13 research outputs found
Performance evaluation of hyper-parameter tuning automation in YOLOV8 and YOLO-NAS for corn leaf disease detection
No full textCorn cultivation was crucial in Southeast Asia, significantly contributing to regional food security and economies. However, leaf diseases posed a significant threat, causing substantial losses in production and quality. This research utilized artificial intelligence (AI) technology to address this issue by automating the hyper-parameter tuning process in YOLO (You Only Look Once) object detection models for early corn leaf disease detection. High-resolution images of corn leaves were captured and preprocessed for consistency. The preprocessing stage involved creating new dataset folders for images and labels, resizing images while preserving their aspect ratio, and rotating them if necessary. The images, containing 11,596 labeled instances, were analyzed using YOLOv8 and YOLO-NAS models. Each image's detected disease regions were converted into YOLO-format text files with x, y, width, and height coordinates, describing the presence and severity of infections. The models' performances were evaluated using precision, recall, mAP50, and mAP50-95 metrics. YOLOv8m achieved a mAP50 of 98.5% and mAP50-95 of 67.8%, while YOLO-NAS-L demonstrated superior detection capabilities with a mAP50 of 70.3% and mAP50-95 of 38.9%. This automated system facilitated early disease identification and enabled prompt preventive measures, thereby enhancing crop yields and mitigating losses. The findings highlighted the potential of advanced AI-driven detection systems in revolutionizing crop management and supporting global food security.
Modulating the line shape of magnetoconductance by varying the charge injection in polymer light-emitting diodes
No full textWe fabricate the phenyl-substituted poly(p-phenylene vinylene) copolymer (super yellow, SY-PPV)-based polymer light-emitting diodes (PLEDs) with different device architectures to modulate the injection of opposite charge carriers and investigate the corresponding magnetoconductance (MC) responses. At the first glance, we find that all PLEDs exhibit the positive MC responses. By applying the mathematical analysis to fit the curves with two empirical equations of a non-Lorentzian and a Lorentzian function, we are able to extract the hidden negative MC component from the positive MC curve. We attribute the growth of the negative MC component to the reduced interaction of the triplet excitons with charges to generate the free charge carriers as modulated by the applied magnetic field, known as the triplet exciton-charge reaction, by analyzing MC responses for PLEDs of the charge-unbalanced and hole-blocking device configurations. The negative MC component causes the broadening of the line shape in MC curves
Design and development of aircraft cargo fire early detection simulation system using arduino nano microcontroller
No full textFire in the aircraft cargo can cause dangerous damage to aircraft systems during flight. To prevent aircraft cargo fires, the fire early detection system must be built. In this work, we design and develop the fire early detection simulation system for aircraft cargo using Arduino nano microcontroller. The aircraft cargo is prone to fire due to the load of any type of goods such as dangerous goods, flammable stuff, or liquids, etc. This paper simulates the fire that occurs in artificial aircraft cargo and designs the detection and extinguisher prototypes using three kind sensors: flame, smoke, and temperature sensors combined with SMS gateway for user notification. We used SIM800L GSM module as communication tools to send and achieve data through short messages service (SMS) between security system and cellphones. Three sensors including flame, smoke, and temperature sensors were used as the warning indication to the hardware. When the sensors detect the fire and smoke, the red LED, buzzer, and vacuum pump will be on active mode, and SMS notification will be delivered immediately to the user’s cell phone. As the fire has been extinguished by the vacuum pump, the red LED, buzzer, and vacuum pump return to standby mode and the fire warning alarm system will turn off. This research is successfully developing the fire early detection simulation systems that can be applied in real aircraft cargo
Analisis Manajemen Risiko (Studi Kasus pada Gudang Obat Rumah Sakit Tentara Pematangsiantar)
No full textIn this research author describes the thesis with the title “ The Analysis of Risk Management (Case Study inthe medicine warehouse of Tentara Hospital )“ , is a company engaged in the field of enterprise services. The purpose of study was to find out how to apply risk management in the hospitals pharmacy unit. The method used is observation and interviews directly to the employees of the hospital. From the analysis of the overall pharmaceutical unit, Tentara hospital has 27 types of risk that may occur. The method that the author used to identify the risk is Failure Mode and Affect Analysis (FMEA), to prevent failure and its impact before it happens. The risk analysis will be input for risk evaluation and decision – making process regarding the treatment of such risks. Including in this sense is the way and the right strategy in treating these risks. Results of analysis of this paper was written based on the data obtained from the hospital that is the result of interviews the pharmacy unit, organizational structure and documents that related to the permises activities of pharmacy unit and other data that support this research. The conclusion that obtained from this research is the hospital management in pharmacy unit has been effective, but there are still shortcomings and possible risks that will happen.97 HalamanSkripsi Sarjan
