UMT Artificial Intelligence Review最新文献

{"title":"Deep Feature Learning And Classification Of Remote Sensing Images","authors":"Zohaib Y Ahmad, Bushra Naz, Sara Ali, Zakir Shaikh, Bhavani Shankar","doi":"10.32350/umtair.21.004","DOIUrl":"https://doi.org/10.32350/umtair.21.004","url":null,"abstract":"Hyperspectral imaging has been largely utilized in applications involving remote sensing to describe the composition of thousands of spectral bands in a single scene. Hyperspectral images (HSI) require an accurate training model for extracting the characteristics of scenes presented in an image. Image learning models involving spectral resolution present major challenges because of the complex nature of image frames. Several attempts have been made to address this complexity. Nevertheless, these models have failed to retain a deeper understanding of hyperspectral images. Since there are mixed pixels, limited training samples, and duplicate data, so the deep learning method solves the problem.In this method, spectral values (for every pixel) of the hyperspectral images are sequentially fed into spectral long-short-term memory (LSTM) through several routes to study the spectral features. Most of the existing state-of-the-art models are based on spectral-spatial frameworks. The added spatial features add more dimensions to hyperspectral images. However, these classification models do not take advantage of the sequential nature of these images. Due to the presence of mixed pixels, limited training samples, and redundant data, the utilization of deep learning techniques addresses the problems. This paper describes a method for the classification of hyperspectral images through spectral-spatial LSTM networks. For extracting the first principal constituent from such an image, principle component analysis (PCA) was used in spectral and spatial joint feature networks (SSJFN), as well as spectral and spatial individual extraction of the features via LSTM, to get the uniform end-to-end network. Furthermore, it was aimed to achieve the integration of all processes in a neural network by making a classifier to overcome the training error and backpropagation, which may lead to learning more features. During categorization, SoftMax classification considers the spatial and spectral characteristics of all the pixels independently to get two different outcomes. Afterwards, joint spectral-spatial results are gained by using the strategy of decision fusion. The classification accuracy improves by 2.69%, 1.53%, and 1.08% when compared to the rest of the state-of-art methods.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127430981","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 Based Implementation of Home Automation Using Smart Mirror","authors":"Aqib Ali, Baqir Nadeem Hashmi, Aliya Batool, Samreen Naeem, Sania Anam, Muhammad Munawar Ahmed","doi":"10.32350/umtair.21.002","DOIUrl":"https://doi.org/10.32350/umtair.21.002","url":null,"abstract":"When ordered, it may be folded in half quickly and effortlessly. IoT (Internet of Things) technology drives the Smart Mirror's functionality. Standard mirror functionality is included, in addition to showing the user's social notifications, daily tasks, weather updates, breaking news, reminders, voice assistant notifications, and smartphone notifications. The Smart Mirror is connected to the Raspberry Pi-based network through Wi-Fi. A two-way mirror or an acrylic mirror sheet is used with the Raspberry-Pi mainboard to conceal the Mirror's rear end from the user. It supports modules written in any programming language. When Python is used as the primary programming language, these changes take care of the hardware and software limitations. This work discusses the creation and building of the Mirror in appropriate manner. In addition, possible uses of the Mirror are discussed. Compared to this DIY method, the cost is substantially lower, and the result is more predictable. The result produced by the support vector machine classifier are of accuracy which is 84% for detecting theft, and the confusion matrix is often diagonal, showing that this classifier can accurately labelled the data. Similarly, F1 score of 0.82% shows that there are a few false positives and false negatives, which is a favorable indicator.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125693538","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":"Analyzing the Application of SIR Model to Study the Outbreak of COVID-19: A Case Study in Pakistan","authors":"Ijaz Yusuf, Kishmala Ijaz, Hassan Qudrat Ullah","doi":"10.32350/umtair.22.01","DOIUrl":"https://doi.org/10.32350/umtair.22.01","url":null,"abstract":"The current study aims to examine the exponential rate of the spread of COVID-19 by employing a system dynamic model. The outbreak of COVID-19 was first evidenced on Feb 26, 2020 in Pakistan. The local bodies and law enforcing agencies took the initial preventive measures to restrict COVID-19 to a particular locality but all in vain. A large number of people were infected by this virus which increased the death rate countrywide. The numbers of infected people were alarming and a need was felt to develop the model to calculate the existing reproduction number and transmission rate and highlight its varied values in the coming days. People-friendly measures and government-based policies must be explored to fight against this deadly disease. This paper aims to develop an epidemic model using the system dynamic framework of simulation software STELLA. Additionally, the current study’s purpose is to experiment with the system dynamic model to replicate the progression of the communicable disease and probe multiple combinations of people-based and government-based measures to reduce the spread of the COVID-19 pandemic. These containment measures are of two types; people-based measures and government-based measures which directly affect the reproduction number and infection growth rate of the mitigating circumstances due to COVID-19. Combined efforts of the public and government can combat this global pandemic. The reduced number of reproduction number/recurring cases and infection growth rate are the key metrics to judge and evaluate the effectiveness of containment/ control measures. Therefore, this research points to a more holistic combination of public and government-oriented measures that play a vital role in reducing the increasing infection rate of COVID-19. Simulation results were traced to replicate the real-life settings against four combinations of containmentmeasures in tabular form and graphical form.