2022 IEEE World AI IoT Congress (AIIoT)最新文献

{"title":"Real Time FPGA-Based CNN Training and Recognition of Signals","authors":"Tyler Groom, K. George","doi":"10.1109/aiiot54504.2022.9817153","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817153","url":null,"abstract":"Training a machine learning model requires many resources and a fast, efficient processing system. This work proposes an FPGA based machine learning model for fast and efficient signal recognition, allowing for a mobile application of a training model. This is composed of several processes and steps. First is receiving the signal and running it against the current model. Second is applying several filtering methods, as well as noise, to change how the signal is represented. Finally, training the current model based on the data generated from the original signal, updating the list of recognized items. This is run on an FPGA using python on a Linux environment, utilizing a CPU based training algorithm.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"354 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131289118","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":"Research and Development of an E-commerce with Sales Chatbot","authors":"Mostaq M. Hossain, Mubassir Habib, Mainuddin Hassan, Faria Soroni, Mohammad Monirujjaman Khan","doi":"10.1109/aiiot54504.2022.9817272","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817272","url":null,"abstract":"E-commerce is the process of conducting commerce through computer networks. An individual sitting in front of a computer may use all of the internet's resources to purchase or sell things. Unlike conventional commerce, which is carried out physically with a person's effort to travel and obtain items, e- commerce has made it simpler for humans to eliminate physical labor and save time. This online business management system has also assisted retailers in saving money on upfront costs such as storefronts and staff. The objective is to design an advanced e- commerce system with a smart chatbot to provide a user-friendly experience for consumers. Consumers will save time with the quick accessibility feature of the chatbots in the system. With the help of natural language processing, we have developed a realtime chatbot with smart features. On this smart e-commerce website, we have tried to solve some of the problems with the existing e-commerce platform in our country. The system operates on the Django platform, which is built on Python. The system's architecture is created by using Django's Model-View- Template. HTML, CSS, JavaScript, and bootstrap are utilized for the front end and validation. For the backend, we have used an SQLite database. Clients, as it has been discovered, usually have a difficult time shopping on e-commerce because no support assistant can provide immediate feedback. The system consists of several sections, including the registration system, the login system, the search system, the order system, the add product system, the view product system, the order received system, and an interface to communicate with the bot. If users have any queries, they may contact the admin panel via the contact us page. Overall, the system is quick and reliable. A user-friendly interface boosts the purchasing experience for consumers across the country who have access to the internet. The system's accuracy is high enough for satisfying results and thus successfully supports people in making better judgments while being low-cost and user-friendly in design.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131174255","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":"Classification of “Like” and “Dislike” Decisions From EEG and fNIRS Signals Using a LSTM Based Deep Learning Network","authors":"Maria Ramirez, M. Khalil, Johnny Can, K. George","doi":"10.1109/aiiot54504.2022.9817329","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817329","url":null,"abstract":"Neuromarketing is an innovative discipline that combines neuroscience with marketing and refers to analyzing physiological and brain signals to obtain insight into consumer behavior. The field's potential for reducing the uncertainty that has previously hindered marketing efforts to explain consumer behavior has accelerated growth within the area. Most recently, artificial intelligence (AI) has driven neuromarketing research forward by enabling researchers to conduct tests more effectively because AI assists in revealing patterns that were previously hard to detect. In this paper, deep learning is applied by employing a particular type of recurrent neural network called long short-term memory (LSTM) to recognize subject preferences from combined electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127485073","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":"Classification of Various Workout Motions Using Wearable Sensors","authors":"Chad O'Brien, Cheol-Hong Min","doi":"10.1109/aiiot54504.2022.9817337","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817337","url":null,"abstract":"A wearable sensor system is worn at two different locations on the body to automatically classify different workout activities being performed by the trainees in the gym. The sensor provides raw acceleration data in the x, y, and z-axis, then imported into MATLAB. The classifier predicts the workout actions based on the time and frequency features extracted from the sensor data. The classifier used was a Quadratic kernel function for Support Vector Machine (SVM) using Bayesian optimization with 30 iterations. A training dataset with labels was used to train the SVM. The model was trained and tested using separate test data, and an average accuracy of 99% was obtained. Different sensor locations were compared and concluded that the wrist was the most preferred location for workout classification.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126963991","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":"Mental Health Stigma and Natural Language Processing: Two Enigmas Through the Lens of a Limited Corpus","authors":"Min Hyung Lee, Richard Kyung","doi":"10.1109/aiiot54504.2022.9817362","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817362","url":null,"abstract":"Mental health stigma is an elephant in the room. It exacerbates one's illness, impedes approaches to treatment, and ultimately contributes to the persistence of a “mental health epidemic.” A definitive solution for managing stigmatized language is yet to be discovered, especially on the internet, where stigma is virtually ubiquitous in the forms of user posts, text messages, and biased articles. This study proposes text classification, a subset of natural language processing (NLP), as a solution to identify stigma in context. NLP is frequently used to detect human sentiments and emotions to eradicate hate speech, racism, and personal attacks; however, it has not been thoroughly explored in the field of mental health stigma, and the lack of preexisting data presents a challenge. Facing limited resources, the study hypothesized that the BERT model's fine-tuning method allowed for a small corpus to provide satisfactory results. The model returned surprisingly impressive results (0.94 accuracies, 0.91 F1-Score). The study not only confirms that NLP can be used as an effective solution to detect and later reduce stigma but also that the BERT model is still proficient with a limited corpus. Therefore, NLP tasks historically focused on thoroughly researched fields with an abundance of data, can also be used effectively in underdeveloped, unexplored fields of research that currently lack the datasets needed for training.