Showing papers in "Multimedia Tools and Applications in 2019"

Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey

Abstract: Topic modeling is one of the most powerful techniques in text mining for data mining, latent data discovery, and finding relationships among data and text documents. Researchers have published many articles in the field of topic modeling and applied in various fields such as software engineering, political science, medical and linguistic science, etc. There are various methods for topic modelling; Latent Dirichlet Allocation (LDA) is one of the most popular in this field. Researchers have proposed various models based on the LDA in topic modeling. According to previous work, this paper will be very useful and valuable for introducing LDA approaches in topic modeling. In this paper, we investigated highly scholarly articles (between 2003 to 2016) related to topic modeling based on LDA to discover the research development, current trends and intellectual structure of topic modeling. In addition, we summarize challenges and introduce famous tools and datasets in topic modeling based on LDA.

Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation

Abstract: Fruit category identification is important in factories, supermarkets, and other fields Current computer vision systems used handcrafted features, and did not get good results In this study, our team designed a 13-layer convolutional neural network (CNN) Three types of data augmentation method was used: image rotation, Gamma correction, and noise injection We also compared max pooling with average pooling The stochastic gradient descent with momentum was used to train the CNN with minibatch size of 128 The overall accuracy of our method is 9494%, at least 5 percentage points higher than state-of-the-art approaches We validated this 13-layer is the optimal structure The GPU can achieve a 177? acceleration on training data, and a 175? acceleration on test data We observed using data augmentation can increase the overall accuracy Our method is effective in image-based fruit classification

Feature selection for text classification: A review

Abstract: Big multimedia data is heterogeneous in essence, that is, the data may be a mixture of video, audio, text, and images. This is due to the prevalence of novel applications in recent years, such as social media, video sharing, and location based services (LBS), etc. In many multimedia applications, for example, video/image tagging and multimedia recommendation, text classification techniques have been used extensively to facilitate multimedia data processing. In this paper, we give a comprehensive review on feature selection techniques for text classification. We begin by introducing some popular representation schemes for documents, and similarity measures used in text classification. Then, we review the most popular text classifiers, including Nearest Neighbor (NN) method, Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), and Neural Networks. Next, we survey four feature selection models, namely the filter, wrapper, embedded and hybrid, discussing pros and cons of the state-of-the-art feature selection approaches. Finally, we conclude the paper and give a brief introduction to some interesting feature selection work that does not belong to the four models.

Remote health monitoring of elderly through wearable sensors

Abstract: Due to a rapidly increasing aging population and its associated challenges in health and social care, Ambient Assistive Living has become the focal point for both researchers and industry alike. The need to manage or even reduce healthcare costs while improving the quality of service is high government agendas. Although, technology has a major role to play in achieving these aspirations, any solution must be designed, implemented and validated using appropriate domain knowledge. In order to overcome these challenges, the remote real-time monitoring of a person’s health can be used to identify relapses in conditions, therefore, enabling early intervention. Thus, the development of a smart healthcare monitoring system, which is capable of observing elderly people remotely, is the focus of the research presented in this paper. The technology outlined in this paper focuses on the ability to track a person’s physiological data to detect specific disorders which can aid in Early Intervention Practices. This is achieved by accurately processing and analysing the acquired sensory data while transmitting the detection of a disorder to an appropriate career. The finding reveals that the proposed system can improve clinical decision supports while facilitating Early Intervention Practices. Our extensive simulation results indicate a superior performance of the proposed system: low latency (96% of the packets are received with less than 1 millisecond) and low packets-lost (only 2.2% of total packets are dropped). Thus, the system runs efficiently and is cost-effective in terms of data acquisition and manipulation.

Abstractive text summarization using LSTM-CNN based deep learning

Abstract: ive Text Summarization (ATS), which is the task of constructing summary sentences by merging facts from different source sentences and condensing them into a shorter representation while preserving information content and overall meaning. It is very difficult and time consuming for human beings to manually summarize large documents of text. In this paper, we propose an LSTM-CNN based ATS framework (ATSDL) that can construct new sentences by exploring more fine-grained fragments than sentences, namely, semantic phrases. Different from existing abstraction based approaches, ATSDL is composed of two main stages, the first of which extracts phrases from source sentences and the second generates text summaries using deep learning. Experimental results on the datasets CNN and DailyMail show that our ATSDL framework outperforms the state-of-the-art models in terms of both semantics and syntactic structure, and achieves competitive results on manual linguistic quality evaluation.

