Search results

Nowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of agricultural products. Pesticides can be used to improve agricultural land products. This study aims to make the spraying of cherry trees more effective and efficient with the designed artificial intelligence (AI)-based agricultural unmanned aerial vehicle (UAV).

Two approaches have been adopted for the AI-based detection of cherry trees: In approach 1, YOLOv5, YOLOv7 and YOLOv8 models are trained with 70, 100 and 150 epochs. In Approach 2, a new method is proposed to improve the performance metrics obtained in Approach 1. Gaussian, wavelet transform (WT) and Histogram Equalization (HE) preprocessing techniques were applied to the generated data set in Approach 2. The best-performing models in Approach 1 and Approach 2 were used in the real-time test application with the developed agricultural UAV.

In Approach 1, the best F1 score was 98% in 100 epochs with the YOLOv5s model. In Approach 2, the best F1 score and mAP values were obtained as 98.6% and 98.9% in 150 epochs, with the YOLOv5m model with an improvement of 0.6% in the F1 score. In real-time tests, the AI-based spraying drone system detected and sprayed cherry trees with an accuracy of 66% in Approach 1 and 77% in Approach 2. It was revealed that the use of pesticides could be reduced by 53% and the energy consumption of the spraying system by 47%.

An original data set was created by designing an agricultural drone to detect and spray cherry trees using AI. YOLOv5, YOLOv7 and YOLOv8 models were used to detect and classify cherry trees. The results of the performance metrics of the models are compared. In Approach 2, a method including HE, Gaussian and WT is proposed, and the performance metrics are improved. The effect of the proposed method in a real-time experimental application is thoroughly analyzed.

This paper aims to design an AI-based drone that can facilitate the complicated and time-intensive control process for detecting healthy and defective solar panels. Today, the use of solar panels is becoming widespread, and control problems are increasing. Physical control of the solar panels is critical in obtaining electrical power. Controlling solar panel power plants and rooftop panel applications installed in large areas can be difficult and time-consuming. Therefore, this paper designs a system that aims to panel detection.

This paper designed a low-cost AI-based unmanned aerial vehicle to reduce the difficulty of the control process. Convolutional neural network based AI models were developed to classify solar panels as damaged, dusty and normal. Two approaches to the solar panel detection model were adopted: Approach 1 and Approach 2.

The training was conducted with YOLOv5, YOLOv6 and YOLOv8 models in Approach 1. The best F1 score was 81% at 150 epochs with YOLOv5m. In total, 87% and 89% of the best F1 score and mAP values were obtained with the YOLOv5s model at 100 epochs in Approach 2 as a proposed method. The best models at Approaches 1 and 2 were used with a developed AI-based drone in the real-time test application.

The AI-based low-cost solar panel detection drone was developed with an original data set of 1,100 images. A detailed comparative analysis of YOLOv5, YOLOv6 and YOLOv8 models regarding performance metrics was realized. Gaussian, salt-pepper noise addition and wavelet transform noise removal preprocessing techniques were applied to the created data set under the proposed method. The proposed method demonstrated expressive and remarkable performance in panel detection applications.

The purpose of this paper is to investigate Halbach array effects in surface mounted permanent magnet machine (SMPM) in terms of both self-sensing and torque capabilities. A comparison between a conventional SMPM, which has radially magnetized rotor, and a Halbach machine has been carried out.

The geometric parameters of the two machines have been optimized using genetic algorithm (GA) with looking Pareto. The performance of the machines’ geometry has been calculated by finite element analysis (FEA) software, and two parametric machine models have been realized in Matlab coupled with the FEA and GA toolboxes. Outer volume of the machine, thus copper loss per volume has been kept constant. The Pareto front approach, which simultaneously considers looks two aims, has been used to provide the trade-off between the torque and sensorless performances.

The two machines’ results have been compared separately for each loading condition. According to the results, the superiority of the Halbach machine has been shown in terms of sensorless capability compromising torque performance. Additionally, this paper shows that the self-sensing properties of a SMPM machine should be considered at the design stage of the machine.

A Halbach machine design optimization has been presented using Pareto optimal set which provides a trade-off comparison between two aims without using weightings. These are sensorless performance and torque capability. There is no such a work about sensorless capability of the Halbach type SMPM in the literature.

The purpose of this paper is to identify the radio frequency identification (RFID) strategic value attributes (RFIDSVAs) mechanism selections preferences and also integration of RFID tags with technology coordination tools (IRTWTCTs) alternatives ranking performance decisions in supply chain management (SCM). RFID-enabled techno-economic feasibility decisions are enhancing the SC visibility in apparel supply chains (ASCs). The RFIDSVAs mechanism selections have performed significant agility to strategic competitive advantages, namely, inventory visibility, multi-tags ownership transfer within trusted third party, etc.

Fuzzy analytical hierarchy process (FAHP) and FAHP-fuzzy Technique for Order of Preference by Similarity to Ideal Solution (FTOPSIS) approaches have been used to evaluate the quantitative assessment of RFIDSVA mechanisms selection decision based on weight priority orders and IRTWTCTs alternatives selection in ASC networks. The comparison of FAHP and FAHP-FTOPSIS approaches to evaluate the integrated framework develop in RFIDSVAs mechanisms and IRTWTCTs alternatives selection decisions in Indian multi-tier ASC networks.

The result found that the FAHP-FTOPSIS approaches have used to prioritizing the RFIDSVA mechanism selection weights and also identify the IRTWTCTs alternatives ranking preferences order in apparel SCM. The comparison between the FAHP and FAHP-FTOPSIS approach to quantitative assessments from RFIDSVA mechanisms and IRTWTCTs alternatives selection decisions, which enable them SC agility potential across multi-tier visibility in ASC networks. ASC stakeholders can be benefited by techno-economic feasibility decisions, RFID-enabled shop floor activities, multi-tags ownerships transfer in SCs and knowledge-based cryptography tags/items separation in SCs.

The research work has considered only five RFIDSVA mechanisms and also three integration of RFIDTWTCTs alternatives in multi-tier ASC. The strategic competitive advantages are achieved by RFID-enabled break-even tags price decisions and also techno-economic feasibility decision by contractual design multi-tier SC stakeholder’s involvements.

The pilot project study explores that the quantitative assessment decision has based on RFID-enable techno-economic feasibility in ASCs. Stakeholders can be benefited by inventory control of the financial losses, reducing the inventory inaccuracies and multi-tags ownership transfer within trusted third-party traceability in ASC networks.

This study explores the RFID-enabled apparel SC process and activities visibility (natural fibre’s fibre producer, fibre dyeing producer, yarn spinning producer, knitting and finishing producer).