Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697185
Pratiksha Dilip Nandanwar, V. Wadhai, Akshita Chanchlani, V. Thakare
Cervical cancer is the second largely hazardous metastatic tumor that develops in a woman’s cervix. If it is detected at the premature stage and treated correctly then there can be less mortality ratio rate due to cervical cancer .In preliminary stage Pap smear is the simple scrutiny test generally used for the revealing of cancer. For precise screening and detection, cervical cancer is categorized as normal and abnormal cancer which includes the cell and cytoplasm in the identical structure. It is complicated task to distinguish a cancerous nucleus in the cell. Medical image processing is mainly significant but time consuming and complicated task. Medical Image preprocessing of cervical cancer pap smear images and its scrutiny is act of investigating images for recognizing objects and evaluating their impact. The primary reason of Image processing is for discovering of various kinds of unnecessary cells and exposing the amount it spreads. So for the precise segmentation of cervical cells in Pap smear image becomes an essential job to automatically identify the precancerous transforms in the cervix. Image segmentation basically refers to method of division of the image into several segments for tracing objects and borders in image. Various Image processing and segmentation algorithms are utilized to section the nucleus alone in microscopic images.The primary scope of this paper is to spotlight on how the morphological operations on cervical cancer pap smear images is achieved to fine-tune to appropriate pixel concentration and proper contrast for sorting out the tumor piece from an image. In the addressed proposed work morphological operations like erosion, dilation, opening, and closing are executed and implemented with the aid of structuring element entitled as kernel. Python libraries are used for implementation of proposed work. As the morphological transformation is applied, minimum and maximum pixel intensity is also been computed.
{"title":"Analysis of Pixel Intensity Variation by Performing Morphological Operations for Image Segmentation On Cervical Cancer Pap Smear Image","authors":"Pratiksha Dilip Nandanwar, V. Wadhai, Akshita Chanchlani, V. Thakare","doi":"10.1109/iccica52458.2021.9697185","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697185","url":null,"abstract":"Cervical cancer is the second largely hazardous metastatic tumor that develops in a woman’s cervix. If it is detected at the premature stage and treated correctly then there can be less mortality ratio rate due to cervical cancer .In preliminary stage Pap smear is the simple scrutiny test generally used for the revealing of cancer. For precise screening and detection, cervical cancer is categorized as normal and abnormal cancer which includes the cell and cytoplasm in the identical structure. It is complicated task to distinguish a cancerous nucleus in the cell. Medical image processing is mainly significant but time consuming and complicated task. Medical Image preprocessing of cervical cancer pap smear images and its scrutiny is act of investigating images for recognizing objects and evaluating their impact. The primary reason of Image processing is for discovering of various kinds of unnecessary cells and exposing the amount it spreads. So for the precise segmentation of cervical cells in Pap smear image becomes an essential job to automatically identify the precancerous transforms in the cervix. Image segmentation basically refers to method of division of the image into several segments for tracing objects and borders in image. Various Image processing and segmentation algorithms are utilized to section the nucleus alone in microscopic images.The primary scope of this paper is to spotlight on how the morphological operations on cervical cancer pap smear images is achieved to fine-tune to appropriate pixel concentration and proper contrast for sorting out the tumor piece from an image. In the addressed proposed work morphological operations like erosion, dilation, opening, and closing are executed and implemented with the aid of structuring element entitled as kernel. Python libraries are used for implementation of proposed work. As the morphological transformation is applied, minimum and maximum pixel intensity is also been computed.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122958833","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697267
Swatej Patil, Suyog Vairagade, Dipti Theng
Social Networking sites like Twitter, Instagram, and Facebook have become an essential part of our daily lives, but social media comes with its own advantages and disadvantages. Many of the time, these social networking platforms are used to distribute fake news or incorrect information, and there is a growing demand for classification and categorization of this type of content. As a result, we have explored a novel technique for classifying fake news that incorporates machine learning methods. This paper describes the development of a method that provides the TF-IDF Vectorizer to classify which news is legitimate and which is fraudulent. Implementation is performed using datasets from Kaggle. The results indicate that this method performs effectively.