Multi-layer security of medical data through watermarking and chaotic encryption for tele-health applications

Abstract: In this paper, we present a robust and secure watermarking approach using transform domain techniques for tele-health applications. The patient report/identity is embedding into the host medical image for the purpose of authentication, annotation and identification. For better confidentiality, we apply the chaos based encryption algorithm on watermarked image in a less complex manner. Experimental results clearly indicated that the proposed technique is highly robust and sufficient secure for various forms of attacks without any significant distortions between watermarked and cover image. Further, the performance evaluation of our method is found better to existing state-of-the-art watermarking techniques under consideration. Furthermore, quality analysis of the watermarked image is estimated by subjective measure which is beneficial in quality driven healthcare industry.

Android malware detection based on system call sequences and LSTM

Abstract: As Android-based mobile devices become increasingly popular, malware detection on Android is very crucial nowadays. In this paper, a novel detection method based on deep learning is proposed to distinguish malware from trusted applications. Considering there is some semantic information in system call sequences as the natural language, we treat one system call sequence as a sentence in the language and construct a classifier based on the Long Short-Term Memory (LSTM) language model. In the classifier, at first two LSTM models are trained respectively by the system call sequences from malware and those from benign applications. Then according to these models, two similarity scores are computed. Finally, the classifier determines whether the application under analysis is malicious or trusted by the greater score. Thorough experiments show that our approach can achieve high efficiency and reach high recall of 96.6% with low false positive rate of 9.3%, which is better than the other methods.

A healthcare monitoring system using random forest and internet of things (IoT)

Abstract: The Internet of Things (IoT) enabled various types of applications in the field of information technology, smart and connected health care is notably a crucial one is one of them. Our physical and mental health information can be used to bring about a positive transformation change in the health care landscape using networked sensors. It makes it possible for monitoring to come to the people who don't have ready access to effective health monitoring system. The captured data can then be analyzed using various machine learning algorithms and then shared through wireless connectivity with medical professionals who can make appropriate recommendations. These scenarios already exist, but we intend to enhance it by analyzing the past data for predicting future problems using prescriptive analytics. It will allow us to move from reactive to visionary approach by rapidly spotting trends and making recommendations on behalf of the actual medical service provider. In this paper, the authors have applied different machine learning techniques and considered public datasets of health care stored in the cloud to build a system, which allows for real time and remote health monitoring built on IoT infrastructure and associated with cloud computing. The system will be allowed to drive recommendations based on the historic and empirical data lying on the cloud. The authors have proposed a framework to uncover knowledge in a database, bringing light to disguise patterns which can help in credible decision making. This paper has evaluated prediction systems for diseases such as heart diseases, breast cancer, diabetes, spect_heart, thyroid, dermatology, liver disorders and surgical data using a number of input attributes related to that particular disease. Experimental results are conducted using a few machine learning algorithms considered in this paper like K-NN, Support Vector Machine, Decision Trees, Random Forest, and MLP.

Impact of digital fingerprint image quality on the fingerprint recognition accuracy

Abstract: Despite the large body of work on fingerprint identification systems, most of it focused on using specialized devices. Due to the high price of such devices, some researchers directed their attention to digital cameras as an alternative source for fingerprints images. However, such sources introduce new challenges related to image quality. Specifically, most digital cameras compress captured images before storing them leading to potential losses of information. This study comes to address the need to determine the optimum ratio of the fingerprint image compression to ensure the fingerprint identification system’s high accuracy. This study is conducted using a large in-house dataset of raw images. Therefore, all fingerprint information is stored in order to determine the compression ratio accurately. The results proved that the used software functioned perfectly until a compression ratio of (30–40%) of the raw images; any higher ratio would negatively affect the accuracy of the used system.

Interest point based face recognition using adaptive neuro fuzzy inference system

Abstract: In this paper, an efficient face recognition method using AGA and ANFIS-ABC has been proposed. At first stage, the face images gathered from the database are preprocessed. At Second stage, an interest point which is used to improve the detection rate consequently. The parameters used in the interest point determination are optimized using the Adaptive Genetic Algorithm. Finally using ANFIS, face images are classified by using extracted features. During the training process, the parameters of ANFIS are optimized using Artificial Bee Colony Algorithm (ABC) in order to improve the accuracy. The performance of the proposed ANFIS-ABC technique is evaluated using an ORL database with 400 images of 40 individuals, YALE-B database with 165 images of 15 individuals and finally with real time video the detection rate and false alarm rate is compared with proposed and existing methods to prove the system efficiency.

