This paper attempts to provide a demonstration the importance of the feature selection (FS) in the data mining filed for the optimization. The author’s aim to develop a Convolutional Neural Network (CNN) based Network Intrusion Detection System (NIDS). The CNN was trained using the NSL-KDD dataset. The approach is divided into two methodologies: the first one, is to apply the CNN to the NSL-KDD dataset without FS, in the second methodology: the Information Gain (IG), Grain Ratio (GR) and Correlation Attribute (CA) were applied as FS methods then the CNN is use to classify the intrusion. The performance is proven by comparing our results with other previous works. Our experimentation results show that CNN with FS has a good accuracy 99,72%, true positive rate: 99,29%, false positive rate: 0,18%. Thus, the CNN with FS has outperform the other methods. But the methods use in the FS phase don’t guarantee the use of the best subset or the optimal subset. As future orientation is to develop another method for FS which guarantee the selection of the best and the optimal relevant feature.
The utilization of Le`vy flight to create new candidate solutions is one of the most powerful elements of CS. Candidate solutions are modified using this method by making a lot of minor modifications and a few big jumps. As a result, CS will be able to significantly increase the link between exploration and exploitation while also improving its search capabilities. The cuckoo search optimization (CSO) algorithm is applied to interval type-2 fuzzy logic controller (IT2FLC) in this research to determine the optimal parameters of membership functions (MFs) of interval type-2 fuzzy logic systems (IT2FLSs). The study takes into account two forms of MFs: triangular and trapezoidal. When perturbations are applied during the execution of each control issue, the CSO algorithm's performance and efficiency improve significantly. The proposed approach is tested using two benchmark control problems: water tank controller and inverted pendulum controller.
Regarding the ubiquity of digitalization and electronic processing, an automated review processing system, also known as sentiment analysis, is crucial. There were many architectures and word embeddings employed for effective sentiment analysis. Deep learning is now-a-days becoming prominent for solving these problems as huge amounts of data get generated per second. In deep learning, word embedding acts as a feature representative and plays an important role. This paper proposed a novel deep learning architecture which represents hybrid embedding techniques that address polysemy, semantic and syntactic issues of a language model, along with justifying the model prediction. The model is evaluated on sentiment identification tasks, obtaining the result as F1-score 0.9254 and F1-score 0.88, for MR and Kindle dataset respectively. The proposed model outperforms many current techniques for both tasks in experiments, suggesting that combining context-free and context-dependent text representations potentially capture complementary features of word meaning. The model decisions justified with the help of visualization techniques such as t-SNE.
Face recognition using 3D scans can be achieved by many approaches, but most of these approaches are based on high quality depth sensors. In this paper, the authors use the normal maps obtained from the Kinect sensor to investigate the usefulness of data augmentation and signal-level fusion derived from depth data captured by a low quality sensor. In this face recognition process, the authors first preprocess the captured 3D scan of each person by cropping the face and reducing the noise; normals are computed and separated into three maps: Nx, Ny, and Nz. the authors combine the three normal maps to form an RGB image; these images are used to train a convolutional neural network. The authors investigate the order of components that yields to the best accuracy and compare it with previous results obtained on CurtinFaces and KinectFaceDB databases, achieving rank one identification rate of 94.04% and 91.35%, respectively.
The future of computer vision lies in deep learning to develop machines to solve our human problems. One of the most important areas of research is smart video surveillance. This feature is related to the study and recognition of movements, and it's used in many fields, like security, sports, medicine, and a whole lot of new applications. The study and analysis of human activity is very important to improve because it is a very sensitive field, like in security, the human needs a machine's help a lot; and in recent years, developers have adopted many advanced algorithms to discover the type of movements humans preform, and the results differ from one to another. The most important part of human activity recognition is real time, so one can detect any issue, like a medical problem, in time. In this regard, the authors will use methods of deep learning to reach a good result of recognition of the nature of human action in real time clips.
