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

23,598 Article Results

Performance of dyslexia dataset for machine learning algorithms

10.11591/ijeecs.v36.i2.pp994-1001
J. Jincy , P. Subha Hency Jose
Learning disability is a condition usual amongst most populace due to poor phonological capability in humans making them impaired. One such neurological disorder is developmental dyslexia, a lack of reading and writing skills leading to difficulty in school education. The essential causes of developmental dyslexia are the consumption of more drug treatments during pregnancy, the over-the-counter purchase of medicines for minor ailments without the recommendation of physicians, and uncared-for head accidents during early life. The occurrence of this trouble is acute in India. Attempts were made by many to detect dyslexic children to reduce the intensity of this hassle. In this proposed effort, machine learning is used to locate significant styles characterizing people using EEG samples. A dataset is used for examination of developmental dyslexia, and classification is done using K nearest neighbor (KNN), decision tree, linear discriminant analysis (LDA), and support vector machine (SVM) to evaluate the performance. This piece of research work is done on MATLAB to provide results on simulation with classification accuracy of 90.76% for SVM, sensitivity of 89% for SVM, and LDA with 91.89% specificity for SVM providing optimum yield.
Volume: 36
Issue: 2
Page: 994-1001
Publish at: 2024-11-01

Modified back-line inset feed 1x4 array microstrip antenna for 5.8 GHz frequency band

10.11591/ijeecs.v36.i2.pp892-900
Md Fazlul Hasan , Dayang Azra Awang Mat , Md Abu Sayed
This paper presents the design of 1x4 array microstrip antenna utilizing modified backline feeding technique at 5.8 GHz frequency band. The antenna, designed on flame retardant (FR-4) substrate with a dielectric constant of 4.4, aims to achieve reduced harmonics and mutual coupling between closely spaced antenna elements. The primary scope of the paper is investigating the performance of a single band microstrip antenna employing the proposed modified backline feeding method. Moreover, developed design came out with the result and critical analysis by various parameters such as, gain, return loss, voltage standing wave ratio (VSWR), and directivity. Therefore, the proposed design of microstrip antenna with backward linefeed (BLF) demonstrates a directivity of 10.29 dBi, return loss of -21.947 dB, and VSWR of 1.173; are significant improvement compared to recent literature shown in this paper. The adoption of proposed back line feeding technique (BLF) represents a promising alternative for addressing poor wireless connectivity issues in terms of antenna design, gain, and direction within microstrip technology.
Volume: 36
Issue: 2
Page: 892-900
Publish at: 2024-11-01

Improving imbalanced class intrusion detection in IoT with ensemble learning and ADASYN-MLP approach

10.11591/ijeecs.v36.i2.pp1209-1217
Soni Soni , Muhammad Akmal Remli , Kauthar Mohd Daud , Januar Al Amien
The exponential growth of the internet of things (IoT) has revolutionized daily activities, but it also brings forth significant vulnerabilities. intrusion detection systems (IDS) are pivotal in efficiently detecting and identifying suspicious activities within IoT networks, safeguarding them from potential threats. It proposes a ensemble approach aimed at enhancing model performance in such scenarios. Recognizing the unique challenges posed by imbalanced class distribution, the research employs three sampling techniques LightGBM adaptive synthetic sampling (ADASYN) with multilayer perceptron (MLP), XGBoost ADASYN with MLP, and LightGBM ADASyn with XGBoost to address class imbalance effectively. Evaluation confusion matrix performance metrics underscores the efficacy of ensemble models, particularly LightGBM ADASYN with MLP, XGBoost ADASYN with MLP, and LightGBM ADASYN with XGBoost, in mitigating imbalanced class issues. The LightGBM ADASYN with MLP model stands out with 99.997% accuracy, showcasing exceptional precision and recall, demonstrating its proficiency in intrusion detection within minimal false positives negatives. Despite computational demands, integrating XGBoost within ensemble frameworks yields robust intrusion detection results, highlighting a balanced trade-off between accuracy, precision, and recall. This research offers valuable insights into the strengths with different ensemble models, significantly contributing to the advancement of accurate and reliable IDS in realm of IoT.
Volume: 36
Issue: 2
Page: 1209-1217
Publish at: 2024-11-01

