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

29,939 Article Results

Hybrid clustering based on multi-criteria segmentation for higher education marketing

10.12928/telkomnika.v19i5.18965
Hardika; Universitas Sahid Surakarta Khusnuliawati , Dhian Riskiana; Universitas Sahid Surakarta Putri
Market segmentation in higher education institutions is still rarely applied although it can assist in defining the right strategies and actions for the targeted market. The problem that often arises in market segmentation is how to exploit the preferences of students as customers. To overcome this, the combination of hybrid clustering method with multiple criteria will be applied to the case of the market segmentation for students in higher education institutions. The integration of geographic, demographic, psychographic, and behavioral criteria from students is used to get more insightful information about student preference. Data result of the integration will be processed using hybrid clustering using K-means and self organizing map (SOM) algorithm. The hybrid clustering conducted to get promising clustering result along with the visualization of segmentation. This study successfully produces five student segments. It received 1,386 as the Davies-Bouldin index (DBI) value and 2,752 as the quantization error (QE) value which indicates a good clustering result for market segmentation. In addition, the visualization of the clustering result can be seen in a hexagonal map.
Volume: 19
Issue: 5
Page: 1498-1506
Publish at: 2021-10-01

Multi-spectral images classification based on intelligent water drops algorithm

10.11591/ijeecs.v24.i1.pp116-125
Almas Ahmed Khaleel
Mosul's city land covers soil, cultivated land, stony, pastoral land, water, and ploughed agricultural land. We have classified multispectral images captured by the sensor (TM) carried on the Landsat satellite. Integrated approach of intelligent water drops (IWDs) algorithm is used to identify natural terrain. In this research, IWDs have been suggested to find the best results for multispectral image classification. The purpose of using an algorithm, give accurate and fast results by comparing the IWD algorithm with the K-mean algorithm. The IWD algorithm is programmed using the Matlab2017b software environment to demonstrate the proposed methodology's effectiveness. The proposed integrated concept has been applied to satellite images of Mosul city in Iraq. By comparing the IWD with the K-mean, we found clear time superiority of the IWD algorithm, equal 1.4122 with (K-mean) time equal 18.9475. Furthermore, the water drop algorithm's classification accuracy is 95%, while the K-mean classification accuracy is 83.3%. Based on the analysis and results, we conclude the IWD is a robust promising and approach to detecting remote sensing image changes and multispectral image classification.
Volume: 24
Issue: 1
Page: 116-125
Publish at: 2021-10-01

Large scale data analysis using MLlib

10.12928/telkomnika.v19i5.21059
Ahmed; Informatics Institute for Postgraduate Studies Hussein Ali , Maan; Imam Aadham University College Nawaf Abbod , Mohammed; AL-Iraqia University Khamees Khaleel , Mostafa; Imam Aadham University College Abdulghafoor Mohammed , Tole; Universitas Ahmad Dahlan Sutikno
Recent advancements in the internet, social media, and internet of things (IoT) devices have significantly increased the amount of data generated in a variety of formats. The data must be converted into formats that is easily handled by the data analysis techniques. It is mathematically and physically expensive to apply machine learning algorithms to big and complicated data sets. It is a resource-intensive process that necessitates a huge amount of logical and physical resources. Machine learning is a sophisticated data analytics technology that has gained in importance as a result of the massive amount of data generated daily that needs to be examined. Apache Spark machine learning library (MLlib) is one of the big data analysis platforms that provides a variety of outstanding functions for various machine learning tasks, spanning from classification to regression and dimension reduction. From a computational standpoint, this research investigated Apache Spark MLlib 2.0 as an open source, autonomous, scalable, and distributed learning library. Several real-world machine learning experiments are carried out in order to evaluate the properties of the platform on a qualitative and quantitative level. Some of the fundamental concepts and approaches for developing a scalable data model in a distributed environment are also discussed.
Volume: 19
Issue: 5
Page: 1735-1746
Publish at: 2021-10-01

Artificial neural network technique for improving prediction of credit card default: A stacked sparse autoencoder approach

10.11591/ijece.v11i5.pp4392-4402
Sarah A. Ebiaredoh-Mienye , E. Esenogho , Theo G. Swart
Presently, the use of a credit card has become an integral part of contemporary banking and financial system. Predicting potential credit card defaulters or debtors is a crucial business opportunity for financial institutions. For now, some machine learning methods have been applied to achieve this task. However, with the dynamic and imbalanced nature of credit card default data, it is challenging for classical machine learning algorithms to proffer robust models with optimal performance. Research has shown that the performance of machine learning algorithms can be significantly improved when provided with optimal features. In this paper, we propose an unsupervised feature learning method to improve the performance of various classifiers using a stacked sparse autoencoder (SSAE). The SSAE was optimized to achieve improved performance. The proposed SSAE learned excellent feature representations that were used to train the classifiers. The performance of the proposed approach is compared with an instance where the classifiers were trained using the raw data. Also, a comparison is made with previous scholarly works, and the proposed approach showed superior performance over other methods.
Volume: 11
Issue: 5
Page: 4392-4402
Publish at: 2021-10-01