Counting-based secret sharing technique for multimedia applications

Abstract: Secret Sharing is required in situations where access to important resources has to be protected by more than one person. We propose new secret-sharing scheme that works based on parallel counting of the ones within the shares to generate the secret output. Our work presented two different modeling variations that are mainly different in the secret-sharing keys generation where both are studied elaborating their pros and cons. Our counting-based secret shares key reconstruction is implemented and simulated considering the security level required by the usage functions. Comparisons showed interesting results that are attractive to be considered. This secret sharing method is of great benefit to all multimedia secret sharing applications such as securing bank sensitive accounts and error tracking, voting systems trust, medical agreements, wills and inheritance authentication management.

A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis

Abstract: Nowadays, social media has become a tremendous source of acquiring user’s opinions. With the advancement of technology and sophistication of the internet, a huge amount of data is generated from various sources like social blogs, websites, etc. In recent times, the blogs and websites are the real-time means of gathering product reviews. However, excessive number of blogs on the cloud has enabled the generation of huge volume of information in different forms like attitudes, opinions, and reviews. Therefore, a dire need emerges to find a method to extract meaningful information from big data, classify it into different categories and predict end user’s behaviors or sentiments. Long Short-Term Memory (LSTM) model and Convolutional Neural Network (CNN) model have been applied to different Natural Language Processing (NLP) tasks with remarkable and effective results. The CNN model efficiently extracts higher level features using convolutional layers and max-pooling layers. The LSTM model is capable to capture long-term dependencies between word sequences. In this study, we propose a hybrid model using LSTM and very deep CNN model named as Hybrid CNN-LSTM Model to overcome the sentiment analysis problem. First, we use Word to Vector (Word2Vc) approach to train initial word embeddings. The Word2Vc translates the text strings into a vector of numeric values, computes distance between words, and makes groups of similar words based on their meanings. Afterword embedding is performed in which the proposed model combines set of features that are extracted by convolution and global max-pooling layers with long term dependencies. The proposed model also uses dropout technology, normalization and a rectified linear unit for accuracy improvement. Our results show that the proposed Hybrid CNN-LSTM Model outperforms traditional deep learning and machine learning techniques in terms of precision, recall, f-measure, and accuracy. Our approach achieved competitive results using state-of-the-art techniques on the IMDB movie review dataset and Amazon movie reviews dataset.

A novel chaotic image encryption algorithm based on improved baker map and logistic map

Abstract: A novel image encryption algorithm based on double chaotic systems is proposed in this paper. On account of the limited chaotic range and vulnerability of a single chaotic map, we use the two-dimensional Baker chaotic map to control the system parameters and the state variable of the logistic chaotic map. After control, the parameter of the logistic map is varying, and the generated logistic sequence is non-stationary. The improved map has been proven to be random and unpredictable by complexity analysis. Furthermore, a novel image encryption algorithm, including shuffling and substituting processes, is proposed based on the improved chaotic maps. Many statistical tests and security analysis indicate that this algorithm has an excellent security performance, and it can be competitive with some other recently proposed image encryption algorithms.

Gesture recognition based on skeletonization algorithm and CNN with ASL database

Abstract: In the field of human-computer interaction, vision-based gesture recognition methods are widely studied. However, its recognition effect depends to a large extent on the performance of the recognition algorithm. The skeletonization algorithm and convolutional neural network (CNN) for the recognition algorithm reduce the impact of shooting angle and environment on recognition effect, and improve the accuracy of gesture recognition in complex environments. According to the influence of the shooting angle on the same gesture recognition, the skeletonization algorithm is optimized based on the layer-by-layer stripping concept, so that the key node information in the hand skeleton diagram is extracted. The gesture direction is determined by the spatial coordinate axis of the hand. Based on this, gesture segmentation is implemented to overcome the influence of the environment on the recognition effect. In order to further improve the accuracy of gesture recognition, the ASK gesture database is used to train the convolutional neural network model. The experimental results show that compared with SVM method, dictionary learning + sparse representation, CNN method and other methods, the recognition rate reaches 96.01%.