Auto digitization of aerial images to map generation from UAV feed

10.11591/ijeecs.v36.i2.pp1338-1346
Raju Jagadeesh Kannan , Karunesh Pratap Yadav , Balasubramanian Sreedevi , Jehan Chelliah , Surulivelu Muthumarilakshmi , Jeyaprakash Jeyapriya , Subbiah Murugan
Nowadays the rapid growth of unmanned aerial vehicles (UAVs) bridges the space between worldly and airborne photogrammetry as well as allow flexible acquisition of great solution images. In the case of natural disasters such as floods, tsunamis, earthquakes, and cyclones, their effects are most often felt in the micro-spaces and urban environments. Therefore, rescuers have to go around to get to the victims. This paper presents an auto digitization of aerial images to map generation from UAV feed at night time. In case of a power outage and an absence of alternative light sources, rescue operations are also slowed due to the darkness caused by the lack of electricity and the inability to light additional sources. In other words, to save lives, we need to know about all essential large-scale feature spaces in the dark so that we can use this information in times of disaster. The research proposed a soft framework for crisis mapping to aid in mapping the state of the aerial landscape in disaster-stricken areas, allowing strategic rescue operations to be more effectively planned.
Volume: 36
Issue: 2
Page: 1338-1346
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

Forecasting research influence: a recurrent neural network approach to citation prediction

10.11591/ijeecs.v36.i2.pp1070-1082
Naser Jamal , Mohammad Alauthman , Muhannad Malhis , Abdelraouf M. Ishtaiwi
As the volume of scientific publications continues to proliferate, effective evaluation tools to determine the impact and quality of research articles are increasingly necessary. Citations serve as a widely utilized metric for gauging scientific impact. However, accurately prognosticating the long-term citation impact of nascent published research presents a formidable challenge due to the intricacy and unpredictability innate to the scientific ecosystem. Sophisticated machine learning methodologies, particularly recurrent neural networks (RNNs), have recently demonstrated promising potential in addressing this task. This research proposes an RNN architecture leveraging encoder-decoder sequence modeling capabilities to ingest historical chronicles and predict succeeding evolution via latent temporal dynamics learning. Comparative analysis between the RNN approach and baselines, including random forest, support vector regression, and multi-layer perceptron, demonstrate superior performance on unseen test data and rigorous k-fold cross-validation. On a corpus from Petra University, the RNN methodology attained the lowest errors (root mean squared error (RMSE) 1.84) and highest accuracy (0.91), area under the curve (AUC) (0.96), and F1-score (0.92). Statistical tests further verify significant improvements. The findings validate our deep learning solution's efficacy, robustness, and real-world viability for long-term scientific impact quantification to aid stakeholders in research evaluation. The findings intimate that RNN-based predictive modeling constitutes a potent technology for citation-driven scientific impact quantification.
Volume: 36
Issue: 2
Page: 1070-1082
Publish at: 2024-11-01

An interactive visualization tool for the exploration and analysis of multivariate ocean data

10.11591/ijeecs.v36.i2.pp1329-1337
Preetha K. G. , Saritha S. , Jishnu Jeevan , Chinnu Sachidanandan , P. A. Maheswaran
Ocean data exhibits great heterogeneity from variances in measuring methods, formats, and quality, making it extremely complicated and diverse due to a variety of data kinds, sources, and study elements. A few examples of data sources are satellites, buoys, ships, self-driving cars, and distant systems. The processing of data is made more challenging by the significant regional and temporal variations in oceanic characteristics including temperature, salinity, and currents. This work presents an interactive tool for multivariate ocean parameter visualisation, specifically overlays, based on Python. In ocean data visualisation, overlays are extra visual layers or data points that are layered to improve comprehension over a basic map. Based on the available data and the visualisation goals, these overlays are chosen and blended. Users can customise overlays with this tool, which also supports formatting, 2D and 3D visualisation, and data preparation. In order to reduce artefacts, it uses kriging interpolation for 3D visualisation and a modified version of the ray casting algorithm for representing octree data. By integrating overlays like as bathymetry, currents, temperature, and marine life, users can produce visually appealing and comprehensive depictions of ocean data. This method provides a thorough grasp of intricate marine processes by making it easier to see patterns, trends, and abnormalities in the data.
Volume: 36
Issue: 2
Page: 1329-1337
Publish at: 2024-11-01

Internet based highly secure data transmission system in health care monitoring system

