The advent of cloud computing has made it simpler for users to gain access to data regardless of their physical location. It works for as long as they have access to the internet through an approach where the users pay based on how they use these resources in a model referred to as “pay-as-per-usage”. Despite all these advantages, cloud computing has its shortcomings. The biggest concern today is the security risks associated with the cloud. One of the biggest problems that might arise with cloud services availability is Distributed Denial of Service attacks (DDoS). DDoS attacks work by multiple machines attacking the user by sending packets with large data overhead. Therefore, the network is overwhelmed with unwanted traffic. This paper proposes an intrusion detection framework using Ensemble feature selection with RNN (ERNN) to tackle the problem at hand. It combines an Ensemble of multiple Machine Learning (ML) algorithms with a Recurrent Neural Network (RNN).  The framework aims to address the issue by selecting the most relevant features using the ensemble of six ML algorithms. These selected features are then used to classify the network traffic as either normal or attack, employing RNN. The effectiveness of the proposed model is evaluated using the CICDDoS2019 dataset, which contains new types of attacks. To assess the performance of the model, metrics like precision, accuracy, F-1 score, and recall are taken into consideration.

An administrator is employed to identify network security breaches in their organizations by using a Network Intrusion detection and Prevention System (NIDPS), which is presented in this paper that can detect and preventing a wide range of well-known network attacks. It is now more important than ever to recognize different cyber-attacks and network abnormalities that build an effective intrusion detection system plays a crucial role in today's security. NSL-KDD benchmark data set is extensively used in literature, although it was created over a decade ago and will not reflect current network traffic and low-footprint attacks. Canadian Institute of Cyber security introduced a new data set, the CICIDS2017 network data set, which solved the NSL-KDD problem. With our approach, we can apply a variety of machine learning techniques like linear regression, Random Forest and ID3. The efficient IDPS is indeed implemented and tested in a network environment utilizing several machine learning methods. A model that simulates an IDS-IPS system by predicting whether a stream of network data is malicious or benign is our objective. An Enhanced ID3 is proposed in this study to identify abnormalities in network activity and classify them. For benchmark purposes, we also develop an auto encoder network, PCA, and K-Means Clustering. On CICIDS2017, a standard dataset for network intrusion, we apply Self-Taught Learning (STL), which is a deep learning approach. To compare, we looked at things like memory, Recall, Accuracy, and Precision.

Building fixtures like lighting are very important to be modelled, especially when a higher level of modelling details is required for planning indoor renovation. LIDAR is often used to capture these details due to its capability to produce dense information. However, this led to the high amount of data that needs to be processed and requires a specific method, especially to detect lighting fixtures. This work proposed a method named Size Density-Based Spatial Clustering of Applications with Noise (SDBSCAN) to detect the lighting fixtures by calculating the size of the clusters and classifying them by extracting the clusters that belong to lighting fixtures. It works based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN), where geometrical features like size are incorporated to detect and classify these lighting fixtures. The final results of the detected lighting fixtures to the raw point cloud data are validated by using F1-score and IoU to determine the accuracy of the predicted object classification and the positions of the detected fixtures. The results show that the proposed method has successfully detected the lighting fixtures with scores of over 0.9. It is expected that the developed algorithm can be used to detect and classify fixtures from any 3D point cloud data representing buildings.

Nowadays, detecting unusual events in the network has been the subject of many researches. Network traffic is huge and very large, and this leads to high data size and increased noise, which makes it very difficult to extract meaningful information to detect abnormal events. Early detection of attacks improves the stability of a system. Each attack is a type of specific behavior,But some attacks may behave similarly and differ only in some features. This article presents a new way to detect malware and attacks in the cloud computing environment. In this method, data clustering separates the data from each other to provide better conditions for model construction by balancing the data in different classes. This research uses a combination of Adabost, Random Forest and Bosted Gradient Tree algorithms as ensemble learning to improve malware detection in cloud computing. In order to combine boosted learners and build a higher level model, the voting mechanism is used. In the proposed model, ensemble learning, using the strengths of various algorithms, creates a useful, high-performance system for detecting malware in cloud computing. By applying the proposed method on real data, it was observed that the accuracy of the proposed method is equal to 99. 96%, its accuracy is equal to 99. 97% and its recall is equal to 99. 95% which compared to previous methods, it has a noticeable advantage, but its computational complexity has not changed much.

