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

Design of an effective multiple objects tracking framework for dynamic video scenes

10.11591/ijai.v13.i4.pp3879-3891
Sunil Kumar Karanam , Narasimha Murthy Pokale Kavya
Nowadays, the applications corresponding to video surveillance systems are getting popular due to their wide range of deployment in various places such as schools, roads, and airports. Despite the continuous evolution and increasing deployment of object-tracking features in video surveillance applications, the loopholes still need to be solved due to the limited functionalities of video-tracking systems. The existing video surveillance systems pose high processing overhead due to the larger size of video files. However, the traditional literature report quite sophisticated schemes which might successfully retain higher object detection accuracy from the video scenes but needs more effectiveness regarding computational complexity under limited computing resources. The study thereby identifies the scope of enhancement in traditional object-tracking functions. Further, it introduces a novel, cost-effective tracking model based on Gaussian mixture model (GMM) and Kalman filter (KF) that can accurately identify numerous mobile objects from a dynamic video scene and ensures computing efficiency. The study's outcome shows that the proposed strategic modelling offers better tracking performance for dynamic objects with cost-effective computation compared to the popular baseline approaches.
Volume: 13
Issue: 4
Page: 3879-3891
Publish at: 2024-12-01

WEKA-based machine learning for traffic congestion prediction in Amman City

10.11591/ijai.v13.i4.pp4422-4434
Areen Arabiat , Mohammad Hassan , Omar Almomani
Traffic congestion leads to wasted time, pollution, and increased fuel consumption. Traffic congestion prediction has become a developing research topic in recent years, particularly in the field of machine learning (ML). The evaluation of various traffic parameters is used to predict traffic congestion by relying on historical data. In this study, we will predict traffic congestion in Amman City, specifically at the 8th circle, using different ML classifiers. The 8th circle links four main streets: Westbound, Northbound, Eastbound, and Southbound. Datasets were collected from the greater Amman municipality hourly. The logistic regression (LR), k-nearest neighbor (KNN), decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) classifiers have been chosen to predict traffic congestion at each street linked with the 8th circle. The waikato environment for knowledge analysis (WEKA) data mining tool is used to evaluate chosen classifiers by determining accuracy, F-measure, sensitivity, and precision evaluation metrics. The results obtained from all experiments have demonstrated that SVM is the best classifier to predict traffic congestion. The accuracy of SVM to predict traffic congestion at Westbound Street, Northbound Street, Eastbound Street, and Southbound Street was 99.4%, 99.7%, 99.6%, and 99.1%, respectively.
Volume: 13
Issue: 4
Page: 4422-4434
Publish at: 2024-12-01

Review of cloud computing models in education and the unmet needs

10.11591/ijai.v13.i4.pp4029-4036
Aminah Rezqallah Malkawi , Muhamad Shahbani Abu Bakar , Zulkhairi Dahalin
This article thoroughly examines recently proposed cloud computing (CC) models used within the higher educational institutions (HEI) field, scrutinizing their objectives, structures, and incorporated requirements. Each model's unique architecture and functionality are analyzed to understand their potential educational contributions. Beyond technical considerations, the study explores nuanced requirements essential for successful integration in educational settings. The review exposes diverse aims pursued by the models, such as enhanced scalability, collaborative learning, and resource management, emphasizing their capacity to reshape traditional educational paradigms. However, a notable gap emerges-the absence of cultural and requirement elicitation models within the frameworks. Despite growing cultural diversity and varied educational needs, most models lack components addressing cultural nuances and robust requirement elicitation. In conclusion, the paper identifies a pressing need for a transformative shift in developing CC models for education. The absence of dedicated cultural and requirement elicitation models challenges the holistic effectiveness of these frameworks. Future efforts should prioritize integrating culturally sensitive components and comprehensive requirement elicitation strategies to create adaptive, universally applicable, and inclusive CC educational environments. Addressing these gaps will pave the way for a nuanced and responsive integration of CC technologies in diverse educational settings.
Volume: 13
Issue: 4
Page: 4029-4036
Publish at: 2024-12-01