{"title":"Machine Learning Techniques for the Classification of Fake News","authors":"Swatej Patil, Suyog Vairagade, Dipti Theng","doi":"10.1109/iccica52458.2021.9697267","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697267","url":null,"abstract":"Social Networking sites like Twitter, Instagram, and Facebook have become an essential part of our daily lives, but social media comes with its own advantages and disadvantages. Many of the time, these social networking platforms are used to distribute fake news or incorrect information, and there is a growing demand for classification and categorization of this type of content. As a result, we have explored a novel technique for classifying fake news that incorporates machine learning methods. This paper describes the development of a method that provides the TF-IDF Vectorizer to classify which news is legitimate and which is fraudulent. Implementation is performed using datasets from Kaggle. The results indicate that this method performs effectively.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126087837","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697240
Minakshee M. Patil, V. Wadhai
Depression is an illness that involves the body, mood, and thoughts, and it adversely affects human life. Depression not only lowers the happiness index of individuals but also reduces mindfulness. The increase in the prevalence of clinical depression has been linked to a range of serious outcomes, particularly to an increase in the number of suicide attempts and deaths; making it a public health concern. This underlines the need of an intelligent depression detection system which is able to automatically classify the individual as healthy or depressed. Selection of effective biomarkers plays a vital role in the design of an intelligent depression detection system. For our work, we have used acoustic features extracted from the spontaneous speech samples of the volunteers. By experimenting and evaluating classification results for the dataset of 54 depressed and 75 healthy individuals using different speech features, we found that speech features can be used as a reliable biomarker for depression detection. Speech features like MFCC, pitch, jitter, shimmer and energy have performed better in classifying an individual as a depressed or a healthy one. In the study, the performance of different classifiers like Random Forest, Support Vector Machine (SVM), Gaussian Mixture Model (GMM) and Naive Bayes has been investigated. Among these, hybrid classifier using GMM and SVM has given the best overall classification result.
{"title":"Selection Of Classifiers For Depression Detection Using Acoustic Features","authors":"Minakshee M. Patil, V. Wadhai","doi":"10.1109/iccica52458.2021.9697240","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697240","url":null,"abstract":"Depression is an illness that involves the body, mood, and thoughts, and it adversely affects human life. Depression not only lowers the happiness index of individuals but also reduces mindfulness. The increase in the prevalence of clinical depression has been linked to a range of serious outcomes, particularly to an increase in the number of suicide attempts and deaths; making it a public health concern. This underlines the need of an intelligent depression detection system which is able to automatically classify the individual as healthy or depressed. Selection of effective biomarkers plays a vital role in the design of an intelligent depression detection system. For our work, we have used acoustic features extracted from the spontaneous speech samples of the volunteers. By experimenting and evaluating classification results for the dataset of 54 depressed and 75 healthy individuals using different speech features, we found that speech features can be used as a reliable biomarker for depression detection. Speech features like MFCC, pitch, jitter, shimmer and energy have performed better in classifying an individual as a depressed or a healthy one. In the study, the performance of different classifiers like Random Forest, Support Vector Machine (SVM), Gaussian Mixture Model (GMM) and Naive Bayes has been investigated. Among these, hybrid classifier using GMM and SVM has given the best overall classification result.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124186130","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697294
Devangi Agarwal, S. Desai
Human behaviour and actions are greatly affected by their emotions. Through human computer interactions (HCI) interpreting of emotions has become easier. Modals like Facial Emotion Recognition(FER) that considers the facial features of the human, Speech Emotion Recognition (SER) that concentrates on the texture of human speech, Electroencephalography (EEG) that deals with brain waves and Electroencephalogram(ECG) that focuses on one’s heart rate are few of the widely used unimodels that are in place for recognizing emotions. In this paper we see how multimodal system tends to provide higher accurate results than the unimodels in existence. In order to implement the multimodal system two fusion methods were considered that are Feature Level Fusion and Decision Level Fusion. It was observed that Feature Level Fusion was preferred by most researchers due to its capability of providing more valid results in case of compatible features. Facial-Speech, Speech-ECG and Speech-Facial are few of the well liked multimodals that have been implemented by varied researchers. Out of these Facial-EEG provided most robust and efficient outputs.
