2022 IEEE International Conference on Data Science and Information System (ICDSIS)最新文献

{"title":"Voice Recognition Chat bot for Consumer Product Applications","authors":"M. Kathirvelu, A. Janaranjani, A.T Navin Pranav, Ronak Pradeep","doi":"10.1109/ICDSIS55133.2022.9915884","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915884","url":null,"abstract":"The concept and implementation of a voice recognition chat bot for customer assistance is presented in this paper. Chat bots are automated tools that aid in the replication of human behaviour in a dialogue. They also aid humans in a discussion or when they have a question about something on the internet. They can be used to communicate between clients and the system in web-services. The bot’s questions are analysed using AI techniques, and suitable replies are gathered from a database. The output is provided in the form of speech and text. New questions that aren’t in the database are processed and added to the database for future inquiries. As a result, we give a review of the strategies used to create Chatbots in this work. A few examples of chatbot design are also explored to help understand how chatbots work and what kind of techniques are available for developing chatbots. With the rapid advancement of Chatbot technology, it is envisaged that it would be able to supplement human limitations and increase productivity.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134527807","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":"Fake Reviews Filtering System Using Supervised Machine Learning","authors":"Deepanshu Jain, Sayam Kumar, Yashika Goyal","doi":"10.1109/ICDSIS55133.2022.9915878","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915878","url":null,"abstract":"As the surge in internet users is expanding prominently, the role of the online reviewing system is also rising. For companies, the legitimacy of internet evaluations is critical, as it can directly impact their reputation and profitability. It plays an indispensable role in influencing people’s perceptions of a product or service. This research projects light on the best technique to identify and filter out authentic reviews while proposing a flexible and user-friendly website. The website will have a tremendous sway on customers and will assist them in making a better judgment about a product/service. The website is deployed with the designed supervised learning model. Firstly, the user will have to enter the URL of the website where the product is located. After which, the dataset is extracted from the given URL using Python tools for Web Scraping. The data is then analyzed and dissected using Natural Language Processing techniques to extract sound features from it. Ultimately, different Machine Learning Models are further trained on the dataset. The experimental results of this research reveal that the model performs at an accuracy of 89.12% on the datasets. The major objective of this research is to provide a fake review filtering system that will provide users with more reliable review information and eliminate revenue loss of the companies at an exponential rate.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133083823","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":"Secured Data Compression and Data Authentication in Internet of Thing Networks Using LZW Compression Based X.509 Certification","authors":"S. Karthikeyan, T. Poongodi","doi":"10.1109/ICDSIS55133.2022.9915855","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915855","url":null,"abstract":"The Internet of Things (IoT) is a collection of physical entities that forms a huge communication between the IoT devices. The exchange of data between these IoT devices may lead to modification of data and transmission of raw data may easily prone to such modification attacks. In order to mitigate the data modification, it is necessary to compress and authenticate the raw data via devices before encrypting the data via IoT sensors to safeguard it from modification attacks. In this paper, we compress the data using LZW lossless compression scheme and then X.509 certification is used to authenticate the data using mutual authentication mechanism. The model is tested in python over a high-end computing engine, where the comparison with existing model shows that the encoded key size after compression of original data gets reduced than other methods with protection against data modification attacks.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130851586","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":"Evaluation of Student’s Performance in Programming Using Item Response Theory","authors":"V. Hegde, S. Shushruth","doi":"10.1109/ICDSIS55133.2022.9915978","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915978","url":null,"abstract":"In most areas of study, many colleges and universities now recognize that a unified approach has numerous advantages. However, the aptitude of the learner has been overlooked as a critical component in student achievement. As a result, a variety of tactics, such as personalization, have been developed to support learners and adapt to a variety of learners. IRT (Item Response Theory) was employed in the development of the learning model, which was then deployed in an e-learning environment. Assessments of different level of difficulty were provided throughout the learning process. IRT assesses a student’s understanding of the topics using a probabilistic technique that considers the difficulties of the test items. The test score was evaluated using the Rasch model, and the item data was used to assign a ranking to the courses. Lessons are scaled back until the student reaches his or her competency level. The results reveal that the personalized learning model can assess a student’s success depending on their test score. As a result, the amount of time spent studying is reduced. The student’s order to enlighten was elevated using the personalized learning framework. Consequently, the intellectual development was improved.