10.11591/ijres.v13.i3.pp681-686
Gubbala Bhaskar Phani Ram , Shankar Thirunarayanan
The health care systems in our contemporary countries are advancing rapidly in terms of maturity and professionalism. In an effort to alleviate the current burden on the public health system and boost the popularity of regular health self-checks, this method has been developed for producing prediagnoses that are easier to use, quicker, and more accurate. To ascertain how well the heart is circulating oxygen throughout the body, a pulse test, a painless examination that measures an individual's degree of oxygen saturation, is used. It can be used to evaluate the state of any patient with a disease, particularly those with pulmonary problems. Diseases in these patients could need ongoing observation and care. Our system comes to the rescue in order to resolve this problem. This portable system is simple to use and may be taken anywhere by the subject. The internet of things (IoT) will update the pertinent parameters. This health monitoring system's controller is made up of an adaptor, a saturation of peripheral oxygen (SPO2 ) sensor (a blood oxygen meter), a temperature sensor, a heart rate sensor, a WiFi module, and a liquid crystal display (LCD).
Volume: 13
Issue: 3
Page: 681-686
Publish at: 2024-11-01

Improved automated parallel implementation of GMM background subtraction on a multicore digital signal processor

10.11591/ijres.v13.i3.pp552-559
Smail Bariko , Abdessamad Klilou , Abdelouahed Abounada , Assia Arsalane
Scene segmentation is an essential step in a wide range of video processing applications, for instance, object recognition and tracking. The Gaussian mixture model (GMM) for background subtraction (BS) has gained widespread usage in scene segmentation, despite its known computational intensity. To tackle this challenge, we propose a practical solution to accelerate processing through a parallel implementation on an embedded multicore platform. In this paper, we present an improved automated parallel implementation of the GMM algorithm using the Orphan directive provided by open multiprocessing (OpenMP). Experimental assessments conducted on the eight cores of the C6678 digital signal processor (DSP) demonstrate significant advancements in parallel efficiency, particularly when handling high-resolution frames, including high-definition (HD) and full-HD resolutions. The achieved parallel efficiency surpasses the results obtained with classical OpenMP scheduling modes, encompassing dynamic, static, and guided approaches. Specifically, the parallel efficiency reaches approximately 82% for full-HD resolution frames and, 99.3% for low-resolution frames, respectively.
Volume: 13
Issue: 3
Page: 552-559
Publish at: 2024-11-01

Optimizing hyperspectral classification: spectral similarity-based band selection with chord k-means

10.11591/ijeecs.v36.i2.pp1309-1318
Origanti Subhash Chander Goud , Thogarachetti Hitendra Sarma , Chigarapalle Shobha Bindu
Band selection is crucial for achieving high classification accuracy in hyperspectral image (HSI) analysis, especially when ground truth data are limited. While unsupervised algorithms are preferred in such scenarios, the effectiveness of k-means clustering depends heavily on the choice of similarity measure. This article presents a novel two-level clustering approach for band selection. In the first level, bands are clustered using k-means with various similarity measures such as Euclidean distance, spectral angle mapper (SAM), and spectral information divergence (SID). Subsequently, the second level leverages the chord metric k-means clustering to form clusters of HSI scenes upon optimal band clusters from the first level. This initial band selection reduces dimensionality and guides subsequent k-means clustering. The proposed chord-based clustering method, utilizing the chord metric, outperforms standard k-means variants, demonstrating significant improvements in accuracy. Experimental results on publicly available hyperspectral datasets confirm the effectiveness of the proposed approach as an alternative to traditional k-means algorithms, showcasing significant improvements in accuracy.
Volume: 36
Issue: 2
Page: 1309-1318
Publish at: 2024-11-01

Applying inductive logic programming to automate the function of an intelligent natural language interfaces for databases

10.11591/ijeecs.v36.i2.pp983-993
Hanane Bais , Mustapha Machkour
One of the foundational subjects in both artificial intelligence (AI) and database technologies is natural language interfaces for databases (NLIDB). The primary goal of NLIDB is to enable users to interact with databases using natural languages such as English, Arabic, and French. While many existing NLIDBs rely on linguistic operations to meet the challenges of user’s ambiguity existing in natural language queries (NLQ), there is currently a growing emphasis on utilizing inductive logic programming (ILP) to develop natural language processing (NLP) applications. This is because ILP reduces the requirement for linguistic expertise in building NLP systems. This paper outlines a methodology for automating the construction of NLIDB. This method utilizes ILP to derive transfer rules that directly translate NLQ into a clear and unambiguous logical query, which subsequently translatable into database query languages (DQL). To acquire these rules, our system was trained within a corpus consisting of parallel examples of NLQs and their logical interpretations. The experimental results demonstrate the promise of this approach, as it enables the direct translation of all NLQs with grammatical structures similar to those already present in the trained corpus into a logical query.
Volume: 36
Issue: 2
Page: 983-993
Publish at: 2024-11-01

