Articles

This research is a collaboration involving a university team, a partnering corporation, and a hemodialysis clinic, which is a cross-disciplinary research initiative in the field of Artificial Intelligence of Things (AIoT) within the medical informatics domain. The research has two objectives: (1) The development of an <i>Internet of Things (IoT)</i><i>-based</i><i> Information System</i> customized for the hemodialysis machines at the clinic, including transmission bridges, clinical personnel dedicated web/app, and a backend server. The system has been deployed at the clinic and is now officially operational; (2) The research also utilized de-identified, anonymous data (collected by the officially operational system) to train, evaluate, and compare <i>Deep Learning-based Intradialytic Blood Pressure</i><i> (BP)</i><i>/Pulse </i><i>Rate (PR) </i><i>Predictive Models</i>, with subsequent suggestions provided. Both objectives were executed under the supervision of the Institutional Review Board (IRB) at Mackay Memorial Hospital in Taiwan. The system completed for objective one has introduced three significant services to the clinic, including automated hemodialysis data collection, digitized data storage, and an information-rich human-machine interface as well as graphical data displays, which replaces traditional paper-based clinical administrative operations, thereby enhancing healthcare efficiency. The graphical data presented through web and app interfaces aids in real-time, intuitive comprehension of the patients’ conditions during hemodialysis. Moreover, the data stored in the backend database is available for physicians to conduct relevant analyses, unearth insights into medical practices, and provide precise medical care for individual patients. The training and evaluation of the predictive models for objective two, along with related comparisons, analyses, and recommendations, suggest that in situations with limited computational resources and data, an Artificial Neural Network (ANN) model with six hidden layers, SELU activation function, and a focus on artery-related features can be employed for hourly intradialytic BP/PR prediction tasks. It is believed that this contributes to the collaborating clinic and relevant research communities.

Sentiment analysis, a vital aspect of natural language processing, involves the application of machine learning models to discern the emotional tone conveyed in textual data. The use case for this type of problem is where businesses can make informed decisions based on customer feedback, identify the sentiments of their employees, and make decisions on hiring or retention, or for that matter, classify a text based on its topic like whether it is about a particular subject like physics or chemistry as is useful in search engines. The model leverages a sequential architecture, transforms words into dense vectors using an Embedding layer, and captures intricate sequential patterns with two Long Short-Term Memory (LSTM) layers. This model aims to effectively classify sentiments in text data using a 50-dimensional embedding dimension and 20 % dropout layers. The use of rectified linear unit (ReLU) activations enhances non-linearity, while the SoftMax activation in the output layer aligns with the multi-class nature of sentiment analysis. Both training and test accuracy were well over 80%.

Business merchants and investors in Nigeria are interested in the foreign exchange volatility forecasting accuracy performance because they need information on how volatile the exchange rate will be in the future. In the paper, we compared Exponential Generalized Autoregressive Conditional Heteroskedasticity with order p=1 and q= 1, (EGARCH (1,1)) and Recurrent Neural Network (RNN) based on long short term memory (LSTM) model with the combinations of p = 10 and q = 1 layers to model the volatility of Nigerian exchange rates. Our goal is to determine the preferred model for predicting Nigeria’s Naira exchange rate volatility with Euro, Pounds and US Dollars. The dataset of monthly exchange rates of the Nigerian Naira to US dollar, Euro and Pound Sterling for the period December 2001 – August 2023 was extracted from the Central Bank of Nigeria Statistical Bulletin. The model efficiency and performance was measured with the Mean Squared Error (MSE) criteria. The results indicated that the Nigeria exchange rate volatility is asymmetric, and leverage effects are evident in the results of the EGARCH (1, 1) model. It was observed also that there is a steady increase in the Nigeria Naira exchange rate with the euro, pounds sterling and US dollar from 2016 to its highest peak in 2023. Result of the comparative analysis indicated that, EGARCH (1,1) performed better than the LSTM model because it provided a smaller MSE values of 224.7, 231.3 and 138.5 for euros, pounds sterling and US Dollars respectively.

The stock market is very volatile and hard to predict accurately due to the uncertainties affecting stock prices. However, investors and stock traders can only benefit from such models by making informed decisions about buying, holding, or investing in stocks. Also, financial institutions can use such models to manage risk and optimize their customers' investment portfolios. In this paper, we use the Long Short-Term Memory (LSTM-RNN) Recurrent Neural Networks (RNN) to predict the daily closing price of the Amazon Inc. stock (ticker symbol: AMZN). We study the influence of various hyperparameters in the model to see what factors the predictive power of the model. The root mean squared error (RMSE) on the training was 2.51 with a mean absolute percentage error (MAPE) of 1.84%.

