Publication Search

Detection and identification of plant diseases is critical to the success and efficiency of agricultural production. Plant disease outbreaks are becoming more frequent throughout the world, and the presence of these diseases in cultivated plants has a significant impact on productivity. Therefore, researchers are focusing on developing effective and reliable plant disease detection methods. Thus, farmers can take advantage of early detection of this disease to minimize future losses. This article discusses machine learning approaches as well as decision trees, K-nearest neighbors, naive Bayes, support vector machines (SVM), and random forests for detecting coffee leaf diseases using leaf images. The above-mentioned classifications were researched and compared to determine the most suitable plant disease prediction model with the highest accuracy. Compared with other classification algorithms, the SVM algorithm achieves the highest accuracy of 99.75%. All the models trained above will be used by farmers to quickly identify and classify new diseases in images as a prevention strategy. As a preventive measure, farmers can detect and classify new diseases in images early.

When producing a perfect product, design process namely 2D modeling and 3D drawing, are closely related. The purpose of this study is to design a 3D model of a gun mastering machine product as a fan drive using CAD applications. The method of this study is decision data on API production (analytical product inspection). Measurement of sterling machine degradation using CPK (deviation) received results of -0.97, -0.22, 0.86, 0.11, 0.11 between zero and what indicates this specification. On average, the results of the stirling fluid fluorescent agent measurement are red numbers indicating that the survey dimensions are absent, especially from the basic dimensions of point 4, with samples 2, 3, and 5 exceeding the specified tolerance limits.

Automatic Speech Recognition (ASR) for the Indonesian language faces significant challenges due to high Word Error Rate (WER), especially when using pre-trained models without fine-tuning. This study develops an optimized ASR system using a hybrid cloud architecture that integrates the Faster-Whisper large-v3 engine with advanced audio preprocessing techniques. The system adopts a distributed architecture, with Google Colab (Tesla T4, 15GB VRAM) as the GPU server and Ubuntu 22.04 LTS (8 core, 32GB RAM) as the client. Evaluation was conducted on five Indonesian audio samples covering formal news, informal conversations, and long-duration recordings. The system achieved an 80% success rate in processing, with WER ranging from 27.69% (formal news) to 645.16% (informal conversations). Resource utilization was also efficient, with 21.3% GPU usage and 35.4% RAM usage. Processing time remained stable for normal-sized files but experienced timeouts on large files (>50MB). The results indicate that hybrid cloud architecture is feasible for distributed ASR processing in Indonesian, with several areas still open for optimization toward production deployment.

This paper presents the design and implementation of an automatic Virgin Coconut Oil (VCO) making device using an Arduino Uno microcontroller. Virgin Coconut Oil has gained popularity due to its health benefits and versatile uses in various industries. The traditional process of making VCO involves manual effort and precise timing, which can be tedious and inconsistent. The proposed automated system aims to streamline the VCO production process by integrating sensors, actuators, and a microcontroller to achieve precise control and monitoring of the process variables. The Arduino Uno microcontroller serves as the central unit for data acquisition, processing, and control, facilitating automation through programmed logic. Key components of the automated VCO maker include temperature sensors for monitoring heating stages, a motor for stirring, and relays for controlling heating elements. The system utilizes feedback loops to maintain optimal conditions during each phase of VCO production, ensuring reproducibility and quality. The design also emphasizes user-friendly operation, with an interface that provides real-time feedback on process parameters and allows manual intervention if necessary. Safety features are incorporated to prevent overheating and ensure operational reliability. Overall, the developed automatic VCO maker offers a practical solution to enhance the efficiency and consistency of VCO production, catering to both small-scale producers and commercial enterprises in the food and cosmetic industries

Milk consumption and the need for beef cattle for food purposes or sacrificial purposes continue to increase from year to year. This increase is in line with the increasing level of the economy and awareness of the need for nutritious food. However, the increase in demand still faces many production constraints due to the difficulties faced by farmers, the decline in cattle production from year to year in Indonesia. This causes Indonesia to have to import beef for 35.95% of the total national beef consumption. With many factors that affect the decline in the production rate of dairy cows or beef cattle every year, one of them is air pollution and poor air quality in cages. Along with the development of technology, a monitoring and detection system for air cleanliness in cattle pens was created, using the MQ-7 sensor as the concentration of carbon monoxide, the MQ-135 sensor as the concentration of ammonia gas, the MQ-2 sensor as the smoke detection, and When the air pollution value of each sensor input is according to the air pollution standard index (ISPU), the outputs namely indicator lights, buzzers and blowers will be on, then there will be temporary air neutralization in the cage. This tool is made easier by internet of things technology, so that it can send notifications via telegram and can see the level of air pollution levels through the web.