Convolutional neural networks breast cancer classification using Palestinian mammogram dataset

10.11591/ijeecs.v36.i2.pp1149-1162
Hanin Saadah , Amani Yousef Owda , Majdi Owda
Breast cancer is widespread across the globe. It’s the primary cause of death in cancer fatalities. According to the Palestinian Ministry of Health annual report, it ranked as the third reported death of all reported cancer deaths in the West Bank. Mammogram screening is the most common technique to diagnose breast abnormalities, but there is a challenge in the lack of skilled experts able to accurately interpret mammograms. Machine learning plays an important role in medical image processing particularly in early detection when the treatment is less expensive and available. In this paper we proposed different convolutional neural network (CNN) models to detect breast abnormalities with promising results. Six CNN models were used in this research on a unique (first-hand) dataset collected from the Palestinian Ministry of Health. The models are VGG16, VGG19, DenseNet121, ResNet50, Xception, and EfficientNetB7. Consequently, DenseNet121 outperformed other models with 0.83 and 0.85 for testing accuracy and area under curve (AUC) respectively. As a future work, the outperformed model can be combined with other patient data like genetic information, medical history, and lifestyle factors to evaluate the risk of developing specific diseases. This would increase the survival rate and enable proactive measures.
Volume: 36
Issue: 2
Page: 1149-1162
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

Characterization of UF-18 cacao pods using Arduino-based load compressor testing machine

10.11591/ijeecs.v36.i2.pp741-748
Maricel Gamolo Dayaday , Renel M. Alucilja , Ritchell Joy T. Cuarteros , Jeffrey A. Lavarias
Bean damage is one of the primary concerns in the pod-breaking process. Studies for pod-breaking machines are ongoing to ensure that the products made from these machines are of good quality. The objective of the study is to determine the physical and mechanical characteristics of the UF-18 pod. The Arduino-based load compressor testing machine was designed and developed to characterize the UF-18 pod. It was found that the average geometric mean diameter, surface area, and sphericity index of 115.37 mm, 41,899.48 mm², and 0.6372, respectively, and with a variation of ±27.17, ±14538133.04, and ±0.00038 respectively. Furthermore, the cacao pod samples had an average dimension of 181.29 mm, 94.26 mm, 90.01 mm, and 17.44 mm measured for the length, equatorial diameter, intermediate diameter and external thickness, respectively. Different pod sizes and thicknesses require various forces ranging from 36.94 to 92.42 kg (362.38 N to 906.64 N) and time ranging from 6-11 seconds to be able to break the pods. Determining the physical and mechanical properties of cacao pods enables fabricators to design efficient machines, which lessens the force to break and the damage to the beans, thus producing quality beans.
Volume: 36
Issue: 2
Page: 741-748
Publish at: 2024-11-01

Embedded systems as programmable square wave generator in wireless power transfer

10.11591/ijres.v13.i3.pp568-576
Sabriansyah Rizqika Akbar , Eko Setiawan , Achmad Basuki
This study focuses on the design and development of programmable frequency generator using embedded devices that are able to produce square wave signals in the wireless power transfer (WPT) transmitter. We validate the accuracy of the output signal by measuring distance error. We validate that our system can change and sweep the frequency and produce high power by measuring the absorbed power in the load. We conduct the frequency sweep analysis to find optimal frequency and the frequency splitting phenomenon. The experiments show that the system can produce and sweep the square wave signals with less than 1% error. We also find that the frequency splitting occurred when distance among two coils in the range 0.5-6.5 cm and the splitting disappeared when the distance is above 7.5 cm. The frequency splitting shows that the measured optimum frequency differs from the calculation. The difference confirms that the programmable frequency generator is needed to adjust the frequency that can transfer maximum power to the load.
Volume: 13
Issue: 3
Page: 568-576
Publish at: 2024-11-01
1 2 3
...
1573 1574
Show 10 of 1574

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