B. G. Swamy, Bethi Pardhasaradhi, U. S. Acharya, P. Srihari, Sreenivasulu Reddy, R. Annavajjala
{"title":"FPGA Accelerated Automotive ADAS Sensor Fusion","authors":"B. G. Swamy, Bethi Pardhasaradhi, U. S. Acharya, P. Srihari, Sreenivasulu Reddy, R. Annavajjala","doi":"10.1109/CSNT57126.2023.10134612","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134612","url":null,"abstract":"Fusion of multi-modal sensor data is crucial to improve the performance of advanced driver assistance and safety systems. Usually, sensors such as radars, lidars, and cameras work individually to provide the time-varying kinematics (also referred to as tracks) of other vehicles and objects in the field of view of the ego vehicle. Further, these individual tracks are fused in a decentralized manner to achieve the fused tracks. For an automotive vehicle, low-latency and high-speed sensor fusion is a requirement to improve the overall safety. Rather than running the entire fusion algorithm in the central processing unit, some portion of the code or the whole fusion algorithm can be accelerated on a field programmable gate array to improve the overall functionality. With this objective, in this paper we propose a dedicated digital signal processing (DSP) architecture to realize the fusion algorithm which involves computation of fused state and covariance matrix by making use of matrix-to-matrix multiplications and matrix inversion. The matrix inversion is carried out using an efficient LU decomposition method, and matrix multiplication is realized as a vector-to-vector multiplication DSP architecture. Moreover, a folded DSP architecture is proposed for the state and covariance sub-modules to accelerate the overall functionality. Simulations are presented for two-dimensional constant velocity (CV) model with 4-dimensional state space, three-dimensional CV model with 6-dimensional state space, and three-dimensional constant acceleration (CA) model with 9-dimensional state space. Our results indicate that the proposed architecture is well suited for automotive sensor fusion.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114814194","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}
S. Niveditha, S. Shreyanth, V. Kathiroli, Priyanka Agarwal, S. Ram Abishek
{"title":"Kernelized Deep Networks for Speech Signal Segmentation Using Clustering and Artificial Intelligence in Neural Networks","authors":"S. Niveditha, S. Shreyanth, V. Kathiroli, Priyanka Agarwal, S. Ram Abishek","doi":"10.1109/CSNT57126.2023.10134609","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134609","url":null,"abstract":"Speech signal segmentation is a key component of speech processing tasks, such as speaker recognition, speech recognition, and emotion recognition. Traditional approaches often have low accuracy and high computational complexity. To address this issue, we propose a novel approach using kernelized deep networks. The method utilizes Mel-Frequency Cepstral Coefficients (MFCC) and Linear Predictive Coding (LPC) for feature extraction, with Spectral subtraction, wavelet denoising and Wiener filtering as preprocessing techniques. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are used for dimensionality reduction. Spectral clustering using the graph Laplacian and normalized Laplacian matrix is then employed to cluster the speech signals into different segments. The Lanczos algorithm, Implicitly Restarted Arnoldi Method and Krylov subspace is used to train the networks and classify the signals. Results on TIMIT and BURN corpus demonstrate that the proposed approach outperforms traditional techniques in terms of segmentation accuracy and reduces computational complexity. This research highlights the potential of kernelized deep networks for speech segmentation and contributes to the field of speech processing.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122062070","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":"An Event-Driven Spectrum-Aware Routing Protocol Based on Hungarian Algorithm in Cognitive Radio Sensor Networks","authors":"Hongya Wang, L. Tan","doi":"10.1109/CSNT57126.2023.10134584","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134584","url":null,"abstract":"An event-driven spectrum-aware routing algorithm based on the Hungarian algorithm (ESRH) is proposed to improve the spectrum utilization and the energy efficiency of cognitive radio sensor networks(CRSN). The method performs clustering in a distributed and self-organized manner and selects the node with the largest weight as the cluster head (CH). The Hungarian algorithm is used to assign the channels with smaller occupancy probability of primary user (PU), longer idle time and higher throughput to sensor nodes (SUs), which reduces the channel competition from SUs to PUs and improves the data transmission success rate. The gateway nodes and packet forwarding nodes are used for relay communication between clusters. Simulation results show that ESRH outperforms ESAC and ERP algorithms in terms of transmission performance, routing stability and network lifetime in a multi-round event-driven CRSN.