ASR-FANET: An adaptive SDN-based routing framework for FANET

10.11591/ijece.v11i5.pp4403-4412
Alaa Taima Albu-slaih , Hayder Ayad Khudhair
Flying ad hoc network (FANET) is widely used in many military, commercial and civilian applications. Compared with mobile adhoc network (MANET) and vehicular ad hoc network (VANET), FANET holds unique characteristics such as high mobility, intermittent links and frequent topology changes, which cause a challenging task in the design of routing protocols. A novel adaptive software defined networking (SDN)-based routing framework for FANET called ASR-FANET is proposed in this article to solve the above challenges. The ASR-FANET framework is mainly composed of three important parts, which are the topology discovery mechanism, statistics gathering mechanism and route computation mechanism. In topology discovery mechanism, the periodic information about network topology is collected, including nodes and links. In statistics gathering mechanism, the status of the wireless network connection and flight statistics are collected. In route computation mechanism, the optimal path is calculated based on link costs. The performance of ASR-FANET framework is also has been evaluated by comprehensive simulations. The simulation results show that proposed framework is much better than other traditional protocols in packet delivery fraction, average end to end delay, normalized routing load, packet loss and throughput.
Volume: 11
Issue: 5
Page: 4403-4412
Publish at: 2021-10-01

The study of convex-dual-layer remote phosphor geometry in upgrading WLEDs color rendering index

10.11591/ijece.v11i5.pp3890-3896
Huu Phuc Dang , Nguyen Thi Phuong Loan , Nguyen Thi Kim Chung , Nguyen Doan Quoc Anh
The white-light light-emitting diode (LED) is a semiconductor light source that usually has one chip and one phosphor layer. Because of that simple structure, the color rendering index (CRI) is really poor. Therefore, structure with double layer of phosphor and multiple chips has been studied with the phosphorus proportions and densities in the silicone are constantly changed to find the best option to improve optical properties. In research, we use red phosphor Ca5B2SiO10:Eu3+ layer to place above the yellow phosphor one, and both of them have a convex design. Then, the experiments and measurements are carried out to figure out the effects of this red phosphor as well as the convex-double-layer remote phosphor design on the LED’s performances. The measured results reveal that the light output is enhanced significantly when using convex-dual-layer structure instead of the single-layer design. Additionally, the Ca5B2SiO10:Eu3+ concentration benefits CRI and CQS at around 6600 K and 7700 K correlated color temperature (CCT). Yet, the lumen output shows a slight decline as this red phosphor concentration surpass 26% wt. Through the experiments, it is found that a double layer of chip and double phosphorus is the best structure which could support the quality of CRI and luminous flux.
Volume: 11
Issue: 5
Page: 3890-3896
Publish at: 2021-10-01

Identification of important features and data mining classification techniques in predicting employee absenteeism at work

10.11591/ijece.v11i5.pp4587-4596
Amal Al-Rasheed
Employees absenteeism at the work costs organizations billions a year. Prediction of employees’ absenteeism and the reasons behind their absence help organizations in reducing expenses and increasing productivity. Data mining turns the vast volume of human resources data into information that can help in decision-making and prediction. Although the selection of features is a critical step in data mining to enhance the efficiency of the final prediction, it is not yet known which method of feature selection is better. Therefore, this paper aims to compare the performance of three well-known feature selection methods in absenteeism prediction, which are relief-based feature selection, correlation-based feature selection and information-gain feature selection. In addition, this paper aims to find the best combination of feature selection method and data mining technique in enhancing the absenteeism prediction accuracy. Seven classification techniques were used as the prediction model. Additionally, cross-validation approach was utilized to assess the applied prediction models to have more realistic and reliable results. The used dataset was built at a courier company in Brazil with records of absenteeism at work. Regarding experimental results, correlationbased feature selection surpasses the other methods through the performance measurements. Furthermore, bagging classifier was the best-performing data mining technique when features were selected using correlation-based feature selection with an accuracy rate of (92%).
Volume: 11
Issue: 5
Page: 4587-4596
Publish at: 2021-10-01

Cervical cancer classification using convolutional neural network-support vector machine