A semantic similarity search engine for movies

10.11591/ijece.v14i6.pp7137-7144
Ahmad Mustafa , Hammam Mheidat , Adam Shatnawi
Semantic similarity has been gaining traction in the field of natural language processing. It is a measure of how similar two pieces of text are in terms of their meaning. It can be used to improve search engine results. We propose a deep learning-based approach to build a semantic similarity search engine for movies based on a movie summary. Filmmakers can gain insight into audience preferences and trends, allowing them to create more engaging and successful films. The dataset used in this study was gathered from internet movie database (IMDb), it includes movie summaries along with their corresponding name movies. The test dataset was generated using ChatGPT to be very close to human input. The universal sentence encoder (USE) model presented promising results in semantic similarity, the model results show that for the top 5 similar movies, the model returned 176 out of 300 movies (58.6%). For the top 10 similar movies, the model returned 211 out of 300 movies (70.3%). Additionally, for the top 15 similar movies, the model returned 229 out of 300 movies (76.3%). And, for the top 20 similar movies, the model returned 249 of 300 movies (83%). This method can be applied to movie recommendation systems or to organize films in a collection automatically.
Volume: 14
Issue: 6
Page: 7137-7144
Publish at: 2024-12-01

Nearest neighbor analysis of the spread of tuberculosis in Padang

10.11591/ijphs.v13i4.24385
Rapitos Sidiq , Indang Dewata , Heldi Heldi , Neni Fitra Hayati
The rate of Tuberculosis (TB) cases in Padang has never dropped appreciably from year to year. Cases continue to be reported in all working regions of Puskesmas (primary healthcare center) although the precise transmission site is unknown. This study aims to determine the distribution pattern of TB sufferers in 4 Health Center working areas with the highest incidence using nearest neighbor analysis. This quantitative descriptive study used secondary data from the Padang Health Office and 4 working regions of primary healthcare centers from 2022 to March 2023, totaling 938 cases. The evidence is supported by actual observations of the physical conditions of the environment where TB patients live. The investigation of the ArcGIS program discovered that of the 4 working regions of primary healthcare centers. Mapping revealed that all locations showed a cluster pattern of TB transmission. It is hoped that these findings will be useful for health institutions in determining interventions so they can break the chain of TB transmission.
Volume: 13
Issue: 4
Page: 1568-1577
Publish at: 2024-12-01

Investigations on the behavioral analysis of unbalanced synchronous generators

10.11591/ijpeds.v15.i4.pp2097-2104
Djilali Kouchih , Redouane Hachelaf , Mohamed Tadjine , Mohamed Seghir Boucherit
This paper describes a new methodology for the modeling and analysis of three-phase synchronous generators operating under an unbalanced regime. For this, an improved state model has been developed in order to determine significant signatures on stator and rotor electromagnetic quantities. This methodology is characterized by some advantages. Firstly, it can be generalized for the modeling of severe defects like open-phase and short circuits. Furthermore, by comparison to classical approaches based on the finite elements and symmetrical components methods, this approach gives a good compromise between precision and simulation time. The obtained results show the effectiveness of this approach for the analysis of unbalanced synchronous generators.
Volume: 15
Issue: 4
Page: 2097-2104
Publish at: 2024-12-01