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133481541","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":"Fine Tuning and Comparing Tacotron 2, Deep Voice 3, and FastSpeech 2 TTS Models in a Low Resource Environment","authors":"T. Gopalakrishnan, Syed Ayaz Imam, Archit Aggarwal","doi":"10.1109/ICDSIS55133.2022.9915932","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915932","url":null,"abstract":"Text-to-speech (TTS) models are used to generate speech from a sequence of characters provided as input. Existing TTS systems require a high-quality large dataset and vast computational resources for training. However, most of the publicly available datasets do not meet such standards, and access to powerful GPUs may not always be possible. Hence, in our work, we have successfully trained and compared TTS models, specifically Tacotron 2, FastSpeech 2, and Deep Voice 3 on a Tesla T4 GPU using a subset of the LJSpeechl.1 dataset. Subsequently, we have surveyed to analyze the performance of the models when trained on small datasets, and we discovered that the Tacotron 2 TTS model synthesized the most realistic sounding speeches. The survey revealed that the Tacotron 2 TTS model achieved a mean opinion score (MOS) at a 95% confidence interval of 4.25± 0.17, and sounded the most natural to our listeners when compared to the ground truth.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133284704","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":"Application of Wireless Sensor Networks for Advancements in Non Intrusive Precision Beekeeping","authors":"R. Anaghaa, H. Guha, C. Raghavendra, H. H. Adithya, H. J. Lekhashree","doi":"10.1109/ICDSIS55133.2022.9915828","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915828","url":null,"abstract":"Honey bees play a vital role in many ecological and environmental processes which are of immense value to all life forms. In the last fifty years, their contribution to the pollination of dependent crops has increased three folds, playing a key role in ecological systems, industrial crop production, production of commercial products with medicinal properties. The conventional method involves manual inspection, which requires the bee keeper to visually inspect the activities by opening the hive. This causes agitation among the bees. In addition, this method is purely based on experience of the bee keeper and is prone to human error. These factors have led to the need for advancement in apicultural techniques bringing under its umbrella numerous researchers working on various specializations. This work presents a brief discussion on some of the systems developed based on the concepts of Wireless Sensor Networks which have been deployed to monitor bee health and honey production, detect abnormal activities like swarming, absconding of bees, bee hive robbery and identification of queen-less states.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133288500","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":"Plant Health Monitoring System and Smart Gardening using IoT","authors":"R. D, A. R, Deepak. G, G. S","doi":"10.1109/ICDSIS55133.2022.9915830","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915830","url":null,"abstract":"Plant heath is the scientific framework associated with controlling pest infection and pathogen intervention. This in large scale could be helpful in managing effectiveness of field or forest. The food we eat in and the cattle we grow all have close correlation with plant health. The plant health monitoring system includes chlorophyll analysis, crop density or growth analysis and nutrient analysis using image processing technique. The proposed method monitors the plant health by Chlorophyll meter is used for identifying nutrient deficiency in plants. The existing chlorophyll meter is expensive and has many disadvantages. A low-cost chlorophyll meter is implemented and it has combined assistance of internet of things. The results are compared with that of spectrophotometer and all its enhancements are highlighted. The objective is satisfied there by introduction of low cost and less complexity. The ultrasonic sensors transmit and receives waves from the target it hits. This is mounted at the top of the crop or field there by continuously monitoring the growth and indicating the periodical growth updation. The nutrition of the plant is monitored by the image processing technique, using plant image acquired from the camera. The raspberry pi board is the heart of the entire system where it controls the entire experimentation.