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

31,458 Article Results

Classification of endometrial adenocarcinoma using histopathology images with extreme learning machine method

10.11591/ijeecs.v36.i2.pp961-971
Riries Rulaningtyas , Anny Setijo Rahaju , Rosa Amalia Dewi , Ummi Hanifah , Endah Purwanti , Osmalina Nur Rahma , Katherine Katherine
As many as 70-80% of endometrial cancer cases are endometrial adenocarcinoma. Histopathological assessment is based on the degree of differentiation, into well-differentiated, moderate-differentiated, and poorly-differentiated. Management and prognosis differ between grades, so differential diagnosis in determining the degree of tumor differentiation is crucial for appropriate treatment decisions. Histopathological image analysis offers detailed diagnostic results, but manual analysis by a pathologist is very complicated, error-prone, quite tedious, and time-consuming. Therefore, an automatic diagnostic system is needed to assist pathologists in grading the tumor. This research aims to determine the degree of differentiation of endometrial adenocarcinoma based on histopathological images. The extreme learning machine (ELM) method performs image classification with gray level run long matrix (GLRLM) features and a combination of local binary pattern (LBP)-GLRLM features as input. Experimental results show that the ELM model can achieve satisfactory performance. Training accuracy, testing accuracy, and model precision with GLRLM features were 97.13%, 91.33%, and 80% and combined LBPGLRLM features were 91.03%, 71.33%, and 100%. Overall, the model created can determine the degree of tumor differentiation and is useful in providing a second opinion for pathologists.
Volume: 36
Issue: 2
Page: 961-971
Publish at: 2024-11-01

Improving quality of life through brain-computer interfaces: an integrated stress prediction method using machine learning

10.11591/ijeecs.v36.i2.pp1030-1042
Shrivatsa D. Perur , Harish H. Kenchannavar
In recent days, people must deal with stress brought on by the demands of modern living, which constantly presents new obstacles. Stress, a state of mental tension triggered by challenging circumstances, has become a global risk factor impacting individual well-being. Understanding variations in stress resilience is crucial for tailoring treatment strategies. Previous studies have explored stress prediction using measures like electroencephalography (EEG), blood pressure (BP), heart rate (HR), and interventions such as Kriya Yoga and mindfulness meditation. The experimentation is done on the data collected from people who practice heartfulness meditation regularly. The research employs machine learning (ML) algorithms alongside physiological parameters such as EEG, BP, HR, and psychological parameters, perceived stress scale (PSS), to precisely classify, measure, and predict stress levels. The investigations are done using K-nearest neighbor (KNN), random forest (RF), and kernel-support vector machine (k-SVM). An accuracy of 98.27% accuracy was achieved with the RF algorithm in classifying stressed and non-stressed individuals.
Volume: 36
Issue: 2
Page: 1030-1042
Publish at: 2024-11-01

Speech enhancement by using novel multiband spectral subtraction method along with a reduction of the cross spectral component

10.11591/ijeecs.v36.i2.pp933-941
Jagadish S. Jakati , Ramesh B. Koti , Sidramayya Matad , Jagannath Jadhav , Shrishail Basvant Mule , Sanmati Bedakihale , Vireshkumar G. Mathad , Amar R. Bandekar
It is essential to enhance the speech signal's clarity and quality in order to maintain the message's content. By boosting the noisy voice signal, the speech signal quality can be raised. Two techniques are presented in this study to significantly minimize the additive background noise. In order to minimize non-stationary additive noise concerning the speech signal, the first approach employs modified multiband spectral subtraction. With this technique, spectral subtraction is carried out based on the signal to noise ratio (SNR) values in various noisy speech frames. When the noisy signal and noise signal are somewhat correlated, a second method is used to minimize the cross spectral components. These techniques are used to get over the drawbacks of the fundamental spectrum subtraction method. To improve the noisy speech signal, both techniques are combined.
Volume: 36
Issue: 2
Page: 933-941
Publish at: 2024-11-01

