In this paper, we present a voice recognition based victim detection system using an Unmanned Aerial Vehicle (UAV). When large-scale disaster such as huge earthquake occurs, the building collapses and it is expected that many people will be buried in rubble. Under circumstances, very important to detect victims effectively order promptly rescue raise survival rate. Therefore, study, propose for detecting rescuing whose are speaker installed on UAV makes sounds react, detected by capturing...

In this research, we present a system that enables independent walking in individuals with visual impairment by recognizing tactile paving. The warns the user about dangers posed deviations from path or possible collisions. Therefore, paving itself and obstacles on it must be detected. This paper discusses problems related to detecting To address these problems, new camera-based method is introduced, which detects automatically. relies dynamic threshold approach HSV color space, making image...

Understanding social media contents has been a primary research topic since the dawn of networking. Especially, contextual understanding noisy text, which is characterized by high percentage spelling mistakes with creative spelling, phonetic typing, wordplay, abbreviations, and Meta tags. Thus, data processing demands more complex system than traditional natural language processors. Also people easily mixing two or languages together to express their thoughts in context. So automatic...

Text summarization plays an important problem in natural language understanding and information retrieval. Automatic text get much more attention by people presently because it is efficiently effectively serve time decision making process even for day to life. Presently deep learning models than the traditional approaches. The primary objective of this research work propose a methodology address Tamil sports news which can automatically create extractive summary data with use Natural...

An entity relationship data model is a high level conceptual that describes information as entities, attributes relationships and constraints. Entity diagrams to design the database of software. It involves sequence tasks including extracting requirements, identifying their attributes, between constraints finally drawing diagram. As such diagram has become tedious task for novice designer. This research addresses above issue, proposes Natural Language Processing based tool which accepts...

Recently, method of controlling machine with natural control called Natural User Interface has attracted attention. particularly, human hand is considered to be communication media that can communicate information most naturally. In this paper, user detected by following acquired skin color the user's face, through face detection. After detecting hand, gesture determined. Finally, a robot controlled have multi movements according several patterns. We succeeded in acquiring from and both...

Concentration is the ability to focus mind on a specific context at time. This important do any activities efficiently such as learning and driving. Especially, for students, it tough be stay focused because of distractions. A single moment drifting in may cause significant impact student's performance. Therefore finding that alert student regain attention, would help him improve concentrated while learning. Several types researches have been conducted find out connection between...

In this research, we present a system that can support visually handicapped people to walk alone safely on tactile paving. The warn the user in case of danger by mistaking walking path and meeting with obstacle against direction. Here, conduct warning detecting paving obstacles it. Thus, potential accidents involving be prevented. guides interpreting information obtained from automatic detection paper, is mainly discussed, processing images on-user camera which exists main system. We propose...

This paper reviews studies and developments in recruitment techniques interact with computer science. And novel approach proposed as Intelligent Recruitment System (IRS) which consist of resume classification ranking deep learning alongside NLP techniques, Automatic question generation(AQG) system measure technical proficiency an applicant using the knowledge base merged ontology designed web local sources soft skills measuring answering about different skill sets matching similarity...

Automatic analyzing and extracting useful information from the noisy social media content are currently getting attention research community. It is common to find people easily mixing their native language along with English express thoughts in media, using Unicode characters or written Roman Scripts. Thus these types of code-mixed text characterized by a high percentage spelling mistakes phonetic typing, wordplay, creative spelling, abbreviations, Meta tags, so on. Identification languages...

In this paper, we have proposed a hybrid approach to face recognition using PCA and LDA in border control like time-critical application. Duplicate passports, unauthorized VISA, fake identities, criminals dramatically increased within the last few years Sri Lanka due lack of proper identification system at borders. Even though traditional VISA granting process biometrics are sent borders final destinations such as immigration counters, there no measures airports, prove that it is same person...

Several robot-related studies have been conducted in recent years; however, on the autonomous travel of small mobile robots spaces are lacking. In this study, we investigate development for that need to and cover entire smooth surface, such as those employed cleaning tables or solar panels. We consider an obstacle-available surface target it by proposing a spiral motion method. To achieve motion, focus developing avoidance obstacles, return original path, fall prevention when traverse...

