{"title":"Violence Detection using Deep Learning Techniques","authors":"Himanshu Gupta, Syed Taqi Ali","doi":"10.1109/ICETCI55171.2022.9921388","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921388","url":null,"abstract":"In the past years, human action recognition has been improved. Violence recognition is one of the best challenging research topics in the field of computer vision. Its one of the specific application is to find violence from surveillance cameras in public places, private places etc. We want an immediate control on these violent incidents. Human operator needed for monitoring the screen of surveillance video, which often leads to mistake and neglect to pinpoint the occurrence of unusual events, its require to them in a powerful search for automated violence detection systems. This paper discusses this research problem and explores LSTM and BiLSTM based solution to solve it. In addition, a layer of attention is present and used a new content database that collected from surveillance camera and normal recorded videos available on YouTube, Facebook etc. This database is publicly available. From the comprehensive tests conducted on Hockey Fight and dataset containing crowd and normal public scenes. It seems that BiLSTM model has more accuracy in the combat situation than LSTM model.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116639663","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":"Predicting Atmospheric Variables in the MERRA-2 Database using Neural Networks","authors":"Bhavye Mathur","doi":"10.1109/ICETCI55171.2022.9921371","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921371","url":null,"abstract":"Meteorological research often requires modelling atmospheric variables. With an increase of interest in climate science due to the urgency of climate change, easier access to meteorological data could help accelerate climate mitigation efforts. Specifically, analysis in aviation fields would be impacted greatly with more accurate data. Equations from the International Standard Atmosphere (ISA) are conventionally used to calculate barometric variables but yield only ideal results because they are generalisations of our atmosphere. For applications in aviation and weather research, more accurate values are desired. NASA's MERRA-2 database provides detailed meteorological information about pressure, temperature, humidity, and wind in 3-hour intervals from 1980. However, the data is too large to be feasibly used and inaccessible. Making a mathematical model to summarise it is therefore incredibly valuable. Conventional statistical models fail to represent the complexity of such atmospheric data making machine learning a worthy competitor. This research has successfully explored the possibility of using Artificial Intelligence-based Neural Networks to create a model to predict atmospheric variables from 4-D inputs (latitude, longitude, altitude, and time) to greatly improve upon the standard barometric equations in the ISA.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124697952","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":"Machine Learning Approach for New Crop Disease Predict and Alert System: A Review","authors":"E. Ekanayaka, Ppnv Kumara","doi":"10.1109/ICETCI55171.2022.9921364","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921364","url":null,"abstract":"Agriculture plays a very important role in Sri Lanka. Still, most of the people’s main livelihood in rural areas is agricultural production, such that vegetables, fruits, and spices. Those products are very profitable, and they affect not only a person’s economy but also the country’s economy. Crop diseases are the enemies of those products. Crop diseases can reduce or ruin the yield as a result of stealing the energy of a crop. It will be a great loss to farmers. Also, affect the country’s economy because the agricultural products market has down with the failure to supply does not meet the demand. Crops can be affected by an existing disease as well as a new disease. It is okay when crops affect by an existing disease because farmers are aware of that disease and can follow the existing prevention methods to reduce the risk, but if a new disease affects the crops what can they do? Sometimes farmers fail to get any action until it spread all over the country rapidly. That is the necessity of having a system to give an alert for everyone to be aware of a new crop disease as soon as it arises in any area. It is a precious benefit that can predict other risky crops for that new disease using the new advancement in technology. Crop diseases can be classified into basically two categories infectious and non-infectious. Infectious diseases can be further categorized as viruses, bacteria, fungi, and pests. In the agriculture field, not any system to classify or predict new diseases. The health field has used the method of classification to predict new human diseases. This research paper gives to research on various crop diseases and technology review of Machine Learning algorithms that can be used for new disease prediction through classification.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121135479","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}
Sudharmendra G V, Swaroop B S, Gokul L M, Vineetha B, P. H. B.
