The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Interest in machine learning with Deep Neural Network architectures has exponentially increased since the adoption of Convolution layers and GPUs for faster and larger network sizes. The efficiency of this combination has been proved for many different modalities (speech, video, images, etc.). The next natural progression is to develop dedicated hardware architectures that eventually allows for online...
Image classification domain has been an area which has attracted a lot of researchers over past years. Many classification methodologies for spatial image datasets has been developed. Artificial intelligence based approaches are getting popular now a days for getting the image classification task done in more efficient and correct way. The prime goal is to develop a classification mechanism which...
Design and implementation are two major aspects of the software development and the deviation between them needs to be minimized to the best extent possible. Of the many difficulties in detecting the deviation is the absence of common notation to compare the implementation artefact (code) against the design artefact. In this paper we present an approach to bridge the gap by providing a methodology...
Educational Data Mining is a prominent area to explore information in educational fields using data mining algorithms. In this paper we have used few learning algorithms to effectively rate the faculty belonging to an educational institute on the basis of feedback submitted by the students. Our proposed model uses sentimental analysis and machine learning classifier algorithms for capturing the emotions...
Medical imaging has been identified as one of the fastest growing of all health care sectors. Despite the overwhelming benefits of computed tomography (CT) in diagnosis, there is concern over radiation induced cancer. Retaining diagnostically acceptable medical image quality with minimum radiation dose is the current need in the healthcare system. In this paper we have optimized WH-HYPR low dose image...
The aging population and high labor cost have accelerated the need for service robots for household activities. The household activity being diverse robot training over dynamic environments is required. Our work aims in developing an algorithm for teaching a manipulator to perform a task. Teaching pendant simplifies the process of teaching for the end user and also trains manipulator to a user specific...
The rise of social media has brought about a new realm for people all over the globe to interact and share information and opinions. Twitter, Facebook, Blogs, Google+, etc. have become the most sought after platforms for people to share their opinions, feelings and feedback about the latest trends and products. Unlike formal documentation, people are free to express themselves in multiple languages,...
In Ad-hoc networks, routing is complex as nodes are mobile due to which paths are destroyed and generated again and again. The difficulty in MANET is to find a feasible path between communicating nodes as routing is non-deterministic polynomial hard which is due to mobile nature of nodes. Many past works focused on finding a feasible path from a source to destination by considering only a single parameter...
Nowadays, most of the cipher cryptographic technologies target on designing the algorithms which oppose an analytical attack by another third party intellectual property (3PIP) having access to cipher-text. In this regard, the physical security of cryptographic devices needs an immediate attention. Currently, due to the distributed functionality of the Integrated Circuit (IC) manufacturing industry,...
The increasing demand for underlaying cellular network has benefit form Device-to-Device (D2D) communication, where one need to apply productive plan for resource allocation to increase system capacity and mitigate interference. The bipartite graph matching strategy is used for optimizing the resource allocation among all other strategies; Kuhn-Munkres (KM) is one of algorithm applied to increase...
This work proposes an efficient method for the data pre-processing step of the information cycle. The method considers the open domain news feeds as data source. We try to handle the issue of open domain news data becoming unmanageably huge by designing a hybrid schema. The schema consists of two fold processing. One sifting and other filtering, both at logical levels. The data feeds are subjected...
Resonators can be energized using different feeding mechanisms. The effect of U-shaped Microstrip feed electromagnetically coupled to an open loop resonator is presented in this paper. The proposed feeding mechanism induces a band-stop response for the resonator. The band-stop filter optimized by simulation is fabricated and tested using Keysight E 5080 A Vector Network Analyzer. The measured results...
The highly imbalanced nature of software fault datasets results in poor performance of machine leaning techniques used for software fault prediction. The objective of this paper is to evaluate sampling techniques and Meta-Cost learning in software fault prediction to alleviate problem of imbalanced data. We evaluate four sampling techniques in metrics as well as code smells based fault prediction...
Recently, Convolutional neural network (CNN) architectures in deep learning have achieved significant results in the field of computer vision. To transform this performance toward the task of intrusion detection (ID) in cyber security, this paper models network traffic as time-series, particularly transmission control protocol / internet protocol (TCP/IP) packets in a predefined time range with supervised...
With the development of Internet e-commerce, shopping online has become very popular. Online stores have the advantage of having more items in their catalogue without worrying about shop constraints. In this scenario, recommendation systems are useful as they can help users in identifying items that they might be interested in. After shopping users usually provide feedback in the form review and ratings...
In this paper we present a bottom up procedure for segmentation of text lines written or printed in the Latin script. The proposed method uses a combination of image morphology, feature extraction and Gaussian mixture model to perform this task. The experimental results show the validity of the procedure.
India is primarily an agriculture-based country and its economy largely depends upon the agriculture. But, most of the crops grown by the farmer are affected by weeds. Weed identification and control remains one of the most challenging tasks in agriculture. The most widely used methods for weed control is manual spraying of herbicides. But, this method has several negative impacts. Since hand labor...
The communication barrier of deaf and dumb community with the society still remains a matter of concern due to lack of perfect sign language translators. Usage of mobile phones for communication remains a dream for deaf and dumb community. We propose an android application that converts sign language to natural language and enable deaf and dumb community to talk over mobile phones. Developing Sign...
Video steganography is a technique used for secret communication. In video steganography, the secret information is concealed in a video file. An MP4 video steganography method that hides audio and image data in wavelet domain is proposed in this paper. A video file consists of I-frame, P-frame, and B-frame. An I-frame, or intra frame, is decoded independently without referencing other frames. P-frames...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.