International Journal on Future Revolution in Computer Science & Communication Engineering
Not a member yet
1384 research outputs found
Sort by
Fuzzy Logic and ANFIS based Short Term Solar Energy Forecasting
Get PDFAccurate forecasting of solar energy is a key issue for a meaningful integration of the solar power plants into the grid. Solar photovoltaic technology is most preferable and vital all other sources of renewable energy. We know that the solar Energy is very irregular so the result output of solar voltaic systems (SPV) diverted by the atmospheric nature like temperatures, humidity, wind velocity, solar irradiance and other climatologically facts. It�s necessary to prediction of solar energy is most important to minimise uncertainty in power harness from solar photovoltaic system. In this work fuzzy logic model and ANFIS model have been developed for manipulating solar irradiation (w/m2) data to forecasting short term solar energy. In the month of September 2017 has been monitoring for an hourly data of solar irradiance used as input and actual desired output. In the present paper sets the Normalization of input and desired output in between 0.1 to 0.9 for reducing confluence problems. Acquired results are match up to the manipulated data and get valid result. The implementation of the model is estimated on the basis of mean absolute percentage error
Wavelet-based Image Splicing Forgery Detection
Get PDFDigital image processing is a progressive field which has made development over period of time in a way that it becomes easy to play with artifacts of image by manipulating them using transformation such as copy-paste, copy-move, rotation, smoothing of boundaries, scaling, color enhancing, resizing, addition of noise, blurring, compressing etc. Forgery performed with a digital image, raising a doubt about the authenticity of it. Image splicing is one of the most used method for tampering an image by compositing two or many image fragments to create a spliced image. In this paper, a wavelet-based mechanism is proposed to detect image splicing forgery by taking edge information of an image as a distinguishing feature by performing edge analysis using wavelet transform. Haar-based Discrete Wavelet Transform (DWT) is used for edge analysis that decompose an image into four sub-images and it followed by Speed-Up Robust Feature (SURF) method which is a keypoint-based feature extractor technique. SURF extracts features from the decomposed images of DWT and used that features for performing classification using SVM linear classifier
Energy Efficient Power Allocation In Cognitive Radio Network
Get PDFEnergy efficient wireless cellular networks have been the subject of intense research in recent years. Green radio networks are the demand of new era of communication system. In order to improve the energy of cognitive radio network, the technique for power allocation in transmission link is proposed in this paper. Recently, many technological and network issues like interference and resource allocation or power optimization in cognitive radio network have been studied but only in terms of spectrum sensing. Different from the other work, the optimization of power in order to maximize the energy with consideration of imperfect spectrum sensing is proposed. Simulation result shows that for every value of power levels energy will be improved
Performance Analysis between OLSR and FSR Protocols under Black Hole Attack Using FPGA
Get PDFSecurity is an important part of wireless ad hoc network or mobile ad hoc network. A mobile ad hoc network (MANET) is an infrastructure less category of wireless network. Routing protocols in Mobile ad hoc network is divided into three categories, Reactive (also known as on demand) routing protocol, Proactive (also known as table driven) routing protocol and Hybrid protocol. Security is an important part in MANET because when we send data source node to destination node in mobile ad hoc network, we want protection in path between source to destination and complete transfer data packet between source node to destination node. In this research paper we use two proactive routing protocol known as OLSR (Optimized Link state Routing) Protocol and FSR (Fisheye State Routing) Protocol. OLSR is a flat routing and Unipath protocol based on multipoint relay not multipath. FSR is a hierarchical routing and multipath protocol based on multiple paths. In this research work we check the performance of these two protocols under five different performance matrices known as Packet delivery ratio (PDR), Packet loss (PL), Average end to end delay (AEED), Normalized Routing load (NRL) and Throughput on black hole attack. Black hole attack is an active attack, in this attack attacker node absorbs the data packet and give the fake reply. In this research paper we analysis the performance two protocol one is unipath known as OLSR and second is Multipath known as FSR under Black hole Attack. The performance of FSR is better than OLSR, because OLSR is unipath and maximum data packet is absorbs in OLSR single path. FSR is better because FSR is Multipath and minimum data packet is absorbs in FSR multi path
Road Accident Analysis System using Data Mining
Get PDFInformation Mining is expelling from hid cases from huge database. It is by and large used as a piece of a displaying, perception, coercion recognizable proof and consistent disclosure. In information mining, machine learning is fundamentally connected as research which is normally learnt to see complex cases and settle on cunning decisions in light of information. Globalization has impacted various countries. There has been an extraordinary addition in the monetary activities and use level, provoking augmentation of development and transportation. The extension in the vehicles, movement provoke street mischances. Contemplating the essentialness of the street prosperity, government is trying to recognize the explanations behind street mischances to diminish the mishaps level
Improving Performance of Primary System Storage using Data Deduplication