10.12928/telkomnika.v19i5.20406
Jane Eva; Universitas Indonesia Aurelia , Zuherman; Universitas Indonesia Rustam , Ilsya; Universitas Indonesia Wirasati
Cervical cancer is the second most common cancer in women worldwide, and occurs when there are presences of abnormal cells in the cervix, which continue to grow uncontrollably. In the early stages, cervical cancer indications are not perceptible; however, it is easily detected with different forms of machine learning methods, such as the convolutional neural network (CNN). This is a popular method with a wide range of applications and known for its high accuracy value. Moreover, there is a support vector machine (SVM) with several kernel functions that is commonly used in the classification of diseases, and also known for its high accuracy value. Therefore, the combination of CNN–SVM with several linear kernels functions as classifier for the categorization of cervical cancer.
Volume: 19
Issue: 5
Page: 1605-1611
Publish at: 2021-10-01

Analysis of frequent itemset generation based on trie data structure in Apriori algorithm

10.12928/telkomnika.v19i5.19273
Ade; Politeknik Negeri Bandung Hodijah , Urip Teguh; Politeknik Negeri Bandung Setijohatmo
Apriori is one technique of data mining association rules that aims to extract correlations between sets of items in the transaction database. The main problem with the Apriori algorithm is the process of scanning databases repeatedly to generate itemset candidates. This research examines the combination of pruning by using the trieapproach and multi-thread implementation in three algorithms to obtain frequent itemset. Trie is a data structure in the form of an ordered tree to store a set of strings where every node in the tree contains the same prefix. The use of a full combination trie (different from frequent pattern (FP) tree using links) allows the implementation of arrays and the hash calculation to achieve the addressing of itemset combination. In this research, the measure to get the address is called Hash-node calculation used to update support value. For these three alternatives, run time processing is analyzed based on the number of itemset combinations and transaction data at a certain minimum support value. The experimental results show that an algorithm thatexploits resource capabilities by applying multi-threadperforms almost seven times betterthanan algorithm implemented in single-thread in calculating hash-node. The fastest run time of the multi-thread approach is 43 minutes with 150-itemset combinations on 100,000 transaction data.
Volume: 19
Issue: 5
Page: 1553-1564
Publish at: 2021-10-01

Proportional fair buffer scheduling algorithm for 5G enhanced mobile broadband

10.11591/ijece.v11i5.pp4165-4173
Asmae Mamane , M. Fattah , M. El Ghazi , Y. Balboul , M. El Bekkali , S. Mazer
The impending next generation of mobile communications denoted 5G intends to interconnect user equipment, things, vehicles, and cities. It will provide an order of magnitude improvement in performance and network efficiency, and different combinations of use cases enhanced mobile broadband (eMBB), ultra reliable low latency communications (URLLC), massive internet of things (mIoT) with new capabilities and diverse requirements. Adoption of advanced radio resource management procedures such as packet scheduling algorithms is necessary to distribute radio resources among different users efficiently. The proportional fair (PF) scheduling algorithm and its modified versions have proved to be the commonly used scheduling algorithms for their ability to provide a tradeoff between throughput and fairness. In this article, the buffer status is combined with the PF metric to suggest a new scheduling algorithm for efficient support for eMBB. The effectiveness of the proposed scheduling strategy is proved through à comprehensive experimental analysis based on the evaluation of different quality of service key performance indicators (QoS KPIs) such as throughput, fairness, and buffer status.
Volume: 11
Issue: 5
Page: 4165-4173
Publish at: 2021-10-01

Incident forecasting model for motorcycle driving based on IoT and artificial intelligence

10.11591/ijeecs.v24.i1.pp444-451
Esteban Alejandro Cárdenas-Lancheros , Nelson Enrique Vera-Parra
Internet of things (IoT) and artificial intelligence provide more and more solutions to the exercise of capturing data effectively, taking them through processing and analysis stages to extract valuable information. Currently, technological tools are applied to counteract incidents in motorcycle driving, whether they are part of the same vehicle or are externally involved in the environment. Incidents in motorcycle driving are increasing due to the demand for the acquisition of these vehicles, which makes it important to generate an approach towards reducing the risk of road accidents based on the analysis of dynamic behavior while driving. The development of this research began with the detection and storage of data associated with the dynamic acceleration variable of a motorcycle while driving, this with the help of a 3-axis accelerometer sensor generating a dataset, which was processed and analyzed for later be taken by three predictive classification models based on machine learning which were decision trees, K-Nearest neighbors and random forests. The performance of each model was evaluated in the task of better classifying the level of accident risk, concerning the driving style based on certain levels of acceleration. The random forest model showed a slightly better performance compared to that shown by the other two models, with 97.24% accuracy and recall, 97.16% precision and 97.17% F1 score.
Volume: 24
Issue: 1
Page: 444-451
Publish at: 2021-10-01

Role of artificial intelligence in cloud computing, IoT and SDN: Reliability and scalability issues

