Corn Disease Classification Using Transfer Learning and Convolutional Neural Network

Indonesia is an agricultural country with abundant agricultural products. One of the crops used as a staple food for Indonesians is corn. This corn plant must be protected from diseases so that the quality of corn harvest can be optimal. Early detection of disease in corn plants is needed so that farmers can provide treatment quickly and precisely. Previous research used machine learning techniques to solve this problem. The results of the previous research were not optimal because the amount of data used was slightly and less varied. Therefore, we propose a technique that can process lots and varied data, hoping that the resulting system is more accurate than the previous research. This research uses transfer learning techniques as feature extraction combined with Convolutional Neural Network as a classification. We analysed the combination of DenseNet201 with a Flatten or Global Average Pooling layer. The experimental results show that the accuracy produced by the combination of DenseNet201 with the Global Average Pooling layer is better than DenseNet201 with Flatten layer. The accuracy obtained is 93% which proves the proposed system is more accurate than previous studies.

Pillar Algorithm in K-Means Method for Identification Health Human Resources Availability Profile in Central Java

Based on data from the Ministry of Health, the distribution ratio between health workers and patients in Indonesia is still not equal distributed. It influenced by the distribution of health human resources that are not in accordance with the ideal needs of health services. This results need to identify the profile of the availability of health human resources in Indonesia. In this study, an approach will be implemented to identify the profile of health human resources availability using K-Means Clustering with a combination of pillar algorithms in optimizing the selection of the initial cluster centroid. Chi-square analysis is used to determine the disparity in the needs of health human resources with the conditions of the availability of health human resources in the Central Java region. The data collection method used in this research is the observation method, while the scientific method used in this research is the K-Means Clustering method. The results showed that the application has been generated can dynamically determine the health human resource cluster based on the disparity category of health human resource availability in the Central Java region. In addition, the labeling of the Pillar K-Means cluster based on the Chi-square test has a high degree of accuracy, namely 80%.

Development of Cloud-Based Co-Parenting Strengthening System

Co-parenting emphasizes how couple manage their relationship in the parenting domains and carry out their role as parents. Based on research conducted by Feinberg and colleagues (2012), there are four overlapping domains of co-parenting: (1) child rearing agreement; (2) support/undermining partner’s parenting; (3) joint family management; and (4) division of labor. The interference of mobile-based technology is needed on the co-parenting relationship between the couple with reference to the four domains of co-parenting. The method used was the Systems Development Life Cycle (SDLC) model. It was divided into six stages of the process: requirement analysis, system design, implementation, system testing, system deployment, and system maintenance. In implementation, the system at an early stage has four main features: (1) child’s activity scheduling and reminder; (2) co-parenting’s education contents; (3) partner’s feedback; and (4) co-parenting’s assessment. The results that are proven by experts, agreed that educational content in the application is very necessary for more knowledge for parents, UI/UX design that is friendly and easy to understand by users, as well as the use of the latest reliable and flexible technology.

Performance Evaluation of Digital Image Processing by Using Scilab

Scilab is an open-source, cross-platform computational environment software available for academic and research purposes as a free of charge alternative to the matured computational copyrighted software such as MATLAB. One of important library available for Scilab is image processing toolbox dedicated solely for image and video processing. There are three major toolboxes for this purpose: Scilab image processing toolbox (SIP), Scilab image and video processing toolbox (SIVP) and recently image processing design toolbox (IPD). The target discussion in this paper is SIVP due to its vast use out there and its capability to handle streaming video file as well (note that IPD also supports video processing). Highlight on the difference between SIVP and IPD will also be discussed. From testing, it is found that in term of looping test, Octave and FreeMat are faster than Scilab. However, when converting RGB image to grayscale image, Scilab outperform Octave and FreeMat.

Morphogenesis Analysis for Digital Image Production with L-System

The process of forming an image requires a correct color composition, location and distance between the lines to produce a good image. Human abilities in both creativity and high imagination are very limited, especially in forming new images by utilizing existing image patterns or images that resemble old images. Here we showed the implementation of L-System to generate new image generations with additional flame as a fire effect/glow on images for image transformation. This research used the L-System algorithm, Iterated Function System, and Voronoi Diagram to improve the result of image transformation. The results of this study indicated that mathematical calculations can be applied in the formation of images and the resulting images can be abstract and symmetrical. The next generation of images produced in this research can be in unlimited numbers as the generation of morphogenesis processes. The process of generating images is carried out randomly by merging the two existing images with morphogenesis analogy. The resulting images can be exported into jpg, png, and svg formats. Furthermore, this research showed that the implementation of the calculation for the variation reach the value of 99.48% while the image variation composition has a value of 99.29%.