Ultra-miniaturized dual-band implantable antenna for retinal prosthesis

10.11591/ijeecs.v36.i2.pp760-776
Abdelmouttalib Bousrout , Asma Khabba , Saida Ibnyaich , Tomader Mazri , Mohamed Habibi , Tole Sutikno
This article presents two miniaturized antennas designed for retinal prosthesis devices, aimed at enhancing vision for blind individuals with functional optic nerves. The implantable antenna is 2.2 mm wide, 2.15 mm tall, and 0.78 mm thick. It works in the ISM bands but is small because it uses slot incorporation and high-permittivity substrates. High-frequency structure simulator (HFSS) electromagnetic simulations show great performance, with a 16.66% impedance bandwidth at 2.4 GHz and a 10.34% bandwidth at 5.8 GHz. The peak gain values are -27.76 dB at 2.4 GHz and -16.40 dB at 5.8 GHz. We have also developed an extraocular antenna for telemetry and energy transfer, with dimensions of 36×36×1.6 mm3 . Validation through CST calculation software confirms the efficacy of both antenna designs. Implantable antennas hold significant promise in biomedical antenna research, demonstrating capabilities conducive to retinal implantation and offering potential advancements in vision restoration technology.
Volume: 36
Issue: 2
Page: 760-776
Publish at: 2024-11-01

Improved search method for classified reusable components on cloud computing

10.11591/ijeecs.v36.i2.pp1092-1104
Adnan Rawashdeh , Mouhammd Alkasassbeh , Radwan Dwairi , Hani Abu-Salem , Hashem Al-Mattarneh
Expanding development environments to accommodate huge amounts of reusable components along with associated maintenance and evolution responsibilities has become difficult and costly for software organizations to cope with, while benefits are limited to owner organizations. The challenge of organizing reusable assets so that finding the right component needed has always been a big challenge. The literature of software reuse lacks a comprehensive search method that is efficient and covers the entire system development lifecycle (SDLC). This research work attempts to make an efficient use of the cloud computing advantages and thus, encourages the migration of reusable components to the clouds. The maintenance, the search process and cost-related problems encountered with traditional in-house development environments can be resolved conclusively on the cloud. This research work proposes a multi-classification and clusters approach to migrate reusable components to the cloud. Accordingly, it applies indexing process to classified reusable components achieving efficient search. In addition, the proposed approach adopts a comprehensive SDLC-based classification to organize reusable components so that searching and finding an appropriate component becomes an easy task due to the fact it is bound to the particular undergoing phase. Cloud computing provides more storage and resources with low cost, compared to traditional in-house development environments.
Volume: 36
Issue: 2
Page: 1092-1104
Publish at: 2024-11-01

Comparative analysis on liver benchmark datasets and prediction using supervised learning techniques

10.11591/ijeecs.v36.i2.pp1043-1051
Tilakachuri Balakrishna , Jagadeeswara Rao Annam , Dasari Haritha
Disease diagnosis is most challenging task today. Different datasets are available in web source that contains important features to diagnose the diseases. This paper explores different classification algorithms on medical liver bench mark datasets like BUPA and Indian Liver patient dataset (ILPD). The ILPD is best fit for the model and also gives high classifier accuracy. In proposed model the following classifiers like Naïve Bayes (NB), support vector machine (SVM), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) classification, multi-layer perceptron (MLP), artificial neural network (ANN), deep belief network (DBN) and probabilistic neural network (PNN) are used. The results shown that ILPD is best dataset for all classifiers and RF classification in particular is best classifier.
Volume: 36
Issue: 2
Page: 1043-1051
Publish at: 2024-11-01

Artificial intelligence in accounting and auditing: bibliometric analysis in Scopus 2020-2023

