Articles

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

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

27,404 Article Results

Low-resolution image quality enhancement using enhanced super-resolution convolutional network and super-resolution residual network

10.11591/ijeecs.v39.i1.pp634-643
Mohammad Faisal Riftiarrasyid , Rico Halim , Andien Dwi Novika , Amalia Zahra
This research explores the integration of enhanced super-resolution convolutional network (ESPCN) and super-resolution residual network (SRResNet) to enhance image quality captured by low-resolution (LR) cameras and in internet of things (IoT) devices. Focusing on face mask prediction models, the study achieves a substantial improvement, attaining a peak signal-to-noise ratio (PSNR) of 28.5142 dB and an execution time of 0.34704638 seconds. The integration of super-resolution techniques significantly boosts the visual geometry group-16 (VGG16) model’s performance, elevating classification accuracy from 71.30% to 96.30%. These findings highlight the potential of super-resolution in optimizing image quality for low-performance devices and encourage further exploration across diverse applications in image processing and pattern recognition within IoT and beyond.
Volume: 39
Issue: 1
Page: 634-643
Publish at: 2025-07-01

Context dependent bidirectional deep learning and Bayesian gaussian auto-encoder for prediction of kidney disease

10.11591/ijeecs.v39.i1.pp387-398
Jayashree M , Anitha N
Chronic kidney disease (CKD) has emerged as a significant global health issue, leading to millions of premature deaths annually. Early prediction of CKD is crucial for timely diagnosis and preventive measures. While various deep learning (DL) methods have been introduced for CKD prediction, achieving robust quantification results remains challenging. To address this, we propose the context-dependent bi-directional DL and Bayesian gaussian autoencoder (CDBDP-BGA) method for CKD prediction. This approach utilizes clinical parameters and symptoms from a structured dataset. By incorporating context dependence into the bi-directional long short-term memory (Bi-LSTM) model, CDBDP-BGA efficiently redistributes the representation of information, enhancing its modeling capabilities. Feature selection is optimized using a BGA-based algorithm, which employs the Bayesian gaussian function. The SoftMax activation function classifies CKD into five distinct stages based on estimated-glomerular filtration-rate (eGFR), considering both symptoms (texture and numerical features) and clinical parameters (age, sex, and creatinine). Simulation results using two datasets demonstrate that CDBDP-BGA outperforms conventional methods, achieving 97.4% accuracy without eGFR and 98.7% with eGFR.
Volume: 39
Issue: 1
Page: 387-398
Publish at: 2025-07-01

BFT water color classification in tilapia aquaculture using computer vision

10.11591/ijeecs.v39.i1.pp497-508
Bondan Suwandi , Sakinah Puspa Anggraeni , Toto Bachtiar Palokoto , Budi Sulistya , Wisnu Sujatmiko , Reza Septiawan , Nashrullah Taufik , Arief Rufiyanto , Arif Rahmat Ardiansyah
Biofloc technology (BFT) is one of the most promising aquaculture cultivation methods in the modern aquaculture era because of its high efficiency level, especially in water and fodder use. Usually, the general condition of the biofloc can be known from the color of the water. By utilizing the vision sensor, BFT color identification can be done automatically, which helps cultivators find out their BFT system’s condition. In this research, a classification was made for the watercolor of the BFT Tilapia system based on the microbial community color index (MCCI) value and the initial cultivation conditions where algae and nitrifying bacteria had not developed significantly. The color classifications of the bioflocs are clear, green, browngreen, green-brown, and deep-brown. Clear color is the new classification to indicate BFT water conditions in the initial cultivation phase. Further, two computer vision algorithm methods are introduced to classify the color of BFT system water. The first method combines the B/W algorithm and MCCI calculations, while the second algorithm uses the Manhattan distance algorithm approach. From the experiments that have been carried out, both computer vision algorithms methods for classifying biofloc colors have shown promising results.
Volume: 39
Issue: 1
Page: 497-508
Publish at: 2025-07-01

An innovative image encryption scheme integrating chaotic maps, DNA encoding and cellular automata

