2023 2nd International Conference for Innovation in Technology (INOCON)最新文献

{"title":"INOCON 2023 Schedule","authors":"","doi":"10.1109/inocon57975.2023.10101141","DOIUrl":"https://doi.org/10.1109/inocon57975.2023.10101141","url":null,"abstract":"","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125196657","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":"Facial Emotional Recognition Using Convolutional Neural Network","authors":"Deepak Raj, Md. Abdul Wassay","doi":"10.1109/INOCON57975.2023.10101347","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101347","url":null,"abstract":"The face of a person is his identity. Most of his emotions, issues can be derived from his face. Face is the window to the soul which was said by famous French doctor Duchenne de Boulogne. He used several techniques to support his theory like giving shocks of electric impulses to understand how a person reacts to muscular contractions. He also tried to induce some of the expressions of bizarre looking. The ultimate aim is to analyze how much muscles contribute to emotion. He successfully derived lots of human emotions which is hidden. After 200 years this field is still active as it requires more experiments to extract invisible truths of human truths. Lots of Emotion Recognition which is automatic have been seen in the field of Marketing and Advertising. It is also seen in the field of Medical, Law and order$ldots$etc. The main fundamental question arrives whether it is good to enter into our personal space. This a question which has lots of dimension. Those who are against this practice is claiming that this is a violation of human rights by which we can use the stored data to harm the society in future. Even though it is a major concern if we can rectify the above the scope in this area is phenomenal. Lots of researchers are still working on this area because of mainly one reason that is its wide application in the area of Medical Science. It can be used by a doctor for diagnosing a person with certain psychological disorders, children with Autism, person with Parkinson’s disease. It can be widely used to diagnose children with Autism so that particular child can be motivated at early stage leads to his success in future and thus provide a good citizen to the society. In our research we are using several datasets such as FER2013, CK+$ldots$etc. These datasets have been given to a model which includes Deep Convolutional Neural Network. Here input image is given to a model using camera. The particular image has to done preprocessing to extract fine features in the model. After pre-processing we should extract emotions from the photo which is given as input by comparing it with datasets and extract the emotions from the given photo. By using FER2013 dataset the author got validation accuracy of around 99.3347 percentage and test accuracy around 60.94 percentage, with CK + it is around 96.87 percentage and 71.62 percentage for validation and test respectively.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141046","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":"Analytical Approach for Soil and Land Classification Using Image Processing with Deep Learning","authors":"Yerrolla Aparna, G. Somasekhar, Nuthanakanti Bhaskar, K. Raju, G. Divya, K. Madhavi","doi":"10.1109/INOCON57975.2023.10101169","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101169","url":null,"abstract":"Agriculture highly depends on soil. Soils are available in a number of types. Each type of soil has unique characteristics, and various crops grow in each type of soil. For a number of reasons, researchers have recently developed an interest in land mappings and classifications. Soil health and analysis of soil health, that are important for the healthy crop productions, are receiving more attention from the research community as a result of the rising demanding for the agricultural fields. The soil classification is the process of categorizing soil sets into groups with comparable qualities and behaviors. Soil is a mineral storehouse. Farmers depends on the soil to grow various crops; however, most farmers are aware of which crops grow in particular soil. The classification of soil and land is essential. Soil type identification is necessary to avoid quantitative losses in agricultural productivity. Therefore, an analytical approach for soil and land classification using image processing and deep learning is presented in this methodology. The process of applying different operations to an image in order to either improve it or extract useful information from it is described as image processing. Using a deep learning algorithm based a convolutional neural network, this method categorizes images of soil and land.