Financial markets have become more and more complex, so has been the number of data sources. Stock price prediction has hence become a tough but important task. The time dependencies in stock price movements tend to escape from traditional models. In this work, a hybrid ARIMA-LSTM model is suggested to enhance accuracy of stock price forecasts. Based on time series indicators like adjusted closing prices of S&#x26;P 500 stocks over a decade (2010–2019), the ARIMA-LSTM model combines influences of both autoregressive time series forecasting with the substantial sequence learning property of LSTM. Data preprocessing in all aspects including missing values interpolation, outlier’s detection and data scaling – Min-Max guarantees data quality. The model is trained on 90/10 training/testing split and met with main performance metrics: MaE, MSE &#x26; RMSE. As indicated in the results, the proposed ARIMA-LSTM model gives a MAE value and MSE value of 0.248 and 0.101 respectively and RMSE of 0.319, a measure high accuracy on stock price prediction. Coupled comparative analysis with other Artificial Neural Networks (ANN) and BP Neural Networks (BPNN) are examples of machine learning reference models, further illustrates the suitability and superiority of ARIMA-LSTM approach as compared to the underlying models with the least MAE and strong predictive capability. This work demonstrates the efficiency of integrating the classical time series models with deep learning methods for financial forecasting.

In the constantly evolving world of cloud computing, appropriate resource allocation is essential for both keeping costs down and ensuring an ongoing flow of apps and services. Because of its adaptability to specific tasks and human behavior, machine learning (ML) is a desirable choice for fulfilling those needs. This study Efficient cloud resource allocation is critical for optimizing performance and cost in cloud computing environments. In order to improve the precision of resource allocation, this study investigates the use of Long Short-Term Memory (LSTM). The LSTM model achieved 97% accuracy, 97.5% precision, 98% recall, and a 97.8% F1-score (F1-score: harmonic mean of precision and recall), according to experimental data. The confusion matrix demonstrates strong classification performance across several resource classes, while the accuracy and loss curves verify steady learning with minimal overfitting. The suggested LSTM model performs better than more conventional ML (machine learning) models like Gradient Boosting (GB) and Logistic Regression (LR), according to a comparative study. These findings underscore the LSTM (Long Short-Term Memory) model’s robustness and suitability for dynamic cloud environments, enabling more accurate forecasting and efficient resource management.

Crime is a serious and widespread problem in their society, thus preventing it is essential. Assignment. A significant number of crimes are committed every day. One tool for dealing with model crime is data mining. Crimes are costly to society in many ways, and they are also a major source of frustration for its members. A major area of machine learning research is crime detection. This paper analyzes crime prediction and classification using data mining techniques on a crime dataset spanning 2006 to 2016. This approach begins with cleaning and extracting features from raw data for data preparation. Then, machine learning and deep learning models, including RNN-LSTM, ARIMA, and Linear Regression, are applied. The performance of these models is evaluated using metrics like Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The RNN-LSTM model achieved the lowest RMSE of 18.42, demonstrating superior predictive accuracy among the evaluated models. Data visualization techniques further unveiled crime patterns, offering actionable insights to prevent crime.

The field of sentiment analysis is a crucial aspect of natural language processing (NPL) and is essential in discovering the emotional undertones within the text data and, hence, capturing public sentiments over a variety of issues. In this regard, this study suggests a deep learning technique for sentiment categorization on a Twitter dataset that is based on Long Short-Term Memory (LSTM) networks. Preprocessing is done comprehensively, feature extraction is done through a bag of words method, and 80-20 data is split using training and testing. The experimental findings demonstrate that the LSTM model outperforms the conventional models, such as SVM and Naïve Bayes, with an F1-score of 99.46%, accuracy of 99.13%, precision of 99.45%, and recall of 99.25%. Additionally, AUC-ROC and PR curves validate the model’s effectiveness. Although, it performs well the model consumes heavy computational resources and longer training time. In summary, the results show that deep learning performs well in sentiment analysis and can be used to social media monitoring, customer feedback evaluation, market sentiment analysis, etc.