Volume-3 Issue-4, June 2023 – Indian Journal of Artificial Intelligence and Neural Networking (IJAINN) https://www.ijainn.latticescipub.com Exploring Innovation | ISSN: 2582-7626 (Online) | A Periodical Journal | Reg. No: C/1383209 | Published by Lattice Science Publication (LSP) Sat, 30 Dec 2023 05:56:15 +0000 en-US hourly 1 https://wordpress.org/?v=7.0 https://www.ijainn.latticescipub.com/wp-content/uploads/2021/01/cropped-IJAINN-logo-WF-32x32.png Volume-3 Issue-4, June 2023 – Indian Journal of Artificial Intelligence and Neural Networking (IJAINN) https://www.ijainn.latticescipub.com 32 32 D1066063423 https://www.ijainn.latticescipub.com/portfolio-item/d1066063423/ Wed, 20 Dec 2023 07:04:52 +0000 https://www.ijainn.latticescipub.com/?post_type=portfolio&p=2077 The Indian Journal of Artificial Intelligence and Neural Networking (IJAINN) has ISSN 2582-7626 (online), open-access, peer-reviewed, periodical bi-monthly international journal, which is published by Lattice Science Publication (LSP) in February, April, June, August, October and December.The aim of the journal is to publish high quality peer–reviewed original articles in the area of Artificial Intelligence and Neural Networking that covers Neural Networks, Fuzzy Logic, Simulated Biological Evolution Algorithms (Like Genetic Algorithm), Ant Colony Optimization, Reasoning and Evolution, Intelligence Applications, Computer Vision and Speech Understanding, Multimedia and Cognitive Informatics, Data Mining and Machine Learning Tools, Heuristic and Ai Planning Strategies and Tools, Computational Theories of Learning, Technology and Computing (Like Particle Swarm Optimization), Intelligent System Architectures, Knowledge Representation, Bioinformatics, Natural Language Processing, Multiagent Systems, Supervised Learning, Unsupervised Learning, Deep Learning, Big Data and AI Approaches, Reinforcement Learning, Learning with Generative Adversarial Networks, Regression and Prediction, Problem Solving and Planning, Clustering, Classification, Neural Information Processing, Vision and Speech Perception, Heterogeneous and Streaming Data, Probabilistic Models and Methods, Reasoning and Inference, Marketing and Social Sciences, Knowledge Discovery, Web Mining, Information Retrieval, Design and Diagnosis, Game Playing, Streaming Data, Music Modelling and Analysis, Robotics and Control, Multi-Agent Systems. #Neural Networks #Fuzzy Logic #Simulated Biological Evolution Algorithms (Like Genetic Algorithm) #Ant Colony Optimization #Reasoning and Evolution #Intelligence Applications #Computer Vision and Speech Understanding #Multimedia and Cognitive Informatics #Data Mining and Machine Learning Tools #Heuristic and AI Planning Strategies and Tools #Computational Theories of Learning #Technology and Computing (Like Particle Swarm Optimization) #Intelligent System Architectures #Knowledge Representation #Bioinformatics #Natural Language Processing #Multiagent Systems #Supervised Learning #Unsupervised Learning #Deep Learning #Big Data and AI Approaches #Reinforcement Learning #Learning with Generative Adversarial Networks #Regression and Prediction #Problem Solving and Planning #Clustering #Classification #Neural Information Processing #Vision and Speech Perception #Heterogeneous and Streaming Data #Probabilistic Models and Methods #Reasoning and Inference #Marketing and Social Sciences #Knowledge Discovery #Web Mining, Information Retrieval #Design and Diagnosis #Game Playing #Streaming Data #Music Modelling and Analysis #Robotics and Control #Multi-Agent systems #PhD #Academic #Scopus #SCI #LatticeScience #Springer, #ScienceDirect #IEEE #Mendeley #Research #Scholarship #UGC #SSRN #LatticeScience #ESCI #Science #Journal #Conference #SSRN #PubLons

The post D1066063423 appeared first on Indian Journal of Artificial Intelligence and Neural Networking (IJAINN).

