-4d90550d17f4602e089-1bb6 20220519054358989 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Recent Technology and Engineering (IJRTE) IJRTE 22773878 10.35940/ijrte.2277-3878 https://www.ijrte.org/ 11 30 2019 8 4 CSE Department, Institute of Technology, Nirma University, Ahmedabad , India. Ansh Kapoor* Sarthak Shah CSE Department, Institute of Technology, Nirma University, Ahmedabad , India. Shashank Agrawal CSE Department, Institute of Technology, Nirma University, Ahmedabad , India. Preeti Kathiria* CSE Department, Institute of Technology, Nirma University, Ahmedabad , India. Smita Agrawal CSE Department, Institute of Technology, Nirma University, Ahmedabad , India. The word “smart” is being used in various fields and is worldwide accepted to mean intelligence. Smart services are one of the most emerging technologies being used in the IoT era, which has widely changed the equipment into more intelligent, remotely accessible, and interconnected. To use any electric device, we require to interact with it, or there is a need for the presence of a person at a particular place is needed. Moreover, to overcome this, The System examines the smart auditorium feature that current owners of the auditorium are facing about the power consumption by the auditorium and the wastage of the valuable electric energy. The proposed system helps in providing comfortable, efficient, and effective control of electrical devices like lights, Air conditioner, and achieve insignificant power saving. 11 30 2019 11305 11309 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9575.118419 https://www.ijrte.org/portfolio-item/D9575118419/ Digital analyst at Mckinsey and company Bangalore. Pulkit Juneja* Hemant Jain System software developer in the TensorIT server team at NVIDIA. Anshupriya Srivastava pursuing a master’s degree in data science from Duke university, North Carolina. Gayathri Prakasam Assistant Professor (Senior) in the School of Computing Science and Engineering at VIT University, Vellore, Tamil Nadu, India. Facial animation is quickly becoming an important feature of virtual assistants and is gaining traction as the preferred communication technique between man and machine. In addition to lip movement, facial expressions such as those of the eyes and cheeks help in conveying the sentiment and context of what is being spoken. This paper aims to present a new methodology to create an emotionally expressive virtual AI that is capable of understanding the sentiment of the conversation and displaying emotions during conversations. To achieve this the system uses a generative chatbot and combines it with a 3D talking head that is animated parametrically. This work could be beneficial to virtual assistants and help facilitate more lifelike interactions, holding significance in environments that require the user to feel more comfortable with their interactions. The complexities lie in developing a domain specific chat-bot that will not only provide valuable replies but also recognize and display appropriate facial expressions while communicating. 11 30 2019 11311 11316 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9576.118419 https://www.ijrte.org/portfolio-item/D9576118419/ Associate professor, HOD MSc IT, Jain University. Puja Shashi Suchithra R Director of MCA department in Jain Deemed to be University,Bangalore The main purpose of this work is to develop a new scheme to profoundly retrieving features to perform the process of identifying a brain regions from the MR neonatal brain image. First the input MR neonatal brain image is denoised by using the Modified Fuzzy Adaptive Non Local Mean Filter (FANLMF) and then the contrast of the image is enhanced using the Adaptive Average Intensity Based Histogram Equalization (AAIHE). After pre-processing the input MR image, the next step is to retrieve the features of a similar image. To capture the features from the pre-processed image, this project offers a new technique for retrieving features called Patch Based Deep Local Feature Learning (PBDLFL). After retrieving the deep features, the next step is to divide the brain regions based on these retrieved features. To implement this process, the supervised segmentation scheme is employed. Among several supervised segmentation scheme this works employs proposed approach named Self Similarity Multi Level Clustering (SSMLC). Finally, the retrieved features are given as an input to these SSMLC approach for separating the regions of the brain. To understand the effectiveness of the proposed deep feature retrieval and proposed segmentation scheme, four performance metrics are employed namely, Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), Jaccard Index (JI) and Sensitivity (SEN). The experimental results show that the new PBDLFL and SSMLC perform better than other existing approaches. 11 30 2019 11854 11861 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9579.118419 https://www.ijrte.org/portfolio-item/D9579118419/ Department of Aeronautical Engineering, Hindustan Institute of Technology and Science, Chennai, India. Elumalai E S* Mukesh Kumar Department of Aeronautical Engineering, Hindustan Institute of Technology and Science, Chennai, India. Dominic Xavier D Department of Aeronautical Engineering, Hindustan Institute of Technology and Science, Chennai, India. Sarath Kumar R Department of Aeronautical Engineering, Hindustan Institute of Technology and Science, Chennai, India. Seralathan S Department of Mechanical Engineering, Hindustan Institute of Technology and Science, Chennai, India. An extensive study is made on the buckling types and conditions of various types cylindrical shells based on their design and material properties. Based on those, numerical analysis is done