10.11591/ijeecs.v36.i2.pp1319-1328
Jorge Miguel Chávez-Díaz , Laura Aquiño-Perales , Jorge Luis De-Velazco-Borda , Juan Alberto Villagómez-Chinchay , Willian Sebastian Flores-Sotelo
El propósito del estudio fue presentar los resultados de un análisis bibliométrico y revisión de literatura sobre la producción científica relacionada con la inteligencia artificial aplicada a la contabilidad y auditoría, contenida en la base de datos Scopus entre 2020 y 2023. Para la primera parte, se realizó un análisis descriptivo y cuantitativo. Se utilizó análisis bibliométrico con búsqueda de palabras clave en la base de datos Scopus. Para la segunda parte se siguió un enfoque subjetivo basado en un análisis cualitativo a partir de la interpretación del autor. Ambos enfoques fueron considerados por su complementariedad. Se identificaron las principales características cuantitativas de las revistas, autores, artículos, estructura conceptual y estructura social. Asimismo, las implicaciones éticas de la Inteligencia Artificial aplicada a la contabilidad y auditoría, y la forma en que impacta en la contabilidad, la auditoría fiscal, la estrategia financiera y la toma de decisiones que contribuyen a la creación de valor para su organización. Cambie la aversión a la IA por la adaptabilidad y la comprensión de que se extrajeron sus auditorías y contabilidad forense. El trabajo del contable-auditor estará cada vez más informatizado. Deberían centrarse más en el análisis, hay que transformar el perfil profesional de forma sinérgica con la inteligencia artificial. El estudio pretende servir como base teórica para futuras investigaciones.
Volume: 36
Issue: 2
Page: 1319-1328
Publish at: 2024-11-01

Utilization of learning media based on augmented reality on design material network topology

10.11591/ijeecs.v36.i2.pp1083-1091
Manda Rohandi , Jemmy A. Pakaja , Arip Mulyanto , Dian Novian , Hermila A. , Sri Ayu Ashari , Bariq Nugraha
Augmented reality (AR) is a growing technology that has great potential in the field of education. This article explores using AR as an interactive learning medium in a secondary education environment. The study involves the implementation of AR in network topology material to enhance student engagement and understanding. This research consists of the design and development of AR applications following the curriculum of the network topology subject at SMK Negeri 1 South Bulango using the waterfall model. The results showed that using AR-based learning media can increase student engagement in the learning process. Three-dimensional visualization of network topology design can improve students’ interest and motivation to understand the material better. AR allows students to interact directly with the network topology design model.
Volume: 36
Issue: 2
Page: 1083-1091
Publish at: 2024-11-01

Effects of TiO2 in graphene-quantum-dot film on lighting color uniformity of a white light-emitting diodes

10.11591/ijeecs.v36.i2.pp800-807
Phan Xuan Le , Pham Hong Cong
Improvement in color uniformity of white light-emitting diodes (WLED) is one of the imperative goals for high-quality solid-state illumination. The conventional WLED model with a single yellow phosphor YAG:Ce3+ (TiO2@GD) is proposed to fulfill this goal. The TiO2@GD composites prove to possess excellent biocompatibility, low toxicity, and thermal and chemical stability, holding great potential in high-power WLED production. By maintaining a constant GDs content of 10 wt%, the research explores the impact of varying TiO2 doping concentrations on the lighting performance of the WLEDs via the mean of light scattering. The TiO2@GD layer also induces a red-shift in the emitted light spectrum, contributing to a reduction in color variation. While a decline in luminosity and color rendering performance becomes evident with excessive TiO2 content, the study underscores the potential of TiO2@GD as a viable diffusing layer for LEDs to obtain improved angular uniformity of color distribution.
Volume: 36
Issue: 2
Page: 800-807
Publish at: 2024-11-01

Development of an IoT-based sleep pattern monitoring system for sleep disorder detection

10.11591/ijeecs.v36.i2.pp777-784
Muhammad Nur Ikhwan Md Shahrum , Ida Syafiza Md Isa , Nur Latif Azyze Mohd Shaari Azyze , Haslinah Mohd Nasir , Tole Sutikno
Inadequate sleep can cause various health problems including heart disease and obesity. In this work, a sleep monitoring system that monitors human sleep patterns is developed using the internet of things (IoT) and Raspberry Pi. The system is designed to record any detected movements and process the data using machine learning to provide valuable insight into a person’s sleep patterns including sleep duration, the time taken to fall asleep, and the frequency of waking up. This information is very useful to provide the sleep disorder diagnostics of an individual including restless leg, parasomnia and insomnia syndrome besides giving recommendations to improve their sleep quality. Also, the system allows the processed data to be stored in the cloud database which can be accessed through a mobile application or web interface. The performance of the system is evaluated in terms of its accuracy and reliability in detecting sleep order diagnostics. Based on the confusion matrix, the results show the accuracy of the system is 90.32%, 91.80%, and 91.80% in detecting the restless leg, parasomnia and insomnia syndrome, respectively. Meanwhile, the system showed high reliability in monitoring 10 participants for 8 hours and updated the recorded data and its analysis in the cloud.
Volume: 36
Issue: 2
Page: 777-784
Publish at: 2024-11-01