{"title":"Profile - Decentralized Application for Education","authors":"Sudharmendra G V, Swaroop B S, Gokul L M, Vineetha B, P. H. B.","doi":"10.1109/ICETCI55171.2022.9921360","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921360","url":null,"abstract":"Decentralized applications have evolved in the recent past. Many sectors have shown focus towards the Decentralized applications. This paper extends the application to the education sector. The work is associated with the creation of a Decentralized Application on the Ethereum Blockchain, which includes the decentralized way of storing data such as the student details. Face detection feature has been incorporated to tackle the problem of proxy attendance and other malpractices. The Decentralized Application interacts with the smart contract written on the Ethereum network. The smart contract created involves in storing the details of the student’s education timeline, such as his/ her marks, institution information, etc. Cloud technology has been used to store large files which cannot be stored in the smart contracts. Many natural calamities and other causes have led to the destruction of the stored details in the traditional databases, these problems have been overcome with this use of Cloud technology, where it provides features like replicability to avoid loses, reliability to avoid failures, scalability to avoid shortage of resources, etc. Authentication has been addressed with the help of face recognition tool which detects the identity of a person. This attempt of solving the above problems have been stated in this paper. Addition of a security layer with face recognition, storage of media files in the AWS S3 cloud, and interaction with the Decentralized Application, makes this paper unique from the other papers.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131778520","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":"Crop Type and Stress Detection using Transfer Learning with MobileNet","authors":"Anurag Varma Penmetsa, T. Sarma","doi":"10.1109/ICETCI55171.2022.9921356","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921356","url":null,"abstract":"Image classification has been used to identify and classify different crops and tell us about their health condition. It is in high demand to investigate for an on-the-fly classification for crop discrimination and stress identification having a camera installed on the UAV. This paper proposes a new MobileNet+D3 architecture to identify the crop class from the leaf images and to detect the crop stress. In this study, the leaf images of 10 different crops have been collected from both healthy and unhealthy plants. The proposed model is compared with traditional machine learning algorithms like KNN and SVM along with a Deep CNN model with different activation functions like ReLU, Leaky ReLU and Adam optimizer. The proposed MobileNet+D3 model achieved an accuracy of 97% which is higher than all the methods considered in the comparative study. The proposed method is more suitable for real-time classification on low computing devices.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134141946","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":"Complex Valued, Multi-Layer Hopfield Neural Network","authors":"G. Ramamurthy, T. J. Swamy","doi":"10.1109/ICETCI55171.2022.9921359","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921359","url":null,"abstract":"Based on a Complex Valued Neural Network (CVNNs) with the neurons placed in multiple layers, several interesting associative memories are proposed and their dynamics is investigated. Specifically, the synaptic weight matrix was chosen to be Block Hermitian, Block Jacobi, Block Toeplitz and Block Hankel. It is reasoned that in the case of such structured multilayer CVNNs, an interesting Convergence theorem holds true which enables that utilization of such an Artificial Neural Network as an associative memory. It is expected that the CVNNs proposed in this research paper have biological significance.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133553463","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":"3D-D2D: An Efficient Hybrid Model For Hyperspectral Image Classification","authors":"Sohan K R, Satish Kumar Singh","doi":"10.1109/ICETCI55171.2022.9921372","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921372","url":null,"abstract":"Hyperspectral Image (HSI) classification started with the machine learning classifiers like SVM (Support Vector Machine). It transitioned towards deep neural networks, which perform better than their classifier counterparts.CNN (Convolution Neural Networks) approaches are widely found in the current literature, including architectures like 2D CNN,3D CNN, and various other models using a combination of multiple CNN architectures. The correctness of HSI classification depends on both spectral and spatial features. 2D CNN cannot capture spatial features six, resulting in poor performance. On the other hand, 3D CNNs are computationally heavy and are not widely deployed. To overcome these bottlenecks, hybrid models were proposed where both 3D and 2D CNN are used together to exploit both spatial and spectral features. These models perform considerably well and are more computationally efficient when compared to 3D CNN. This paper proposes a custom hybrid model composed of 3D CNN with Max-Pooling coupled with depth-wise 2D CNN for reduced computational cost. It has considerably fewer learning parameters compared to other proposed CNN models. The performance of the proposed model was evaluated on Indian Pines, University of Pavia, and Salinas Scenes remote sensing datasets and results of the same were compared with state of the art and various other CNN models to validate the performance of the proposed model.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129739359","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}
A. Lomuscio, L. Moss, Ekaterina Ovchinnikova, Riccardo Rosati
