No abstract

The agriculture industry is of great importance in many countries and plays a considerable role in the national budget. Also, there is an increased interest in plantation and its effect on the environment. With vast areas suitable for farming, countries are always encouraging farmers through various programs to increase national farming production. However, the vast areas and large farms make it difficult for farmers and workers to continually monitor these broad areas to protect the plants from diseases and various weather conditions. A new concept dubbed Precision Farming has recently surfaced in which the latest technologies play an integral role in the farming process. In this paper, we propose a SMART Drone system equipped with high precision cameras, high computing power with proposed image processing methodologies, and connectivity for precision farming. The SMART system will automatically monitor vast farming areas with precision, identify infected plants, decide on the chemical and exact amount to spray. Besides, the system is connected to the cloud server for sending the images so that the cloud system can generate reports, including prediction on crop yield. The system is equipped with a user-friendly Human Computer Interface (HCI) for communication with the farm base. This multidrone system can process vast areas of farmland daily. The Image processing technique proposed in this paper is a modified ResNet architecture. The system is compared with deep CNN architecture and other machine learning based systems. The ResNet architecture achieves the highest average accuracy of 99.78% on a dataset consisting of 70,295 leaf images for 26 different diseases of 14 plants. The results obtained were compared with the CNN results applied in this paper and other similar techniques in previous literature. The comparisons indicate that the proposed ResNet architecture performs better compared to other similar techniques.

Background Due to the high demand of robots to perform several industrial tasks, such as welding, machining, pick and place, position control in robotics has attracted high attention recently. Controllers’ improvement is also continuous specifically in terms of design simplicity and performance accuracy. This research plans to obtain the SimMechanics model of a two-degree of freedom (DOF) robot and to propose an integrated controller of a proportional–derivative (PD) controller and a fuzzy logic (FL) controller. Methodology The SimMechanics model of the 2-DOF robot is obtained using MATLAB SimMechanics toolbox from a CAD assembly design of the 2-DOF robot. Then, the proposed PD-FL integrated controller is designed and simulated in MATLAB Simulink. The PD controller is widely used for its simplicity, but it doesn’t have a satisfactory performance in difficult tasks. Furthermore, the FL controller is also easy for design and implementation even by non-experts in control theory, but it has the disadvantage of long computational time for multi-input systems due to the increased fuzzy rules. Results The FL controller is integrated with the PD controller for enhanced performance of the 2-DOF robot. The PD-FL integrated controller is developed and tested to control the 2-DOF robot for point-to-point position control and also tip trajectory tracking (TTT) such as triangular TTT and rhombic TTT. Conclusion The PD-FL integrated controller demonstrates enhanced performance compared to the conventional PD controller in both point-to-point position control and TTT. Furthermore, the PD-FL integrated controller has the advantage of less fuzzy rules which helps to overcome the computational time issue of the FL controller.

The paper presents a simple approach for detecting frauds by comparing the finger prints a person live and after death. There are changes occur in the fingerprint after the death of a person. A comparative study is made on the samples (both live and dead samples), in order to find any possible changes in the characteristics of the live and dead fingerprint samples. A set of dead samples are analyzed using various techniques to find the similar properties /characteristics in those samples. Those properties will be compared with the live samples. If any changes in the properties/characteristics of the live and dead samples are identified, then it can be studied thoroughly and can be used to identify whether a given fingerprint was taken when the person was alive or dead. This work will be used for fraud detection.

No abstract