range of prices for each coin it sells. The fluctuation of each coin is affected by any social events or by several important companies or people behind it. The aim of this research is to compare three cryptocurrencies, which are Bitcoin, Ethereum, and Binance Coin, using Social Network Analysis (SNA) by visualizing them using Business Intelligence (BI Dashboard). This study uses the SNA parameters of degree, diameter, modularity, centrality, and path length for each network and its actors and their actual market price by crawling(data collecting process) from Twitter as one of the social media platforms. From the research conducted, the popularity of cryptocurrencies is affected by their market price and the activeness of their actors on social media. These results are important because they could help in the decision-making to buy cryptocurrencies with high popularity on social media because they tend to retain their value over time and could benefit from price spikes from influential people. Doi: 10.28991/HIJ-2022-03-02-09 Full Text: PDF

The emergence of health informatics opens new opportunities and doors for different disease diagnoses. The current work proposed the implementation of five different stand-alone techniques coupled with four different novel hybridized paradigms for the clinical prediction of hepatitis C status among patients, using both sociodemographic and clinical input variables. Both the visualized and quantitative performances of the stand-alone algorithms present the capability of the Gaussian process regression (GPR), Generalized neural network (GRNN), and Interactive linear regression (ILR) over the Support Vector Regression (SVR) and Adaptive neuro-fuzzy inference system (ANFIS) models. Hence, due to the lower performance of the stand-alone algorithms at a certain point, four different novel hybrid data intelligent algorithms were proposed, including: interactive linear regression-Gaussian process regression (ILR-GPR), interactive linear regression-generalized neural network (ILR-GRNN), interactive linear regression-Support Vector Regression (ILR-SVR), and interactive linear regression-adaptive neuro-fuzzy inference system (ILR-ANFIS), to boost the prediction accuracy of the stand-alone techniques in the clinical prediction of hepatitis C among patients. Based on the quantitative prediction skills presented by the novel hybridized paradigms, the proposed techniques were able to enhance the performance efficiency of the single paradigms up to 44% and 45% in the calibration and validation phases, respectively. [ABSTRACT FROM AUTHOR]

Purpose – The authors constructed an automatic essay scoring (AES) model in a discussion forum where the result was compared with scores given by human evaluators. This research proposes essay scoring, which is conducted through two parameters, semantic and keyword similarities, using a SentenceTransformers pre-trained model that can construct the highest vector embedding. Combining these models is used to optimize the model with increasing accuracy. Design/methodology/approach – The development of the model in the study is divided into seven stages: (1) data collection, (2) pre-processing data, (3) selected pre-trained SentenceTransformers model, (4) semantic similarity (sentence pair), (5) keyword similarity, (6) calculate final score and (7) evaluating model. Findings – The multilingual paraphrase-multilingual-MiniLM-L12-v2 and distilbert-base-multilingual-cased-v1 models got the highest scores from comparisons of 11 pre-trained multilingual models of SentenceTransformers with Indonesian data (Dhini and Girsang, 2023). Both multilingual models were adopted in this study. A combination of two parameters is obtained by comparing the response of the keyword extraction responses with the rubric keywords. Based on the experimental results, proposing a combination can increase the evaluation results by 0.2. Originality/value – This study uses discussion forum data from the general biology course in online learning at the open university for the 2020.2 and 2021.2 semesters. Forum discussion ratings are still manual. In this survey, the authors created a model that automatically calculates the value of discussion forums, which are essays based on the lecturer's answers moreover rubrics.

Introduction. Paediatric HIV and sickle cell disease (SCD) are two stigmatising and potentially fatal illnesses that place a significant burden on families. HIV patients benefit from a longstanding free-service national programme in Cameroon, and this could considerably alleviate burden of care on HIV caregivers, possibly leading to better quality of life (QoL) in HIV caregivers compared to SCD caregivers. Our study aimed to compare the QoL between caregivers of children and adolescents with SCD and HIV and explore factors associated with this QoL in Cameroon. Methods and Materials. We conducted a hospital-based cross-sectional analytic study at Douala Laquintinie Hospital from February to May 2023. A questionnaire was administered to caregivers of paediatric patients (≤18 years) with SCD and HIV. The Pediatrics Quality of Life-Family Impact Module (PedsQL FIM), the 7-item Generalized Anxiety Disorder (GAD-7), and the 9-item Patient Health Question (PHQ-9) tools were used as measures of quality of life, anxiety, and depression, respectively. Multivariable linear regression was used to determine factors associated with quality of life. A significance level was set at p

Cryptocurrencies are digital assets that are widely used for trading and investing. One of the characteristics that traders take advantage of for profit is the high volatility of the price. Its volatile and rapidly changing prices have made cryptocurrency price predictions a challenging and highly sought-after research topic. Cryptocurrency price predictions usually only use historical prices on the dataset, while price movements are also influenced by other aspects such as sentiment contained in social media. This study proposes a new machine learning method to predict Ethereum and Solana cryptocurrency price, which integrates cryptocurrency historical price data and social media sentiment as inputs of the prediction model. FinBERT, a pre-trained sentiment analysis model is used to extract the sentiment implied in social network tweets into daily sentiment score, which are then combined with the historical market price data. The hybrid model of LSTM-GRU model is used to train the dataset and perform cryptocurrency price prediction. The experiment results show that the presented method can successfully predict the Ethereum and Solana price movement and has superior performance than all the benchmark models.