]]> The Indian Journal of Artificial Intelligence and Neural Networking (IJAINN) has ISSN 2582-7626 (online), open-access, peer-reviewed, periodical bi-monthly international journal, which is published by Lattice Science Publication (LSP) in February, April, June, August, October and December.The aim of the journal is to publish high quality peer–reviewed original articles in the area of Artificial Intelligence and Neural Networking that covers Neural Networks, Fuzzy Logic, Simulated Biological Evolution Algorithms (Like Genetic Algorithm), Ant Colony Optimization, Reasoning and Evolution, Intelligence Applications, Computer Vision and Speech Understanding, Multimedia and Cognitive Informatics, Data Mining and Machine Learning Tools, Heuristic and Ai Planning Strategies and Tools, Computational Theories of Learning, Technology and Computing (Like Particle Swarm Optimization), Intelligent System Architectures, Knowledge Representation, Bioinformatics, Natural Language Processing, Multiagent Systems, Supervised Learning, Unsupervised Learning, Deep Learning, Big Data and AI Approaches, Reinforcement Learning, Learning with Generative Adversarial Networks, Regression and Prediction, Problem Solving and Planning, Clustering, Classification, Neural Information Processing, Vision and Speech Perception, Heterogeneous and Streaming Data, Probabilistic Models and Methods, Reasoning and Inference, Marketing and Social Sciences, Knowledge Discovery, Web Mining, Information Retrieval, Design and Diagnosis, Game Playing, Streaming Data, Music Modelling and Analysis, Robotics and Control, Multi-Agent Systems. #Neural Networks #Fuzzy Logic #Simulated Biological Evolution Algorithms (Like Genetic Algorithm) #Ant Colony Optimization #Reasoning and Evolution #Intelligence Applications #Computer Vision and Speech Understanding #Multimedia and Cognitive Informatics #Data Mining and Machine Learning Tools #Heuristic and AI Planning Strategies and Tools #Computational Theories of Learning #Technology and Computing (Like Particle Swarm Optimization) #Intelligent System Architectures #Knowledge Representation #Bioinformatics #Natural Language Processing #Multiagent Systems #Supervised Learning #Unsupervised Learning #Deep Learning #Big Data and AI Approaches #Reinforcement Learning #Learning with Generative Adversarial Networks #Regression and Prediction #Problem Solving and Planning #Clustering #Classification #Neural Information Processing #Vision and Speech Perception #Heterogeneous and Streaming Data #Probabilistic Models and Methods #Reasoning and Inference #Marketing and Social Sciences #Knowledge Discovery #Web Mining, Information Retrieval #Design and Diagnosis #Game Playing #Streaming Data #Music Modelling and Analysis #Robotics and Control #Multi-Agent systems #PhD #Academic #Scopus #SCI #LatticeScience #Springer, #ScienceDirect #IEEE #Mendeley #Research #Scholarship #UGC #SSRN #LatticeScience #ESCI #Science #Journal #Conference #SSRN #PubLons

Is the Ecosystem of Kolkata Sustainable?: Machine Learning Based Study on Air Quality IndexCROSSMARK Color horizontal
Biswajit Biswas1, Sayantan Ghosh2
1Dr. Biswajit Biswas, Department of Business Administration, University of Kalyani, West Bengal, India.

2Sayantan Ghosh, Performance-io LLP, Kolkata (West Bengal), India.

Manuscript received on 28 April 2023 | Revised Manuscript received on 01 June 2023 | Manuscript Accepted on 15 June 2023 | Manuscript published on 30 December 2023 | PP: 7-13 | Volume-3 Issue-4, June 2023 | Retrieval Number: 100.1/ijainn.D1066063423 | DOI: 10.54105/ijainn.D1066.063423

Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Timely and accurate forecasting of Air Quality Index (AQI) helps the Industries to select suitable control of air pollution measures. It helps people to reduce exposure in pollution. In this present age Air quality Index is one of the burning issues in India. The air contaminations are harmful for our biological system and also for the climate. To keep up the best air quality cross the country different types of air toxins are estimated through the air quality measuring standards. The aim of this research work is modelling air quality of a location with respect to time with the help of Machine Learning (ML). The proposed and developed model was emphasizes particularly in Kolkata, capital of the state West Bengal in India and the findings have direct implications to build & maintain a sustainable ecosystem over there.