Performance Evaluation of Contract Employees Using the Best-Worst and Simple Additive Weighting Methods

All companies need qualified employees to ensure the continuity and progress of the company. Therefore, some companies are very selective in evaluating employee performance based on the criteria set by the company. However, because of the many criteria used in the assessment, a large number of contract employees to be evaluated, and the evaluation that must be proportional, the Human Resources department has difficulty evaluating the performance of contract employees. Therefore, this study aimed to develop a system for evaluating the performance of contract employees by integrating the Best-Worst (BW) and Simple Additive Weight (SAW) methods. The BW method is used to determine the weight of each criterion related to the performance appraisal of contract employees, and the SAW method is used to evaluate the performance of contract employees. The results showed that the system developed can provide a more proportional evaluation. So, this study contributes as a recommendation system for HR managers in determining eligible contract employees to have their work contracts extended based on criteria determined by the company.

Real-time Vehicle Surveillance System Based on Image Processing and Short Message Service

This paper proposes a real-time vehicle surveillance system based on image processing approach tailored with short message service. A background subtraction, color balancing, chain code based shape detection, and blob filtering are used to detect suspicious moving human around the parked vehicle. Once detected, the developed system will generate a warning notification to the owner by sending a short message to his mobile phone. The current frame of video image will also be stored and be sent to the owner e-mail for further checking and investigation. Last stored image will be displayed in a centralized monitoring website, where the status of the vehicle also can be monitored at the same time. When necessary, the stored images can be used during investigation process to assist the authority to take further legal actions.

Flower Pollination Algorithm for Software Effort Coefficients Optimization to Improve Effort Estimation Accuracy

Software effort estimation is one of important area in project management which used to predict effort for each person to develop an application. Besides, Constructive Cost Model (COCOMO) II is a common model used to estimate effort estimation. There are two coefficients in estimating effort of COCOMO II which highly affect the estimation accuracy. Several methods have been conducted to estimate those coefficients which can predict a closer value between actual effort and predicted value. In this paper, a new metaheuristic algorithm which is known as Flower Pollination Algorithm (FPA) is proposed in several scenario of iteration. Besides, FPA is also compared to several metaheuristic algorithm, namely Cuckoo Search Algorithm and Particle Swarm Optimization. After evaluated by using Mean Magnitude of Relative Error (MMRE), experimental results show that FPA obtains the best result in estimating effort compared to other algorithms by reached 52.48% of MMRE in 500 iterations.

Naïve Bayes for Detecting Student’s Learning Style Using Felder-Silverman Index

This paper focuses on detecting student learning styles using the Felder-Silverman Index Learning Style (FSLM). Providing Adaptivity based on learning styles can support students and make the learning process easier for them. However, the student learning styles need to be identified and understood to provide the appropriate adaptability. In this case, we use a questionnaire instrument to detect student’s learning styles. This paper analyses of students from Professional Education Teacher (PPG) at the Ministry of Research, Technology, and Higher Education (Kemenristek DIKTI). The results show that 1998 students who filled out the questionnaire obtained the following conclusions for each zone with a balanced learning style about 29.9% for dimension processing, 34.78% for input dimension, and 36.98% for understanding dimension. However, most students have a moderate sensing learning style with 31.13% for each zone for the dimension of perception. This research contributes to some areas, such as providing FSLSM learning style with a large dataset and capturing students' learning styles based on four dimensions.

Ethnosciences Based Augmented Reality on Botanical Garden

Ethnosciences in natural knowledge needs to be developed as a learning material and insight. In the field of education, ethnoscience is not optimal if it is applied in theory or books. Along with the times, the theory of ethnoscience will be displaced by modern technology, therefore the means of knowledge need to be upgraded to more advanced media to gain new experiences, especially for future generations. Researchers are looking for an ethnoscience approach in the field of technology by taking samples of observations of plant species in the Botanical Gardens. The technology used to develop this media is Markerless Augmented Reality based on Android applications. Researchers use 3D plant model objects from plant species in functions for the environment, including: Waste particle absorbing plants; CO2-absorbing and O2-producing plants; Odor-absorbing/removing plants; Plants to deal with flooding; Absorbent/odor depressant plants; Plants to overcome inundation, Groundwater conservation plants; Beach safety and abrasion plants. The results of the implementation and testing of the application are built and run with the android.apk device. This application is called EARBot (Ethnoscience Based Augmented Reality on Botanical Garden) which is an educational application of knowledge about ethnoscience that uses Markerless Augmented Reality technology.