In the process of developing a business, aspect-based sentiment analysis (ABSA) could help extract customers' opinions on different aspects of the business from online reviews. Researchers have found great prospective in deep learning approaches to solving ABSA tasks. Furthermore, studies have also explored the implementation of text augmentation, such as Easy Data Augmentation (EDA), to improve the deep learning models’ performance using only simple operations. However, when implementing EDA to ABSA, there will be high chances that the augmented sentences could lose important aspects or sentiment-related words (target words) critical for training. Corresponding to that, another study has made adjustments to EDA for English aspect-based sentiment data provided with the target words tag. However, the solution still needs additional modifications in the case of non-tagged data. Hence, in this work, we will focus on modifying EDA that integrates POS tagging and word similarity to not only understand the context of the words but also extract the target words directly from non-tagged sentences. Additionally, the modified EDA is combined with the backtranslation method, as the latter has also shown quite a significant contribution to the model’s performance in several research studies. The proposed method is then evaluated on a small Indonesian ABSA dataset using baseline deep learning models. Results show that the augmentation method could increase the model’s performance on a limited dataset problem. In general, the best performance for aspect classification is achieved by implementing the proposed method, which increases the macro-accuracy and F1, respectively, on Long Short-Term Memory (LSTM) and Bidirectional LSTM models compared to the original EDA. The proposed method also obtained the best performance for sentiment classification using a convolutional neural network, increasing the overall accuracy by 2.2% and F1 by 3.2%. Doi: 10.28991/ESJ-2023-07-01-018 Full Text: PDF

Abstract We report a novel hyperspectral sensor employing a Fabry-Pérot interferometer based on micro-electro-mechnical system and a custom mid-infrared supercontinuum laser. The Fabry-Pérot interferometer allows on-axis filtering, of spectral components of supercontinuum light backscattered from a target, with a spectral resolution of about 25 nm. We demonstrated hyperspectral identification of black polypropylene (PP) and polyethylene (PE500) using the 3–3.5 $$\mu$$ μ m region of the supercontinuum spectrum and a corresponding measurement rate of 62.5 spectra / s. The resulted spectra show excellent agreement with the reference based on an FTIR spectrometer. Furthermore, we showed that the coloring of the plastics has no effect on their identification at this wavelength range.

Desertification alludes to land degradation in arid, semi-arid and sub-humid regions resulting from various variables, counting climatic variations and human activities. When land degradation transpire within the world's drylands. It regularly makes desert-like conditions. Land degradation occurs all over, but is characterized as desertification when it occurs within the drylands. The study employed adjusted MEDALUS methodology using eleven indicators rainfall, evapotranspiration, aridity, soil texture, soil depth, slope gradient, drainage density, plant cover, erosion protection, sensitivity desertification index and Normalized Difference Vegetation Index (NDVI). Remote Sensing and GIS were the main techniques used in the indices computations and mapping. Thus, Shuttle Rader Topographic Map (SRTM) and Landsat 8 satellite imagery for the year 2019 with 30 meter resolution, captured in the month of August (rainy season), covering the study area were acquired from Global Land cover Facility (GLCF) University of Maryland. The study finds that the duration and intensity of rainfall is declining especially at the edge of the desert, extreme north and western part of the area. Rain quickly drained through infiltration and surface runoff which carried the little nutrients attached to the soil. Rainfall and climate is of arid type recording about 300-400mm of rainfall and the soil is low in organic matter content making it weak and less fertile and support only the cultivation of cereals and legumes. The study recommends that there is need to strengthen the laws and policies in controlling desertification and land degradation, establishment of shelterbelts to control desertification and act also as wind breakers and encourage the use of modern techniques such as drip irrigation to check the rate of infiltration and runoff. [ABSTRACT FROM AUTHOR]

Social media is a place that people use to socialize. In addition to socializing, social media is also often used as a crime medium by certain people. In the evidentiary process, law enforcers have the duty to present the evidence used by the suspect in committing his crime. The method used in collecting digital evidence from social media must have a clear scientific basis and guidelines. If the method used is not known as a theory or method in digital forensics, this will undermine all expert testimony and evidence presented in the court. Making a framework that can be recognized by all judicial administrators (judges, public prosecutors, attorneys for defendants, witnesses and defendants) is a solution that can be used as a standard so that the evidence process runs well. The framework that has been created by the researcher is an update from the previous framework. The framework design is made using the Composite Logic method. The composite logic method will collaborate with the Digital Forensics Investigation Models framework to produce a new framework. Based on existing data and facts, this research has produced a framework with better performance than the previous framework.