Human consistency evaluation of static video summaries

Abstract: Automatic video summarization aims to provide brief representation of videos. Its evaluation is quite challenging, usually relying on comparison with user summaries. This study views it in a different perspective in terms of verifying the consistency of user summaries, as the outcome of video summarization is usually judged based on them. We focus on human consistency evaluation of static video summaries in which the user summaries are evaluated among themselves using the consistency modelling method we proposed recently. The purpose of such consistency evaluation is to check whether the users agree among themselves. The evaluation is performed on different publicly available datasets. Another contribution lies in the creation of static video summaries from the available video skims of the SumMe datatset. The results show that the level of agreement varies significantly between the users for the selection of key frames, which denotes the hidden challenge in automatic video summary evaluation. Moreover, the maximum agreement level of the users for a certain dataset, may indicate the best performance that the automatic video summarization techniques can achieve using that dataset.

Multi-target tracking using CNN-based features: CNNMTT

Abstract: In this paper, we focus mainly on designing a Multi-Target Object Tracking algorithm that would produce high-quality trajectories while maintaining low computational costs. Using online association, such features enable this algorithm to be used in applications like autonomous driving and autonomous surveillance. We propose CNN-based, instead of hand-crafted, features to lead to higher accuracies. We also present a novel grouping method for 2-D online environments without prior knowledge of camera parameters and an affinity measure based on the groups maintained in previous frames. Comprehensive evaluations of our algorithm (CNNMTT) on a publicly available and widely used dataset (MOT16) reveal that the CNNMTT method achieves high quality tracking results in comparison to the state of the art while being faster and involving much less computational cost.

Color image chaos encryption algorithm combining CRC and nine palace map

Abstract: The color image encryption algorithm based on the chaos theory is not strong enough. In this paper, we proposed a color image chaos encryption algorithm combining Cyclic Redundancy Check (CRC) and nine palace map. Firstly, the pixel data of the plain image were moved and shuffled based on the theory of nine palace map. And the R, G and B components were extracted and converted into a binary sequence matrix that was then cyclically shifted based on the technology of generating CRC code. Finally, the encrypted image was derived from the XOR operation with random key matrix. The average entropy of encrypted image by our algorithm is 7.9993, which is slight improved compared with the coupled hyper chaotic Lorenz algorithm in previous studies. In addition, the algorithm has the advantages of large key space, high key sensitivity, anti-robust attack, and feasible encryption efficiency.

Survey of robust and imperceptible watermarking

Abstract: Robustness, imperceptibility and embedding capacity are the preliminary requirements of any watermarking technique. However, research concluded that these requirements are difficult to achieve at same time. In this paper, we review various recent robust and imperceptible watermarking methods in spatial and transform domain. Further, the paper introduces elementary concepts of digital watermarking, characteristics and novel applications of watermark in detail. Furthermore, various analysis and comparison of different notable watermarking techniques are discussed in tabular format. We believe that our survey contribution will helpful for fledgling researchers to develop robust and imperceptible watermarking algorithms for various practical applications.

A novel chaotic image encryption technique based on multiple discrete dynamical maps

Abstract: The propagation of information over insecure communication system is one of the most important aspect of digitally advance era. The electronic information is travels in form of binary bits. The secrecy of these digital contents is one of the most important issue of existing world. In this article, we have utilized multiple chaotic iterative maps in order to propose a novel image encryption technique. The suggested encryption added confusion as well as diffusion in offered scheme which is one of the most fundamental aspect of encryption technique. We have tested our anticipated scheme against different performances analysis and compared it with already existing results. The designed scheme is capable of providing an excellent privacy to digital images.

Deep features-based speech emotion recognition for smart affective services

Abstract: Emotion recognition from speech signals is an interesting research with several applications like smart healthcare, autonomous voice response systems, assessing situational seriousness by caller affective state analysis in emergency centers, and other smart affective services. In this paper, we present a study of speech emotion recognition based on the features extracted from spectrograms using a deep convolutional neural network (CNN) with rectangular kernels. Typically, CNNs have square shaped kernels and pooling operators at various layers, which are suited for 2D image data. However, in case of spectrograms, the information is encoded in a slightly different manner. Time is represented along the x-axis and y-axis shows frequency of the speech signal, whereas, the amplitude is indicated by the intensity value in the spectrogram at a particular position. To analyze speech through spectrograms, we propose rectangular kernels of varying shapes and sizes, along with max pooling in rectangular neighborhoods, to extract discriminative features. The proposed scheme effectively learns discriminative features from speech spectrograms and performs better than many state-of-the-art techniques when evaluated its performance on Emo-DB and Korean speech dataset.

