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.

Land-use and land-cover (LULC) classification using remote sensing imagery plays a vital role in many environment modeling and land-use inventories. In this study, a hybrid feature optimization algorithm along with a deep learning classifier is proposed to improve the performance of LULC classification, helping to predict wildlife habitat, deteriorating environmental quality, haphazard elements, etc. LULC classification is assessed using Sat 4, Sat 6 and Eurosat datasets. After the selection of remote-sensing images, normalization and histogram equalization methods are used to improve the quality of the images. Then, a hybrid optimization is accomplished by using the local Gabor binary pattern histogram sequence (LGBPHS), the histogram of oriented gradient (HOG) and Haralick texture features, for the feature extraction from the selected images. The benefits of this hybrid optimization are a high discriminative power and invariance to color and grayscale images. Next, a human group-based particle swarm optimization (PSO) algorithm is applied to select the optimal features, whose benefits are a fast convergence rate and ease of implementation. After selecting the optimal feature values, a long short-term memory (LSTM) network is utilized to classify the LULC classes. Experimental results showed that the human group-based PSO algorithm with a LSTM classifier effectively well differentiates the LULC classes in terms of classification accuracy, recall and precision. A maximum improvement of 6.03% on Sat 4 and 7.17% on Sat 6 in LULC classification is reached when the proposed human group-based PSO with LSTM is compared to individual LSTM, PSO with LSTM, and Human Group Optimization (HGO) with LSTM. Moreover, an improvement of 2.56% in accuracy is achieved, compared to the existing models, GoogleNet, Visual Geometric Group (VGG), AlexNet, ConvNet, when the proposed method is applied.

<p class="Abstract"><span lang="EN-US">With the entry into operation of the Sentinel-2 mission in June 2015, a new land monitoring costellation of twin satellites has been added to Copernicus project from ESA and new insights have been derived through the combination of Sentinel-2 data with other optical/multispectral data, and with other data from satellites belonging to the same Copernicus  project.  To this end, the objective of this paper has been to present new added-value tools first through the integration of different satellite platforms: data from NASA Landsat-8 and ESA Sentinel-1 have been used and combined, and furthermore through the comparison of satellite data all from the same Copernicus project: data from Sentinel-1 and Sentinel-2 have been jointly processed and compared. Although data from optical/multispectral sensors, as those of Landsat-8 and Sentinel-2, and data from SAR on board of Sentinel-1,  are very different,  their combination provides useful and interesting results. The integration and combination of these data can find useful application in many fields from oceans to waterways, from land surfaces to fossil deposits, from vegetation to forest areas. In this works authors have focused their interest in green areas and vegetation monitoring applications, by choosing as case of interest the Royal Palace of Caserta and its gardens.  The idea has started from the increasing interest in monitoring  the cultural heritage monuments and in particular  the surrounding vegetation with the green areas and the parks inside. Satellite images can put into evidence boundaries modifications, the vegetation state, their possible degradation, and other phenomena such as changes in the territories due both to natural and to anthropogenic causes. Data combination from different sources as above specified gives a good number of indexes very useful to analyze the vegetation state and its health in a very deep way. Many of these indexes have been calculated and discussed for investigation.</span></p>

No abstract

The detection of signals with unknown parameters in correlated K-distributed noise, using the generalised Neyman-Pearson strategy is considered. The a priori uncertainty on the signal is removed by performing a maximum likelihood estimate of the unknown parameters. The resulting receivers can be regarded as a generalisation of the conventional detector, but for a zero-memory nonlinearity depending on the amplitude probability density function of the noise as well as on the number of integrated pulses. It is shown that the performance for uncorrelated observations is unaffected by the specific signal pattern, but depends only on the signal-to-noise ratio; moreover, the effect of the clutter correlation on the performance can be accounted for simply by a detection gain. A performance assessment, carried out by computer simulation, shows that the proposed receivers significantly outperform conventional ones as the noise amplitude probability density function markedly deviates from the Rayleigh law. It also shows that the generalised Neyman-Pearson strategy is a suitable means of circumventing the uncertainty on wanted target echos since the operating characteristics of the receivers for the case of signals with unknown parameters closely follow those of the receiver for a completely known signal. Paper 7832F (E15), first received 26th July and in revised form 4th