on a submerged type of cylindrical shell. This analysis is done based on two different conditions. The first one includes design with the addition of stiffeners and the other is based on the design which has no stiffeners. A comparative study is performed between these two and the results are analyzed. Two cylindrical shells, one including stringer and the other without a stringer are modeled using CATIA with specific dimensions. These models are imported into ANSYS to perform an explicit dynamic analysis. Parameters such as equivalent stress, equivalent elastic strain, shear stress, shear elastic strain and total deformation are calculated. The end results are obtained using ANSYS and the graphs are plotted using the values obtained. Based on the results obtained, it is concluded that the use of stiffeners makes the structure widely enviable to bear compressive types of loads. Also, it gives additional strength to the structure with sturdiness at the top and bottom layers. Based on the study, it can be concluded that the use of rectangular type stringer is preferred much more than the other types. 11 30 2019 11317 11325 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9580.118419 https://www.ijrte.org/portfolio-item/D9580118419/ Mechanical department, Vardhaman college of engineering, Hyderabad, India. B. Dhanraj* S. Maruthi Gangadhar Mechanical department, Vardhaman college of engineering,Hyderabad,India. M. Vishnuvardhan Mechanical department, Vardhaman college of engineering, Hyderabad, India K. Rajasekhar Reddy Mechanical department, Vardhaman college of engineering, Hyderabad, India Surface Strength of the gear tooth depends on the contact stress and the bending stress caused due to the applied load on the tip of its gear tooth. Analysis has become popular in decreasing the failures. Fatigue causes in the root bending stress and Surface indentation causes in the contact stress. Then modified Lewis beam strength is used for bending stress and the AGMA method is used for contact stresses by varying the face width. Analytical results are based on Lewis formula and the theoretical values were calculated by AGMA standard so the results were validated. 11 30 2019 11326 11328 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9581.118419 https://www.ijrte.org/portfolio-item/D9581118419/ Assistant professor in Mathematics, Chikkanna Govt. Arts College, BharathiarUniversity,Tamilnadu, India. A. Radharamani* A. Brindha Assistant professor in Mathematics,,Tiruppur Kumaran College for Women,BharathiarUniversity, Tamilnadu, India. Let be a Fuzzy Hilbert space over the fields of and FB( ) is the set of all fuzzy continuous linear operator on .In this paper we introduce the expansion of different fuzzy paranormal operators like n- fuzzy paranormal operator, *- fuzzy paranormal operator and nth -fuzzy paranormal operator, which all are developed from paranormal operators and their characteristics. The study resulted the properties of an n- fuzzy paranormal operator, * fuzzy paranormal operator and nth -fuzzy paranormal operator and their relationship between them. To investigate the nature of these operators, all it needs the nature of the n- fuzzy paranormal operator. 11 30 2019 11862 11866 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9584.118419 https://www.ijrte.org/portfolio-item/D9584118419/ PG & Research Department of Computer Science, Dr. Ambedkar Govt. Arts College(Autonomous), Affiliated to University of Madras, Chennai, Tamil Nadu, India. M. Mercy Evangeline* Dr. K. Shyamala Associate Professor, PG & Research Department of Computer Science, Dr.Ambedkar Govt. Arts College (Autonomous), Affiliated to University of Madras, Chennai, Tamil Nadu, India. In any language, words are considered as the basic or the smallest element with a distinctive meaning. Words can be categorized into several types, depending upon their use and functions. Basically how a word changes its form to express itself in grammatical notation defines its type. The process of categorizing a word to a particular type depending upon its grammatical notation is termed as Part of Speech tagging. In this paper, an attempt has been made to identify part of speech tagging for words in Tamil language, particular to noun inflections. An algorithm has been proposed for Noun Identification for Tamil Language using Morphophonemic Rules (NIMR). A Rule based suffix stripping approach has been adopted for this implementation. The approach proposed here identifies the root word by applying various morphophonemic rules particular to suffixes. It removes the various inflections based on the set of grammatical rules available for Tamil Language and tags the word identified as a Noun. It is proposed to explore the traditional way of categorizing words in Tamil language, avoiding the influence of English grammars. 11 30 2019 11867 11873 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9588.118419 https://www.ijrte.org/portfolio-item/D9588118419/ Department of CSE, PES University, Bangalore, India. Savitha Murthy* Pragnya Suresh Department of CSE, PES University, Bangalore, India. Preet Shah Department of CSE, PES University, Bangalore, India. Dinkar Sitaram Department of CSE, PES University, Bangalore, India. Relocation makes it inevitable for a person to learn the local pronunciations correctly. With the advent of mobile phones, language learning can be made easy and flexible. Our research involves Kannada Kali, a mobile and cloud based application that is being developed to assist people in learning the correct pronunciations of Kannada (a language spoken in India). Automatic Speech Recognition systems which are used to aid pronunciation training require to be trained on sufficient amount of spoken