Classification of waste for recycling has been a focal point for scientists interested in the field of conservation of the environment. Recycling consists of numerous steps, of which one of the most crucial is the segregation of recyclables from all other waste. Due to a lack of safety standards in developing countries, waste collection is often done manually by domestic helpers, or "rag-pickers". Such a process risks individual and public health. The waste collection methods may ultimately cause waste to become non-recyclable due to cross-contamination. Literature shows that research in this direction focuses on a single class of waste detection. The proposed work investigates CNN, YOLO, and faster RCNN-based multi-class classification methods to detect different types of waste at the collecting point. The smart dustbin proposed employs these computer vision methods with a Raspberry Pi microcontroller and camera module. The experimental results for multi-class classification show that the CNN has 80% of accuracy with 60% of the loss. Whereas the YOLO algorithm shows an accuracy of 88% and a loss of 40%. But the best results were obtained from faster RCNN object detection with API, with an accuracy of 91% and a loss of 16%. There is already an existing method for making a smart dustbin, so the results are compared to show how computer vision can be used to make a smart dustbin. This shows how computer vision can be used to make a smart dustbin. Doi: 10.28991/ESJ-2022-06-03-015 Full Text: PDF

Agriculture provides a solution to the vast majority of problems that threaten human existence. When it comes to agriculture, new or contemporary technology can have a significant impact on a number of factors, including how much food is produced and how long it stays edible. The application of best management practices, for instance, is very common these days in the quest to improve agriculture. New hybrids are resistant to illnesses, use fewer pesticides, have natural defenses against pests, and may be grown in methods that minimize the number of diseases and pests that can affect them. Plants are capable of producing oxygen and medicines in addition to the food that they provide. Consequently, agriculture depends on plants that are in good health. A plant needs water, sunlight, and crucial fertilizer in order to receive the nutrients it needs to have a healthy plant. So, it is necessary to keep an eye on the health of the plant. The article discusses various technological solutions that can be implemented to automate the plant monitoring system. The Internet of Things and cloud computing are two technologies that are contributing to the development of intelligent technology by supplanting traditional agricultural practices. This clever device checks on the well-being of the plants. In order to enable intelligent agriculture, the technology relies on sensors that are dependent on IoT sensors. These sensors monitor the temperature, soil moisture, intensity of the sun's light, air quality value of the soil, vibration, and humidity in the immediate environment of the plant. The networking of these sensors ensures that the plant will continue to be healthy and will function in the appropriate manner. The findings that have been obtained up to this point are encouraging for the continuance of this strategy, which results in the highest possible profit for farmers. Doi: 10.28991/ESJ-2022-06-05-07 Full Text: PDF

No abstract

Channel or spectral estimation is a ground-breaking feature in wireless communication systems as it helps in obtaining information about a wireless channel at any state of time. Employing this can help in reducing the intensity of noise and bit error rate (BER). Here, images are processed, channels are estimated and image restoration is being done. Orthogonal Frequency Division Multiplexing (OFDM) is looked upon as a very popular multiplexing cum modulation technique used in wireless communication systems and so, it is selected to play a cardinal role in channel estimation. The LMS algorithm is preferred in this technique since it is a simpler technique and provides results which are desirable. To simulate realistic conditions, OFDM signal is passed through Additive White Gaussian Noise (AWGN) and also a multipath fading channel. In this paper, an FFT based OFDM, adopting several digital modulation techniques like BPSK, QPSK, 8PSK and 16QAM is being implemented on images. The values of BER is observed for different values of SNR and a comparison is drawn out for the aforementioned modulation techniques. Results prove that BPSK provides the least BER for a particular value of SNR and hence, it can be observed to give the best performance.

This work gives a brief overview of handoff technology and how it is useful in the field of cellular communication. The work touches upon the differences and similarities between soft and hard handover. It also looks into how handoff algorithms can be optimized using fuzzy logic technology, and the various advantages of such an optimization over conventional methods of handover.