Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,456 Article Results

An model for structured the NoSQL databases based on machine learning classifiers

10.11591/ijict.v14i1.pp229-239
Amine Benmakhlouf
Today, the majority of data generated and processed in organizations is unstructured. NoSQL database management systems perform the management of this data. The problem is that these unstructured databases cannot be analyzed by traditional OLAP analytical treatments. The latter are mainly used in structured relational databases. In order to apply OLAP analyses on NoSQL data, the structuring of this data is essential. In this paper, we propose a model for structuring the data of a document-oriented NoSQL database using machine learning (ML). This method is broken down into three steps, first the vectorization of documents, then the learning via different ML algorithms and finally the classification, which guarantees that documents with the same structure will belong to the same collection. Therefore, the modeling of a data warehouse can be carried out in order to create OLAP cubes. Since the models found by learning allow the parallel computation of the classifier, our approach represents an advantage in terms of speed since we will avoid doubly iterative algorithms, which rely on textual comparisons (TC). A comparative study of the performances is carried out in this work in order to detect the most efficient methods to perform this type of classification.
Volume: 14
Issue: 1
Page: 229-239
Publish at: 2025-04-01

Data analysis and visualization on titanic and student’s performance datasets-an exploratory study

10.11591/ijict.v14i1.pp68-76
Seong-Cheol Kim , Surender Reddy Salkuti , Alka Manvayalar Suresh , Madhu Sree Sankaran
Exploratory data analysis (EDA) is all about exploring the data in order to identify any underlying pattern before you try to use it to make a predictive model. It also plays a major role in the data discovery process as it is used to analyze data and to recapitulate their different characteristics, which is displayed efficiently with the help of data visualization methods. This paper aims to identify errors in the dataset, to understand the existing hidden structure and to identify new ones, to detect points in a dataset that deviate to a greater extent from the collected data (outliers), and also to find any relationship or intersection between the variables and constants. Two datasets are used namely ‘Titanic’ and ‘student’s performance’ to perform data analysis and ‘data visualization’ to depict ‘exploratory data analysis’ which acts as an important set of tools for recognizing a qualitative understanding. The datasets were explored and hence it assisted with identifying patterns, outliers, corrupt data, and discovering the relationship between the fields in the dataset.
Volume: 14
Issue: 1
Page: 68-76
Publish at: 2025-04-01

A convex hull based geofencing system to eradicate COVID

10.11591/ijece.v15i2.pp1817-1825
Parul Arora , Suman Deswal
The World Health Organization (WHO) has identified coronavirus disease (COVID-19), as a global pandemic due to its quick global spread to more than 183 countries. Many countries have used movement control orders (MCO) and high alert levels to halt the spread. The primary goal of this research is to provide a geofencing architecture that is specially tailored to the MCO's standard requirement for monitoring an individual's whereabouts during a lockdown. Whenever an individual tests Corona positive, Geofencing uses technology to notify an anticipated network of people who may be affected and to enable traceability for potential patients. Computational techniques such as Delaunay triangulation (inpolygon) and triangle weight characterization (inside polygon) are applied to analyze the geographical boundary in which the patient is isolated. Convex hull, on the other hand, is a better technique than computational algorithms. It is considered the best mathematical technique because it takes the least amount of time (0.014985 sec) to detect the patient within the geofence layer and has the lowest standard deviation when compared with the other computational techniques.
Volume: 15
Issue: 2
Page: 1817-1825
Publish at: 2025-04-01

