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

A performance evaluation of convolutional neural network architecture for classification of rice leaf disease

10.11591/ijai.v10.i4.pp1069-1078
Afis Julianto , Andi Sunyoto
Plant disease is a challenge in the agricultural sector, especially for rice production. Identifying diseases in rice leaves is the first step to wipe out and treat diseases to reduce crop failure. With the rapid development of the convolutional neural network (CNN), rice leaf disease can be recognized well without the help of an expert. In this research, the performance evaluation of CNN architecture will be carried out to analyze the classification of rice leaf disease images by classifying 5932 image data which are divided into 4 disease classes. The comparison of training data, validation, and testing are 60:20:20. Adam optimization with a learning rate of 0.0009 and softmax activation was used in this study. From the experimental results, the InceptionV3 and InceptionResnetV2 architectures got the best accuracy, namely 100%, ResNet50 and DenseNet201 got 99.83%, MobileNet 99.33%, and EfficientNetB3 90.14% accuracy.
Volume: 10
Issue: 4
Page: 1069-1078
Publish at: 2021-12-01

Web-based software application design for solar PV system sizing

10.12928/telkomnika.v19i6.21666
Lambe Mutalub; Kwara State University Adesina , Olalekan; Kwara State University Ogunbiyi , Mustapha; Kwara State University Mubarak
The solar photovoltaic (PV) energy source systems generally rely on the availability of sunlight, its duration, and the capacity of storage devices if it is not a grid-tie system. The components of the PV sources come in different sizes and capacities, depending on the various applications and available products in the market. Therefore, sizing of PV components becomes important to the functionality and reliability of solar PV sources. This work is aimed at the development of a web-based software application designed for sizing the capacity of solar PV source components that meet required energy demand. A description of photovoltaic system components, available types, and sizing techniques are discussed. Parameter evaluation algorithms with flowcharts were developed for PV components. Consequently, web-based software was developed and simulated for a different case study. The results described the estimated load, average daily load, ratings of PV system components such as inverter, battery, solar panel, and charge controller. The cost estimates of each component, the total estimated cost of the project, and the specification of components’ purchasing store are similarly presented. Thus, the developed application can be applied to size different ranges of microgrid systems meant for several applications.
Volume: 19
Issue: 6
Page: 2009-2019
Publish at: 2021-12-01

An overview of information extraction techniques for legal document analysis and processing

10.11591/ijece.v11i6.pp5450-5457
Ashwini V. Zadgaonkar , Avinash J. Agrawal
In an Indian law system, different courts publish their legal proceedings every month for future reference of legal experts and common people. Extensive manual labor and time are required to analyze and process the information stored in these lengthy complex legal documents. Automatic legal document processing is the solution to overcome drawbacks of manual processing and will be very helpful to the common man for a better understanding of a legal domain. In this paper, we are exploring the recent advances in the field of legal text processing and provide a comparative analysis of approaches used for it. In this work, we have divided the approaches into three classes NLP based, deep learning-based and, KBP based approaches. We have put special emphasis on the KBP approach as we strongly believe that this approach can handle the complexities of the legal domain well. We finally discuss some of the possible future research directions for legal document analysis and processing.
Volume: 11
Issue: 6
Page: 5450-5457
Publish at: 2021-12-01

On the evaluation of the IEEE 802.11ac WLAN performance with QoS deployment

10.11591/ijeecs.v24.i3.pp1618-1627
Ziyad Khalaf Farej , Omer Mohammed Ali
The increase in the number of users on wireless local area networks (WLAN) and the development of large size applications have increased the demand for high-speed data rate and low latency. The IEEE 802.11ac was developed to provide very high throughput WLANs. Many enhancements are added to the medium access control (MAC) and physical (PHY) layers to increase data rate and improve network performance, these features enable the IEEE 802.11ac standard to provide quality of service (QoS) for multimedia applications. This paper concentrates on the impact of QoS on the system performance in term of delay and throughput. Four scenarios are proposed to investigate the network performance with different (from 1 up to 8) spatial stream (SS). The objective modular network testbed in C++ (OMNet++ modeler v5.5.1) is used to simulate and model these scenarios. For 8×8 SS, the results of simulation show the best throughput (maximum) and delay (minimum) values of (622, 484, 399.3, 382.96 Mbps) and (0.0211, 0.0589, 0.1037, 0.1202 sec) for 5, 15, 30 and 45 node number scenarios respectively. Although the number of nodes increases, the system performance decreases, however when QoS is deployed the performance is enhanced and its best improvement is obtained at the highest (45) node number scenario with values of 94.4% and 56.1% for throughput and delay respectively.
Volume: 24
Issue: 3
Page: 1618-1627
Publish at: 2021-12-01