Hydroponic plant cultivation is booming, but stock and sales are hard to predict. Poor prediction can cause farmers to overstock and lose money. This study suggests a framework that uses several machine learning models, including Linear Regression (LR), Random Forest (RF), Decision Tree (DT), and Extreme Gradient Boosting. "Ensemble Learning," which combines these models, should yield more accurate and generalizable results than a single model. This framework is assessed using historical hydroponic plant sales data and related factors like price, weather, and market trends. The model's performance is measured by the difference between predictions and actual values using RMSE and MAE metrics. This framework should improve hydroponic plant stock and sales predictions. Farmers can make better production, inventory, and harvest distribution decisions. Besides reducing financial losses, this reduces food waste and improves food security.

The combination of activities carried out by humans and technology is related to administrative systems that create information from organized work processes. PT. Farmhouse Production in the administration of data management is carried out with the help of Microsoft Excel and documents are written, and copied in the traditional way which results in the accumulation of accumulated paper resulting in complexity and difficulty in finding the required documents. Therefore, a balance of human resources, database, hardware, software, and a new strategy is needed to overcome the problems that can burden the company by realizing a website that is easy to apply so that any file is found quickly by paying attention to supervision, control, and methodical organization using PIESCES analysis as a method used to detect deficiencies and weakness in the old system. With this analysis, the new system is the right support in managing data that is collected in an orderly manner and stored neatly in large storage without being randomized and the work is more strategic because the information generated is valuable to the recipient or leader.

Many manufacturers create numerous types of automobiles with diverse advantages ranging from engine capacity, type of design, and fantastic features to their products in response to the large number of enthusiasts and requests from the general public. Consumers are frequently perplexed while making decisions regarding brand, model, type, price, engine capacity, transmission, year of manufacturing, fuel capacity, and other aspects of the car's benefits due to the growing range of options available. Brand, model, type, price, engine and transmission size, year of production, and gasoline capacity are all factors in choosing a car. The MOORA system only recommends vehicles from the three well-known manufacturers Honda, Toyota, and Suzuki. A Honda CRV with a value of Y_i = 0.225 was recommended as the first recommendation, followed by a Honda BRV with a value of Y_i = 0.211, and a Honda Brio with a value of Y_i = 0.204. The recommendations were based on Honda brand criteria and CVT transmission.

Agriculture is an activity of managing biological natural resources with the help of technology, capital, labor and management to produce agricultural commodities which include food crops, horticulture, plantations and or livestock in an agro-ecosystem. Most of the Indonesian people's livelihoods are as farmers, so the agricultural sector is very important to develop in this country. Poktan Beno Raharjo in Glonggong Village, Madiun Regency has a problem, namely the absence of an information system that is useful for managing agricultural production data, managing farmer data, managing village granary data, recording planting of food crops and horticultural crops, managing subsidized fertilizer assistance. The mobile-based Poktan information system was created using the dart programming language with the flutter framework using the waterfall method and testing using the black box testing method.

The waste processing and renewable energy are being the issues in the industrial 4.0 era. Kitchen and organic trash in the rural areas will become a disaster if there is no solutions. On the other hand, kitchen and organic waste have a positive side, that they can be converted into biogas which can be converted into electricity. On the Minister of Energy and Mineral Resources Regulation Number 27 of 2014, supports the development of biogas and will buy electricity from the biogas conversion. The potential for biogas that obtained by the organic trash per 1000 people is 7619.8 liters of biogas, it meas that the energy contained is still abundant and the production can still be increased if processed with a modern digester system. This research produces a tool in the form of a portable digester that named GenBIoT (IoT-based Biogas Generator) which can be used by the public to produce biogas that  used by home industries or general factories. This research used the research method that similar to System Development Life Cycle (SDLC), this tool is built with several stages starting from planning analysis, designing, functional testing, data analysis and reporting of the results or implementing this tool that can be used as an alternative, as a cheap and easy source energy. This tool is based on the Internet of Things so that this tool can be monitored regarding gas pressure in the reactor, biogas volume and it will detect if there is a biogas leak so it will displayed on the system. To produce the maximum biogas composition, 50% of cow dung is required, 40% of kitchen trash and 10% of water with a ratio of 5: 4: 1 so it will produce 40 kg of biogas with a volume of methane gas (VGM) 0.11 m3 of biogas for cow dung. and 0.04 m3. The third experiment becomes the basis of future biogas production with energy produced from biogas per day of 716.39 Wh