A novel one-dimensional chaotic map with improved sine map dynamics

10.11591/ijece.v15i2.pp2128-2137
Mohamed Htiti , Ismail Akharraz , Abdelaziz Ahaitouf
These days, keeping information safe from people who should not have access to it is very important. Chaos maps are a critical component of encryption and security systems. The classical one-dimensional maps, such as logistic, sine, and tent, have many weaknesses. For example, these classical maps may exhibit chaotic behavior within the narrow range of the rate variable between 0 and 1and the small interval's rate variable. In recent years, several researchers have tried to overcome these problems. In this paper, we propose a new one-dimensional chaotic map that improves the sine map. We introduce an additional parameter and modify the mathematical structure to enhance the chaotic behavior and expand the interval's rate variable. We evaluate the effectiveness of our map using specific tests, including fixed points and stability analysis, Lyapunov exponent analysis, diagram bifurcation, sensitivity to initial conditions, the cobweb diagram, sample entropy and the 0-1 test.
Volume: 15
Issue: 2
Page: 2128-2137
Publish at: 2025-04-01

Enhancing predictive modelling and interpretability in heart failure prediction: a SHAP-based analysis

10.11591/ijict.v14i1.pp11-19
Niaz Ashraf Khan , Md. Ferdous Bin Hafiz , Md. Aktaruzzaman Pramanik
Predictive modelling plays a crucial role in healthcare, particularly in forecasting mortality due to heart failure. This study focuses on enhancing predictive modelling and interpretability in heart failure prediction through advanced boosting algorithms, ensemble methods, and SHapley Additive exPlanations (SHAP) analysis. Leveraging a dataset of patients diagnosed with cardiovascular diseases (CVD), we employed techniques such as synthetic minority over-sampling technique (SMOTE) and bootstrapping to address class imbalance. Our results demonstrated exceptional predictive performance, with the gradient boosting (GBoost) model achieving the highest accuracy of 91.39%. Ensemble techniques further enhanced performance, with the voting classifier (VC), stacking classifier (SC), and Blending achieving accuracies of 91.00%. SHAP analysis uncovered key features such as time, Serum_creatinine, and Ejection_fraction, significantly impacting mortality prediction. These findings highlight the importance of transparent and interpretable machine learning models in healthcare decision-making processes, facilitating informed interventions and personalized treatment strategies for heart failure patients.
Volume: 14
Issue: 1
Page: 11-19
Publish at: 2025-04-01

High speed space division multiplexing based integrated fiber transmission system and its impact on atmospheric conditions

10.11591/ijece.v15i2.pp1745-1753
Kakarla Phaneendra Kumar , T. Sreenivasulu Reddy
With several advantages over traditional wireless and fiber optic cables, free space optical communication is becoming more and more popular because of its high speed and bandwidth applications. In particular, the high transmission capacity of free space optics (FSO) communication systems makes them preferred, which enables them to handle the growing amount of internet traffic. Because FSO has no regulatory limitations, operates over large distances with high levels of security, and transmits data faster than radio frequency communication technologies are widely utilized. However, given different atmospheric conditions, the availability and capacity of FSO optical bands represent a major concern. For next-generation information transmission networks to satisfy end users high-capacity demands, the transmission technology known as space-division multiplexing (SDM) has become essential. Hence in this work, High speed space division multiplexing based integrated fiber/FSO transmission system and its impact on atmospheric conditions is presented. The SDM transmission system developed in this study is based on an integrated multimode fiber (MMF)/ FSO link with linear polarized (LP) spatial modes. This approach takes into consideration extreme climate conditions like snow and turbulence while evaluating performance. Utilizing bit error rate (BER) and received optical power (ROP) are the performance of FSO is evaluated in different weather conditions.
Volume: 15
Issue: 2
Page: 1745-1753
Publish at: 2025-04-01

Enhancing spatiotemporal weather forecasting accuracy with 3D convolutional kernel through the sequence to sequence model