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117222843","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":"Framework in Supply Chain using Inventory Management, Big Data and Inventory Analytics","authors":"Charisha Shyam Sukha, S. Prabhu","doi":"10.1109/CSNT57126.2023.10134627","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134627","url":null,"abstract":"Data deluge or Big Data has created a massive demand for big data analytics in Industry 4.0. This paper aims to understand the supply chain’s big data analytics (BDA) and the need for inventory analytics. The findings of this paper are optimizing inventory management with the help of inventory analytics and the applications and challenges of BDA in supply chain. The research is essential considering new applications and challenges which have evolved in recent years and technological advancements which have created more unique opportunities across industries.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125931896","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}
Neeraj Varshney, G. Kumar, Ankit Kumar, S. Pandey, Teekam Singh, K. Singh
{"title":"Machine Learning Based Algorithm for Earthquake Monitoring","authors":"Neeraj Varshney, G. Kumar, Ankit Kumar, S. Pandey, Teekam Singh, K. Singh","doi":"10.1109/CSNT57126.2023.10134640","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134640","url":null,"abstract":"In this paper, we are trying to predict the Earthquake before it happens using seismic indicators anywhere around the world. It is an important task, on detecting seismic events from seismic time series using machine learning techniques. When we train a dataset for any one location it should also be applicable to detect at the other locations. Earthquakes are one of the most dangerous and deadly natural disasters. It is very important for the safety of all human beings as well as all the animals living on the planet to predict the earthquake way before it is going to happen. The population of the earth is increasing at a very rapid rate so the human population is also settling in the areas where the region is at very high risk of earthquakes which also causes more people to be affected by the impact of the earthquakes and more people to die. During this research various machine learning techniques were used such as Support Vector Machine, Random Forest, Neural Network, Convolutional Neural Network, Quantum Machine Learning, K-Nearest Neighbor, Machine Learning Risk Prediction Algorithm, Deep learning Model, and Regression.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129450635","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":"Comprehensive Evaluation Model Based on Nonlinear Classify Algorithm of SVM","authors":"Xiaoyun Fan, Jianfeng Lu, Yongchang Ren","doi":"10.1109/CSNT57126.2023.10134657","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134657","url":null,"abstract":"System evaluation is an important branch of system science and the main content of the system engineering, and it also provides a scientific basis for the system evaluation. This paper presents a comprehensive evaluation model based on nonlinear classify algorithm of SVM. First of all, study and evaluate the foundation work, including evaluation index system, the index weight determination and the treatment of data standardization; Then, the research SVM, accurate description of nonlinear classify algorithm after clarify the basic thought, shows the five kinds of commonly used kernel function, and improve traditional SVM aiming at the existing problems. The content of this paper effectively solves the problem about model selection and over learning, nonlinear and the dimensionality curse, local minimum, it also improves the training speed and precision of SVM at the same time, reducing the amount of calculation, and it has very strong adaptability and practical value.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129848839","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}
Chengguang Wang, Wei Jiang, Yang Yu, Huiqi Jing, Ying Qin, Jian Li
{"title":"Research on Information Security of Network Accounting Based on the Combination of Apriori and AOI Algorithms","authors":"Chengguang Wang, Wei Jiang, Yang Yu, Huiqi Jing, Ying Qin, Jian Li","doi":"10.1109/CSNT57126.2023.10134691","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134691","url":null,"abstract":"The development of computer networks has also revolutionized the traditional accounting discipline. The cybernetic nature of network accounting determines that information security is the key to network accounting. The risk of accounting information system mainly comes from three aspects: firstly, the network’s accounting information storage has changed the traditional information storage mode, replacing the traditional paper mode with electronic storage, thus the information storage faces significant risks and the relevant data may be lost at any time; secondly, with the continuous development of Internet technology, computer and system viruses have many changing forms and types, making them difficult to identify and likewise Finally, in the network accounting information system, all data transmission relies on network or hardware storage devices, and the risk of data being stolen and illegally used during data transmission increases. In this paper, we will analyse the main security issues in the current development of network accounting and achieve the most effective protection of accounting data by introducing network accounting information based on a combination of Apriori and AOI algorithms. An analytical approach based on the meaning and logic of the APRIORI algorithm and the AOI algorithm, through algorithm implementation, and a general description of the process design based on APRIORI and AOI is given.