target language data. Since collecting such data in not easy, the objective of our research is to detect mispronounced segments of words with minimal data. When there is scarcity of data, a comparative approach where spoken word segments are compared with the canonical pronunciations is more effective for detecting anomaly in pronunciation. Since syllables are basic independent units of pronunciation, the spoken words are segmented into syllables for effective comparison and feedback. We propose an unsupervised segmentation method called Spectrogram Formant Contour Analysis that detects syllable boundaries by analysing the change in contours of the formants in the spoken word spectrograms. The task of mispronunciation detection is more effective when the application can identify the actual syllable pronounced and communicate the correct pronunciation to the user. For the purpose of syllable classification, our method employs a novel approach where a model is trained on phonemes and given syllables as input for identification. Our study includes comparing the performance of three machine learning algorithms, namely, Convolution Neural Network, Support Vector Machines and K-Nearest Neighbours on the task of identifying phonemes when they are trained on minimal data. The accuracy of KNN on phoneme classification was the best with 80% for clean and 60% for noisy data. In case of our initial results on syllable classification for Kannada Kali, Support Vector Machines gave the highest accuracy of almost 30%. 11 30 2019 11874 11882 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9589.118419 https://www.ijrte.org/portfolio-item/D9589118419/ Department of Allied Mechanics, Assistant Professor, The Tashkent institute of projection, building and maintenance of automobile roads, Tashkent, Uzbekistan, Uzbekistan. K.J. Rustamov* The purpose of the tests was to verify the theoretical studies performed, as well as to confirm the functionality of the developed multi-purpose machine with excavation and bulldozer equipment. Mounting on the basis of TTZ-80 working equipment allowed us to conduct experimental studies, with the determination of energy performance indicators during the most energy-intensive operation - digging and leveling the soil. 11 30 2019 12032 12036 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9592.118419 https://www.ijrte.org/portfolio-item/D9592118419/ Department of Civil Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Malaysia. Nur Ain Nazirah Mohd Arshad* Rafidah Hamdan* Department of Civil Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Malaysia. Nuratikah Ahmad Department of Civil Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Malaysia. Phosphorus in wastewater accelerates eutrophication in water body. Textile wastewater is one of contributors to the phosphorus loading into water body which promotes the growth of algae, reducing the oxygen content and detrimental to surface water ecosystem. Myriad existing treatments for phosphorus removal have been developed but it requires a high cost treatment and maintenance. Rock filter system emerged as one of the alternative method for phosphorus removal from wastewater with steel slag as the filter media. However, application of the system in treating industrial wastewater is still unclear especially in big scale application and requires extensive study. This study is done to provide solution of phosphorus loading from textile wastewater using steel slag as filter material and to investigate the removal capacity of steel slag with high calcium and low ferum content. The steel slag was analyzed using XRF for its composition and to ensure the steel slag has high Ca content. Then, the aerated steel slag filter system was set-up on the site of textile industry for a month and analyzed according to parameter of pH, alkalinity, COD, DO, temperature and TSS. The result from this study showed that the aerated high calcium low ferum steel slag filter has a high efficiency of phosphorus removal rates varied from 35% to 67% in treating textile wastewater. It was found that aerated steel slag system was efficient in phosphorus removal by using industrial wastewater. 11 30 2019 11883 11886 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9595.118419 https://www.ijrte.org/portfolio-item/D9595118419/ Asst. Professor at K.L.E. Institute of Technology, Hubli, India Tejas K. Rayangoudar* H. C. Nagraj Principal of NMIT Bangalore, India Gait refers to person identification based on the observation of human walking style. One of the prominent hurdles in gait recognition is, the challenges posed by change in apparels like clothes and object held by the subject. The paper explores the feature extraction techniques like CHOG and Elliptical Fourier Descriptors in spatial and frequency domain respectively to mitigate this negative impact on gait recognition. The CHOG behavioural feature extraction technique is used to capture the effective distribution of local gradient on gait sequence images. Further the Elliptical Fourier Descriptor (EFD) is found in frequency domain to access the geometric characteristics of a spatial domain image. The work is carried out on 36 subjects with 5 different apparels and 3 different objects each with 6 gait cycles from standard dataset CASIA SET – B and CMU - MoBo. SVM classifier is used to effectively discriminate the gait cycle patterns using optimal hyper plane. The results obtained have given an improvement of 7% to 24% increase in gait recognition over earlier techniques like GEI, CDA, LDA, ENTROPY, static and dynamic region splitting. 11 30 2019 11887 11892 CC-BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.D9597.118419 https://www.ijrte.org/portfolio-item/D9597118419/