10.11591/ijeecs.v39.i1.pp710-719
Gaverchand Kukaram , Venkatesan Ramasamy , Yasmin Abdul
In the current digital era, securing image transmission is crucial to ensure data integrity, prevent tampering, and preserve confidentiality as images traverse unsecured channels. This paper presents an innovative encryption scheme that synergistically combines a two-dimensional (2-D) logistic map, deoxyribonucleic acid (DNA) encoding, and 1-D cellular automata (CA) rules to significantly bolster encryption robustness. The proposed model initiates with the generation of a key image via the 2-D logistic map, yielding intricate chaotic sequences that fortify the encryption mechanism. DNA cryptography is employed to amplify randomness through diffusion properties, providing robust defense against various cryptographic attacks. The integration of 1-D CA rules further intensifies encryption complexity by iteratively processing DNA-encoded sequences. Experimental results substantiate that the proposed encryption scheme demonstrates exceptional endurance against a vast spectrum of attacks, affirming its superior security.
Volume: 39
Issue: 1
Page: 710-719
Publish at: 2025-07-01

New technic of transfer learning for detecting epilepsy by EfficientNet and DarkNet models

10.11591/ijeecs.v39.i1.pp345-352
Fatima Edderbali , Hamid El Malali , Elmaati Essoukaki , Mohammed Harmouchi
Epileptic seizures are one of the most prevalent brain disorders in the world. Electroencephalography (EEG) signal analysis is used to distinguish between normal and epileptic brain activity. To date, automatic diagnosis remains a highly relevant and significant research topic which can help in this task, especially considering that such diagnosis requires a significant amount of time to be carried out by an expert. As a result, the need for an effective seizure approach capable to classify the normal and epileptic brain signal automatically is crucial. In this perspective, this work proposes a deep neural network approach using transfer learning to classify spectrogram images that have been extracted from EEG signals. Initially, spectrogram images have been extracted and used as input to pre-trained models, and a second refinement is performed on certain feature extraction layers that were previously frozen. The EfficientNet and DarkNet networks are used. To overcome the lack of data, data augmentation was also carried out. The proposed work performed excellently, as assessed by multiple metrics, such as the 0.99 accuracy achieved with EfficientNet combined with a support vector machine (SVM) classifier.
Volume: 39
Issue: 1
Page: 345-352
Publish at: 2025-07-01

Non-contact breathing rate monitoring using infrared thermography and machine learning

10.11591/ijeecs.v39.i1.pp669-680
Anadya Ghina Salsabila , Rachmad Setiawan , Nada Fitrieyatul Hikmah , Zain Budi Syulthoni
Monitoring vital physiological parameters such as breathing rate (BR) is crucial for assessing patient health. However, current contact-based measurement methods often cause discomfort, particularly in infants or burn patients. This study aims to develop a non-contact system for monitoring BR using infrared thermography (IRT). This approach permits to detects and tracks the nose from thermal video, extracts temperature variations into a breathing signal, and processes this signal to estimate BR. The estimated BR is then classified into three health categories (bradypnea/normal/tachypnea) using k-nearest neighbors (k-NN). To evaluate system accuracy and robustness, experiments were conducted under three conditions: (i) stationary breathing, (ii) breathing with head movements, and (iii) specific breathing patterns. Results demonstrated high consistency with contact-based photoplethysmography (PPG) measurements, achieving complement of the absolute normalized difference (CAND) index values of 94.57%, 93.71%, and 96.06% across the three conditions and mean absolute BR errors of 1.045 bpm, 1.259 bpm, and 0.607 bpm. The k-NN classifier demonstrated high performance with training, validation, and testing accuracies of 100%, 100%, and 99.2%, respectively. Sensitivity, specificity, precision, and F-measure results confirm system reliability for non-contact BR monitoring in clinical and practical settings.
Volume: 39
Issue: 1
Page: 669-680
Publish at: 2025-07-01

Web GIS-based postcode alternative system for resolving “last mile” problem in Jordan’s home delivery