Due to their significant impact on the balance of energy on the surface and in the atmosphere, the clouds have always been considered by various researchers in the meteorological and climatological fields. The ability to remotely measure the characteristics and parameters of the cloud has been proven to examine their changes in different locations and times. One of the most important aspects of cloud research is cloud detection in remotely sensed images. The purpose of the present study is to provide a stereographic based technique for detecting clouds according to the height of the clouds with the highest possible spatial resolution and using Geostationary meteorological images. First, a stereo pair is selected on board two platforms of the Meteosat-8 (IODC) and the Meteosat-10, using the SEVIRI Sensor with high resolution spatial resolution (HRV). Then, with respect to the different viewing geometry of the two sensors, both images are reprojected into a similar reference grid and finally, by forming line of sight (LOS) of the two sensors in an epipolar sheet, the parallax value in two images on the clouds is estimated. The advantage of this method in estimating cloud height is that the stereo measurements only depend on the fundamental geometric relationships between observations of the visible components of the clouds. Other estimation methods, require the assumption that the cloud has a local thermodynamic equilibrium and some knowledge about the apparent temperature, etc. But in most cases, the amount of cloud emission is unknown, the temperature profile of the atmosphere is unavailable, and the cloud does not have thermodynamic equilibrium with its surroundings. In this study, a new method for revealing cloud pixels based on cloud height is presented. After estimating the height of the clouds, it is possible to separate the pixels of clouds from the intersection pixels based on the existing altitude difference, and in fact, it is possible to detect the cloud based on the estimated height in pixels. The results of this study indicate the high accuracy and the feasibility of using stereography to detect cloud pixels in satellite imagery. The advantage of our proposed method is the use of cloud-height information that not only increases the spatial resolution, but also helps to extract 3D cloud information, which is of particular importance in the studies of solar irradiance, and other cloud research applications. And finally, having a knowledge in this regard in Iran is also very important, because a new branch of meteorological studies, entitled "Meteorological stereography" will be established in the country and will help to lead to more extensive research in this area.

Nowadays the cloud computing environment is widely utilized for transmitting and receiving data securely. Inorder to secure the data the encryption method is used but still due to some limitations the security process is diminished. Therefore, this paper proposes a new algorithm to provide better security while transmitting data through the network. At first, the sensitivity of data is determined using a lightweight convolutional neural network (LWCNN) model which is used to categorize the unclassified data into two categories normal sensitive data and highly sensitive data. After determining the level of data sensitivity, the encryption process is performed further. The efficient hash function-based duplication detection approach is employed to maintain confidential information before outsourcing it to a cloud server. Subsequently, the ideal keys are generated for each data based on its sensitivity level using the proposed fuzzy tuna swarm (FTS) algorithm. Finally, the data is encrypted by converting plain text into ciphertext which is only visible to authorized users. The experimental results show that the LWCNN model utilized for data sensitivity classification achieved 94% accuracy and the FTS algorithm proposed for optimal key generation took much less communication time of about 1800μs than other compared techniques.

Snow as one of the precipitation forms has important effect in hydrological cycle and water resources management. Snow monitoring particularly in mountainous basin without modern technology is very difficult according to temporal and spatial variation of snow property. Remote sensing is one of advanced technology in measurement of snow properties. MODIS imagery is one of new sensors that provide the possibility of snow cover measurement.In this research, the ability of MODIS imagery for detection of snow cover from other earth phenomena such as cloud has been assessed. Some methods of snow cover detection have been applied in Haraz basin that is one of important basin in North of Iran. Results showed that false color image of moderate infrared bands has ability of snow and cloud detection and the best algorithm is the one that can envisage digital number of pixels deviation.