Keywords: Air Quality Index, Machine Learning (ML), Python, Suitable control.
Scope of the Article: Machine Learning

Download PDF

The post D1066063423 appeared first on Indian Journal of Artificial Intelligence and Neural Networking (IJAINN).

]]> D1070063423 https://www.ijainn.latticescipub.com/portfolio-item/d1070063423/ Tue, 27 Jun 2023 11:17:41 +0000 https://www.ijainn.latticescipub.com/?post_type=portfolio&p=1878 The Indian Journal of Artificial Intelligence and Neural Networking (IJAINN) has ISSN 2582-7626 (online), open-access, peer-reviewed, periodical bi-monthly international journal, which is published by Lattice Science Publication (LSP) in February, April, June, August, October and December.The aim of the journal is to publish high quality peer–reviewed original articles in the area of Artificial Intelligence and Neural Networking that covers Neural Networks, Fuzzy Logic, Simulated Biological Evolution Algorithms (Like Genetic Algorithm), Ant Colony Optimization, Reasoning and Evolution, Intelligence Applications, Computer Vision and Speech Understanding, Multimedia and Cognitive Informatics, Data Mining and Machine Learning Tools, Heuristic and Ai Planning Strategies and Tools, Computational Theories of Learning, Technology and Computing (Like Particle Swarm Optimization), Intelligent System Architectures, Knowledge Representation, Bioinformatics, Natural Language Processing, Multiagent Systems, Supervised Learning, Unsupervised Learning, Deep Learning, Big Data and AI Approaches, Reinforcement Learning, Learning with Generative Adversarial Networks, Regression and Prediction, Problem Solving and Planning, Clustering, Classification, Neural Information Processing, Vision and Speech Perception, Heterogeneous and Streaming Data, Probabilistic Models and Methods, Reasoning and Inference, Marketing and Social Sciences, Knowledge Discovery, Web Mining, Information Retrieval, Design and Diagnosis, Game Playing, Streaming Data, Music Modelling and Analysis, Robotics and Control, Multi-Agent Systems. #Neural Networks #Fuzzy Logic #Simulated Biological Evolution Algorithms (Like Genetic Algorithm) #Ant Colony Optimization #Reasoning and Evolution #Intelligence Applications #Computer Vision and Speech Understanding #Multimedia and Cognitive Informatics #Data Mining and Machine Learning Tools #Heuristic and AI Planning Strategies and Tools #Computational Theories of Learning #Technology and Computing (Like Particle Swarm Optimization) #Intelligent System Architectures #Knowledge Representation #Bioinformatics #Natural Language Processing #Multiagent Systems #Supervised Learning #Unsupervised Learning #Deep Learning #Big Data and AI Approaches #Reinforcement Learning #Learning with Generative Adversarial Networks #Regression and Prediction #Problem Solving and Planning #Clustering #Classification #Neural Information Processing #Vision and Speech Perception #Heterogeneous and Streaming Data #Probabilistic Models and Methods #Reasoning and Inference #Marketing and Social Sciences #Knowledge Discovery #Web Mining, Information Retrieval #Design and Diagnosis #Game Playing #Streaming Data #Music Modelling and Analysis #Robotics and Control #Multi-Agent systems #PhD #Academic #Scopus #SCI #LatticeScience #Springer, #ScienceDirect #IEEE #Mendeley #Research #Scholarship #UGC #SSRN #LatticeScience #ESCI #Science #Journal #Conference #SSRN #PubLons

The post D1070063423 appeared first on Indian Journal of Artificial Intelligence and Neural Networking (IJAINN).