Analisis Manajemen Risiko (Studi Kasus pada Gudang Obat Rumah Sakit Tentara Pematangsiantar)
No full textIn this research author describes the thesis with the title “ The Analysis of Risk Management (Case Study inthe medicine warehouse of Tentara Hospital )“ , is a company engaged in the field of enterprise services. The purpose of study was to find out how to apply risk management in the hospitals pharmacy unit. The method used is observation and interviews directly to the employees of the hospital. From the analysis of the overall pharmaceutical unit, Tentara hospital has 27 types of risk that may occur. The method that the author used to identify the risk is Failure Mode and Affect Analysis (FMEA), to prevent failure and its impact before it happens. The risk analysis will be input for risk evaluation and decision – making process regarding the treatment of such risks. Including in this sense is the way and the right strategy in treating these risks. Results of analysis of this paper was written based on the data obtained from the hospital that is the result of interviews the pharmacy unit, organizational structure and documents that related to the permises activities of pharmacy unit and other data that support this research. The conclusion that obtained from this research is the hospital management in pharmacy unit has been effective, but there are still shortcomings and possible risks that will happen.97 HalamanSkripsi Sarjan
Use of Ni/CNT Particles as Additive Fillers in Ebonite Bipolar Plates for Proton-Exchange Membrane Fuel Cells
No full textThe triplet-triplet annihilation process of triplet to singlet excitons to fluorescence in polymer light-emitting diodes
No full textSynthesis and Characterization Analysis of Banana Peel Carbon Activated as Adsorption of Copper (Cu)
No full textActivated carbon is a porous material widely used in various industrial and environmental applications, especially as an adsorbent in liquid waste treatment and gas purification. Banana peel, an abundant and renewable carbon source, is an environmentally friendly and sustainable raw material for activated carbon. However, optimization of the activation process is essential to improve the characteristics and adsorption performance of activated carbon. This study aims to evaluate the effect of KOH activation on the synthesis and characterization of banana peel-based activated carbon. Carbonization and chemical activation processes were carried out, then morphology and chemical structure characterization were performed using Field Emission Scanning Electron Microscopy (FE-SEM), Energy Dispersive X-ray (EDX), and Fourier Transform Infrared Spectroscopy (FTIR). The analysis showed that the activated carbon obtained has a well-developed pore structure with a porosity level of 74.80% and contains O-H, C-H, C=O, and C-Cl functional groups, which play a role in metal ion interactions. The hydrophilic nature of the activated carbon was studied through contact angle analysis, while the adsorption capacity towards copper ions (Cu) was determined using an Atomic Absorption Spectrophotometer (AAS). The results showed that the highest adsorption efficiency of 99.99% was achieved on activated carbon with 20% concentration and 15 minutes contact time. With good pore characteristics and high adsorption efficiency, banana peel-based activated carbon has the potential to be an efficient and sustainable adsorbent in heavy metal waste treatment applications. This research provides further insight into the utilization of biomass waste to produce functional materials of high-added value
PERAN KOMUNITAS PEMULUNG DALAM PENGELOLAAN SAMPAH DI TPST PIYUNGAN SEBAGAI UPAYA PENGENDALIAN PENCEMARAN DI KABUPATEN BANTUL
No full textThe increasing problem of waste in Piyungan Landfill (TPST) is caused by
the lack of maximum waste management in Piyungan Landfill (TPST). To be able
to overcome the problem of waste requires many parties such as the role of the
Mardiko Scavenger Community. With regard to these problems, the author
discusses how the role of scavenger communities in waste management in Piyungan
Landfill (TPST) as an effort to control pollution in Bantul Regency and whether
there are obstacles related to the role of scavenger communities in waste
management. management at Piyungan Landfill (TPST) as an effort to control
pollution in Bantul Regency.
This research is an empirical legal research in which it is based on social
facts. The data taken in this study is primary data supplemented with secondary
data. The data collection methods used are interviews and literature studies. The
data analysis method used is qualitative data analysis. From the results of research
that has been done, the authors can conclude that the role of the Mardiko Scavenger
Community in waste management in Piyungan Landfill (TPST) is still limited to
sorting waste independently, has not managed waste as a whole because there are
obstacles related to the role of the Mardiko Scavenger Community in waste
management in Piyungan Landfill (TPST)
