Air quality, water pollution, and radiation pollution are major factors that pose genuine challenges in the environment. Suitable monitoring is necessary so that the world can achieve sustainable growth, by maintaining a healthy society. In recent years, the environment monitoring has turned into a smart environment monitoring (SEM) system, with the advances in the internet of things (IoT) and the development of modern sensors. Under this scenario, the present manuscript aims to accomplish a critical review of noteworthy contributions and research studies on SEM, that involve monitoring of air quality, water quality, radiation pollution, and agriculture systems. The review is divided on the basis of the purposes where SEM methods are applied, and then each purpose is further analyzed in terms of the sensors used, machine learning techniques involved, and classification methods used. The detailed analysis follows the extensive review which has suggested major recommendations and impacts of SEM research on the basis of discussion results and research trends analyzed. The authors have critically studied how the advances in sensor technology, IoT and machine learning methods make environment monitoring a truly smart monitoring system. Finally, the framework of robust methods of machine learning; denoising methods and development of suitable standards for wireless sensor networks (WSNs), has been suggested.
We have implemented a robust image watermarking technique for the copyright protection based on 3-level discrete wavelet transform (DWT). In this technique a multi-bit watermark is embedded into the low frequency sub-band of a cover image by using alpha blending technique. The insertion and extraction of the watermark in the grayscale cover image is found to be simpler than other transform techniques. The proposed method is compared with the 1-level and 2-level DWT based image watermarking methods by using statistical parameters such as peak-signal-to-noise-ratio (PSNR) and mean square error (MSE). The experimental results demonstrate that the watermarks generated with the proposed algorithm are invisible and the quality of watermarked image and the recovered image are improved.
This paper presents a novel method of landslide detection by exploiting the Mask R-CNN capability of identifying an object layout by using a pixel-based segmentation, along with transfer learning used to train the proposed model. A data set of 160 elements is created containing landslide and non-landslide images. The proposed method consists of three steps: (i) augmenting training image samples to increase the volume of the training data, (ii) fine tuning with limited image samples, and (iii) performance evaluation of the algorithm in terms of precision, recall and F1 measure, on the considered landslide images, by adopting ResNet-50 and 101 as backbone models. The experimental results are quite encouraging as the proposed method achieves Precision equals to 1.00, Recall 0.93 and F1 measure 0.97, when ResNet-101 is used as backbone model, and with a low number of landslide photographs used as training samples. The proposed algorithm can be potentially useful for land use planners and policy makers of hilly areas where intermittent slope deformations necessitate landslide detection as prerequisite before planning.
Modern sensors find their wide usage in a variety of applications such as robotics, navigation, automation, remote sensing, underwater imaging, etc. and in recent years the sensors with advanced techniques such as the artificial intelligence (AI) play a significant role in the field of remote sensing and smart agriculture. The AI enabled sensors work as smart sensors and additionally the advent of the Internet of Things (IoT) has resulted into very useful tools in the field of agriculture by making available different types of sensor-based equipment and devices. In this paper, we have focused on an extensive study of the advances in smart sensors and IoT, employed in remote sensing and agriculture applications such as the assessment of weather conditions and soil quality; the crop monitoring; the use of robots for harvesting and weeding; the employment of drones. The emphasis has been given to specific types of sensors and sensor technologies by presenting an extensive study, review, comparison and recommendation for advancements in IoT that would help researchers, agriculturists, remote sensing scientists and policy makers in their research and implementations.
Biometric traits such as fingerprint, retina scan, and palm-prints are used to identify a person at attendance monitoring, banking, passport, travel, and many other applications. Biometric-based person identification is the only method that never changes according to time, and no one can copy it without knowledge. Footprint-based biometric is one way to recognize a person based on different features associated with human footprints. For example, some places, such as airports, nanotechnology laboratories, silicon industries, temples, and public areas, require high security. It is necessary to add a footprint-based biometric trait for such high alert areas. The number of subjects taken by existing footprint-based methods is limited to very few subjects. The above research gaps motivate to add more subjects for this study. The proposed algorithm utilizes the fuzzy logic-based method for personal identification. Considerably 220 subjects with temporal aspects are taken into account to fill the existing methods gap. Three approaches, Fine Gaussian SVM (FSVM), Fine KNN (FKNN), and Fuzzy Ensemble Subspace Discriminant (FESD), have been utilized to create the enhanced human footprint matcher. The Fine Gaussian SVM approach exhibits an accuracy of 84.7%, the FKNN approach results in an accuracy of 92.3%, and the FESD approach gives an accuracy of 98.89%. FESD approach rectifies the recognition rate(to reach the required accuracy of 98.88%) False Match Rate (FMR, the rate of falsely as genuine classified imposters) at 0.01, False Non-Match Rate at 0.093 which is the rate of falsely as imposter classified genuine users) to a set of different matchers for the identification task. It improves the speed of recognition with 220 subjects by implementing the prototype schemes for footprint biometric to evaluate system properties, including accuracy and performance.
The real cause of breast cancer is very challenging to determine and therefore early detection of the disease is necessary for reducing the death rate due to risks of breast cancer. Early detection of cancer boosts increasing the survival chance up to 8%. Primarily, breast images emanating from mammograms, X-Rays or MRI are analyzed by radiologists to detect abnormalities. However, even experienced radiologists face problems in identifying features like micro-calcifications, lumps and masses, leading to high false positive and high false negative. Recent advancement in image processing and deep learning create some hopes in devising more enhanced applications that can be used for the early detection of breast cancer. In this work, we have developed a Deep Convolutional Neural Network (CNN) to segment and classify the various types of breast abnormalities, such as calcifications, masses, asymmetry and carcinomas, unlike existing research work, which mainly classified the cancer into benign and malignant, leading to improved disease management. Firstly, a transfer learning was carried out on our dataset using the pre-trained model ResNet50. Along similar lines, we have developed an enhanced deep learning model, in which learning rate is considered as one of the most important attributes while training the neural network. The learning rate is set adaptively in our proposed model based on changes in error curves during the learning process involved. The proposed deep learning model has achieved a performance of 88% in the classification of these four types of breast cancer abnormalities such as, masses, calcifications, carcinomas and asymmetry mammograms.
Ensemble learning method is a collaborative decision-making mechanism that implements to aggregate the predictions of learned classifiers in order to produce new instances. Early analysis has shown that the ensemble classifiers are more reliable than any single part classifier, both empirically and logically. While several ensemble methods are presented, it is still not an easy task to find an appropriate configuration for a particular dataset. Several prediction-based theories have been proposed to handle machine learning crime prediction problem in India. It becomes a challenging problem to identify the dynamic nature of crimes. Crime prediction is an attempt to reduce crime rate and deter criminal activities. This work proposes an efficient authentic method called assemble-stacking based crime prediction method (SBCPM) based on SVM algorithms for identifying the appropriate predictions of crime by implementing learning-based methods, using MATLAB. The SVM algorithm is applied to achieve domain-specific configurations compared with another machine learning model J48, SMO Naïve byes bagging and, the Random Forest. The result implies that a model of a performer does not generally work well. In certain cases, the ensemble model outperforms the others with the highest coefficient of correlation, which has the lowest average and absolute errors. The proposed method achieved 99.5% classification accuracy on the testing data. The model is found to produce more predictive effect than the previous researches taken as baselines, focusing solely on crime dataset based on violence. The results also proved that any empirical data on crime, is compatible with criminological theories. The proposed approach also found to be useful for predicting possible crime predictions. And suggest that the prediction accuracy of the stacking ensemble model is higher than that of the individual classifier.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.