In this study, adaptive neuro-fuzzy inference system, and feed forward neural network as two artificial intelligence-based models along with conventional multiple linear regression model were used to predict the multi-station modelling of dissolve oxygen concentration at the downstream of Mathura City in India. The data used are dissolved oxygen, pH, biological oxygen demand and water temperature at upper, middle and downstream of the river. To predict outlet of dissolved oxygen of the river in each station, considering different input combinations as i) 11 inputs parameters for all three locations except, dissolved oxygenat the downstream ii) 7 inputs for middle and downstream except dissolved oxygen, at the target location and lastly iii) 3 inputs for downstream location. To determine the accuracy of the model, root mean square error and determination coefficient were employed. The simulated results of dissolved oxygen at three stations indicated that, multi-linear regression is found not to be efficient for predicting dissolved oxygen. In addition, both artificial intelligence models were found to be more capable and satisfactory for the prediction. Adaptive neuro fuzzy inference system model demonstrated high prediction ability as compared to feed forward neural network model. The results indicated that adaptive neuro fuzzy inference system model has a slight increment in performance than feed forward neural network model in validation step. Adaptive neuro fuzzy inference system proved high improvement in efficiency performance over multilinear regression modeling up to 18% in calibration phase and 27% in validation phase for the best models. [ABSTRACT FROM AUTHOR]

The number of news produced every day is as much as 3 million per day, making readers have many choices in choosing news according to each reader's topic and category preferences. The recommendation system can make it easier for users to choose the news to read. The method that can be used in providing recommendations from the same user is collaborative filtering. Neural collaborative filtering is usually being used for recommendation systems by combining collaborative filtering with neural networks. However, this method has the disadvantage of recommending the similarity of news content such as news titles and content to users. This research wants to develop neural collaborative filtering using sentences BERT. Sentence BERT is applied to news titles and news contents that are converted into sentence embedding. The results of this sentence embedding are used in neural collaboration with item id, user id, and news category. We use a Microsoft news dataset of 50,000 users and 51,282 news, with 5,475,542 interactions between users and news. The evaluation carried out in this study uses precision, recall, and ROC curves to predict news clicks by the user. Another evaluation uses a hit ratio with the leave one out method. The evaluation results obtained a precision value of 99.14%, recall of 92.48%, f1-score of 95.69%, and ROC score of 98%. Evaluation measurement using the hit ratio@10 produces a hit ratio of 74% at fiftieth epochs for neural collaborative with sentence BERT which is better than neural collaborative filtering (NCF) and NCF with news category.

Hospital is one of the most complex organization with highly intensive interaction between stakeholders (patients, nurses, doctors, staff, etc.). In the operation of a hospital, the use of Information technology has been proven to improve effectiveness and efficiency. However, in the majority of cases, the processes to achieve the Strategic Objectives through implementation of Information Technology are full of challenges. Based on the case study in Dharmais Cancer Hospital, there are many symptoms that are identified by this study and lead to 4 issues, namely: lack of ownership from Business users, lack of alignment between business strategy and IT strategy, lack of awareness to use IT as a tool for competitive advantage, and low quality of IT operation performances. In order to solve the issues and support the achievement of Strategic Business Objective through IT, an Enterprise Architecture approach can be used to develop baseline architecture, identify the target architecture, finding the gap, and use the gap as recommendation to solve those issues. The methodology chosen is TOGAF ADM, based on its focus on processes and its flexibility to combine artifacts and approaches that are most suitable for the case. This study develops 7 recommendations to Strengthen Business area of organization, 5 recommendations to Align IT plan with Business Strategy, 16 recommendations to Implement several IT solutions as Competitive Advantage for organization, and 8 recommendations to provide higher performances by enabling Service Management approach for IT Operation. This study also shows how TOGAF ADM can improve the awareness of the business users to the business itself. Doi: 10.28991/esj-2021-01278 Full Text: PDF

Enriching visitors'experiences at religious,historical sites (RHS) is getting more attention than before. This research aims to identify and investigatethe influential factors enriching the visitors'experience at such a site, using Al-Khandaq battle site as the case study. Forty-tworespondents were interviewed at the site and NVivo 12 pro software was used to code and analyze theresponses. The study explored tourist motivations, expectations, and perceptions as the guiding constructs in detailed qualitative analysis. Foremost, learning, reliving the experience of the events of the battle, and Islamic values were the primarymotivation to the historic site visitation. Next, findings reveal the extent to which tourists' expectations can be met through the availability of an open museum, accessibility, and the spatial and experiential simulation of the ancient Al-Khandaq path. Lastly, the need to reconstruct the historical site in spatial planning and experiential dimensions formed the main thrust of theelement of visitors'perception. Based on the foregoing, the study recommends that Al-Khandaq site should be developed traditionally as an open museum, displaying both religious and historical elements of the battle with emphasis on the visual connection to the Prophet's mosque.