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128256571","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":"Deep Convolutional Neural Network-based Automatic Detection of Brain Tumour","authors":"Indraneel Paul, Adyasha Sahu, P. Das, S. Meher","doi":"10.1109/INOCON57975.2023.10101238","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101238","url":null,"abstract":"Deep convolutional neural networks (DCNNs) have been extensively studied for different types of detection and classification in the field of biomedical image processing. Many of them have produced results that are on par with or even better than those of radiologists and neurologists. But, the challenge to get good results from such DCNNs is the requirement of large dataset. In this paper, a unique single-model based approach for classifying brain tumours on small dataset is presented in this study. A modified DCNN called the RegNetY-3.2G is used, integrated with regularization DropOut and DropBlock to prevent over-fitting. Furthermore, an improved augmentation technique called the RandAugment is used to lessen the problem of small dataset. Lastly, MWNL (Multi-Weighted New Loss) method and end to end CLS (cumulative learning strategy) is used to address the problem of unequal size of sample, complexity in the classification and to lessen the effect of aberrant samples on training.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128296918","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":"Customer Segmentation Analysis Using LRFM Based Product and Brand Dimensions","authors":"Mirdatul Husnah, R. Vinarti","doi":"10.1109/INOCON57975.2023.10100974","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10100974","url":null,"abstract":"The development of information technology (IT) has encouraged transaction activities in companies so they can grow rapidly and be competitive. One of them is the utilization of customer behavior, which is widely used in helping companies make important marketing decisions and be competitive. One of them is the utilization of customer behavior, which is widely used in helping companies make important marketing decisions. However, the company considers that customer behavior is only limited to data recording, while transaction data can also be further analyzed by the company to gain knowledge about its customers. To overcome these problems, customer segmentation can be carried out to assist companies in adjusting marketing strategies and describing the relationship between products and customers. Customer segmentation is carried out using the LRFM/product and LRFM/product methods with the fuzzy C-Means algorithm. The results of the study show that customers who are in cluster 1 have good loyalty to the brand and product. This is characterized by a long duration, low recency, high frequency, and a large monetary value for the product or brand. And cluster 2 is a customer cluster with minimal loyalty or that does not yet have loyalty to the product and brand.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130838681","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":"Using Sysbench, Analyze the Performance of Various Guest Virtual Machines on A Virtual Box Hypervisor","authors":"Anchal Pokharana, Rishit Gupta","doi":"10.1109/INOCON57975.2023.10101143","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101143","url":null,"abstract":"Virtual Machines are classified as computers program also called image, which acts as a whole computer. It is real time emulation of an OS which work on a host machine and has access to some portion of its resources but acts as a whole computer. In this analysis of VMs same host is used for all the testing. To test various machines three OS are used Ubuntu 21.04, LinuxMint and ZorinOS. These are all UNIX-Based Linux systems based on the same Distro: Debian. Analysis of the virtual machines has been done under the identical circumstances using benchmarking tool. In this paper various benchmarking operations have been performed using Sysbench Benchmarking Tool to compare their results. All these OS have been installed on Virtual Box Hypervisor.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127297763","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":"Artificial Intelligence Based Hybrid Models for Prediction of Stock Prices","authors":"Harmanjeet Singh, M. Malhotra","doi":"10.1109/INOCON57975.2023.10101297","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101297","url":null,"abstract":"Stock price forecasting has recently become an important practical component of the economic arena. An intriguing task, stock price forecasting is regarded to be related to the volatility and noise of stock market activity. To address these issues and accurately predict stock prices, this paper proposes a hybrid framework based on a learning model such as stacked Long Short Term Memory (LSTM) and Convolutional network. Experiments with several possible outcomes are run to assess the proposed framework using the stock price data set. The model was trained on ADANI stock price from the last roughly fourteen years on stacked LSTM with a Convolutional network and evaluated on an assessment criteria Root Mean Square Error (RMSE). The stacked LSTM model has proven to be a competitive model against the other models in stock price prediction in various scenarios.