10.11591/ijece.v15i2.pp2022-2030
Renaldy Fredyan , Karli Eka Setiawan , Kelvin Asclepius Minor
Accurate weather forecasting is important when dealing with various sectors, such as retail, agriculture, and aviation, especially during extreme weather events like heat waves, droughts, and storms to prevent disaster impact. Traditional methods rely on complex, physics-based models to predict the Earth's stochastic systems. However, some technological advancements and the availability of extensive satellite data from beyond Earth have enhanced meteorological predictions and sent them to Earth's antennae. Deep learning models using this historical data show promise in improving forecast accuracy to enhance how models learn the data pattern. This study introduces a novel architecture, convolutional sequence to sequence (ConvSeq2Seq) network, which employs 3D convolutional neural networks (CNN) to address the challenges of spatiotemporal forecasting. Unlike recurrent neural network (RNN)--based models, which are time-consuming due to sequential processing, 3D CNNs capture spatial context more efficiently. ConvSeq2Seq overcomes the limitations of traditional CNN models by ensuring causal constraints and generating flexible length output sequences. Our experimental results demonstrate that ConvSeq2Seq outperforms traditional and modern RNN-based architectures in both prediction accuracy and time efficiency, leveraging historical meteorological data to provide a robust solution for weather forecasting applications. The proposed architecture outperforms the previous method, giving new insight when dealing with spatiotemporal with high density.
Volume: 15
Issue: 2
Page: 2022-2030
Publish at: 2025-04-01

The advances in natural language processing technology and its impact on modern society

10.11591/ijece.v15i2.pp2325-2333
Nadezhda Borisova , Elena Karashtranova , Irena Atanasova
A wide range of information, such as books, news, reports, and other content, is constantly being produced, much of which is available online. Machine translation, spam detection, natural language interfaces, and question-answering applications have become increasingly popular. Natural language processing (NLP) is at the core of the automatic retrieval of information stored on computers. This article discusses NLP and its applications in daily activities. It covers the main stages of NLP and provides examples of its advances in various higher-level tasks. The objective is to highlight the significance of NLP in processing online content and in efficient interactions between humans and computers across various applications. As an essential element of artificial intelligence, NLP provides solutions for real-world problems and has the potential to transform the way companies operate.
Volume: 15
Issue: 2
Page: 2325-2333
Publish at: 2025-04-01

Evaluating tumor heterogeneity in oncology with genomic-imaging and cloud-based genomic algorithms

10.11591/ijece.v15i2.pp2427-2435
Gurumoorthi Gurulakshmanan , Raveendra N. Amarnath , Sivaprasad Lebaka , Munnangi Koti Reddy , Nagarajan Mohankumar , Surulivelu Muthumarilakshmi , Chelliah Srinivasan
The goal of this initiative is to rethink how oncology is traditionally practiced by integrating novel approaches to genomic imaging with cloud-based genomic algorithms. The research intends to give a thorough knowledge of cancer biology by focusing on the decoding of tumor heterogeneity as its primary objective. It is possible to get a more nuanced understanding of the intricacy of tumors via the integration of high-resolution imaging tools and sophisticated genetic analysis. It is a pioneering use of cloud computing, which enables the quick analysis of large genomic information. The major goal is to decipher the complex genetic variants that are present inside tumors in order to direct the creation of individualized treatment strategies. This discovery marks a significant step forward, since it successfully bridges the gap between genetics and imaging. Diagnostic accuracy and treatment effectiveness have both been improved. This innovative technique permits real-time analysis, which in turn enables treatment tactics to be adjusted in a timely manner. It makes a significant contribution to the continuous development of oncological research as well as its translation into better clinical outcomes for cancer patients.
Volume: 15
Issue: 2
Page: 2427-2435
Publish at: 2025-04-01