Maternal hair lead and cytokine pro-inflammatory effects in preterm birth

10.11591/ijphs.v13i4.24146
Qonita Nur Qolby , Julian Dewantiningrum , Besari Adi Pramono , Nani Maharani , Eka Djatnika Nugraha , Muflihatul Muniroh
This case-control study analyzed the lead (Pb), interleukin 6 (IL-6), and tumor necrosis factor alpha (TNF-α) levels in pregnant women with preterm birth (PTB) in Central Java, Indonesia. Hair samples from 72 pregnant women were collected non-invasively. The prenatal exposure to Pb was determined with the total reflection X-ray fluorescence (TXRF) method. Serum IL-6 and TNF-α were examined using enzyme-linked immunosorbent assays (ELISA). The Pb concentration in hair was slightly higher in women with PTB than those without PTB; however, this difference was not statistically significant. An elevated hair Pb level was not associated with increased PTB risk (OR 24.69, 95% CI 0.93–653.82, p>0.05). A serum TNF-α level ≥27 pg/ml, a serum IL-6 level ≥9 pg/ml, and the spouse’s smoking frequency were significantly associated with increased PTB risk (TNF-α OR 42.25, 95% CI 5.26–339.61; IL-6 OR 22.33, 95% CI 3.12–158.54; spouse’s smoking frequency OR 1.28, 95% CI 1.09–1.5), while the maternal hemoglobin concentration significantly decreased PTB risk (OR 0.43, 95% CI 0.2–0.927). This study demonstrates that maternal hair Pb concentration has no significant relationship with PTB. Serum TNF-α, IL-6, and the spouse’s smoking frequency potentially increased PTB risk, while the maternal hemoglobin level is a protective factor.
Volume: 13
Issue: 4
Page: 1826-1833
Publish at: 2024-12-01

Components of basic feeding rule for infants aged 6-24 months: a scoping review

10.11591/ijphs.v13i4.24304
Fitri Haryanti , Fitriana Andarwati , Hani Risnawati , Lely Lusmilasari , Sri Hartini
Introducing complementary foods at six months helps supplement nutrients and address potential eating challenges in infants. Childhood eating difficulties can contribute to growth issues. This scoping review aimed to identify the components of feeding rules for infants aged 6-24 months. A systematic search of three electronic databases yielded 5,174 abstracts, with 18 complete articles assessed for eligibility. After eliminating 8 articles, 10 met the criteria. The feeding rules comprise three main components: schedule, environment, and procedure. Adhering to these basic rules can enhance a child's growth rate and reduce the risk of failure to thrive. Responsive feeding is closely linked to these rules, categorized based on feeding schedule, procedures, and environment. Hence, it is crucial for healthcare professionals to provide counseling on the fundamental principles of complementary feeding.
Volume: 13
Issue: 4
Page: 1938-1945
Publish at: 2024-12-01

A novel scheme for unified streamlined traffic management in 5G backhaul network

10.11591/ijece.v14i6.pp6981-6991
Deepa Thippanna , Praveen Jayappa
The issues associated with the 5G backhaul network act as the underlying reason for concern. Existing literature towards the 5G backhaul network offers various ranges of sophisticated schemes that are yet to possess open-end issues. Therefore, the proposed study introduces a novel scheme for effective 5G backhaul network traffic management. The scheme hypothesizes that if an efficient gateway node is selected, it can better communicate between the macro-base station and the core network. The study contributes to developing a sophisticated system design to identify the blockage region, a macro-base station, and a small base station. These attributes incorporate the capability of a gateway node to identify the bottleneck condition during peak traffic situations in the 5G backhaul network. The study outcome shows better communication performance in contrast to the existing system. The study outcome shows the proposed scheme to offer 47% increased throughput, 80% reduced latency, and 55% reduced algorithmic processing time in contrast to existing schemes.
Volume: 14
Issue: 6
Page: 6981-6991
Publish at: 2024-12-01

Pneumonia detection on x-ray image using improved depthwise separable convolutional neural networks