Score level based latent fingerprint enhancement and matching using SIFT feature

Abstract: Latent fingerprint identification is such a difficult task to law enforcement agencies and border security in identifying suspects. It is a too complicate due to poor quality images with non-linear distortion and complex background noise. Hence, the image quality is required for matching those latent fingerprints. The current researchers have been working based on minutiae points for fingerprint matching because of their accuracy are acceptable. In an effort to extend technology for fingerprint matching, our model is to propose the enhancementand matching for latent fingerprints using Scale Invariant Feature Transformation (SIFT). It has involved in two phases (i) Latent fingerprint contrast enhancement using intuitionistic type-2 fuzzy set (ii) Extract the SIFTfeature points from the latent fingerprints. Then thematching algorithm is performedwith n- number of images and scoresare calculated by Euclidean distance. We tested our algorithm for matching, usinga public domain fingerprint database such as FVC-2004 and IIIT-latent fingerprint. The experimental consequences indicatethe matching result is obtained satisfactory compare than minutiae points.

Spectrogram based multi-task audio classification

Abstract: Audio classification is regarded as a great challenge in pattern recognition. Although audio classification tasks are always treated as independent tasks, tasks are essentially related to each other such as speakers’ accent and speakers’ identification. In this paper, we propose a Deep Neural Network (DNN)-based multi-task model that exploits such relationships and deals with multiple audio classification tasks simultaneously. We term our model as the gated Residual Networks (GResNets) model since it integrates Deep Residual Networks (ResNets) with a gate mechanism, which extract better representations between tasks compared with Convolutional Neural Networks (CNNs). Specifically, two multiplied convolutional layers are used to replace two feed-forward convolution layers in the ResNets. We tested our model on multiple audio classification tasks and found that our multi-task model achieves higher accuracy than task-specific models which train the models separately.

A survey on sentiment analysis and opinion mining for social multimedia

Abstract: Social media sentiment analysis (also known as opinion mining) which aims to extract people's opinions, attitudes and emotions from social networks has become a research hotspot. Conventional sentiment analysis concentrates primarily on the textual content. However, multimedia sentiment analysis has begun to receive attention since visual content such as images and videos is becoming a new medium for self-expression in social networks. In order to provide a reference for the researchers in this active area, we give an overview of this topic and describe the algorithms of sentiment analysis and opinion mining for social multimedia. Having conducted a brief review on textual sentiment analysis for social media, we present a comprehensive survey of visual sentiment analysis on the basis of a thorough investigation of the existing literature. We further give a summary of existing studies on multimodal sentiment analysis which combines multiple media channels. We finally summarize the existing benchmark datasets in this area, and discuss the future research trends and potential directions for multimedia sentiment analysis. This survey covers 100 articles during 2008---2018 and categorizes existing studies according to the approaches they adopt.

Invisible steganography via generative adversarial networks

Abstract: Nowadays, there are plenty of works introducing convolutional neural networks (CNNs) to the steganalysis and exceeding conventional steganalysis algorithms. These works have shown the improving potential of deep learning in information hiding domain. There are also several works based on deep learning to do image steganography, but these works still have problems in capacity, invisibility and security. In this paper, we propose a novel CNN architecture named as ISGAN to conceal a secret gray image into a color cover image on the sender side and exactly extract the secret image out on the receiver side. There are three contributions in our work: (i) we improve the invisibility by hiding the secret image only in the Y channel of the cover image; (ii) We introduce the generative adversarial networks to strengthen the security by minimizing the divergence between the empirical probability distributions of stego images and natural images. (iii) In order to associate with the human visual system better, we construct a mixed loss function which is more appropriate for steganography to generate more realistic stego images and reveal out more better secret images. Experiment results show that ISGAN can achieve start-of-art performances on LFW, PASCAL-VOC12 and ImageNet datasets.

A hybrid approach to scheduling real-time IoT workflows in fog and cloud environments

Abstract: In this paper, we propose a hybrid fog and cloud-aware heuristic for the dynamic scheduling of multiple real-time Internet of Things (IoT) workflows in a three-tiered architecture. In contrast to traditional approaches where the main processing of IoT jobs is performed in the fog layer, our approach attempts to schedule computationally demanding tasks with low communication requirements in the cloud and communication intensive tasks with low computational demands in the fog, utilizing possible gaps in the schedule of the fog and cloud virtual machines. Furthermore, during the scheduling process, our approach takes into account the communication cost incurred by the transfer of data from the sensors and devices in the IoT layer to the fog layer. The performance of the proposed heuristic is evaluated and compared via simulation to a baseline cloud-unaware strategy, under different cases of workload. The simulation results reveal that the proposed scheduling heuristic provides on average 76.69% lower deadline miss ratio, compared to the baseline policy. However, this is achieved at a significant monetary cost, due to the usage of cloud resources.

