Developing nations today face a major hurdle of excessive waste generation due to overpopulation and rapid urbanization. Also, the management systems in such countries are ineffective limited. Considering this issue, an effective efficient system would be great societal benefit. Artificial Intelligence Deep Learning has found its way into many diverse areas recent years. This research work proposes Garbage Detection System using object detection models automatically detect locate garbage...

Active Synthetic Aperture Radar (SAR) sensors use their own source of illumination to sense the earth surface. SAR have ability penetrate through clouds and smoke like conditions, can operate on day night, a sensitivity each property in microwave region. Generally, speckle is found images at time image acquisition transmission. Speckle satellite degrades quality makes it less informative about target/features under study. Denoising or reduction great challenge for researchers worldwide as...

Hyperspectral Image generally contains hundreds of spectral bands and thus provides a huge amount information for particular scene. Despite this, the classification task hyperspectral image is considered difficult due to less number labeled samples available. In recent years, deep learning algorithms have grown as most significant highly effective tasks. But these require data which not suitable images getting costly. To mitigate this problem, we can employ semi-supervised techniques that...

Change detection is one of the crucial aspects analyzing dynamic changes in various land cover types, especially case cropland. With increasing availability high-resolution remote sensing data, different deep learning techniques have emerged as an effective means for accurately detecting changes. Detecting intraclass variations main challenge cropland change detection, apart from crop phenology, shadow, and illumination effects. Here, a novel image pre-processing technique introduced to help...

With the advancement in technology, artificial intelligence and computer vision are being used extensively health care sector. Specifically, there's a lot of research happening brain tumor detection classification. A can be defined as chronic disease which tissues start to grow an uncontrollable manner. There very few technologies currently use detect tumors such CT - Scans MRIs. And, require expert diagnosis type location tumor, tasks time-consuming. This is reason, there need for automatic...

There has been extensive research in the field of Hyperspectral Image Classification using deep neural networks. The learning based approaches requires huge amount labelled data samples. But case Image, there are less number Therefore, we can adopt Active Learning combined with to be able extract most informative By this technique, train classifier achieve better classification accuracies is considerable carried out for selecting diverse samples from pool unlabeled We present a novel...

LSTM is a valuable approach in the context of land cover change detection due to its ability capture temporal dependencies and long-term patterns sequential data. Land involves analyzing satellite images or time series data identify classify changes surface features over time. By step analysis images, can even small gradual area. The recurrent nature allows it understand relationship between neighboring pixels which could also help fix missing noise pixel if any. Lastly, feature extraction...

Among various algorithms for protein and nucleotide alignment, Needleman-Wunsch algorithm is widely accepted as it can divide the problem into sub-problems. We present two parallel approaches of with single kernel multi-kernel invocation using skewing transformation which used traversing calculation dynamic programming matrix. also compare these traditional CPU sequential approach resulted in six-fold performance improvement. Furthermore, we same ideology on shared memory two-fold...

Beyond the Automation Pyramid, industries are currently embracing intelligence. One of challenges in Industry 4.0 is to conduct Predictive maintenance (PdM) for Investment Casting Process, which one oldest metal-forming industrial processes. According existing works, PdM achieved by data-driven methods scheduling just-in-time maintenance. However, traditional Machine Learning (ML) techniques can make good predictions some extent but not guaranteed be accurate. This limitation served as...