Larvicidal activity of granulated pharmaceutical products using Indonesian holy basil leaf extract

10.11591/ijphs.v10i4.21004
Azis Ikhsanudin , Lolita Lolita , Zayyana Septya Ramadani
Ocimum sanctum Linn, known as holy basil, is a larvicide, which is relatively safe compared to synthetic insecticides. This study investigates the larvicidal activity of a granule formulation of Indonesian holy basil leaf extract against third larval instar of Aedes aegypti. The extract of holy basil leaves was obtained by a maceration process with 96% ethanol. The granule was formulated with various concentrations of holy basil leaf extract, including F1 (2000 ppm), F2 (4000 ppm), and F3 (6000 ppm). The extract contained terpenoid, alkaloid, saponin, flavonoid, and polyphenol compounds. The extract granules had a moisture content of 3.01%, flowability of 1.51 seconds, and dispersion time of 1.09 seconds. The mortality rates of mosquitos treated with the different formulation groups were significantly different from positive control with values of 25.33% (F1), 50.67% (F2), and 90.67% (F3). In conclusion, the granulated formulation of holy basil leaf extract has a larvicidal LC50 of 4405.803 ppm and LC90 of 6080.714 ppm. Therefore, a granulated pharmaceutical product derived from holy basil leaf extract could be developed as a potent larvicide to control dengue fever.
Volume: 10
Issue: 4
Page: 934-941
Publish at: 2021-12-01

Mode NASA blade used to calculate the power generator for (VAWT) by drag and lift coefficients

10.12928/telkomnika.v19i6.17074
Ibrahim Amer; University of Baghdad Ibrahim , Mohammed Saeed; Middle Technical University Mohammed , A.; South Ural State University (SUSU) Ibrahim , O. J.; South Ural State University (SUSU) Abdalgbar
One of the confrontations with increasing demand on power in the entire world the methodologies of provided power divided into traditional methods against renewable methods. This article presents a simulation model to estimate the integrated power from vertical access wind turbine (VAWT) stages of development of a simulation model of local power supply system (LPSS) with (VAWT). However, wind power is one of the quickest developing advances for the sustainable power age. Disturbingly, in the ongoing years a few instances of corruption on telecommunication systems frameworks have emerged because of the presence of wind ranches, and costly and in fact complex restorative estimations needed. The grade of variation of power verified according to the grid size. The parameters were taken in the study through the preparation of the model are (efficiency, cost, and system response) compared to the benefits against disadvantages when combining the two systems to achieve a high performance of the power stability.
Volume: 19
Issue: 6
Page: 1992-1999
Publish at: 2021-12-01

Distributed reflection denial of service attack: A critical review

10.11591/ijece.v11i6.pp5327-5341
Riyadh Rahef Nuiaa , Selvakumar Manickam , Ali Hakem Alsaeedi
As the world becomes increasingly connected and the number of users grows exponentially and “things” go online, the prospect of cyberspace becoming a significant target for cybercriminals is a reality. Any host or device that is exposed on the internet is a prime target for cyberattacks. A denial-of-service (DoS) attack is accountable for the majority of these cyberattacks. Although various solutions have been proposed by researchers to mitigate this issue, cybercriminals always adapt their attack approach to circumvent countermeasures. One of the modified DoS attacks is known as distributed reflection denial-of-service attack (DRDoS). This type of attack is considered to be a more severe variant of the DoS attack and can be conducted in transmission control protocol (TCP) and user datagram protocol (UDP). However, this attack is not effective in the TCP protocol due to the three-way handshake approach that prevents this type of attack from passing through the network layer to the upper layers in the network stack. On the other hand, UDP is a connectionless protocol, so most of these DRDoS attacks pass through UDP. This study aims to examine and identify the differences between TCP-based and UDP-based DRDoS attacks.
Volume: 11
Issue: 6
Page: 5327-5341
Publish at: 2021-12-01