Microstrip patch antenna for energy harvesting in smart buildings

10.11591/ijeecs.v36.i2.pp923-932
Stanley Glenn E. Brucal , Aaron Don M. Africa , Julian Carlos P. Chavez , Nathan H. Devera , Philip Martin Emmanuel A. Escamilla , John Louie L. Payuyo
The present study analyzes the microstrip antenna design for wireless power transfer in smart buildings, harnessing the ambient electromagnetic radiation due to common electronic gadgets that energize wireless sensor networks, computing devices, and connected appliances. With the increased number of these devices, so does the potential for health problems caused by electromagnetic radiation. However, these devices also provide a renewable energy source through their emissions. This study suggests the creation of a 5G Microstrip antenna that enhances the absorption of this radiation for the purpose of recharging batteries in smart buildings. The design capitalizes on the inherent low-profile and cost-effective features of microstrip antennas, making them well-suited for incorporation into building infrastructure and 5G wireless technologies. Although each individual device emits a little amount of energy, the combined effect achieved by advanced antenna design and power converters is anticipated to result in a substantial energy production. The antenna designer tool from MATLAB was used to carry out a conceptual simulation of the microstrip antenna. This has set up the framework of a feasible way of predicting the performance with high efficiency and sustainability for a wireless power transfer (WPT) system.
Volume: 36
Issue: 2
Page: 923-932
Publish at: 2024-11-01

Cost-effective circularly polarized MIMO antenna for Wi-Fi applications

10.11591/ijeecs.v36.i2.pp785-792
Raju Thommandru , Rengarasu Saravanakumar
Antenna is a backbone of communication system, and with the advent of technology, numerous innovations have been made to advance antenna development. An antenna, functioning as a smart device, transmits and receives signals while also working as a transducer. Wireless communication requires a useful device for transmitting and receiving electromagnetic waves. Wireless fidelity (Wi-Fi) is a specific type of wireless communication technology used to transmit data over the internet network. The bandwidth and signal coverage of Wi-Fi have significant limitations. Therefore, an antenna is crucial for improving signal reception to address this issue. This article presents the designing and developing of a cost-effective circularly polarized (CP) 2×2 multiple input multiple output (MIMO) antenna customized for Wi-Fi applications. The application of a notched circular patch antenna serves to achieve circular polarization. The radius of the circular patch is 0.26 λ, and the proposed MIMO antenna effectively showcases CP, characterized by an axial ratio (AR) of 1 dB at 5 GHz and an impressive bandwidth spanning 0.2 GHz (4.9-5.1 GHz). Additionally, the antenna is designed to achieve a high-isolation 2×2 MIMO setup, ensuring antenna isolation surpassing 20 dB. By utilizing the flame retardant (FR4) substrate, presented MIMO antenna strikes a balance between cost-effectiveness and operational efficiency for its intended application, and directional radiation patterns are well-aligned within the desired frequency range.
Volume: 36
Issue: 2
Page: 785-792
Publish at: 2024-11-01

RecommendRift: a leap forward in user experience with transfer learning on netflix recommendations