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123779482","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":"Implementation of Braun and Baugh-Wooley Multipliers Using QCA","authors":"P. Kishore, Rohan Sirimalla, K. Sushma, R. S. Reddy","doi":"10.1109/INOCON57975.2023.10101300","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101300","url":null,"abstract":"Matrix multiplication is a key element in digital signal processing systems, as well as a repetitive procedure in several signal processing and computing tasks. The circuit complexity is mostly determined by the number of multiplications necessary to create the system. A parallel array multiplier is a method for meeting high execution speed requirements. In the last step of a standard Braun multiplier, there is an assembly containing 16 AND gates, 9 Full Adders, as well as a ripple carry adder (RCA). Researchers studied other 4nano devices as an alternative to CMOS since circuits are constrained by technological scalability. Quantum-dot Cellular Automata (QCA) system is really a viable alternative to CMOS technology in a variety of nano devices. It is appealing because of its quick speed, small size, with low power consumption. The creation of a small and high-speed Baugh Wooley multiplier utilizing Quantum Dot Cellular Automata is presented in this study. In DSP processors, multipliers are the fundamental building elements of many calculations. Various adder as well as multiplier models on QCA have already been presented, however there has been little effort done on signed multiplication. This paper utilizes the unique QCA characteristics to design a Baugh-Wooley Multiplier that is fast and efficient to implement both signed and unsigned multiplication and comparison will be done with present implemented multipliers. Multiplication is the basic building block for several DSP processors, Image processing and many other. QCA Designer is used to display simulation results. The computational complexity of algorithms employed inside Digital Signal Processors (DSPs) has significantly grown over time. Braun design is a simulation model of a similar array multiplier. A parallel array multiplier is a form of Braun multiplier. Braun multiplier architecture comprises mainly multiple Carry Save Adders, an array of AND gates, and a Ripple Carry Adder.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127635395","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":"Design, Simulation, Optimization and performance of a MEMS Based Piezoelectric Energy Harvester","authors":"Simhadri Parvathi, S. Raju, M. Srikanth, Y. Geetha Kusuma","doi":"10.1109/INOCON57975.2023.10101260","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101260","url":null,"abstract":"A piezoelectric harvester uses the piezoelectric effect to transform mechanical vibrations into electrical energy. The effectiveness of a piezoelectric cantilever beam to capture vibrational energy is significantly influenced by its geometry. This research proposes an unconventionally shaped MEMS-based energy harvester. The energy harvester has a rectangular cantilever construction with a triangular tip as its main structural element. The simulation findings demonstrated that the new cantilever structure can create greater stress than the triangular and rectangular structures while also improving the stress distribution. COMSOL Multiphysics is used to model the proposed construction. The energy harvesting device is modelled as a rectangular cantilever with a triangular form at the tip using the piezoelectric deployment mode. It is also utilised to examine the Energy Harvester’s mechanical and electrical behaviour. In order to calculate the mesh deformation and to optimise the thickness of the piezoelectric layer, the moving mesh application method is employed. Results from simulations of a rectangular beam with a triangular-shaped tip made of stainless steel as the substrate and lead zirconate titanate (PZT) as the piezoelectric material were obtained. The cantilever’s dimensions are calculated to be 27000 mm by 3000 mm by 200 mm. The outcomes are contrasted against triangular and rectangular shapes. According to the simulation results, the new cantilever structure may create more stress than the triangular and rectangular structures while also improving the stress distribution in the same circumstances. An output voltage of 6.4 mV and a deflection of 100 nm are obtained for a thickness of 200 m. This framework is applicable to wireless sensing devices.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"99 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120937062","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":"Alzheimer’s Disease Classification On sMRI Images Using Convolutional Neural Networks And Transfer Learning Based Methods","authors":"P. Sai, C. Anupama, R. V. Kiran, P. Reddy, N.Naga Goutham","doi":"10.1109/INOCON57975.2023.10101314","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101314","url":null,"abstract":"The most well-known cause of dementia that impairs memory is Alzheimer’s disease. Alzheimer’s patients have a neurodegenerative condition that causes loss of various brain functions. Researchers nowadays have established that a disease’s early diagnosis is the most important factor in improving patient care and treatment. Traditional methods for diagnosing Alzheimer’s disease (AD) are slow, inefficient, and require a lot of learning and training time. Recently, methods based on deep learning have been taken into consideration to classify neuroimaging information related to AD. In this research, we explore the use of transfer learning and convolutional neural networks (CNN) for AD early detection. To extract features for the classification process, we employ Alexnet that has been trained on our datasets. The success of the suggested strategy is explained by experimental research.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116454136","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}