2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)最新文献

{"title":"Semantic Segmentation of Tumors in Kidneys using Attention U-Net Models","authors":"T. Geethanjali, Minavathi, M. Dinesh","doi":"10.1109/ICEECCOT52851.2021.9708025","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9708025","url":null,"abstract":"Accurate segmentation of tumors in kidneys (renal) will assist clinical experts to identify the occurrence of cancer. Physical kidney segmentation on CT images is tedious and varies between individual professionals due to its diverseness. Therefore, deep convolutional neural networks are widely used in renal segmentation tasks to aid in the early detection of renal cancer. Using Attention U-Net architecture, we propose an automated technique for delineating the kidneys and tumor in computed tomography (CT) images. Attention U-Net models place a greater emphasis on regions of interest (kidneys and tumors) and less emphasis on areas that are not in focus. With 19 pre-exercised model segments, the Attention U-Net Architecture is utilized to segment kidney tumors (KiTS 2019). To improve the kidney and tumor IOU scores we ultimately ensemble six Top Models.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133718381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Night Vision Bot using Dynamic IR and Object Detection","authors":"Devesh Abhyankar, Gurumoorty Suresh, Hrithik Sambhaji Karjule, Parth Bhardwaj, Harish Muleva, Anurag Mahajan","doi":"10.1109/ICEECCOT52851.2021.9707949","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9707949","url":null,"abstract":"Robotics as an extension to the field of Engineering has been of great support to the evolution of mankind. Through robotics, even complex tasks can be simplified through simple automation and decreased human intervention. Robots even reduce the workload on humans and increase the level of efficiency and accuracy in doing any task. Robotics has branched out and helped in the development and evolution of many fields such as agriculture, defense, parenting, healthcare, industry, aerospace and, so on. The robots which are used for survey or exploration can be used for many purposes in the fields of Wildlife, Industry and, Defense. These robots are capable of going to the areas which are vulnerable for humans, and they can be controlled from a reasonable distance. This robot due to its small size and in-built night vision camera makes it a very useful tool for surveillance and exploration. This robot has the ability to be controlled from a distance and it will enable the users to view objects clearly at night (or in darkness). These types of robots have been in existence for a couple of years, only for new developments to be added to them. The very recent development involves the integration of IoT (Internet of Things) to control the robot remotely and obtain information from it. The latest addition however is the addition of a new concept, known as Dynamic IR, which involves the control of the intensity of the IR light to produce better images. Moreover, with the addition of Object Detection using Machine Learning Algorithms, it can predict what type of obstacle it may face.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133929942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis on Item-Based and User-Based Collaborative Filtering for Movie Recommendation System","authors":"Neha Shrivastava, Surendra Gupta","doi":"10.1109/ICEECCOT52851.2021.9707955","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9707955","url":null,"abstract":"Recommender system are used to provide recommendations to users on all aspects technology and it is very important for every domain. There are different types of recommendation system are available such as Content Based, Hybrid Based, Collaborative filtering Based etc. Collaborative filtering-based Recommendation is divided into User-based and Item-based Collaborative filtering. The objective of the paper is to analyzed both the collaborative filtering recommendation method for a movie dataset. The outcome of User based and Item based recommendation method show the performance of both method and analyzing which one is provide good results.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131492915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analyzing Digital Advertisement Effectiveness using Image Processing Model with Person’s Attentiveness","authors":"Devam Trivedi, Madhurya Kandamuru, Kanagaraj Venusamy, V. Santhi","doi":"10.1109/ICEECCOT52851.2021.9708026","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9708026","url":null,"abstract":"In recent days, the revenue generated by different advertising mediums is massive, in particular the revenue generated through digital advertisement is approximately 200 billion dollars worldwide in 2020. The revenue generated from these ads often depends on the watch time of the ad and/or the user involvement in the ad. Number of viewers clicking the skip button is an important statistic that helps to determine the quality of the ad. If the ad is appealing to the viewers, it grabs the user’s interest and attention in the first few seconds to increase the watch time, making the user watch the ad completely. A person is more likely to buy the product or service being advertised if he finds the advertisement interesting. An advertisement should provide an insight into the key aspects of the product which will enable the target customer to decide whether he wants to use the product or service. More viewers are taking control by skipping advertisements they don’t want to see. Hence companies must take actions to ensure that theirs reach the target audience, with the right blend of reach and relevance. Ad effectiveness offers a solution to the companies looking to understand the impact of their ads on the audiences they want to influence. Hence, the effectiveness of the advertisement is very important to sell to the target audience. To aid companies in measuring the effectiveness, a tool/application which detects and analyses people’s attentiveness to the advertisement would be of great help in making advertisements that are engaging and appealing to the general public. In this paper, an image processing model is proposed to implement eye gaze and head pose tracking system, to analyze the person’s attentiveness towards the ad. This proposed approach can be used and analyzed by the advertising industry to determine the effectiveness of their advertisement in selling their product or service to the target audience.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131550614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bond Dissociation Energy and Pattern Spectrum for Shape Classification","authors":"Ratnesh Kumar, Kalyani Mali","doi":"10.1109/ICEECCOT52851.2021.9707936","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9707936","url":null,"abstract":"The paper represents an effective, robust and shape-preserving, pattern spectrum based on sigma-pi model. A new idea behind the translation, rotation and scale invariant features are introduced called bond-dissociation energy of sigma and pi bond in a sigma-pi model. In this model, we map the structure of pixels in a shape to the structure of atoms in a crystalline solid-state substance. The model compute the energy required to break the atom from a lattice. The sigma-pi model corresponding to the bond-dissociation energy pattern spectrum provides excellent power, which is demonstrated by excellent retrieval performance on several popular shapes benchmarks, including MPEG-7 CE-Shape-l data set, Myth dataset, Tool dataset and Kimia’s data set. Experimental results obtained from popular databases demonstrate that the proposed model can achieve comparably better results than existing algorithms.