Building circuits on breadboards is an activity which requires a lot of attention and thinking. If there way to guide this process by using modern technologies, the learning can be made more effective interactive. This study proposes solution that provides students with augmented reality visualization expected circuit breadboard before they actually make circuit. The proposed system divided into four main modules based their functionality (a) extracting possible information from electronic...

Comprehension of “Singlish” (an alternative writing system for Sinhala language) texts by a machine had been requirement long period. It has choice many Sri Lankan’s style in casual conversations such as small talks, chats and social media comments. Finding method to translate Singlish or English tried couple years the research community Lanka attempts were based on statistical language translation approaches due challenge finding large dataset use Deep Learning approaches. This addresses...

This research aimed to find a narrow path identification method using autonomous movement of various robots including wheel robots. It was used detect obstacles by sensors, obstacle avoidance behavior and entering behaviors the compact robot ZUMO. Fuzzy logic methods were in order acquire accurate angle information at time entrance into path. Furthermore, both simulation actual verification experiments conducted confirm effectiveness system.

Each and every day there are lots of contents being published on the web. May it be blogs, news articles, movie reviews, product etc. Although this many number published, how far a content reaches engages large expected audience is questionable unpredictable. Our project aims to solve issue. The goal our develop system that, when post or textual given as an input, makes go viral first propose such solution for problem. To make viral, we follow two approaches. First one improve incorporate...

Text summarization helps in reducing the size of a text while preserving its information content. Summarization can be derived as shortening source to version that it's content and overall meaning is preserved. It very difficult for human beings manually summarize large documents text. These methods classified into two broader such extractive abstractive summarization. The prior method consists selecting important sentences; paragraphs etc. from document make brief it by combining them....

Biomédical named entity recognition (BNER) is one of the most essential and initial tasks (discovering relations between biomédical entities, identifying molecular pathways, etc.) information retrieval. Although performed well in ordinary text, it still remains challenging biology domain because complex nature nomenclature, different kinds spelling forms many more reasons. Even though entities biological text are found successfully, classifying them into relevant classes such as genes,...

Protein name identification in text is an important and challenging fundamental precursor biomedical information processing. For example, accurate of protein names affects the finding protein-protein interactions from literature. In this paper, we present efficient technique based on a rich set features: orthographic, morphological as well Proteinhood features which are introduced newly study. The method was evaluated GENIA corpus with use different machine learning algorithms. highest...

Deception detection is important for legal, moral and clinical purposes but still it harder even security officers judges. Therefore an effective,light weight approach a must.There are several technologies used in deception detection. EEG based one such approach. P300 wave most commonly which depends on stimuli. The study provides alternative to instead of using P300.Twelve subjects were participated the signals recorded while they telling truths lies. preprocessed data then fed feature...

Gesture recognition could be effectively used in most instruments targeting the life support of differently abled people. Therefore, an enhanced development was carried out miscellaneous requirements said kind The Kinect capturing device to extract 3-D information and processing using a single board PC low power blue tooth module get connectivity between external devices enabling IoT features system. Different gestures were carefully identified unique command set generated covering each...

Tourism in Sri Lanka is an evolving field which significantly influencing on the development of country. With rapid advancement Affective computing and its' diverse paths where applications are being implemented by facilitating user needs emotions, tourism has become one prominent fields to provide a comprehensive analysis useful inclination specific travel spots based interests emotions. Traditional methodologies guide guides tourists' journey nowadays old fashion tourist himself innovative...

Deep learning-based computer vision has shown improved performance in image classification tasks. Due to the complexities of these models, they have been referred as opaque models. As a result, users need justifications for predictions enhance trust. Thus, Explainable Artificial Intelligence (XAI) provides various techniques explain predictions. Explanations play vital role practical application, apply exact treatment plant disease. However, application XAI disease identification is not...

Code-mixing has become a moving method of communication among multilingual speakers.Most the social media content societies are written in code-mixed text.However, most current translation systems neglect to convert texts standard language.Most user remains unprocessed due unavailability linguistic resource such as parallel corpus.This paper proposes Neural Machine Translation(NMT) model translate Sinhala-English text Sinhala language.Due limited resources available for code-mixed(SECM)...