{"title":"Multimodal Techniques for Emotion Recognition","authors":"Devangi Agarwal, S. Desai","doi":"10.1109/iccica52458.2021.9697294","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697294","url":null,"abstract":"Human behaviour and actions are greatly affected by their emotions. Through human computer interactions (HCI) interpreting of emotions has become easier. Modals like Facial Emotion Recognition(FER) that considers the facial features of the human, Speech Emotion Recognition (SER) that concentrates on the texture of human speech, Electroencephalography (EEG) that deals with brain waves and Electroencephalogram(ECG) that focuses on one’s heart rate are few of the widely used unimodels that are in place for recognizing emotions. In this paper we see how multimodal system tends to provide higher accurate results than the unimodels in existence. In order to implement the multimodal system two fusion methods were considered that are Feature Level Fusion and Decision Level Fusion. It was observed that Feature Level Fusion was preferred by most researchers due to its capability of providing more valid results in case of compatible features. Facial-Speech, Speech-ECG and Speech-Facial are few of the well liked multimodals that have been implemented by varied researchers. Out of these Facial-EEG provided most robust and efficient outputs.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122284203","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697320
P. C. Tikekar, S. Sherekar, V. Thakre
Over the past ten years, Botnet has been an emerging threat that is increasing day by day & has gained popularity amongst researchers. Botnet detection is a very challenging task, so great Scientific research efforts have been made to develop effective & efficient techniques to detect the presence of Botnet. For developing the Botnet detection technique, most of the researchers use machine learning. Sometimes due to the C&C nature of Botnet & various characteristics of different types of bots, it becomes challenging to identify the Botnet. This paper studies & analyze multiple features of Botnet in machine learning techniques responsible for the detection. The paper discusses various Botnet features with their type, traffic parameters, databases, and the Botnet Detection method's parameters essential to test the results. The researcher needs to analyze the existing Botnet detection technique with its databases & parameters to develop a better detection technique.
{"title":"Features Representation of Botnet Detection Using Machine Learning Approaches","authors":"P. C. Tikekar, S. Sherekar, V. Thakre","doi":"10.1109/iccica52458.2021.9697320","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697320","url":null,"abstract":"Over the past ten years, Botnet has been an emerging threat that is increasing day by day & has gained popularity amongst researchers. Botnet detection is a very challenging task, so great Scientific research efforts have been made to develop effective & efficient techniques to detect the presence of Botnet. For developing the Botnet detection technique, most of the researchers use machine learning. Sometimes due to the C&C nature of Botnet & various characteristics of different types of bots, it becomes challenging to identify the Botnet. This paper studies & analyze multiple features of Botnet in machine learning techniques responsible for the detection. The paper discusses various Botnet features with their type, traffic parameters, databases, and the Botnet Detection method's parameters essential to test the results. The researcher needs to analyze the existing Botnet detection technique with its databases & parameters to develop a better detection technique.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126590837","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697261
B. Thorat, M. Jadhav
In the medical field various disease detection methods are under developmental stage. Due to this most of the diseases are not prevent in time and death rate are increases. By increasing the death rate those diseases are come in top ten diseases in the world. One of the hardly detectable disease is Tuberculosis. Every year millions of people were suffering from this disease, due to its complicated structure, recognition of it is very tedious job. Most of the traditional methods take long time to diagnose due to which patient not get proper treatment in time and it may cause of death. Now a day for disease detection biosensor plays an important role. In this paper Cantilever biosensor is designed and simulated for rapid detection of tuberculosis. The surface of cantilever is coated with antibodies and it gets binds with antigen. When the targeted molecules are finds, the surface get stress and it form deflection. Five different models with various materials are designed and discover the maximum displacement. The maximum displacement achieved 1.71 x 1028 µm from model-3 with gold layer on the cantilever for a 100N load corresponds to 28.228 x 10-24 kg weight of antigen.