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128808770","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":"Improved LBP and Discriminative LBP: Two novel local descriptors for Face Recognition","authors":"Shekhar Karanwal","doi":"10.1109/ICDSIS55133.2022.9915933","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915933","url":null,"abstract":"Most of LBP based descriptors develop their feature size by considering the uniform coordination among neighbors and center pixel. Additionally, most of them possesses noisy thresholding function. This limits the discriminativity of these descriptors to large extent. To eliminate all above defined conditions two novel descriptors are introduced called as Improved LBP (ILBP) and Discriminative LBP (DLBP). In ILBP, initially maximum value is attained from the 3x3 patch. Then product is taken between the maximum value and one of best possible values within range (.1-.9) to develop the threshold value. For this work it has been observed that.9 gives the best accuracy therefore.9 is used for obtaining the threshold value. The best range value will be chosen for obtaining the threshold value. Then all neighbors are compared against threshold for forming ILBP code. The ILBP histogram is achieved by computing the ILBP code for each pixel position. In DLBP, the histograms of ILBP and LBP are merged to form the more robust descriptor. For feature compression PCA is used and then classification was done by RBF technique, the SVMs method. Experiments conducted on 2 benchmark datasets i.e. ORL and GT confirms ability of both the descriptors against various methods. Among all it is DLBP which achieves best accuracy.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128910908","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":"A Quick Review and Performance Analysis of Custom and Transfer Learning CNN Architectures for Event Detection in Videos","authors":"Susmitha Alamuru, S. Jain","doi":"10.1109/ICDSIS55133.2022.9915866","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915866","url":null,"abstract":"Event/Action detection in videos is a growing research interest as it has numerous applications such as patient monitoring in health care, anomaly detection in surveillance systems, retrieval of video, human and computer interactions, gaming environment, entertainment environment etc. This is all because of one and only Deep learning due to its capability to outperform the conventional hand-crafted feature extraction algorithms. Transfer learning is significant in training deep neural networks with small datasets. The objective of this paper is to compare popular pretrained CNN models (in Top-1 accuracy) with custom CNN, built from scratch to detect human actions in UCF11 dataset.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124200181","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 of Artificial Intelligence Enabled Intelligent Sixth Generation (6G) Wireless Communication Networks","authors":"S. Periannasamy, C. Thangavel, Sahukar Latha, G. Reddy, S. Ramani, Pooja V. Phad, S.Ravi Chandline, S. Gopalakrishnan","doi":"10.1109/ICDSIS55133.2022.9915945","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915945","url":null,"abstract":"5G Generation connections, which have many novel features compared to Four-G connections, will be dispatched authoritatively very soon. Between 2027 and 2030, it is anticipated that the sixth-generation wireless communication system, utilising the entirety of artificial intelligence, will be implemented. In addition to 5G, there are a number of fundamental challenges that must be addressed, including increased scheme capability, higher data rates, and improved quality of service (QoS). This accessible manuscript discusses upcoming 6G wireless technology and its situation. Emerging technologies such as artificial intelligence and optical wireless technology are discussed. With 6G, mobile networks are anticipated to become one hundred times faster. As 6G expands beyond terrestrial networks and into space, it will enable new scenarios and services with terabytes of data traffic, enabling unprecedented human-machine interaction. 5G is intended to provide peak data rates of 20 Gigabits per second (Gbps) and average user experience rates of 120 Megabits per second (Mbps). It is anticipated that 6G speeds will be closer to 1,000 Gbps and 1 Gbps, respectively. 6G enables options such as holographic communication à la Star Trek and X reality (XR, which integrates AR, VR, and Mixed Reality). One of the goals of 6G cyberspace will be to deliver messages with a microsecond delay as opposed to a 1000-period delay. The 6G technology is enhanced by the combination of artificial intelligence and machine learning (AI), Using sub-mm waves, the 6G significantly influences the calculated communication capability for location determination. Using sub-mm Wave (e.g., wavelengths less than one millimetre) in conjunction with frequency selectivity to determine comparative electromagnetic incorporation charge will lead to significant advancements in wireless sensing technology. In terms of 5G, the calculation of mobile edge computing (MEC) is merely the tip of the iceberg. By the time 6G networks are established, it will be simpler to incorporate computation into collective communication and arithmetic. This generation continues to evolve in response to more distributed radio access networks (RAN) and the desire to utilise the terahertz (THz) range to further extend functionality, reduce latency, and improve spectrum sharing efficiency. It is expected that application 6G will find widespread use in the administration and production of emulsions. Clearly, 5G development communications are more uniform, and global spending has begun. Academic cooperation has started to incubate the next generation of wireless communication systems (namely 6G) in fields such as community security, health monitoring, and space excellent capabilities in order to further the development of wireless networks. Sixth G intended to provide the foundation for the stratification of communication needs in the 2030s.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116046371","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}