Markov processes in Bayesian network computation

10.11591/ijece.v15i2.pp2181-2191
Assem Shayakhmetova , Nurbolat Tasbolatuly , Ardak Akhmetova , Assel Abdildayeva , Marat Shurenov , Anar Sultangaziyeva
The article examines the influence of Markov processes on computations in Bayesian networks (BN), an important area of research within probabilistic graphical models. The concept of Bayesian Markov networks (BMN) is introduced, an extension of traditional Bayesian networks with the addition of a Markov constraint, according to which the probability in a node can only depend on the state of neighboring nodes. This constraint makes the model more realistic for many practical tasks, as most graphical models that reflect real-world processes possess the Markov property. The article also discusses that Bayesian networks, in the absence of evidence, actually exhibit the Markov property. However, when evidence (additional information) is introduced into the model, challenges arise that require more complex computational methods. In response, the article proposes algorithms adapted for working with Bayesian Markov networks in the presence of evidence. These algorithms are aimed at optimizing computations and reducing computational complexity. Additionally, a comparative analysis of calculations in Bayesian networks without Markov constraints and with them is conducted, highlighting the advantages and disadvantages of each approach. Special attention is paid to the practical applications of the proposed methods and their effectiveness in various scenarios.
Volume: 15
Issue: 2
Page: 2181-2191
Publish at: 2025-04-01

Comparison design of dynamic voltage restorers, distribution static compensators and unified power quality conditioner series shunts on voltage sag, and voltage swell

10.11591/ijece.v15i2.pp1396-1410
Yulianta Siregar , Syahrun Mubarok , Nur Nabila Mohamed
One issue with the power system is electrical power quality, which is brought on by short circuit disruptions and growing nonlinear loads. Power systems frequently have short circuits, resulting in voltage sags that can harm delicate loads. Voltage sage and swell issues can be resolved using unified power quality conditioner series shunts (UPQC-S), distribution static compensators (DSTATCOM), and dynamic voltage restorers (DVR). Custom power devices are very useful in overcoming problems with electrical networks. In this research, due to 3-phase short circuit faults, voltage sag and swell simulations were conducted using a load equal to 70% of the total load and a fault location point of 75% of the feeder length, from the results of research conducted with the case study PT. PLN (Persero) UP3 Sibolga Feeder SB 02 shows that DVR performs better than DSTATCOM and UPQC-S in handling voltage sag and voltage swell due to 3-phase short circuit disturbances. The DVR succeeded in providing the largest voltage sag recovery in phase C, increasing the voltage from 0.2481 pu to 0.9776 pu. The DVR is also effective in overcoming voltage swell on phase A, reducing it from 1.724 pu to 0.9969 pu.
Volume: 15
Issue: 2
Page: 1396-1410
Publish at: 2025-04-01

Novel features extraction: pigment epithelial detachment detection using machine learning algorithms

10.11591/ijece.v15i2.pp1572-1583
Sheeba Thankappan Mercy , Albert Antony Raj Saminathan , Anand Murugadhas , Anshy Princella Anand Sheeba
The majority of the retinal diseases have visual symptoms. Any area of the retina, a delicate layer of tissue on the interior the posterior wall of the human eye, can be impacted by retinal disorders. Optical coherence tomography (OCT) is the utmost commonly used imaging procedure for diagnosing retinal disorders such as age-related macular degeneration (ARMD), diabetic retinopathy, pigment epithelial detachment (PED), macular holes, and more. In this study, we put forth a brand-new technique for accurately extracting features from OCT images to identify PED diseases. For the preprocessing step, we examined the wiener filtering method. After that, we segmented the retinal pigment epithelium (RPE) layer used to the thresholding method, extracted the features from the RPE layer, and then gave the features to machine learning (ML) classifiers like the support vector machine (SVM), logistic regression (LR), k-nearest neighbors (KNN), decision tree (DT), random forest (RF), naive Bayes (NB), and artificial neural network (ANN). The total dataset about 200 images among 100 is normal and 100 is PED, we trained the dataset as an unbalanced and balanced group. The RF is the best outcome in comparison of other classifiers. The overall outcome of random forest is 100% accuracy.
Volume: 15
Issue: 2
Page: 1572-1583
Publish at: 2025-04-01