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129860423","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 and Machine Learning based Financial Risk Network Assessment Model","authors":"Yao Liu","doi":"10.1109/CSNT57126.2023.10134653","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134653","url":null,"abstract":"In the vast sea of information, the powerful ability of machine learning(ML) algorithms to identify specific objects through goal guidance makes them stand out from the many methods people use. As a result, ML algorithms are widely used in business decision making. This paper presents a research analysis of financial risk network assessment model(FRNAM)s based on artificial intelligence(AI) and ML algorithms. The main risk sources of supply chain(SC) finance and the integrated risk assessment process are briefly discussed, the risk transmission effect of SC finance is analyzed, and the application of ML algorithms in financial risk assessment(FRA) is studied through the implementation process of ML algorithms and the introduction of decision trees; finally, the risk assessment capability of the FRNAM based on AI and ML is tested with Bank M as the research object. Finally, the risk assessment capability of the FRNAM based on AI and ML was tested with Bank M. The test results verified the effectiveness of the SC FRA model studied in this paper.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128349189","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":"Enhanced VANET Performance by Stable Cluster Head Selection Using Novel Stack of Algorithms","authors":"Parveen Kumar, Bijay Kumar Singh","doi":"10.1109/CSNT57126.2023.10134738","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134738","url":null,"abstract":"The use of VANET turns the roadway into a communal space, enhancing safety and facilitating data sharing among drivers. Data from each automobile is transmitted to the cluster head (CH) via a cluster. There are two main aspects that impact the effectiveness of a VANET network: the optimal number of the vehicle groups and the choice of the control node for stability. In this paper, we model the VANET as a hypergraph network and construct a state-of the-art modularity-based hypergraph clustering formulation by maximising tensor traces and using the modularity matrix as a feed to determine the optimal number of clusters. Automobiles were selected from each group based on how fast they were compared to others in the group, how trustworthy they were deemed by the group as a whole, how long their links lasted, and how well connected they were. All parameters are first transformed to eigenvalues, then a single CH is chosen. By adopting a fuzzy decision-making technique based on three factors, the optimal CH is selected for all vehicles in that cluster. Furthermore, the proposed method for selecting the reliable CH to improve throughput has been validated and significantly improved by comparing it to the other existing techniques.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126939414","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":"Mining and Utilization of English Learning Resources Using the Python NLTK","authors":"Xiaohong Zhou, Jiayue Shao","doi":"10.1109/CSNT57126.2023.10134668","DOIUrl":"https://doi.org/10.1109/CSNT57126.2023.10134668","url":null,"abstract":"In the age of big data, language learning increasingly rely on a large number of text-based corpora. Massive and authentic texts provide an essential English language learning context for English learners in China. Python NLTK (Natural Language Toolkit) is helpful for language learners for its large number of labeled English texts and its support for loading additional texts. These texts are so massive and authentic that they provide a language corpus for English learners. Furthermore, NLTK can extract useful language features with simple set of commands. A quick and systematic analysis of language features make language learning more efficient. This paper tries to describe the basic operation methods of Python NLTK in the mining and utilization of English learning resources, at lexical level, syntactic level and textual level. The research is not only beneficial to individual language learners, but also conducive to the development of corpus research towards systematization and intelligence.","PeriodicalId":355437,"journal":{"name":"2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130633193","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}