Arzara company is a company engaged in the garment sector, the development of the company affects the level of production of goods, so that in order to balance the production needs, it must increase the number of employee needs. The problem that often occurs in Arzara's company is the lack of professionalism of the company's employees, resulting in unilateral termination of employment. Termination of employment of employees of course will also affect the amount of production of goods. The SAW method or often called Simple Additive Weighting is an algorithmic method used for decision making, using certain criteria as the weight of the assessment in decision support. In making employee admission decisions using the SAW method using several criteria, which include expertise (skills), work experience, age, gender, education, health, talent, character, temperament, character, general knowledge tests, psychological tests. By using the PHP programming language, it can be used to assist the company to perform valid recruitment of employees . Applications that have been made can be used as a tool for decision makers while remaining based on a decision support system that is more effective in selecting employee admissions using the SAW ( Simple Additive Weighting ) method . 

CV Aintzane Mandiri is a company engaged in the field furniture. The Raw Material Manager at CV Aintzane is not yet optimal. Purchase Raw materials need to be considered because they will affect the maturity raw material needs and affect the production process. The information system for the supply of raw materials is needed by the company determination of expenditure, input of raw materials, and can minimize supply of raw materials for optimal use throughout the process production. Designing and building a procurement information system using raw materials Material Requirement Planning (MRP) method with programming language Microsoft Visual Basic 6.0, WAMP as server and MySQL as database. The results obtained from this information system can be obtained planning raw material requirements and production optimally and accordingly with company expectations. Keywords : Materials Requirement Planning, Computerized Accounting, Wamp, MySql

The management of production and operations in factory machinery is an optimal management effort in the use of resources consisting of labor, machinery, equipment and raw materials. The production and operations manager directs various inputs in order to produce various outputs or results in units of quantity, quality, price, specific time and location according to consumer demand. Efficiency and effectiveness of the production process to be achieved requires proper scheduling management so that the production output produced can be completed according to target. Management of production and customer orders is still simple, besides that the status of raw material inventories that cannot be directly known can often result in delays in the production process and even production cannot be done as soon as possible. Scheduling orders that enter using the system first in first out where the first order that comes is done, but has not considered the number of orders, priority of customers, maturity of workmanship and engine capacity so that the estimated completion of the order can not be known. To make it more efficient and directed, the Earliest Due Date method is used by sorting the production work based on the closest due date. This method can be used for scheduling on one machine or for scheduling on several machines (parallel machine) so that the scheduling management information system can manage effective production scheduling and produce production reports automatically as needed.

One of the survey activities carried out at the Baitul Giradh Baburrayyan Cooperative was regarding the coffee production of members who are members of the Baitul Oiradh Baburrayyan Cooperative organization, which aims to speed up the data processing process and make it easier to produce reports on production. To carry out these activities quickly and precisely, it is necessary to make an application as a tool in the data processing and presentation of data that will be needed by data users. This data processing application is made using the gambas programming language.

Production of freshwater fish farming (ponds) in Kangkung Subdistrict in 2015 reached 4.42 tons or valued at 97.19 million rupiah and the condition is growing more and more. The number of fish seeds is measured conventionally by observing the senses of the eye and causing inaccurate (inaccurate) measurement results. This study offers a solution for counting fish by using a microcontroller based phototransistor technology. Phototransistor has a linear function of the received light intensity that is flowing current (ON) and if there is a condition of light intensity blocked by fish passing through it then the current does not flow (OFF). The trial results of the fish seed count tool have an accuracy of 97% so that it can be used by fish farmers.  

PT. Vermindo Utama Semarang having its address at Jl. Pawiyatan Luhur Number 25 Semarang is a company engaged in the distribution and production of goods, especially health products. PT. Vermindo Utama Semarang has dozens of Salesmen and a leader. PT. Vermindo Utama Semarang carries out the process of buying and selling wholesale with various customers, the majority of whom are Pharmacies and supermarkets. In running its business, PT. Vermindo Utama Semarang still sells conventionally by using salesmen. And the marketing area still covers Central Java and East Java. Based on the problems above, the writer wants to propose a web-based booking system design to be considered in helping in the promotion of goods from PT. Vermindo Utama Semarang. Application Order System PT. Vermindo Utama Semarang by using PHP and MySql database. Making this application is expected to be one of the efforts that can be done to overcome the problems that often occur so as to increase the effectiveness of work which will certainly affect the quality of service to customers.