10.11591/ijece.v11i5.pp4458-4470
Mohammad Riyaz Belgaum , Zainab Alansari , Shahrulniza Musa , Muhammad Mansoor Alam , M. S. Mazliham
Information technology fields are now more dominated by artificial intelligence, as it is playing a key role in terms of providing better services. The inherent strengths of artificial intelligence are driving the companies into a modern, decisive, secure, and insight-driven arena to address the current and future challenges. The key technologies like cloud, internet of things (IoT), and software-defined networking (SDN) are emerging as future applications and rendering benefits to the society. Integrating artificial intelligence with these innovations with scalability brings beneficiaries to the next level of efficiency. Data generated from the heterogeneous devices are received, exchanged, stored, managed, and analyzed to automate and improve the performance of the overall system and be more reliable. Although these new technologies are not free of their limitations, nevertheless, the synthesis of technologies has been challenged and has put forth many challenges in terms of scalability and reliability. Therefore, this paper discusses the role of artificial intelligence (AI) along with issues and opportunities confronting all communities for incorporating the integration of these technologies in terms of reliability and scalability. This paper puts forward the future directions related to scalability and reliability concerns during the integration of the above-mentioned technologies and enable the researchers to address the current research gaps.
Volume: 11
Issue: 5
Page: 4458-4470
Publish at: 2021-10-01

Formal security analysis of lightweight authenticated key agreement protocol for IoT in cloud computing

10.11591/ijeecs.v24.i1.pp621-636
Ahmed H. Aly , Atef Ghalwash , Mona M. Nasr , Ahmed A. Abd-El Hafez
The internet of things (IoT) and cloud computing are evolving technologies in the information technology field. Merging the pervasive IoT technology with cloud computing is an innovative solution for better analytics and decision-making. Deployed IoT devices offload different types of data to the cloud, while cloud computing converges the infrastructure, links up the servers, analyzes information obtained from the IoT devices, reinforces processing power, and offers huge storage capacity. However, this merging is prone to various cyber threats that affect the IoT-Cloud environment. Mutual authentication is considered as the forefront mechanism for cyber-attacks as the IoT-Cloud participants have to ensure the authenticity of each other and generate a session key for securing the exchanged traffic. While designing these mechanisms, the constrained nature of the IoT devices must be taken into consideration. We proposed a novel lightweight protocol (Light-AHAKA) for authenticating IoT-Cloud elements and establishing a key agreement for encrypting the exchanged sensitive data was proposed. In this paper, the formal verification of (Light-AHAKA) was presented to prove and verify the correctness of our proposed protocol to ensure that the protocol is free from design flaws before the deployment phase. The verification is performed based on two different approaches, the strand space model and the automated validation of internet security protocols and applications (AVISPA) tool.
Volume: 24
Issue: 1
Page: 621-636
Publish at: 2021-10-01

p-norms of histogram of oriented gradients for X-ray images

10.11591/ijece.v11i5.pp4423-4430
Nuha H. Hamada , Faten F. Kharbat
Lebesgue spaces (Lp over Rn) play a significant role in mathematical analysis. They are widely used in machine learning and artificial intelligence to maximize performance or minimize error. The well-known histogram of oriented gradients (HOG) algorithm applies the 2-norm (Euclidean distance) to detect features in images. In this paper, we apply different p-norm values to identify the impact that changing these norms has on the original algorithm. The aim of this modification is to achieve better performance in classifying X-ray medical images related to of COVID-19 patients. The efficiency of the p-HOG algorithm is compared with the original HOG descriptor using a support vector machine implemented in Python. The results of the comparisons are promising, and the p-HOG algorithm shows greater efficiency in most cases.
Volume: 11
Issue: 5
Page: 4423-4430
Publish at: 2021-10-01

Quantitative approach for reclassification of the spatial cluster of archipelagos in Maluku Province for the basis of forest development

10.12928/telkomnika.v19i5.17041
Patrich; IPB University Papilaya , Endang; IPB University Suhendang , I Nengah Surati; IPB University Jaya , Teddy; IPB University Rusolono
In natural resource management, it is necessary to group regions based on the similarity of their spatial and non-spatial characteristics, to efficiency and effectiveness Therefore, this study describes the re-grouping of the twelve island clusters established by the provincial government of Maluku into more homogeneous classes. The re-grouping was carried out based on the biophysical conditions of the regions, therefore, it could be used as the basis for determining the forest management units. The results showed that the twelve designated island clusters could be simplified to eight more homogeneous island clusters with 86.4% accuracy and 82.2 validation. It also showed that there were thirteen significant changes in the grouping of clusters of the island, including the horticultural crop area (Bf) and horticultural crop production (E). Moreover, when the island cluster is reclassified into 5 classes, the grouping would be more accurate, with 94.9% accuracy and 92.4% validation. This study concludes that there are two dominant factors in the classification of the island cluster in Maluku province namely, biophysical and social.
Volume: 19
Issue: 5
Page: 1654-1664
Publish at: 2021-10-01
1 2 3
...
1995 1996
Show 907 of 1996

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