10.11591/ijeecs.v39.i1.pp531-544
Firas Omar , Ahmad Nabot , Bilal Sowan
As more and more people shop online, the postal code system must be more dependable. Due to the absence of a comprehensive postcode system, online purchases and shipping in the developing country of Jordan are complicated. This research paper proposes an alternative delivery system for delivering online purchases to customers without postal codes. Smartphone and computer-based geographic information system (GIS) applications evaluated in Jordan. The scientists found that the users were eager to adopt the system based on its ease of use and adoption rate. A questionnaire survey was distributed to 167 retail stores, delivery logistics employees, university students, and academics. The data collected were then analyzed using SPSS techniques such as POST HOC and ANOVA. To find a home delivery solution, we tested the suggested system app on both desktop and Smartphone platforms. The findings show that it is easier to locate a residential neighborhood. Customer trust and satisfaction with online purchases should increase due to the additional benefits of the system installation. Improve the effectiveness of home delivery services in Jordan with the use of artificial intelligence (AI). Both customers and stores prefer this system for online shopping rather than using postcodes. According to these data, experts can enhance their items by implementing digital sales strategies.
Volume: 39
Issue: 1
Page: 531-544
Publish at: 2025-07-01

Robust k-NN approach for classifying Aquilaria oil species by compounds

10.11591/ijeecs.v39.i1.pp178-189
Noor Aida Syakira Ahmad Sabri , Nur Athirah Syafiqah Noramli , Nik Fasha Edora Nik Kamaruzaman , Nurlaila Ismail , Zakiah Mohd Yusoff , Ali Abd Almisreb , Saiful Nizam Tajuddin , Mohd Nasir Taib
Accurate classification of Aquilaria oil species is essential for ensuring the quality and authenticity of agarwood oils, which are widely used in perfumes and traditional medicine. This study investigated the effectiveness of the k-nearest neighbours (k-NN) machine learning model for classifying Aquilaria oil species based on four significant chemical compounds: dihyro-βagarofuran, δ-guaiene, 10-epi-γ-eudesmol, and γ-eudesmol. The dataset comprised 480 samples of Aquilaria oil, which were analyzed using gas chromatography-mass spectrometry (GC-MS) and gas chromatography-flame ionization detector (GC-FID). The k-NN model, with an optimal k-value of 10 and using euclidean distance as the distance metric, achieved 100% accuracy, sensitivity, specificity, and precision in both training and testing datasets. These results demonstrate the robustness of k-NN in species identification, highlighting the discriminative power of the selected compounds. This study verifies that the integration of chemical profiling with machine learning offers a scalable solution for accurate species identification in the essential oil industry. Future work could explore hybrid models and data expansion techniques to further enhance the classification performance in more complex environmental conditions.
Volume: 39
Issue: 1
Page: 178-189
Publish at: 2025-07-01

Design and development of an automated spirulina (Arthrospira platensis) algae cultivator

10.11591/ijeecs.v39.i1.pp139-147
Miguel Q. Mariñas II , Mark Joseph B. Enojas , Daryll C. Balolong , Charissa Zandra B. Correa , Lemmuel Keith C. Roldan , Mark Lester Teves , Christian Mari Dela Cruz
The cultivation of algae has gotten more attention from algae enthusiasts who have seen the benefits of algae in many uses. To maximize productivity, the parameters for growth of this algae must be controlled, such as pH, turbidity, light intensity, and the mixture solution for optimal growth. In this paper, an automated spirulina algae cultivator is designed and developed in a small-scale pond to replace the existing manual process. The system developed is composed of compact and modular cultivation unit, ph sensor, water level sensor, turbidity sensor, light intensity sensor, and motor actuators for mixing solutions. Each parameter was controlled individually in an on-off control system. A simple nutrient addition program (SNAP) solution is also used for better growth productivity by maximizing its nutrient contents. The pH is maintained at 9 to 12 for a healthy biomass output. Daily weight measurement was conducted using an analytical balance to monitor its growth. Using the developed prototype recorded a 33% higher rate of productivity over the manual process. This setup can potentially be used as a model for mass production of spirulina algae.
Volume: 39
Issue: 1
Page: 139-147
Publish at: 2025-07-01

An efficient DVHOP localization algorithm based on simulated annealing for wireless sensor network