Comparison of the feature selection algorithm in educational data mining

10.12928/telkomnika.v19i6.21594
Agung; Universitas Nasional Triayudi , Iskandar; Universitas Nasional Fitri
Student academic accomplishment is the foremost focus of every educational institution. In developing student achievement in educational institutions, the researchers finally created a new research area, namely educational data mining (EDM). How the Feature Selection algorithm works is by removing unrelated data from educational datasets; therefore, this algorithm can improve the classification performance managed in EDM techniques. This research presents an analysis of the performance of the Feature Selection (FS) algorithm from the student dataset. The results received from other FS algorithms and classifiers will help other researchers to gain some best combination regarding Feature Selection algorithms and the classification. Selecting features that are relevant for student forecast models is a sensitive problem to stakeholders in education because they must make decisions based on the results of the prediction models. For the future, our paper seeks to play a decisive part while developing quality concerning education, as well as guiding different researchers in conducting educational interventions.
Volume: 19
Issue: 6
Page: 1865-1871
Publish at: 2021-12-01

A systematic literature review of machine learning methods in predicting court decisions

10.11591/ijai.v10.i4.pp1091-1102
Nur Aqilah Khadijah Rosili , Noor Hidayah Zakaria , Rohayanti Hassan , Shahreen Kasim , Farid Zamani Che Rose , Tole Sutikno
Envisaging legal cases’ outcomes can assist the judicial decision-making process. Prediction is possible in various cases, such as predicting the outcome of construction litigation, crime-related cases, parental rights, worker types, divorces, and tax law. The machine learning methods can function as support decision tools in the legal system with artificial intelligence’s advancement. This study aimed to impart a systematic literature review (SLR) of studies concerning the prediction of court decisions via machine learning methods. The review determines and analyses the machine learning methods used in predicting court decisions. This review utilised RepOrting Standards for Systematic Evidence Syntheses (ROSES) publication standard. Subsequently, 22 relevant studies that most commonly predicted the judgement results involving binary classification were chosen from significant databases: Scopus and Web of Sciences. According to the SLR’s outcomes, various machine learning methods can be used in predicting court decisions. Additionally, the performance is acceptable since most methods achieved more than 70% accuracy. Nevertheless, improvements can be made on the types of judicial decisions predicted using the existing machine learning methods.
Volume: 10
Issue: 4
Page: 1091-1102
Publish at: 2021-12-01

Low-cost wireless mesh communications based on openWRT and voice over internet protocol

10.11591/ijece.v11i6.pp5119-5126
Nina Siti Aminah , Muhamamad Reza Ramadhani Raharjo , Maman Budiman
Technology makes it easier for us to communicate over a distance. However, there are still many remote areas that find it difficult to communicate. This is due to the fact that communication infrastructure in some areas is expensive to build while the profit will be low. This paper proposes to combine voice over internet protocol (VoIP) over mesh network implemented on openWRT router. The routers are performing mesh functions. We set up a VoIP server on a router and enabled session initiation protocol (SIP) clients on other routers. Therefore, we only need routers as a means of communication. The experiment showed very good results, in the line-of-sight (LOS) condition, they are limited to reception distances up to 145 meters while in the non-line-of-sight (NLOS) condition, they are limited to reception distances up to 55 meters.
Volume: 11
Issue: 6
Page: 5119-5126
Publish at: 2021-12-01

Analysis the digital images by using morphology operators

10.11591/ijeecs.v24.i3.pp1654-1662
Hadeel Amjed Saeed , Sumaya Hamad , Azmi Tawfik Hussain
In this paper, we deal with morphology images that try to improve the use of images. On the one hand, the process is used to obtain the histogram of the image then converted it into a non-color image (gray scale). The next step is to perform the erosion, dilation, open and close operations on the images, how these methods have important effects, and how can be used on a variable number of images, and found the differences between them. These operations were applied on four different images, check images, four basic operations (dilation, erosion, open and close) for each image were performed. Then, retrieving process to the original state of the image (the colored copy) was applied. The results found that retrieving the original images is difficult, and there is the occurrence of some noises on the image when it was retrieved. Finally, conclusions of the work are presented.
Volume: 24
Issue: 3
Page: 1654-1662
Publish at: 2021-12-01

Blockchain-based adoption framework for authentic land registry system in Malaysia

