Recent Patents on Engineering - Volume 14, Issue 3, 2020

Background: Image forensics deal with the problem of authentication of pictures or their origins. There are two types of forensics techniques namely active and passive. Passive forgery is also known as blind forensics technique. In passive forgery, copy-move (cloning) image forensics is most common forgery technique. In this approach, an object or region of a picture is copied and positioned somewhere else in the same image. The active method used watermarking to solve picture genuineness problem. It has limitations like human involvement or particularly equipped cameras. To overwhelm these limitations, numerous passive authentication approaches have been developed. Moreover, both approaches do not require any prior information about the picture. Objective: The prime objective of this survey is to provide an inclusive summary as well as recent advancement, challenges and future direction in image forensics. In today’s digital era, digital pictures and videos are having a great impact on our life as well as society, as they became an important source of information. Though earlier it was very difficult to doctor the picture, nowadays digital pictures can be doctored easily with the help of editing tools and the internet. These practices make pictures as well as videos genuineness deceptive. Conclusion: This paper presents the current state-of-the-art of passive (cloning) image forensics techniques, challenges and future direction of this research domain. Furthermore, the major open issues in developing a robust cloning image forensics detector with their performance are discussed. Lastly, the available benchmark datasets are also discussed.

Multiple-Input Multiple-Output (MIMO) systems have been endorsed to enable future wireless communication requirements. The efficient system designing appeals an appropriate channel model that considers all the dominating effects of the wireless environment. Therefore, some complex or less analytically acquiescent composite channel models have been proposed typically for Single-Input Single-Output (SISO) systems. These models are explicitly employed for mobile applications, though, we need a specific study of a model for the MIMO system which can deal with radar clutters and different indoor/outdoor and mobile communication environments. Subsequently, the performance enhancement of the MIMO system is also required in such a scenario. The system performance enhancement can be examined by low error rate and high capacity using spatial diversity and spatial multiplexing respectively. Furthermore, for a more feasible and practical system modeling, we require a generalized noise model along with a composite channel model. Thus, all the patents related to MIMO channel models are revised to achieve the nearoptimal system performance in a real-world scenario. This review paper offers the methods to improve MIMO system performance in less and severe fading as well as shadowing environment and focused on a composite Weibull-gamma fading model. The development is the collective effects of selecting the appropriate channel models, spatial multiplexing/detection, and spatial diversity techniques both at the transmitter and the receivers in the presence of arbitrary noise.

In this paper, medical images are used to realize the Computer-Aided Diagnosis (CAD) system, which develops targeted solutions to existing problems. Relying on the MiCOM platform, this system has collected and collated cases of all kinds, based on which a unified data model is constructed according to the gold standard derived by deducting each instance. Afterwards, the object segmentation algorithm is employed to segment the diseased tissues. Edge modification and feature extraction are performed for the tissue block segmented. The features extracted are classified by applying support vector machines or the Naive Bayesian classification algorithm. From the simulation results, the CAD system developed in this paper allows the realization of diagnosis and treatment and sharing of data resources.

Large amount of data coming from different sources and formats is available on the web which generates heterogeneity problem. Semantic web technologies play an important role for collecting, merging, matching and aggregating big data from heterogeneous resources by determining the semantic correspondence between the entities. However, achieving good efficiency is major challenge for large scale ontology matching task. Objective: We propose a PBOM framework for coping with the large scale ontology matching problem. Methods: Our proposal first selects the source ontology and calculates the similarity of concepts within source ontology by using Lin measure. We use clustering algorithm for partition of the source ontology, obtained clusters of source ontology then used to divide the target ontology. During matching process, we run matchers from the pool of the matchers over each clusters. We aggregate the result of element level matchers and structure level matchers according to weighted sum aggregation. Each cluster is executed in its processor in parallel with other clusters. Result: We have presented step wise execution of proposed approach over one cluster of source and target ontology. The evaluation of our framework is performed by OAEI datasets of bibliographic benchmark 2014, biomedical track 2015 and anatomy 2016. Conclusion: Results show that, the performance of our approach is better in term of F-measure. The combination of clustering algorithm and parallel processing reduces the memory space and time complexity of matching process.

Background: In order to better realize the real-time on-line monitoring of the working state of the coal mill and determine the status of the equipment used in the coal mill, the intelligent embedded system of the coal mill based on DSP was studied. Methods: Firstly, the working requirement of the coal mill and the task of data acquisition system have been briefly introduced, and the requirement of the overall embedded system design has been put forward. Then, the structure design was analysed including both hardware and software, and the embedded system design including digital signal processing, and data acquisition was completed. All patents related to intelligent embedded data acquisition and storage system are described in detail. Results: After that, the function test of the actual coal mill embedded system was carried out, which proved the practicability and reliability of the designed embedded system for coal mill and based on DSP. Conclusion: The embedded system improves the automation level of coal mill, and is of great significance to the on-line monitoring and research of large-scale machinery and equipment in the future.

Background: In order to improve the efficiency of fault treatment of mining motor, the method of model construction is used to construct the type of kernel function based on the principle of vector machine classification and the optimization method of parameters. Methodology: One-to-many algorithm is used to establish two kinds of support vector machine (SVM) models for fault diagnosis of motor rotor of crusher. One of them is to obtain the optimal parameters C and g based on the input samples of the instantaneous power fault characteristic data of some motor rotors which have not been processed by rough sets. Patents on machine learning have also shows their practical usefulness in the selction of the feature for fault detection. Results: The results show that the instantaneous power fault feature extracted from the rotor of the crusher motor is obtained by the cross validation method of grid search k-weights (where k is 3) and the final data of the applied Gauss radial basis penalty parameter C and the nuclear parameter g are obtained. Conclusion: The model established by the optimal parameters is used to classify and diagnose the sample of instantaneous power fault characteristic measurement of motor rotor. Therefore, the classification accuracy of the sample data processed by rough set is higher.