10.11591/ijeecs.v36.i2.pp1218-1225
Surabhi Anuradha , Pothabathula Naga Jyothi , Surabhi Sivakumar , Martha Sheshikala
In today’s fast-paced lifestyle, streaming movies and series on platforms like  Netflix is a valued recreational activity. However, users often spend considerable time searching for the right content and receive irrelevant recommendations, particularly when facing the “cold start problem” for new users. This challenge arises from existing recommender systems relying on factors like casting, title, and genre, using term frequency-inverse document frequency (TF-IDF) for vectorization, which prioritizes word frequency over semantic meaning. To address this, an innovative recommender system considering not only casting, title, and genre but also the short description of movies or shows is proposed in this study. Leveraging Word2Vec embedding for semantic relationships, this system offers recommendations aligning better with user preferences. Evaluation metrics including precision, mean average precision (MAP), discounted cumulative gain (DCG), and ideal cumulative gain (IDCG) demonstrate the system’s effectiveness, achieving a normalized DCG (NDCG)@10 of 0.956. A/B testing shows an improved click-through rate (CTR) of recommendations, showcasing enhanced streaming experience.
Volume: 36
Issue: 2
Page: 1218-1225
Publish at: 2024-11-01

Experimental of information gain and AdaBoost feature for machine learning classifier in media social data

10.11591/ijeecs.v36.i2.pp1172-1181
Jasmir Jasmir , Dodo Zaenal Abidin , Fachruddin Fachruddin , Willy Riyadi
In this research, we use several machine learning methods and feature selection to process social media data, namely restaurant reviews. The selection feature used is a combination of information gain (IG) and adaptive boosting (AdaBoost) which is used to see its effect on the classification performance evaluation value of machine learning methods such as Naïve Bayes (NB), K-nearest neighbor (KNN), and random forest (RF) which is the aim of this research. NB is very simple and efficient and very sensitive to feature selection. Meanwhile, KNN is known for its weaknesses such as biased k values, overly complex computation, memory limitations, and ignoring irrelevant attributes. Then RF has weaknesses, including that the evaluation value can change significantly with only small data changes. In text classification, feature selection can improve the scalability, efficiency and accuracy of text classification. Based on tests that have been carried out on several machine learning methods and a combination of the two selection features, it was found that the best classifier is the RF algorithm. RF produces a significant increase in value after using the IG and AdaBoost features. Increased accuracy by 10%, precision by 12.43%, recall by 8.14% and F1-score by 10.37%. RF also produces even accuracy, precision, recall, and F1-score values after using IG and AdaBoost with an accuracy value of 84.5%; precision of 85.58%; recall was 86.36%; and F1-score was 85.97%.
Volume: 36
Issue: 2
Page: 1172-1181
Publish at: 2024-11-01

Pavement health 4.0: a novel AI-enabled PavementVision approach for pavement health monitoring and classification

10.11591/ijeecs.v36.i2.pp1163-1171
Jaykumar Soni , Rajesh Gujar , Mohammed Shakil Malek
To determine the extent of pavement damage and forms of pavement distress, road pavement conditions must be precisely assessed. As a result, monitoring systems are regarded as an important stage in the maintenance procedure. In recent times, numerous investigations have been carried out to track the condition of pavement and monitor road surfaces. In the undertaken study, we have proposed a novel artificial intelligent (AI) and computer vision-enabled PavementCarevision 4.0 approach to detect and classify pavement health conditions i.e., defects. In this study, a customized pavement-2000 dataset has been designed which contains more than 2,000 images of a variety of pavement defects. In the initial phase, we pre-processed and enhanced pavement images using the customized adjustable linear contrast enhancement methodology. The enhanced pavement image samples were fed to the proposed customized YOLOV8 enabled PavementHealth 4.0 framework for pavement condition detection of a variety of pavement defects such as longitudinal cracks, alligator cracks, transverse cracks, and potholes. The proposed customized YOLOV8 enabled PavementHealth 4.0 framework has achieved an accuracy of 99.20 percent; an receiver operating characteristic (ROC) value of 0.98 and outperformed existing AI-based state-of-the-art methodologies such as pose NET, YOLOv7, YOLOv5, long short-term memory network (LSTM), Mask region-based convolutional neural network (R-CNN), and decision tree.
Volume: 36
Issue: 2
Page: 1163-1171
Publish at: 2024-11-01
1 2 3
...
2097 2098
Show 430 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