Journal of ICT Research and Applications

Prediction of On-time Student Graduation with Deep Learning Method

Nathanael Victor Darenoh, Fitra Abdurrachman Bachtiar, Rizal Setya Perdana — Thu, 27 Jun 2024 00:00:00 +0700

Universities have an important role in providing quality education to their students so they can build a foundation for their future. However, a problem that often arises is that the process experienced will be different for each individual. Therefore, it is necessary to apply on-time graduation predictions for students with academic attributes in the hope that educational institutions can better understand student conditions and maximize on-time student graduation. In this study, a deep learning method was implemented to help predict on-time graduation for students at the Faculty of Computer Science, University of Brawijaya. Based on the test results and hyperparameter tuning using Optuna, the best hyperparameter configuration for the deep learning method consisted of number of layer combinations = 4; first-layer nodes = 118; first dropout = 0.3393; second-layer nodes = 83; second dropout = 0.0349; third-layer nodes = 88; third dropout = 0.0491; fourth-layer nodes = 65; fourth dropout = 0.4169; number of epochs = 244; learning rate = 0.0710; and optimizer = SGD. Thus, an accuracy rate of 86.61% was achieved for the two classes of the test data set, i.e., on-time graduation and not on-time graduation.

Skin Lesion Segmentation for Melanoma Using Dilated DenseUNet

Ammar Al-Zubaidi, Mohammed Al-Mukhtar, Mina H. Al-hashimi, Haris Ijaz — Thu, 27 Jun 2024 00:00:00 +0700

Melanoma, a highly malignant form of skin cancer, affects individuals of all genders and is associated with high mortality rates, especially in advanced stages. The use of tele-dermatology has emerged as a proficient diagnostic approach for skin lesions and is particularly beneficial in rural areas with limited access to dermatologists. However, accurately, and efficiently segmenting melanoma remains a challenging task due to the significant diversity observed in the morphology, pigmentation, and dimensions of cutaneous nevi. To address this challenge, we propose a novel approach called DenseUNet-169 with a dilated convolution encoder-decoder for automatic segmentation of RGB dermascopic images. By incorporating dilated convolution, our model improves the receptive field of the kernels without increasing the number of parameters. Additionally, we used a method called Copy and Concatenation Attention Block (CCAB) for robust feature computation. To evaluate the performance of our proposed framework, we utilized the International Skin Imaging Collaboration (ISIC) 2017 dataset. The experimental results demonstrate the reliability and effectiveness of our suggested approach compared to existing methodologies. Our framework achieved a high level of accuracy (98.38%), precision (96.07%), recall (94.32%), dice score (95.07%), and Jaccard score (90.45%), outperforming current techniques.

Performance Evaluation of Fractal Wavelet Packet Transform on Wireless Communication Systems

Mohammad Ridwan Effendi, Rheyuniarto Sahlendar Asthan, Achmad Munir — Thu, 27 Jun 2024 00:00:00 +0700

The performance of the phase shift keying (PSK) modulation technique over additive white Gaussian noise (AWGN) and multipath propagation channels generally becomes worse for higher-order modes. Therefore, a new modulation technique should be provided in order to have a system that is capable of transmitting data with higher efficiency while maintaining better performance at the same time. This paper presents the development of a fractal wavelet packet transform incorporated within the M-ary PSK system, namely M-ary PSK orthogonal wavelet division multiplexing (OWDM), which is proposed to obtain high performance of modulation in terms of spectrum efficiency and bandwidth resources intended for wireless communication systems. To demonstrate performance improvement over a Rayleigh frequency selective fading channel and in the presence of AWGN noise, the proposed system was evaluated and compared to the basic modulation system and M-ary PSK employing orthogonal frequency division multiplexing (OFDM). The performance results show that M-ary PSK OWDM had better performance in comparison with M-ary PSK OFDM and the conventional system. By utilizing 16 subcarriers, QPSK OWDM achieved bit error rate performance improvement from 1.5 × 10^-3 to 1 × 10^-4for E_b/N₀ of 20 dB with efficient bandwidth.

Investigating the Effect of m-Commerce Application’s Functional and Non-Functional Attributes on Usability and Continuance Intention

Hotma Antoni Hutahaean, Iman Sudirman, Rajesri Govindaraju — Thu, 27 Jun 2024 00:00:00 +0700

The development of mobile commerce (m-commerce) applications has indicated a shift in goals from ease-of-use to sustainable use in the future. This shift has prompted changes in the combination of attributes that constitute the usability of m-commerce applications. This study developed an m-commerce usability model that combines functional and non-functional attributes. The research data was collected using questionnaires distributed to users living in Jakarta and was processed using the Partial Least Squares Structural Equation Modeling (PLS-SEM) technique. The results demonstrate that efficiency, satisfaction, and effectiveness can explain the usability of m-commerce applications. This study proved that three non-functional usability attributes – productivity, navigation, and memorability – have a positive effect on efficiency, while two functional attributes of usability – content and security – positively influence effectiveness. The study further proved that beside non-functional attributes, functional attributes also play an important role in increasing the user experience in the m-commerce context and thereby contribute to improving the usability of m-commerce systems and the continuance intention. The overall results of the study can be used in developing strategies for m-commerce application developers to design applications that can satisfy users and help them complete their tasks correctly and efficiently.

Performance of Interconnected Hybrid ZigBee-Optic for Extended Wireless Sensor Networks

Sun, 30 Jun 2024 00:00:00 +0700

Wireless sensor networks (WSNs) are widely used to monitor remote areas far away from the monitoring center. For large-scale or high-capacity WSNs, when they contain many sensor nodes, a transmission system with low latency and large bandwidth is required. In order to extend the network range, the use of optical communication is one of the alternatives to provide more capacity and a longer range. This study discusses the performance of a range-extended WSN utilizing a hybrid of ZigBee and optic transmission. The performance of the proposed method was evaluated by analyzing the throughput, delay per meter, package loss, and error, which were then compared to a ZigBee-Wifi based system. The experimental results showed that the throughput of the hybrid ZigBee-Fiber Optic (ZigBee FO) system was about 12% greater than that of the ZigBee-Wifi system, and it transmitted the sensor data with a significantly lower delay, reduced by 83%, compared to the ZigBee-Wifi. The package loss and error of ZigBee-FO was 35.7% lower than that of ZigBee-Wifi. Based on these results, the ZigBee-FO WSN has the advantage of significantly improving network performance by reducing the transmission delay, therefore it is beneficial in extending the WSN range.