10.11591/ijeecs.v39.i1.pp720-736
Omar Arroub , Anouar Darif , Rachid Saadane , My Driss Rahmani , Zineb Aarab
In the last decade, the research community has devoted significant attention to wireless sensor networks (WSNs) because they contribute positively to some critical issues encountered in nature and even in industry. On the other hand, localization is one of the most important parts of WSN. Hence, the conception of an efficient method of localization has become a hot research topic. Lastly, it has been invented, a set of optimal positioning methods that make locate a node with low cost and give precise results. In our contribution, we investigate the source of imprecision in the distance vectorhop (DVHOP) localization algorithm. However, we found the last step of DVHOP caused an imprecision in the calculation. Consequently, our work was to replace this step, aiming to reach satisfactory precision. For that purpose, we created three improved versions of this algorithm by adopting two meta-heuristic (simulated annealing, particle swarm optimization) and Fmincon solver dedicated to optimization in the field of WSN node localization. The experimental results obtained in this work prove the efficiency of simulated annealing (SA)-DVHOP in terms of accuracy. Furthermore, the enhanced algorithm outperforms its opponents by varying the percentage of anchors and the number of nodes.
Volume: 39
Issue: 1
Page: 720-736
Publish at: 2025-07-01

Enhancing vocational computer engineering education with a GPT-driven speech recognition tool

10.11591/ijeecs.v39.i1.pp564-574
Putra Utama Eka Sakti , Alva Hendi Muhammad , Asro Nasiri
This research investigates the effectiveness of an AI-driven speech recognition and GPT-powered learning tool in enhancing vocational students’ proficiency in computer networks. The study involved 100 students from vocational hig school, who used the prototype as part of their learning process. A pre-test/post-test design was employed to assess changes in proficiency, and students also provided feedback on the tool’s usability and impact. The results showed a consistent improvement in proficiency across all classes. A strong positive correlation was found between students’ feedback and their proficiency improvement, suggesting that students who rated the prototype as Very Helpful were more likely to see significant learning gains. However, the correlation between time spent using the tool and proficiency improvement was minimal, indicating that the quality of engagement with the tool was more important than the duration of usage. These findings highlight the prototype’s potential to improve vocational learning outcomes and underscore the importance of user satisfaction in driving success, with future refinements necessary to ensure the tool’s broader effectiveness across different learning contexts.
Volume: 39
Issue: 1
Page: 564-574
Publish at: 2025-07-01

Influences of the Sm3+ -Eu3+ codoped Ba2Gd(BO3)2Cl phosphors on the commercial white light emitting diodes

10.11591/ijeecs.v39.i1.pp62-69
Luu Hong Quan , My Hanh Nguyen Thi
The color quality of current commercial white light emitting diodes (wLEDs) suffers low performance owing to the lack of the red-emission component. Developing quality and stable red-emission phosphors is feasible among various approaches to obtain the red spectral supplement for the w-LEDs in the pursuit of color quality improvement. In this paper, the Sm3+-Eu3+ codoped Ba2Gd(BO¬3)2Cl (BGBC:Sm-Eu) red phosphor was proposed for using in commercial w-LEDs. Its luminescence and influences on w-LED properties were simulated and presented. The solid-phase method was utilized for the fabrication of the phosphor. The results indicated that the phosphor emitted the strong emission in orange-red region with a peak centering at 593 nm. It can be caused by the proficient power shift between Sm3+ and Eu3+. In the w-LED package, the presence of BGBC:Sm-Eu phosphor stimulated the scattering efficiency to promote the blue-light conversion and extraction. The orange emission spectrum of the w-LED increased with the higher BGBC:Sm-Eu doping amount. The luminous strength of the w-LED was enhanced and so was the color temperature uniformity. The color rendering properties declined with high BGBC:Sm-Eu phosphor concentration owing to the red-light dominance over the light spectrum. The BGBC:Sm-Eu phosphor is a promising red phosphor for improving commercial w-LED color-temperature stability and luminosity. It also helps to obtain full-spectrum w-LED with high color rendition when combined with other blue-to-green luminescent materials.
Volume: 39
Issue: 1
Page: 62-69
Publish at: 2025-07-01

Word embedding and imbalanced learning impact on Indonesian Quran ontology population