在医学领域，各种疾病检测方法正处于发展阶段。由于这一点，大多数疾病不能及时预防，死亡率上升。由于死亡率的增加，这些疾病进入了世界十大疾病之列。肺结核是一种很难检测到的疾病。每年有数百万人患有这种疾病，由于其复杂的结构，识别它是非常繁琐的工作。传统方法大多诊断时间长，患者得不到及时治疗，有可能导致死亡。如今，生物传感器在疾病检测中扮演着重要的角色。本文设计并模拟了用于结核病快速检测的悬臂式生物传感器。悬臂梁表面包裹有抗体，并与抗原结合。当目标分子被发现时，表面受到应力并形成偏转。设计了五种不同材料的模型，并找出了最大位移。在100N载荷下，悬臂上有金层的模型-3的最大位移达到1.71 x 1028µm，对应于28.228 x 10-24 kg的抗原重量。
{"title":"Design And Simulate MEMS Based Cantilever Biosensor For Detection of Tuberculosis","authors":"B. Thorat, M. Jadhav","doi":"10.1109/iccica52458.2021.9697261","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697261","url":null,"abstract":"In the medical field various disease detection methods are under developmental stage. Due to this most of the diseases are not prevent in time and death rate are increases. By increasing the death rate those diseases are come in top ten diseases in the world. One of the hardly detectable disease is Tuberculosis. Every year millions of people were suffering from this disease, due to its complicated structure, recognition of it is very tedious job. Most of the traditional methods take long time to diagnose due to which patient not get proper treatment in time and it may cause of death. Now a day for disease detection biosensor plays an important role. In this paper Cantilever biosensor is designed and simulated for rapid detection of tuberculosis. The surface of cantilever is coated with antibodies and it gets binds with antigen. When the targeted molecules are finds, the surface get stress and it form deflection. Five different models with various materials are designed and discover the maximum displacement. The maximum displacement achieved 1.71 x 1028 µm from model-3 with gold layer on the cantilever for a 100N load corresponds to 28.228 x 10-24 kg weight of antigen.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129736573","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697219
Mahendra U. Gaikwad
Over several years satellite technologies are used to serve to ever- increasing demands of wireless communication in terms of volume of traffic and quality of communication services. Satellite has many subsystems; few of them are Attitude and orbit control subsystem, Thermal control. Tracking, telemetry, command and monitoring subsystem, Power subsystem, Communication subsystems, Antennas and Bus subsystem, Ground Station subsystems, Space Qualification subsystem and so on. Long Range communication has also started to contribute to applications in the space sector. We propose a concept that allows continuous monitoring of remote application in nano-satellite constellations by implementing an analogue of an existing open platform network called LoRa Wide Area Network in the constellations making their own LPWAN (Low Power Wide Area Network). Such a network among satellites allows the tracking and monitoring of IoT data over the satellite network. The role of Machine-to-Machine and Internet of market applications in satellite technology, which is now having annual revenue of $1.5 billion, is expected to reach $5.8 million in-service satellite by 2023. The Main performance parameters of IoT-Satellite consortium for value propositions are going to be Lowest Cost, Lowest Energy, Global and Secure availability, Dedicated Networks, Speed, Reliability and System Continuing Integration. The satellite-based applications leading the market in space sector and provides the opportunities for increase in revenue in space sector.
{"title":"Analysis of Orbital Parameters for live Tracking of Nanosatellite","authors":"Mahendra U. Gaikwad","doi":"10.1109/iccica52458.2021.9697219","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697219","url":null,"abstract":"Over several years satellite technologies are used to serve to ever- increasing demands of wireless communication in terms of volume of traffic and quality of communication services. Satellite has many subsystems; few of them are Attitude and orbit control subsystem, Thermal control. Tracking, telemetry, command and monitoring subsystem, Power subsystem, Communication subsystems, Antennas and Bus subsystem, Ground Station subsystems, Space Qualification subsystem and so on. Long Range communication has also started to contribute to applications in the space sector. We propose a concept that allows continuous monitoring of remote application in nano-satellite constellations by implementing an analogue of an existing open platform network called LoRa Wide Area Network in the constellations making their own LPWAN (Low Power Wide Area Network). Such a network among satellites allows the tracking and monitoring of IoT data over the satellite network. The role of Machine-to-Machine and Internet of market applications in satellite technology, which is now having annual revenue of $1.5 billion, is expected to reach $5.8 million in-service satellite by 2023. The Main performance parameters of IoT-Satellite consortium for value propositions are going to be Lowest Cost, Lowest Energy, Global and Secure availability, Dedicated Networks, Speed, Reliability and System Continuing Integration. The satellite-based applications leading the market in space sector and provides the opportunities for increase in revenue in space sector.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"139 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132532178","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697114
Divyam Sheth, A. R. Gupta, L. D'mello
This paper describes an application that performs a semantic search on an employee database. It helps Human Resources employees to target relevant people for their events and trainings. Syntactic or lexical searching involves keyword matching but does not match synonyms and other contextually related data. By using regular keyword search, a document either contains the given word or not, and there is no middle ground. Semantic Search allows the matching of data contextually linked with the search term. High dimensional vectors, also known as embeddings, are generated for a complete sentence and are then used for searching. Under the hood, Google’s Universal Sentence Encoder. The Universal Sentence Encoder encodes text into high dimensional vectors that can be used for text classification, semantic similarity, clustering, and other natural language tasks to provide better performance of the model as compared to a custom trained Convolution Neural Network which also requires more training data.