A novel hybrid DCT and DWT based robust watermarking algorithm for color images

Abstract: In this paper, a novel robust color image watermarking method based on Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) is proposed. In this method, RGB cover image is divided into red, green and blue components. DCT and DWT are applied to each color components. Grayscale watermark image is scrambled by using Arnold transform. DCT is performed to the scrambled watermark image. Transformed watermark image is then divided into equal smaller parts. DCT coefficients of each watermark parts are embedded into four DWT bands of the color components of the cover image. The robustness of the proposed color image watermarking has been demonstrated by applying various image processing operations such as rotating, resizing, filtering, jpeg compression, and noise adding to the watermarked images. Experimental results show that the proposed method is robust to the linear and nonlinear attacks and the transparency of the watermarked images has been protected.

Enhancing speed of SIMON: A light-weight-cryptographic algorithm for IoT applications

Abstract: Multimedia communication is revolutionizing all major spheres of human life. The advent of IoT and its applications in many fields like sensing, healthcare and industry, result exponential increase in multimedia data, that needs to be shared over insecure networks. IoT driven setups are however constrained in terms of resources as a result of their small size. From data security point of view a conventional algorithms cannot be used for data encryption on an IoT platform given the resource constraints. The work presented in this paper studies the performance of SIMON cryptographic algorithm and proposes a light-weight-cryptography algorithm based on SIMON for its possible use in an IoT driven setup. The focus is on speed enhancement benefitting from software prospective, making it different than common studies mostly reflecting hardware implementations. To achieve performance in practical prospective, the contribution looks into SIMON cipher’s characteristics considering utilizing it for internet of things (IoT) healthcare applications. The paper suggests further improvement to implement the original SIMON cryptography in order to reduce the encryption time and maintain the practical trade-off between security and performance. The proposed work has been compared to Advanced Encryption Standard (AES) and the original SIMON block cipher algorithms in terms of execution time, memory consumption. The results show that the proposed work is suitable for securing data in an IoT driven setup.

An efficient employment of internet of multimedia things in smart and future agriculture

Abstract: Efficiently managing the irrigation process has become necessary to utilize water stocks due to the lack of water resources worldwide. Parched plant leads into hard breathing process, which would result in yellowing leaves and sprinkles in the soil. In this work, yellowing leaves and sprinkles in the soil have been observed using multimedia sensors to detect the level of plant thirstiness in smart farming. We modified the IoT concepts to draw an inspiration towards the perspective vision of ’Internet of Multimedia Things’ (IoMT). This research focuses on the smart employment of internet of Multimedia sensors in smart farming to optimize the irrigation process. The concepts of image processing work with IOT sensors and machine learning methods to make the irrigation decision. sensors reading have been used as training data set indicating the thirstiness of the plants, and machine learning techniques including the state-of-the-art deep learning were used in the next phase to find the optimal decision. The conducted experiments in this research are promising and could be considered in any smart irrigation system. The experimental results showed that the use of deep learning proves to be superior in the Internet of Multimedia Things environment.

A novel bit-level color image encryption using improved 1D chaotic map

Abstract: This paper introduces new simple and effective improved one-dimension(1D) Logistic map and Sine map made by the output sequences of two same existing 1D chaotic maps. The comparison analysis of the proposed improved 1D chaotic map and previous 1D chaotic map confirmed the accuracy of the improved chaotic map. To investigate the applications of the improved chaotic system in image encryption, a novel bit-level image encryption system is proposed. Experiments and analysis prove that the improved chaotic map and the algorithm has an excellent performance in image encryption and various attacks.

A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation

Abstract: In medical field, it remains challenging to accurately segment medical images due to low contrast, complex noises and intensity inhomogeneity. To overcome these obstacles, this paper provides a novel edge-based active contour model (ACM) for medical image segmentation. Specifically, an accurate regularization approach is presented to maintain the level set function with a signed distance property, which guarantees the stability of the evolution curve and the accuracy of the numerical computation. More significantly, an adaptive perturbation is integrated into the framework of the edge-based ACM. The perturbation technique can balance the stability of curve evolution and the accuracy of segmentation, which is key for segmenting medical images with intensity inhomogeneity. A number of experiments on both artificial and real medical images demonstrate that the proposed segmentation model outperforms state-of-the-art methods in terms of robustness to noise and segmentation accuracy.