10.11591/ijai.v13.i4.pp4169-4177
Islam Nur Alam , Ghinaa Zain Nabiilah , Erna Fransisca Angela Sihotang , Bakti Amirul Jabar
A single neural network model cannot capture intricate and diverse features due to its ability to learn only a finite set of patterns from the data. Additionally, training and utilising a single model can be computationally demanding. Experts propose incorporating multiple neural network models to address these constraints to extract complementary attributes. Previous research has highlighted challenges network models face, including difficulties in effectively capturing highly detailed spatial features, redundancy in network structure parameters, and restricted generalisation capabilities. This study introduces an innovative neural network architecture that combines the Xception module with the inverse residue structure to tackle these issues. Considering this, the paper presents a model for detecting pneumonia in X-ray images employing an improved depthwise separable convolutional network. This network architecture integrates the inverse residual structure from the MobileNetV2 model, using the rectified linear unit (ReLU) non-linear activation function throughout the entire network. The experimental results show an impressive recognition rate with a test accuracy of 97.24% on the chest x-ray dataset. This method can extract more profound and abstract image features while mitigating overfitting issues and enhancing the network's generalisation capacity.
Volume: 13
Issue: 4
Page: 4169-4177
Publish at: 2024-12-01

Fault diagnosis decentralized of manufacturing systems using Boolean models

10.11591/ijpeds.v15.i4.pp2700-2708
Hireche Slimane , Mohamed Habbab , Abdeldjebar Hazzab , Ahmed Khalil Moussaoui , Ambrish Chandra , Hicham Gouabi , Alhachemi Moulay Abdellah
This paper introduces an approach decentralized to fault detection and isolation (FDI) in manufacturing systems using a Boolean discrete event model. The method incorporates diverse information sources to create distinct models for plant systems and control. The objective is to enhance the understanding of process operations by employing various representation tools tailored to each information source. It is to reduce the number of explosion problems combinatorial and detect faults in the shortest possible time. This comprehensive representation facilitates the fulfillment of three crucial diagnosis functions: detection, localization, and identification. The approach involves Boolean modeling of each process actuator along with its corresponding sensors, a temporal model based on fuzzy expectations of event occurrences, and a set of if...then rules. The goal of this decentralized approach minimize both the complexity and the manual construction effort required for the model. The paper demonstrates the effectiveness of this approach through an illustrative example involving manufacturing systems.
Volume: 15
Issue: 4
Page: 2700-2708
Publish at: 2024-12-01

Multi-label feature aware XGBoost model for student performance assessment using behavior data in online learning environment

10.11591/ijai.v13.i4.pp4537-4543
Shashirekha Hanumanthappa , Chetana Prakash
In light of recent outbreaks like COVID19, the use of online-based learning streams (i.e., e-Learning systems) has increased significantly. Institutional efforts to boost student achievement have made precise predictions of academic success a priority. To analyze student sessions-streams and anticipate academic success, e-learning platforms are starting to combine data mining (DM) with machine-learning (ML) techniques. Recent research highlights the difficulties that ML-based methods have while dealing with unbalanced data. In tackling ensemble-learning, we combine several ML algorithms to select the most appropriate approach for the given data. Current ensemble-based approaches for predicting student achievement, nevertheless, don't do exceptionally well, particularly when it comes to multi-label classification, because they don't factor the relevance of features into their approaches. This study presents multi-label feature aware XGBoost (MLFA-XGB) method that improves upon the previously used ensemble-learning technique. The MLFA-XGB makes use of a robust cross-validation approach for gaining a deeper understanding of feature relationships. The experimental results demonstrate that in comparison with the state-of-the-art ensemble-based student achievement predictive approach, this suggested MLFA-XGB based approach provides much higher accuracy for prediction. 
Volume: 13
Issue: 4
Page: 4537-4543
Publish at: 2024-12-01

