This study investigates the feasibility of using Raspberry Pi-equipped Unmanned Aerial Vehicles (UAVs) for object detection. The research focuses on analyzing the impact of the distance between the UAV and the target person on the accuracy of object detection. Experimental results reveal a decrease in detection accuracy as the distance between the UAV and the target person increases, emphasizing the critical role of distance in efficient object detection systems. By combining drones, Raspberry Pi, and machine learning algorithms, this research showcases the potential of advanced object detection systems. The findings contribute to the growing application of UAV technology by refining and optimizing UAV-based object detection systems.

MalariaSD is a dataset encompassing various stages and classes of the malaria parasite, including Plasmodium falciparum, Plasmodium malariae, Plasmodium vivax, and Plasmodium ovale. These divisions consist of four distinct phases: ring, schizont, trophozoite, and gametocyte stages. The dataset serves as a valuable resource for researchers and healthcare professionals, offering crucial insights into the epidemiology, diagnosis, and treatment of malaria.The MP-IDB , a comprehensive collection of high-quality malaria parasite images, features the aforementioned four stages. This database presents an opportunity to develop and evaluate novel image processing and analysis techniques, aiming to enhance the accuracy and efficiency of malaria diagnosis. In our proposed paper, these images were used to create a new dataset using stable diffusion and advanced image processing methods.By utilizing stable diffusion, we generated a dataset comprising 16 distinct classes. Specifically, we focused on single-celled images and applied cropping and enhancement techniques to produce refined images. Subsequently, this new dataset underwent training through stable diffusion, resulting in the generation of 20 additional images for each class. As a result of our efforts, the image count of the original dataset increased significantly from an average of 12 images to 40 images per class.Through the expansion of the dataset using stable diffusion and image processing, our paper contributes to the advancement of malaria research. The augmented dataset provides a more comprehensive representation of the various stages and classes of malaria parasites, empowering researchers and healthcare professionals to enhance their understanding of malaria’s complexities and improve diagnostic methodologies. MalariaSD is a dataset encompassing various stages and classes of the malaria parasite, including Plasmodium falciparum, Plasmodium malariae, Plasmodium vivax, and Plasmodium ovale. These divisions consist of four distinct phases: ring, schizont, trophozoite, and gametocyte stages. The dataset serves as a valuable resource for researchers and healthcare professionals, offering crucial insights into the epidemiology, diagnosis, and treatment of malaria. The MP-IDB , a comprehensive collection of high-quality malaria parasite images, features the aforementioned four stages. This database presents an opportunity to develop and evaluate novel image processing and analysis techniques, aiming to enhance the accuracy and efficiency of malaria diagnosis. In our proposed paper, these images were used to create a new dataset using stable diffusion and advanced image processing methods. By utilizing stable diffusion, we generated a dataset comprising 16 distinct classes. Specifically, we focused on single-celled images and applied cropping and enhancement techniques to produce refined images. Subsequently, this new dataset underwent training through stable diffusion, resulting in the generation of 20 additional images for each class. As a result of our efforts, the image count of the original dataset increased significantly from an average of 12 images to 40 images per class. Through the expansion of the dataset using stable diffusion and image processing, our paper contributes to the advancement of malaria research. The augmented dataset provides a more comprehensive representation of the various stages and classes of malaria parasites, empowering researchers and healthcare professionals to enhance their understanding of malaria’s complexities and improve diagnostic methodologies.

This paper consists of an overview and a brief description of all the Beagle Boards from the original Beagle Board released in 2008 to the latest board BeagleV released in 2019. The Beaglebone board is one of the high-end hobby-grade boards and has quite a few applications in industrial/consumer electronics as well. Many beginners prefer Arduino boards and Raspberry Pi boards for tinkering. The Beagle Boards are an amalgamation of both Arduino and Raspberry Pi boards. Owing to their high prices, they are not as widely used as the Arduino boards and Raspberry Pi boards, but the Beagle Boards are robust and have an added advantage in the form of on-board GPU and DSP. Furthermore, the on-chip PRU-ICSS contribute to the computing process increasing the efficiency of the boards. The Beagle boards have multiple OS Support (Debian, LXDE, Ubuntu, etc.). The paper also discusses the interfacing of Beagle boards with various peripherals and components. The various types of capes available for the Beagle boards are discussed as well. The paper also presents an introduction on how to get started with the Beagle boards. The applications of the Beagle boards are discussed as well.

Diabetic Retinopathy (DR) is a severe medical concern, and early detection of DR can prevent blindness. Manually examining fundus images to detect lesions is time-consuming and requires expertise. Segmenting exudates from fundus images using Deep Learning methods provides an automated high precision solution to this problem. Our work proposes the Residual Recurrent U-Net (R2 U-Net) for segmenting exudates in retinal fundus images. The network consists of recurrent units with feedback connections leveraging local spatial information from neighboring pixels. There are multiple stacked recurrent units in each layer of the U-Net. Residual skip connections were introduced between different layers of the network to train deeper architectures. The model was trained on the publicly available IDRiD dataset and tested on IDRiD, E-Ophtha, and DiaretDB1 dataset. The metrics were computed at the pixel, exudate (or lesion), and image level. The model achieved a state-of-the-art 93.20% sensitivity and 99.80% specificity on the E-Ophtha at the exudate level, which is better than existing literature. An automated DR detection system would help not only people but also Ophthalmologists to treat Diabetic Retinopathy effectively.

As technology is advancing so house are also getting smarter. Modern houses are gradually shifting from convectional switches to centralized control system, involving remote control switches. Presently, convectional wall switches located in different parts of the house makes it difficult for user to go near them to operate. Even it becomes more difficult for elder people and for physically handicap people to do so. Internet of Things (IoT) conceptualizes the idea of remotely connecting and monitoring real world objects through the Internet. When it comes to our house, this concept can be aptly incorporated to make it smarter, safer and automated. It is a concept where each device is assign to an IP address and through that IP address anyone makes that device identifiable on internet. The Internet is an evolving entity. It started as the Internet of Computers. Research studies have forecast an explosive growth in the number of things or devices that will be connected to the Internet. The resulting network is called the Internet of Things (IoT). IoT is having the potential to change the lifestyle of peoples. In day today’s life, people prefer more of automatic systems rather than any manual systems. The major elements of IoT based home automation system are Raspberry pi and the Relay along with their driving circuitry. Home automation can be defined as a mechanism removing as much human interaction as technically possible and desirable in various domestic processes and replacing them with programmed electronic systems. This project is intended to construct a home automation system that uses any mobile device to control the home appliances. This home automation system is based on IoT. Home automation is very exciting field when it uses new technologies like Internet of Things. Raspberry pi is credit card size computer. Raspberry pi supports large number of peripherals. Raspberry pi is having different communication media like Ethernet port, HDMI port, USB port, Display Serial Interface, Camera Serial Interface, Bluetooth, Bluetooth low energy. It allows to control number of home appliances simultaneously.