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129506900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Prediction of Plant Leaf Diseases Using Deep Learning Models: A Review","authors":"M. Asta Lakshmi, V. Gomathi","doi":"10.1109/ICEECCOT52851.2021.9708043","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9708043","url":null,"abstract":"with the development of automated technology in agriculture and food production, there are still some phases that need an enhancement. One of such necessary phases is the detection of leaf diseases without the requirement of any manual support. Various diseases like blights, leaf spots and other bacterial and fungal infections are found in plant leaves. These defects bring a tremendous negative influence on the quality and quantity of crop yield. In order to prevent the plant leaves from getting destroyed, a better solution is needed to protect them from the beginning stage. Several works have been proposed to recognize and plant diseases. In this paper, a review is conducted to analyze the results of works based on detection of plant leaf diseases using machine learning and deep learning models. Based on the results, a transfer learning model with better performance is to be implemented along with the Jetson Nano kit for faster and efficient processing. As a result, transfer learning model could classify the images of affected plant leaves based on their defects. Location parameters could also be obtained along with the type of disease for early diagnosis of those diseases.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130923349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving document representation using KPCA and clustered word embeddings","authors":"Aakansha Gupta, R. Katarya","doi":"10.1109/ICEECCOT52851.2021.9707915","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9707915","url":null,"abstract":"Text mining approaches have shown to be an efficient way to examine publicly available online information on a variety of topics. However, because of the lack of context, online texts are difficult to represent. Word embedding techniques, such as word2vec, capture semantic relationships between words particularly well when trained on large text collections; but they fail when trained on small datasets. This paper proposes a document representation method based on word clusters. In this approach, Word embeddings created by word2vec are supplemented with morphological information collected from kernel principal component analysis (KPCA) computed on word similarity. After running KPCA, a spherical k-means algorithm is applied, with centroid representing the topic of that cluster. Next, the document is vectorized using the frequencies of these clusters. The proposed approach successfully includes the effects of semantically and morphologically related terms on document proximity through these data-driven notions. When combined with an appropriate weighting system, the proposed approach enables improved document representation and interpretability of the resulted document vectors.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115846700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Realization of Telugu r-phoneme in intervocalic position: An acoustic study","authors":"Venkata Krishna Rao Maddela, Bhaskararao Peri","doi":"10.1109/ICEECCOT52851.2021.9707967","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9707967","url":null,"abstract":"The acoustic characteristics of the phonetic instantiations of a phoneme of a language play a key role in language specific applications such as language identification, speech transcription as text, text-to-speech synthesis and so on. Significant differences exist among different languages and even within the Indian languages, in the realization of phonemes. Hence, acoustic characteristics of members of a phoneme in one language cannot be directly accepted to characterize similar phoneme in another language to accuracies required for language specific applications. Very limited results are available on the phonetic-acoustic characteristics of Telugu consonants. A focused attention is needed for such an analysis of Telugu phone groups based on manner articulation and place of articulation. In this paper some acoustic features of the two allophones of Telugu r-phoneme are studied. The features considered are trill patterns, tap or trill duration, spectral envelope, formants and antiformants at the tap instant. Tap or Trill duration and formant shifts from consonant into or from the context vowels are quantified for intervocalic position of r-phoneme. The rank statistics are used for ensemble analysis. ANOVA analysis is carried out for formant shifts and phone duration.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"317 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122804745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Transportation System using Smartphone","authors":"Abdul Cader Mohamed Nafrees, Saleem Mohamed Salees Raseez, Charles Glany Ubeshanan, Kurunathan Achutharaj, A. L. Hanees","doi":"10.1109/ICEECCOT52851.2021.9708053","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9708053","url":null,"abstract":"Public transportation is the main core in any country which help to increase government income, at the same time save travelers’ cost. Meanwhile, reducing the use of private or individual transport help to save the environment from pollution, which can achieve by providing better public transportation. But, due to time inefficiency in the public busses reduces traveler’s interest towards the use of public busses. This study provides a solution to the passengers to find the public busses in real-time which then helps them to reduce the waiting time in the bus stands and bus holds that are facing by the passengers in a long time. The developed system confirmed that the system provides accurate bus locations in real-time; meanwhile, owners confirm they can track their busses, which helps them to monitor their drivers virtually. Furthermore, this system confirms the cost-effectiveness compared to the previously developed systems. Furthermore, this study can be extended to develop the same system to monitor the crowds inside the bus by using the smartphone camera, which can help in any pandemic situations to keep the social distancing measures.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122830120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High speed divide by 3/4 prescaler using NMOS like latch block","authors":"Harshal Prajapati, Z. Patel","doi":"10.1109/ICEECCOT52851.2021.9707981","DOIUrl":"https://doi.org/10.1109/ICEECCOT52851.2021.9707981","url":null,"abstract":"A new design technique for 3/4 prescaler that improves operating speed and area is presented. The TSPC based 3/4 prescaler, an NMOS like p and n latch block reduces number of transistors and increases the speed of the 3/4 prescaler. The proposed 3/4 prescaler design can increase operation speed by 18% compared to a 3/4 prescaler design [11] with a 1. SV supply in 180nm CMOS technology. The proposed divide by 5/6 prescaler using the proposed 3/4 prescaler achieves 9.61/9.8 GHz operating frequency with a power consumption of 5.63 mW in divide by five mode and 5.42 mW in divide by six mode.","PeriodicalId":324627,"journal":{"name":"2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125237155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}