Development of a prioritized traffic light control system for emergency vehicles

10.11591/ijai.v13.i4.pp4019-4028
Halleluyah Oluwatobi Aworinde , Abidemi Emmanuel Adeniyi , Segun Adebayo , Faith Adeniji , Oluwasegun Julius Aroba
This research presents a model for an adaptive traffic signal control system aimed at improving urban traffic regulation. It dynamically adjusts signal timing based on vehicle volume at intersections, prioritizing emergency vehicles by allowing them immediate passage. Utilizing Arduino coding, the system controls traffic light intensity according to the traffic flow, enhancing road safety and efficiency. This innovative approach not only facilitates faster clearance for emergency services without human intervention but also reduces congestion and accident rates. This research creates a model for a prioritized traffic signal control system. When the vehicular volume at the intersection varies, the signal time alters autonomously. It identifies the ambulance/emergency vehicles and allows the green light for emergency vehicles like ambulances, and fire engines. This approach may be used to detect traffic accidents and infractions of automobile spiral motions. When erected on the road, the entire system allows for quick traffic clearing for rescue vehicles without requiring a policeman. The system's design eliminates the need for sensors or radio frequency identification (RFID) tags, simplifying traffic management. Simulations validate that emergency vehicle travel time is significantly reduced, proving the system's effectiveness in streamlining urban traffic flows.
Volume: 13
Issue: 4
Page: 4019-4028
Publish at: 2024-12-01

The future of artificial intelligence-driven robotics: applications and implications

10.11591/ijra.v13i4.pp361-372
Tole Sutikno
Artificial intelligence (AI)-driven robotics is a rapidly evolving field that is transforming various industries, including healthcare, manufacturing, transportation, logistics, security, retail, agri-food, and construction. The integration of artificial intelligence algorithms and machine learning techniques has propelled robotics beyond mere automation, enabling machines to modify, alter, adjust, learn, and interact with the world in ways previously deemed science fiction. The relentless pursuit of creating intelligent robotic systems has led to a symbiotic relationship between human inventiveness and AI, with AI-driven autonomous cars, drones, and robots transforming transportation, healthcare, and exploration. It offers flexibility and learning capabilities, transforming the way machines interact with humans. The integration of AI and robotics marks a transformative era in which machines become companions and cognitive extensions of human capabilities. In the future, we expect AI-driven robotics to bring significant changes to employment and societal well-being. However, the development of AI-driven robotics, which is the integration of AI and robotics, faces numerous challenges, including ethical concerns, legal issues, regulations, societal implications, and job market impacts for the proliferation of intelligent machines. Furthermore, it also presents challenges in terms of technical complexities in its development.
Volume: 13
Issue: 4
Page: 361-372
Publish at: 2024-12-01

Enhancing sentiment analysis in Kannada texts by feature selection

10.11591/ijece.v14i6.pp6572-6582
Sunil Mugalihalli Eshwarappa , Vinay Shivasubramanyan
In recent years, there has been a noticeable surge in research activities focused on sentiment analysis within the Kannada language domain. The existing research highlights a lack of labelled datasets and limited exploration in feature selection for Kannada sentiment analysis, hindering accurate sentiment classification. To address this gap, the study aims to introduce a novel Kannada dataset and develop an effective classifier for improved sentiment analysis in Kannada texts. The study presents a new Kannada dataset from SemEval 2014 Task4 using Google Translate. It then introduces a modified bidirectional encoder representation from transformers BERT for Kannada dataset called as Kannada-BERT (K-BERT). Further, a probability-clustering (PC) approach is presented to extract the topics and its related aspects. Both the K-BERT classifier and PC approach were merged to attain a K-BERT-PC classifier, integrating a modified BERT model and probability clustering approach for achieving better results. Experimental results demonstrate that K-BERT-PC achieves superior performance in polarity and sentiment analysis accuracy, with an impressive accuracy rate of 91%, surpassing existing classifiers. This work contributes by providing a solution to the scarcity of labelled datasets for Kannada sentiment analysis and introduces an effective classifier, K-BERT-PC, for enhanced sentiment analysis outcomes in Kannada texts.
Volume: 14
Issue: 6
Page: 6572-6582
Publish at: 2024-12-01
1 2 3
...
2097 2098
Show 423 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