{"title":"Using Universal Sentence Encoder for Semantic Search of Employee Data","authors":"Divyam Sheth, A. R. Gupta, L. D'mello","doi":"10.1109/iccica52458.2021.9697114","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697114","url":null,"abstract":"This paper describes an application that performs a semantic search on an employee database. It helps Human Resources employees to target relevant people for their events and trainings. Syntactic or lexical searching involves keyword matching but does not match synonyms and other contextually related data. By using regular keyword search, a document either contains the given word or not, and there is no middle ground. Semantic Search allows the matching of data contextually linked with the search term. High dimensional vectors, also known as embeddings, are generated for a complete sentence and are then used for searching. Under the hood, Google’s Universal Sentence Encoder. The Universal Sentence Encoder encodes text into high dimensional vectors that can be used for text classification, semantic similarity, clustering, and other natural language tasks to provide better performance of the model as compared to a custom trained Convolution Neural Network which also requires more training data.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130952097","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697280
J. Saivijayalakshmi, N. Ayyanathan
India always remains a major Tourist destination, given its diverse culture, geography, history and also being the oldest civilization in the world. In view of India’s enormous potential for growth in Tourism, its imperative that we need a reliable and accurate Tourism demand forecasting solution. We reviewed various research papers based on Time-series & Regression methods. They are simple to compute values and also bring out forecasting tentative data of foreign tourist arrivals. Our tourism growth potential demanded more accurate forecasting which called for exploring other methods. We found "Deep Learning Techniques", are highly useful. Time series methods such as Holtwinter, Auto Regressive Integrated Moving Average and Long-short term memory (LSTM) are used to predict accurately foreign Tourist Visitors to India. Based on our analysis, the best model for predicting Tourist arrivals to India from foreign countries is LSTM, compared with traditional techniques.
{"title":"Comparative Performance Analysis of Deep Learning Technique with Statistical models on forecasting the Foreign Tourists arrival pattern to India","authors":"J. Saivijayalakshmi, N. Ayyanathan","doi":"10.1109/iccica52458.2021.9697280","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697280","url":null,"abstract":"India always remains a major Tourist destination, given its diverse culture, geography, history and also being the oldest civilization in the world. In view of India’s enormous potential for growth in Tourism, its imperative that we need a reliable and accurate Tourism demand forecasting solution. We reviewed various research papers based on Time-series & Regression methods. They are simple to compute values and also bring out forecasting tentative data of foreign tourist arrivals. Our tourism growth potential demanded more accurate forecasting which called for exploring other methods. We found \"Deep Learning Techniques\", are highly useful. Time series methods such as Holtwinter, Auto Regressive Integrated Moving Average and Long-short term memory (LSTM) are used to predict accurately foreign Tourist Visitors to India. Based on our analysis, the best model for predicting Tourist arrivals to India from foreign countries is LSTM, compared with traditional techniques.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129759755","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}
Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697314
Shivani Gupta, Megha Gupta, N. Garg
Cancer is one of the most dreaded diseases of human beings and is a major cause of death all over the globe. More than a million Indians suffer from cancer and a large number of them die from it annually. ML is widely used in the early diagnosis and prognosis of cancer. A variety of machine learning algorithms, including Artificial Neural Network, Bayesian Networks, Support Vector Machines and Decision Tress have been widely used in cancer research for the development of predictive models which are trained by the researchers to give effective and accurate decision. Machine Learning is widely used in the treatment of cancer. Machine Learning is an excellent tool for finding relationships between variables in your data that are too complex for human to economist. This work presents an insight on how machine learning technology is contributing in the field of healthcare especially in cancer diagnosis and its treatment.
{"title":"ML Assistance in Cancer Detection & Treatment","authors":"Shivani Gupta, Megha Gupta, N. Garg","doi":"10.1109/iccica52458.2021.9697314","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697314","url":null,"abstract":"Cancer is one of the most dreaded diseases of human beings and is a major cause of death all over the globe. More than a million Indians suffer from cancer and a large number of them die from it annually. ML is widely used in the early diagnosis and prognosis of cancer. A variety of machine learning algorithms, including Artificial Neural Network, Bayesian Networks, Support Vector Machines and Decision Tress have been widely used in cancer research for the development of predictive models which are trained by the researchers to give effective and accurate decision. Machine Learning is widely used in the treatment of cancer. Machine Learning is an excellent tool for finding relationships between variables in your data that are too complex for human to economist. This work presents an insight on how machine learning technology is contributing in the field of healthcare especially in cancer diagnosis and its treatment.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"453 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124298531","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：