10.11591/ijeecs.v39.i1.pp603-613
Fandy Setyo Utomo , Yuli Purwati , Mohd Sanusi Azmi , Lulu Shafira , Nikmah Trinarsih
This research addresses limitations in Quranic instance classification, exceptionally high dimensionality, lack of semantic relationships in the term frequency-inverse document frequency (TF-IDF) technique, and imbalanced data distribution, which reduce prediction accuracy for minority classes. This study investigates the impact of word embedding and imbalance learning techniques on instance classification frameworks using Indonesian Quran translation and Tafsir datasets to handle previous research limitations. Four classification frameworks were built and evaluated using accuracy and hamming loss metrics. The results show that the synthetic minority oversampling technique (SMOTE) technique, TF-IDF model, and logistic regression classifier provide the best accuracy results of 62.74% and a hamming loss score of 0.3726 on the Quraish Shihab Tafsir dataset. This is better than the performance of previous classifiers backpropagation neural network (BPNN) and support vector machine (SVM) used in the previous framework, with accuracies of 59.91% and 62.26%, respectively. Logistic regression can also provide the best classification results with an accuracy of 67.92% and a hamming loss of 0.3208 using the previous framework. These results are better than the performance of the previous classifiers BPNN and SVM used in the previous framework, with accuracies of 62.26% and 66.98%, respectively. TF-IDF feature extraction outperforms word2vec in instance classification results due to its superior support under limited dataset conditions.
Volume: 39
Issue: 1
Page: 603-613
Publish at: 2025-07-01

Bibliometric analysis and short survey in CT scan image segmentation: identifying ischemic stroke lesion areas

10.11591/csit.v6i2.p91-101
Wahabou K. Taba Chabi , Sèmèvo Arnaud R. M. Ahouandjinou , Manhougbé Probus A. F. Kiki , Adoté François-Xavier Ametepe
Ischemic stroke remains one of the leading causes of mortality and long-term disability worldwide. Accurate segmentation of brain lesions plays a crucial role in ensuring reliable diagnosis and effective treatment planning, both of which are essential for improving clinical outcomes. This paper presents a bibliometric analysis and a concise review of medical image segmentation techniques applied to ischemic stroke lesions, with a focus on tomographic imaging data. A total of 2,014 publications from the Scopus database (2013–2023) were analyzed. Sixty key studies were selected for in-depth examination: 59.9% were journal articles, 29.9% were conference proceedings, and 4.7% were conference reviews. The year 2023 marked the highest volume of publications, representing 17% of the total. The most active countries in this area of research are China, the United States, and India. "Image segmentation" emerged as the most frequently used keyword. The top-performing studies predominantly used pre-trained deep learning models such as U-Net, ResNet, and various convolutional neural networks (CNNs), achieving high accuracy. Overall, the findings show that image segmentation has been widely adopted in stroke research for early detection of clinical signs and post-stroke evaluation, delivering promising outcomes. This study provides an up-to-date synthesis of impactful research, highlighting global trends and recent advancements in ischemic stroke medical image segmentation.
Volume: 6
Issue: 2
Page: 91-101
Publish at: 2025-07-01

HepatoScan: Ensemble classification learning models for liver cancer disease detection

10.11591/csit.v6i2.p167-175
Tella Sumallika , Raavi Satya Prasad
Liver cancer is a dangerous disease that poses significant risks to human health. The complexity of early detection of liver cancer increases due to the unpredictable growth of cancer cells. This paper introduces HepatoScan, an ensemble classification to detect and diagnose liver cancer tumors from liver cancer datasets. The proposed HepatoScan is the integrated approach that classifies the three types of liver cancers: hepatocellular carcinoma, cholangiocarcinoma, and angiosarcoma. In the initial stage, liver cancer starts in the liver, while the second stage spreads from the liver to other parts of the body. Deep learning is an emerging domain that develops advanced learning models to detect and diagnose liver cancers in the early stages. We train the pre-trained model InceptionV3 on liver cancer datasets to identify advanced patterns associated with cancer tumors or cells. For accurate segmentation and classification of liver lesions in computed tomography (CT) scans, the ensemble multi-class classification (EMCC) combines U-Net and mask region-based convolutional network (R-CNN). In this context, researchers use the CT scan images from Kaggle to analyze the liver cancer tumors for experimental analysis. Finally, quantitative results show that the proposed approach obtained an improved disease detection rate with mean squared error (MSE)-11.34 and peak signal-to-noise ratio (PSNR)-10.34, which is high compared with existing models such as fuzzy C-means (FCM) and kernel fuzzy C-means (KFCM). The classification results obtained based on detection rate with accuracy-0.97%, specificity-0.99%, recall-0.99%, and F1S-0.97% are very high compared with other existing models.
Volume: 6
Issue: 2
Page: 167-175
Publish at: 2025-07-01
Show 5 of 1827

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