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126525589","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":"Red Toad, Blue Toad, Hacked Toad?","authors":"L. Rizkallah, Nick Potter, Kyle Reed, Dylan Reynolds, Mohammed Salman, S. Bhunia","doi":"10.1109/aiiot54504.2022.9817361","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817361","url":null,"abstract":"Towards the end of 2012, it was announced by AntiSec, a small labeled sub-group of an anonymous hacktivists, that they leaked one million UDIDs of Apple users. AntiSec claimed the data were taken from a laptop that belonged to an agent who works for the authorities. However, it was later found that the trustworthy source of the leak was a small digital publishing company called BlueToad. In this paper, we investigate the motivation and methods of AntiSec by analyzing the data. There are many inconsistencies surrounding how the leak happened. As far as we know, there has never been a confirmed statement on how the data were accessed, but there are multiple theories. This paper examines the three main claims behind the data leak. We found that AntiSec was able to exploit the system through the vulnerability CVE-2012-0507. AntiSec could have used the UDIDs to track and collect Apple Users' private data; instead, they published the data to the public and blamed authorities for data collection. We analyzed the ramifications of AntiSec's decision. While it was never explicitly announced by BlueToad how they remedied the vulnerability, we provide the defense solutions they should have taken. We offer general tips for users to protect themselves from future attacks. We also detail some alternatives to using the UDID and which implementation Apple chose for their UDID replacement.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124220314","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":"Bit switching decoding of Cyclic Hamming codes for IoT applications","authors":"Praveen Sai Bere, Mohammed Zafar Ali Khan","doi":"10.1109/aiiot54504.2022.9817146","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817146","url":null,"abstract":"Being a requirement of low power transmission for IoT, it requires a decoder offering a good performance. URLLC (Ultra-Reliable Low Latency Communication) had the requirement of Ultra reliability, and Ultra-low latency hence demands a low complexity yet a good performing decoder. The use of hard decision decoding for Block codes over fading channels leads to performance loss. Soft decision decoding gives a good performance, but it is computationally costly. This paper proposes a diversity preserving hard decision decoding scheme for Hamming codes, offering a good performance. The complexity of the proposed decoding technique is of the order of $n$ (codeword length) and is very suitable for IoT and URLLC applications.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121593138","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 Timer Data to Conjunct Self-Reported Measures in Quantifying Deception","authors":"Kevin Matthe Caramancion","doi":"10.1109/aiiot54504.2022.9817182","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817182","url":null,"abstract":"This paper proposes the reduction of self-reported measures in deception quantifying assessment psychometric devices through the integration of digital trace data to limit bias and cognitive laziness. This paper then proceeded to test this proposal through a simulation involving a user study where a previous work's predictive model was recreated to incorporate such changes. The results highly suggest that the conjunction of digital trace data yields lower unaccounted variance (i.e., noise) and stronger forecasting prowess of the predictive models. The intended target audiences of this paper are information scientists, digital forensic professionals, communication experts, and policymakers possibly seeking references in this application area.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117157311","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 model evaluation for 360° video caching","authors":"M. Uddin, Jounsup Park","doi":"10.1109/aiiot54504.2022.9817292","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817292","url":null,"abstract":"360° virtual reality videos enhance the viewing experience by giving a more immersive and interactive environment compared to traditional videos. These videos require large bandwidth to transmit. Typically, viewers observe only a part of the entire 360°videos, called the field of view (FoV), when watching 360°videos. Edge caching can be a good solution to optimize bandwidth utilization as well as improve user quality of experience (QoE). In this research, three machine learning models utilizing random forest, linear regression, and Bayesian regression have been proposed to develop a 360°-video caching algorithm. Tile frequency, user's view prediction probability and tile resolution have been used as feature. The purpose of the developed machine learning models is to determine the caching strategy of 360-degree video tiles. The models are capable to predict the viewing frequency of 360° video tiles (subsets of a full video). We have compared the results of the three developed models and the results show that the random forest regression model outperforms the other proposed models with a predictive R2value of 0.79.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115351970","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":"Optical Features for Automated Determination of Agricultural Product Varieties","authors":"S. Chawathe","doi":"10.1109/aiiot54504.2022.9817320","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817320","url":null,"abstract":"This paper studies methods to determine varieties of agricultural specimens using features extracted from optical images generated by low-cost commodity hardware and simple, efficient algorithms. It presents a framework for this and some related tasks of agricultural informatics, with a focus on data-intensive aspects. It describes a system implementation that permits such data to be iteratively and interactively explored and studied while also permitting efficient programmatic access. The core classification problem of determining a raisin variety is studied experimentally and the quantitative results are competitive with prior work. Some of the methods generate simple, human-understandable classifiers, of which a few examples are presented. Data exploration and visualization is implemented using self-organizing maps (SOMs) and several examples of useful visualizations are described.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115454301","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}