10.12928/telkomnika.v19i6.19276
Abdulaziz; University of Kuala Lumpur Aborujilah , Muhammad Naqib Bin Mohd; University of Kuala Lumpur Yatim , Abdulaleem; University of Kuala Lumpur Al-Othmani
Land registration systems are very essential for property ownership management. The exited land registry systems are less efficient and time-consuming and expose to human errors. By using blockchain technology, most of the principles of good governance in land administration such as transparency and efficiency can be fulfilled. However, there is a lack of experience in developing blockchain-based land registry systems. This paper proposes a blockchain-based adoption framework for land registry management in Malaysia. It elaborates more on developing a prototype that fulfills the main functions of current land registration by using smart contract functionalities. Also, this paper illustrates the main challenges of adopting this technology such as expertise shortage of software developers, implementation difficulties due to scalability of the land transactions, data sharing with different types of blockchain and lack of security attacks resistance. Therefore, there is a need to form an agreed-upon blockchain development platform that meet such constraints.
Volume: 19
Issue: 6
Page: 2038-2049
Publish at: 2021-12-01

Non-linear creep of polypropylene utilizing multiple integral

10.11591/ijaas.v10.i4.pp288-296
Mahmoud Fadhel Idan
Multiple integral representation (MIR) has been used to represent studying the effect of temperature on the amount of nonlinear creep on the semi-crystalline polypropylene (PP) under the influence of axial elastic stress. To complete this research, the kernel functions were selected, for the purpose of performing an analogy, and for arranging the conditions for the occurrence of the first, second and third expansion in a temperature range between 20 °C-60 °C, i.e., between the glass transition and softening temperatures, within the framework of the energy law. It was observed that the independent strain time increased non-linearly with increasing stress and non-linearly decreased with increase in temperature, although the time parameter increased non-linearly with stress and temperature directly. In general, a very satisfactory agreement between theoretical and practical results on the MIR material was observed.
Volume: 10
Issue: 4
Page: 288-296
Publish at: 2021-12-01

SAFEA application design on determining the optimal order quantity of chicken eggs based on fuzzy logic

10.11591/ijai.v10.i4.pp858-871
Sesar Husen Santosa , Agung Prayudha Hidayat , Ridwan Siskandar
The availability of stock in the chicken egg supply chain is influenced by the ability of egg Agents to determine the optimal orders to suppliers. The optimal number of orders is very important to manage for the Bogor City Egg Agent Indonesia because the stock capacity reaches 340 crates. The optimal number of orders for eggs at the Egg Agent is influenced by input variables, namely final stock (crate), selling price (crate), and consumer demand (crate) so that the inventory is under control. The three input variables have fuzzy values that must be processed using fuzzy logic to get the optimal number of orders to suppliers so that the egg stock in the warehouse is well maintained. The optimal order model for eggs in the smart application for egg agent (SAFEA) was developed using a fuzzy logic approach with the triangular and trapezoidal membership function. Based on the optimal order model in the SAFEA application, the optimal order to the supplier is 100-104 crates per day.
Volume: 10
Issue: 4
Page: 858-871
Publish at: 2021-12-01

Medical crisis during pandemic: Career preferences change in medical student

10.11591/ijere.v10i4.21897
Dian Natalia , Rizma Adlia Syakurah
The COVID-19 pandemic is a major threat to global education. Incidental emotions of fear and anxiety during pandemic have unconsciously influenced preference and outcome about their future career. This study aimed to assess the effect of the COVID-19 pandemic towards career preference change in medical students. A total of 1,027 responses from all over the medical students in Indonesia were collected from an online questionnaire which was broadcasted through social media from 14th July 2020–21st July 2020. This study was using Fear of COVID-19 Scale (FCV-19S) and Depression Anxiety Stress-Scale-21 (DASS-21) to assess fear of COVID-19, stress, anxiety, and depression. Out of 1,027 respondents, 44.6% had stressed, 47.8% had anxiety, and 18.5% had depression with an average FCV-19S score was 17.1. The result showed that the fear and anxiety of COVID-19 during the pandemic had associated significantly with the career decisions in medical students (p=<0.05). Indonesian policymakers had to keep in mind that the fear of the COVID-19 pandemic in medical students is due to the high mortality COVID-19 cases of health workers in Indonesia. Health workers need adequate working conditions and specific protection, this requires prompt attention from stakeholders.
Volume: 10
Issue: 4
Page: 1255-1261
Publish at: 2021-12-01
1 2 3
...
1995 1996
Show 887 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