]]> The Indian Journal of Artificial Intelligence and Neural Networking (IJAINN) has ISSN 2582-7626 (online), open-access, peer-reviewed, periodical bi-monthly international journal, which is published by Lattice Science Publication (LSP) in February, April, June, August, October and December.The aim of the journal is to publish high quality peer–reviewed original articles in the area of Artificial Intelligence and Neural Networking that covers Neural Networks, Fuzzy Logic, Simulated Biological Evolution Algorithms (Like Genetic Algorithm), Ant Colony Optimization, Reasoning and Evolution, Intelligence Applications, Computer Vision and Speech Understanding, Multimedia and Cognitive Informatics, Data Mining and Machine Learning Tools, Heuristic and Ai Planning Strategies and Tools, Computational Theories of Learning, Technology and Computing (Like Particle Swarm Optimization), Intelligent System Architectures, Knowledge Representation, Bioinformatics, Natural Language Processing, Multiagent Systems, Supervised Learning, Unsupervised Learning, Deep Learning, Big Data and AI Approaches, Reinforcement Learning, Learning with Generative Adversarial Networks, Regression and Prediction, Problem Solving and Planning, Clustering, Classification, Neural Information Processing, Vision and Speech Perception, Heterogeneous and Streaming Data, Probabilistic Models and Methods, Reasoning and Inference, Marketing and Social Sciences, Knowledge Discovery, Web Mining, Information Retrieval, Design and Diagnosis, Game Playing, Streaming Data, Music Modelling and Analysis, Robotics and Control, Multi-Agent Systems. #Neural Networks #Fuzzy Logic #Simulated Biological Evolution Algorithms (Like Genetic Algorithm) #Ant Colony Optimization #Reasoning and Evolution #Intelligence Applications #Computer Vision and Speech Understanding #Multimedia and Cognitive Informatics #Data Mining and Machine Learning Tools #Heuristic and AI Planning Strategies and Tools #Computational Theories of Learning #Technology and Computing (Like Particle Swarm Optimization) #Intelligent System Architectures #Knowledge Representation #Bioinformatics #Natural Language Processing #Multiagent Systems #Supervised Learning #Unsupervised Learning #Deep Learning #Big Data and AI Approaches #Reinforcement Learning #Learning with Generative Adversarial Networks #Regression and Prediction #Problem Solving and Planning #Clustering #Classification #Neural Information Processing #Vision and Speech Perception #Heterogeneous and Streaming Data #Probabilistic Models and Methods #Reasoning and Inference #Marketing and Social Sciences #Knowledge Discovery #Web Mining, Information Retrieval #Design and Diagnosis #Game Playing #Streaming Data #Music Modelling and Analysis #Robotics and Control #Multi-Agent systems #PhD #Academic #Scopus #SCI #LatticeScience #Springer, #ScienceDirect #IEEE #Mendeley #Research #Scholarship #UGC #SSRN #LatticeScience #ESCI #Science #Journal #Conference #SSRN #PubLons

Characterizing Adaptive Optimizer in CNN by Reverse Mode Differentiation from Full-ScratchCROSSMARK Color horizontal
Ruo Ando1, Yoshihisa Fukuhara2, Yoshiyasu Takefuji3
1Ruo Ando, National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo, Japan.

2Yoshihisa Fukuhara, Musashino University, Department of Data Science, 3-3-3 Ariake, Koto-Ku, Tokyo, Japan.

3Yoshiyasu Takefuji, Musashino University, Department of Data Science, 3-3-3 Ariake, Koto-Ku, Tokyo, Japan.

Manuscript received on 30 June 2023 | Revised Manuscript received on 15 June 2023 | Manuscript Accepted on 15 June 2023 | Manuscript published on 30 June 2023 | PP: 1-6 | Volume-3 Issue-4, June 2023 | Retrieval Number: 100.1/ijainn.D1070063423 | DOI: 10.54105/ijainn.D1070.063423

Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Recently, datasets have been discovered for which adaptive optimizers are not more than adequate. No evaluation criteria have been established for optimization as to which algorithm is appropriate. In this paper, we propose a characterization method by implementing backward automatic differentiation and characterizes the optimizer by tracking the gradient and the value of the signal flowing to the output layer at each epoch. The proposed method was applied to a CNN (Convolutional Neural Network) recognizing CIFAR-10, and experiments were conducted comparing and Adam (adaptive moment estimation) and SGD (stochastic gradient descent). The experiments revealed that for batch sizes of 50, 100, 150, and 200, SGD and Adam significantly differ in the characteristics of the time series of signals sent to the output layer. This shows that the ADAM optimizer can be clearly characterized from the input signal series for each batch size.

Keywords: Characterization of Optimizers, Adaptive Optimizer, Reverse Mode Differentiation, CNN
Scope of the Article: Neural Networks

Download PDF

The post D1070063423 appeared first on Indian Journal of Artificial Intelligence and Neural Networking (IJAINN).

]]>