Get PDFWith the insecure improvement of mechanized data, de-duplication techniques are by and large used to fortification data and limit framework and limit overhead by perceiving and taking out overabundance among data. Instead of keeping different data copies with a similar substance, de-duplication takes out dull data by keeping emerge physical copy and suggesting different abundance data to that copy. De-duplication has become much thought from both the insightful world and industry in light of the way that it can altogether upgrades stockpiling use and extra storage space, especially for the applications with high de-duplication extent, for instance, recorded limit systems. Different de-duplication structures have been proposed considering distinctive de-duplication strategies, for instance, client side or server-side de-duplications, record level or square level de-duplications. Especially, with the approach of conveyed stockpiling, data de-duplication frameworks end up being all the more appealing and segregating for the organization of continually growing volumes of data in dispersed stockpiling organizations which motivates attempts and relationship to outsource data stockpiling
Sensor Based Wearable System to Assist Paralytic Patient with Continuous Health Monitoring
Get PDFIn Today�s world many people are suffering from paralysis and most of the paralytic patients are dependent on care takers. Paralysis is a condition in which there is impairment of one or more muscles in the body. In order to assist these patients, fingers of the hand play a major role in this proposed system. The patient is made to wear the sensor glove and recognition of finger bending is the mathematical interpretation of finger movement by the computing device. The system ensures the patient to express his requirements by converting the finger bending into auditory speech. If the same action is repeated thrice, indicating that the requirement is not yet fulfilled, the system will send a text message to the concerned care taker with the help of GSM module. Home appliances are also controlled by the patient�s finger wearing the sensor glove. In addition to this, the system continuously monitors the patient�s heart beat and body temperature. If the body temperature and heart beat exceeds the normal value, the buzzer will be activated to show the abnormalities with respect to patient so that the care taker can attend the patient
Detection of Diabetic Retinopathy Diseases for Color Fundus Images
Get PDFHere we address the detection of Hemorrhages and microaneurysms in color fundus images. In pre-Processing we separate red, green, blue color channel from the retinal images. The green channel will pass to the further process. The green color plane was used in the analysis since it shows the best contrast between the vessels and the background retina. Then we extract the GLCM(Gray Level Co-Occurance Matrix) feature. In the GLCMs, several statistics information are derived using the different formulas. These statistics provide information about the texture of an image. Such as Energy, Entropy, Dissimilarity, Contrast, Inverse difference , correlation Homogeneity, Auto correlation, Cluster Shade Cluster Prominence, Maximum probability, Sum of Squares will be calculated for texture image. After feature Extraction, we provide this feature to classifier. Finally it will predict about the retinal whether it is hemorrhages or microaneurysms . After predicting the about the retinal image we will localize the affected place. For segmenting the localized place we will use adaptive thresholding segmentation.
Semantic Search Approach in Cloud
Get PDFWith the approach of cloud computing, more and more information data are distributed to the public cloud for economic savings and ease of access. But, the encryption of privacy information is necessary to guarantee the security. Now a days efficient data utilization, and search over encrypted cloud data has been a great challenge. Solution of existing methods depends only on the keyword of submitted query and didn�t examine the semantics of keyword. Thus the search schemes are not intelligent and also omit some semantically related documents. To overcome this problem, we propose a semantic expansion based similar search solution over encrypted cloud data. The solution of this method will return not only the exactly matched files, but also the files including the terms semantically related to the query keyword. In this scheme, a corresponding file metadata is constructed for each file. After this, both the encrypted file metadata set and file collection are uploaded to the cloud server. With the help of metadata set file, the cloud server maintains the inverted index and create semantic relationship library (SRL) for the keywords set. After receiving a query request from user , this server firstly search out the keywords that are related to the query keyword according to SRL. After this, both the query keyword and the extensional words are used to retrieve the files to fulfill the user request. These files are returned in order according to the total relevance score. Our detailed security analysis shows that our method is privacy-preserving and secure than the previous searchable symmetric encryption (SSE) security definition. Experimental evaluation demonstrates the efficiency and effectives of the scheme
A Study on Graph Theory of Path Graphs
Get PDFA simple graph G = (V, E) consists of V , a nonempty set of vertices, and E, a set of unordered pairs of distinct elements of V called edges. Simple graphs have their limits in modeling the real world. Instead, we use multigraphs, which consist of vertices and undirected edges between these vertices, with multiple edges between pairs of vertices allowed. In the mathematical field of graph theory, a path graph or linear graph is a graph whose vertices can be listed in the order v1, v2, …, vn such that the edges are {vi, vi+1} where i = 1, 2, …, n ? 1. Equivalently, a path with at least two vertices is connected and has two terminal vertices (vertices that have degree 1), while all others (if any) have degree 2. Paths are often important in their role as subgraphs of other graphs, in which case they are called paths in that graph. A path is a particularly simple example of a tree, and in fact the paths are exactly the trees in which no vertex has degree 3 or more. A disjoint union of paths is called a linear forest