{"title":"Tutorials","authors":"A. Lomuscio, L. Moss, Ekaterina Ovchinnikova, Riccardo Rosati","doi":"10.1109/ICETCI55171.2022.9921368","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921368","url":null,"abstract":"for Tutorial: Quantum Computing uses the principles of quantum physics to perform computations. Quantum Mechanics is one of the most profound theories of modern physics and it explains the working of nature in best possible and experimentally provable ways. Just like we use the deterministic calculations following the rules of classical mechanics (in classical computations), we try to harness laws of quantum mechanics to get most probable or best possible solutions using Quantum Computations. Quantum computing requires basic or intermediate knowledge of multiple disciplines like quantum physics, linear algebra, basic trigonometry, vectors, matrix operations etc. hence it may look difficult to someone at the beginning however enough practice and exposure to fundamentals can be very helpful for smooth transition from world of classical computing to Quantum Computing. Learning Objective: To build the basic understanding of what Quantum Computing is and develop understanding of the fundamental key concepts used in quantum computations; another goal is to make participants understand the working of basic quantum algorithms. It will make learners aware of the progress made in past few years, and what are the major impacts and applications of the same in Industry. Give on experience of working Abstract for Tutorial: With the advent of next-generation sequencing (NGS) technologies, there arose a need to identify candidate mutations for causality. A challenge often faced in identifying and inferring the causal SNPs from sequence data is that different methods need to be preferentially used to predict the effect of mutations for determining bona fidelity. While there are approaches focused on a wide array of highly sensitive, if not less stringent methods that the NGS has delivered in the recent past, this workshop aims to bridge the gap in using systems genomic approach taking command line scripts to Galaxy based workflows. A special focus of this workshop is on the current trends in genome analyses with special insights into NGS analysis. The sessions largely focus on whole exome sequencing (WES) and whole transcriptome shotgun sequencing (WTSS) or RNA-seq pipelines, Abstract: Humans are considered to be nature's best creation. What takes humans at an advantageous rank as compared to other living beings is possibly intelligence and cognitive abilities. With the advancement of technology especially Deep Neural Network (DNN) we are even succeeding in imparting intelligence in robots. Though robots can ease human life by performing different intelligent activities, they still lack human emotions. The objective of Artificial Emotional Intelligence field is to give computers/robots abilities so that they can not only understand its user's emotions but also can interact Abstract: Radio Frequency (RF) signal classification is a key technique of Dynamic Spectrum Access (DSA) to utilize the unused spectrum in Cognitive Radio (CR) to meet the ever-increasing traff","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130627176","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":"ICT-Assisted Growth Management System for Mud crabs (ICT-AGMAS): Deployment and Evaluation","authors":"Rossian V. Perea, Jesus Paolo B. Cullado","doi":"10.1109/ICETCI55171.2022.9921381","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921381","url":null,"abstract":"This study provided the concept of applying information technology in the aquaculture sector that offers an appropriate growth management system for mud crabs (Scylla spp.) through the utilization of a patented device and software application known as Information and Communication Technology-Assisted Growth Management System (ICT-AGMAS). This utility model (UM) is intended for real-time monitoring of the morphometric development of mud crabs. The automated nature of this technology avoids the farmers from manually checking the crabs within the pond, thus saving time and labor costs. To test its performance, the system was deployed at one of the polyculture aquaculture farms at San Juan I, Ternate, Cavite for five months. A comparison of the actual number of sampled crabs per unit time between the conventional sampling method (manual) and ICT-AGMAS was made by applying deep learning. Evaluation results revealed that the system can offer a faster and easier way of sampling mud crab with a sampling time difference of 143.25 seconds compared to the conventional sampling protocol. In addition, statistics and analysis of the use of the system disclosed a positive user acceptance of applying the technology based on identified descriptive variables. Estimated financial parameters such as payback period, the return of investment (ROI), and net present value (NPV) were also found to be positive and viable.","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129848986","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":"Isotropization of Complex-Valued Reservoir Computing on 2-D Dynamical System","authors":"Bungo Konishi, A. Hirose, R. Natsuaki","doi":"10.1109/ICETCI55171.2022.9921365","DOIUrl":"https://doi.org/10.1109/ICETCI55171.2022.9921365","url":null,"abstract":"Reservoir computing (RC), which achieves high-speed learning through a reservoir layer with recurrent non-linear mapping to a high dimensional space, has been used for prediction and estimation of sequential data. To deal with complex amplitude data such as synthetic aperture radar (SAR) data, RC has been extended to the complex domain, complex-valued reservoir computing (CVRC). In this paper, we analyze 2-D dynamical systems and examined the isotropic dynamics of CVRC. We show that CVRC preserves the periodicity of the input signal and has a high robustness to initial values compared to non-isotropic real-valued RC (RVRC).","PeriodicalId":439683,"journal":{"name":"2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125127283","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}