Recommender system for dengue prevention using machine learning

10.11591/ijai.v14.i2.pp1106-1115
Siriwan Kajornkasirat , Benjawan Hnusuwan , Supattra Puttinaovarat , Kritsada Puangsuwan , Nawapon Kaewsuwan
The study aimed to develop a recommender system for dengue prevention using environmental factors and mosquito larvae data. Data were collected from 100 households in Surat Thani, Thailand using mosquito larval survey in January 2020. Data mining techniques: frequent pattern growth (FP-Growth) and Apriori algorithms were used to find association rules and to compare accuracies for selecting a suitable model. The recommender system was designed as a web application. FP-Growth is more suitable for these data than Apriori algorithm. The factors associated with dengue infection, including community area, densely populated area, and agricultural area. Most areas where mosquito larvae are found are community areas and agricultural areas. Aedes larvae were found most in water containers with dark colors and without a lid. Aedes larvae were also found in small water jars, large water jars, cement tanks, and plastic tanks. The recommender system should be useful to dengue vector prevention and to health service communities, in planning and operational activities.
Volume: 14
Issue: 2
Page: 1106-1115
Publish at: 2025-04-01

Explainable zero-shot learning and transfer learning for real time Indian healthcare

10.11591/ijict.v14i1.pp91-101
Swati Saigaonkar , Vaibhav Narawade
Clinical note research is globally recognized, but work on real-time data, particularly from India, is still lagging. This study initiated by training models on medical information mart for intensive care (MIMIC) clinical notes, focusing on conditions like chronic kidney disease (CKD), myocardial infarction (MI), and asthma using the structured medical domain bidirectional encoder representations from transformers (SMDBERT) model. Subsequently, these models were applied to an Indian dataset obtained from two hospitals. The key difference between publicly available datasets and real-time data lies in the prevalence of certain diseases. For example, in a real-time setting, tuberculosis may exist, but the MIMIC dataset lacks corresponding clinical notes. Thus, an innovative approach was developed by combining a fine-tuned SMDBERT model with a customized zero-shot learning method to effectively analyze tuberculosis-related clinical notes. Another research gap is the lack of explainability because deep learning (DL) models are inherently black-box. To further strengthen the reliability of the models, local interpretable model-agnostic explanations (LIME) and shapley additive explanations (SHAP) explanations were projected along with narrative explanations which generated explanations in a natural language format. Thus, the research provides a significant contribution with ensemble technique of zero-shot learning and SMDBERT model with an accuracy of 0.92 as against the specialized models like scientific BERT (SCIBERT), biomedical BERT (BIOBERT) and clinical BioBERT.
Volume: 14
Issue: 1
Page: 91-101
Publish at: 2025-04-01

Design and implementation of an internet of things enabled stress level detection system using fuzzy logic method for enhanced accuracy and real-time monitoring

10.11591/ijece.v15i2.pp2499-2512
Nurhayati Nurhayati , Nur Hidayah , Muh. Ahyar , Asriyadi Asriyadi , Yuniarti Yuniarti , Muhira Dzar Faraby , Mustika Mustika , Asmah Akhriana , Mukhlisin Mukhlisin
Stress can affect individuals of all ages, from the young to the elderly, leading to a compromised immune system and increased susceptibility to illness. This study addresses this issue by developing an internet of things (IoT) based stress level detection system utilizing fuzzy logic methods. The device measures multiple physiological parameters and processes the data using an ESP32 microcontroller. This allows individuals to monitor and understand their stress levels efficiently and automatically through a liquid crystal display (LCD) display and Android devices. The system integrates various sensors to capture vital signs such as heart rate (HR), respiration rate, and body temperature. These readings are then analyzed using its algorithms to determine the stress level, which is displayed on both the onboard LCD and the connected Android device via an IoT interface. This real-time feedback mechanism empowers users to take proactive measures in stress management. Testing and validation of the device were conducted by comparing its readings with the depression anxiety stress scales (DASS-42) test results. The comparison showed an 80% correlation, demonstrating the device’s accuracy and reliability in detecting stress levels. This innovative approach leverages the advantages of IoT and fuzzy logic to provide a practical and effective solution for stress monitoring and management.
Volume: 15
Issue: 2
Page: 2499-2512
Publish at: 2025-04-01
1 2 3
...
2097 2098
Show 322 of 2098

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration