To enhance the security of single-chaotic systems, we propose a novel image encryption cryptosystem based on true random numbers and chaotic systems. First, we select any one of several chaotic systems. Next, the hash function is used to calculate the initial value of the chaotic system using a plaintext image. Then, we obtain a solution of this chaotic system and use the k-medoids clustering machine-learning algorithm and chaotic sequence to scramble the original image. Finally, new random numbers obtained using a chaotic signal and true random numbers are used to perform the exclusive-OR operator on the scrambled results. To illustrate the effectiveness of our method, a one-dimensional (1D) logistic chaotic system is selected for image encryption. The simulation results show that compared with the existing models, such as image encryption based on chaos and image encryption based on the advanced encryption standar (AES), our method is simpler with a higher security and resists different classical attacks.

A novel image encryption cryptosystem based on true random numbers and chaotic systems

In today’s modern era, parking remains a big problem for a lot of people. This problem consumes a person individual’s time by finding the right spot for parking. In the current research, the concept of an automatic parking system using the vehicle license plate or the number plate recognition is discussed. It will improve the process with much less hassle by removing human interaction. It will also lead to advancement in the security of vehicles evading the requirement of a slip or a magnetic card which is used to goes in and out for registering vehicles in a parking place. The researcher uses image processing algorithms to make an entry in the database of the parking automatically. AVNPR (Automatic Vehicle Number Plate Recognition) is used for the identification of the number of plates. Due to noise issues, deep algorithms like CNN (convolutional neural networks), RNN (recurrent neural networks) do not correctly recognize the miss-identification of the numbers in the vehicle plate. This problem is rectified by the authors by using the GAN (Generative adversarial networks) algorithm. GAN helps to create high-resolution images from a single low-resolution image. After applying the GAN, the classification of the vehicle plate is done through CNN. During experimentation, the proposed approach achieves 99.39% recognition accuracy for a vehicle number plate. Hence, the proposed system is suitable for identifying the numbers in the vehicle number plate automatically. Moreover proposed system compared with existing models, it has been found that it has achieved higher accuracy than the other models.

GAN-based synthetic data augmentation for increased CNN performance in Vehicle Number Plate Recognition

In this digital era, it is a common practice to check reviews about a service or product before it buying. A five star rating scale system provides much easier interface to the consumers for checking the reviews about the corresponding service or product, instead of just classifying the reviews as good, neutral and bad. Moreover, it is very common for a single review which can praise the product and criticize it as well. Even if two reviews over all, show the same sentiment. However, the order in which they praise or criticize a product, can make their star rating quite different. We have considered such observations to deploy our proposed STAR model, which addresses the above concerns by involving the variation of sentiment in reviews, to greatly affect the star rating performance. This work highlights a two Phases based novel approach using transfer learning framework to analyze the reviews by exploiting the variation in human being emotions. The experimental analysis shows that the STAR model outperforms the state-of-the-art models.

STAR: rating of reviewS by exploiting variation in emoTions using trAnsfer leaRning framework

Smart Internet of Things (IoT) applications require real-time and robust predictive analytics, which are based on Machine Learning (ML) models. Building ML models from Big Data is not only time-consuming, but developers often lack the needed expertise for feature engineering, parameter tuning, and model selection. The proliferation of ML libraries and frameworks, data ingestion tools, stream and batch processing engines, visualization techniques, and the range of available hardware platforms further exacerbates the system design, rapid development, and deployment problems. Finally, resource constraints of IoT require that the execution of the analytics engine be distributed across the cloud-edge spectrum. To overcome these daunting challenges, we present Stratum, which is an event-driven Big Data-as-a-Service offering for IoT analytics lifecycle management. Stratum provides users with an intuitive, declarative mechanism based on the principles of model-driven engineering to specify the application and infrastructure requirements. It automates the deployment via generative programming principles. This paper highlights the problems that Stratum resolves, demonstrating its capabilities using real-world case studies.

STRATUM: A BigData-as-a-Service for Lifecycle Management of IoT Analytics Applications

Reversible data hiding for encrypted media not only preserves the privacy of the media content but also can convey additional information during message transmission. Some studies advocate separability, that is, the message can be correctly extracted irrespective of whether the encrypted media has been decrypted. However, current research has focused on encrypted images. Urgent research is required on encrypted three-dimensional (3D) models. This paper proposes a separable reversible data hiding method based on spatial subdivision and space encoding for encrypted 3D models. A bounding volume is first constructed using the vertices with boundary values in the processing model. Each vertex coordinate value is then converted into a ratio (between 0 and 1) of the distance between the vertex and minimum boundary point to the side length of the bounding volume. The owner of the 3D model then uses a secret key to encrypt all ratios except those of the boundary vertices to obtain an encrypted 3D model of the same size as the original model. The spatial subdivision technique and a subdivision threshold are subsequently used to divide the bounding volume into a series of blocks and simultaneously control the vertex distortion. The secret message is embedded in the encrypted vertex by using the space encoding method with an embedding threshold. Experimental results indicate that the proposed algorithm enables high privacy, performs separable reversible data hiding, and has low computational complexity, high embedding capacity, and controllable distortion.

Separable Reversible Data Hiding for Encrypted Three-Dimensional Models Based on Spatial Subdivision and Space Encoding

In this digital world, multimedia content is increasing exponentially. Videos occupy the core of this multimedia data. Today, application of videos can be found in almost every field of security surveillance, traffic supervision, weather monitoring, video conferences, social media, etc. Storage and transmission of this data have thus become a prime concern, keeping security and privacy aspects in mind. In order to address the above issue, a new algorithm has been put forward in this paper based on Multi-Secret Sharing scheme along with temporal reordering of frames. Cryptography involving traditional encryption algorithms like DES and AES are found computationally infeasible in real time due to use of Block Ciphers where 128-bit data is broken into blocks. Same transformation is applied to each block and later re-combined resulting expensive to use. However, the V⊕SEE encryption process requires less bandwidth and computational power as compared to AES and DES. As the number of wireless devices being used today which have limited bandwidth and computational power, the algorithm is designed for efficient computation with limited resources. The qualitative and quantitative evaluation is performed in order to compare the performance of the proposed model, existing models and state-of-the-art models. A computing analysis indicates that the proposed approach can meet the requirement of real-time applications.

V⊕SEE: Video secret sharing encryption technique

Deep learning empowered the license plate recognition (LPR) system which can efficiently extract the information from a vehicle’s license plate. LPR has various applications in this digital world. Due to technology growing at a rocketing pace, there is a rapid growth in the number of vehicles on road. Even self-driving cars are soon to be a common sight. This is causing a fast and frequent growth in the accidents occurrence and other mishaps. Thus, there is a need for monitoring traffic and security surveillance. LPR technique is not new. However, traditionally the extracting features from an image/ license plate were done hand-tunned which make the recognition process time-consuming and error-prone. In this paper, we proposed a novel machine learning approach to recognizing the license plate number. We used one of the most successful deep learning method, convolutional neural network (CNN) for extracting the visual features automatically. Suitable localization and segmentation techniques are employed before CNN model to enhance the accuracy of the proposed model. In addition to this, the D-PNR model also takes care of proper identification from images those are hazy and is not suitable-inclined or noisy images. Qualitative and quantitative evaluation is done in order to compare the performances of the proposed D-PNR model and state-of-the-art models. A computing analysis of our approach also shows that it meets the requirement of the real-time applications, i.e., monitoring traffic and security surveillance

Piyushi Manupriya

Papers

V⊕SEE: Video secret sharing encryption technique

D-PNR: Deep License Plate Number Recognition