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130983375","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":"SENTIMENT ANALYSIS OF ROMAN URDU REVIEWS","authors":"Muhammad Abdullah Aish","doi":"10.32350/umtair.21.01","DOIUrl":"https://doi.org/10.32350/umtair.21.01","url":null,"abstract":"Easy access and economic availability of Computers, Tabs, Smartphones and high—speed internet people are now using web for Social interaction and Business correspondence. People are becoming habitual to post their reviews about any specific entity/product, they used. These reviews are very helpful for both—user and seller. Initially these reviews not too much they can easily be analyzed by reading them. The continuous increase in the amount of these reviews creates a need that reviews can be analyzed and useful pattern be found and explored through automated channel. This need leads to a new filed in the domain of research known as “Sentiment Analysis”. Sentiment Analysis is the study of people’s opinions, sentiments, attitude and emotions expressed in written language or also said that, it is a process of categorizing people’s opinions expressed in the piece of text especially in order to determine whether the writer’s attitude towards a particular topic or product is positive, negative, or neutral. This research is targeting the mining of the sentiments from these reviews of PSL anthums. In this thesis, five different classification model are used for text classification of reviews by using Rapid Miner Tool. Thesis presents a Sentiment Analysis of Roman Urdu reviews on PSL Anthums available on YouTube. These reviews are scraped, pre—process and analysed using Naïve Bayes, Gradient Boost Tree, Support Vector Machine, K-Nearist Neighbours and Artificail Neural Netwrok. The Roman Urdu Sentiment Analysis is perform at 7000 bi-lingual reviews. The Naïve Bayes and and Logistic Regression correctly predicted 68.86% reviews. ANN achived 68.86% on testing dataset and 69.71% on the validation of the results.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124074561","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":"Consumer attitude towards Pakistani Clothing Brands on Facebook before and during Covid-19 pandemic","authors":"Ahmad Amjad, Farman Ali, Gulam Farroque, Fatima Nawaz, Fahad Assad","doi":"10.32350/umtair.21.02","DOIUrl":"https://doi.org/10.32350/umtair.21.02","url":null,"abstract":"Covid-19 has drastically affected businesses, industries and consumers across the world. However, the rise of Digital technology and advancements in e-commerce sector in the past decade allows a way out to cope up with the pandemic challenges and shift their perspective to new normal. This paper provides a consumer analysis of how clothing brands and consumers in Pakistan have reacted to the pandemic when it comes to social media marketing and purchasing of clothes on Facebook. Specifically, it focuses on the first wave of Covid-19 as it provides the core insights into business transformations from both business organization and consumers end, though the current scenario is much more standardized now.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131035421","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":"The Machine Learning Approach for Recommendation System Based on Online Review","authors":"A. Muhammad, Muhammad Nadeem, Muhammad Babar, Muhammad Ali, Muhammad Arslan, Rida","doi":"10.32350/umtair.21.04","DOIUrl":"https://doi.org/10.32350/umtair.21.04","url":null,"abstract":"For the past few years, various recommendation systems have been introduced that give recommendations and suggestions based on online user reviews. These recommenders provide valuable information from user-generated reviews through various processes. These systems use different techniques to extract the important information from the reviews that are valuable enough to give as suggestions to the users based on their interests. In this research, a portable recommender system has been developed based on the three Machine learning that recommend its user about different mobile phones available in the market and helps them select the best one based on the online user reviews.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124556685","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":"Nuclei spotting for computational pathology in microscopic images","authors":"Abdul Basit Syed, Samabia Tehsin, Sumaira Kausar","doi":"10.32350/umtair.21.05","DOIUrl":"https://doi.org/10.32350/umtair.21.05","url":null,"abstract":"Identification and classification of nuclei from microscopy is vital to new pharmaceutical developments. Biologist lacks a robust and efficient way to detect nuclei to natural variation in their appearances as well as differences in image capturing methods. Identification and classification of nuclei from microscopy images is considered as a complex task. A successful implementation will aid researchers immensely in their fight to find pharmaceutical solutions to medical crises while saving both valuable research time and funding. In this study, we employed a modified U-Net a deep learning based approach for nuclei detection where we computed 0.78 value of IOU (intersection over union) on BBBC038v1 dataset. \u0000 ","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121251656","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":"Student's Behavior in Virtual Learning Environment- A Case Study of Pakistan during Pandemic Situation of COVID-19","authors":"Hammad Ghulam Mustafa, Sheza Arif, Waqas Aslam","doi":"10.32350/umtair.21.03","DOIUrl":"https://doi.org/10.32350/umtair.21.03","url":null,"abstract":"Today one of the most challenging tasks is how to connect students with their education. During the Covid-19 era, the physical education system is not suitable for students. Most of the educational institutes start a new education system in Virtual Learning Environment. Suddenly changed the education system, the students towards learning environment is changed. The analysis of students through different machine learning and statistical techniques. The effectiveness of Virtual Learning is measured via the performance of the students. This research reviews different techniques for assessing the performance i.e activity-based, assessments of students, and enrollment-based. The analysis of students' behavior is a long-established task in the area of ML because in the past analyze the student's behavior in the statistical method. To compare, evaluate, and develop analyze the student's behavior in VLE,  we need a standard and high-quality benchmark corpus. But unfortunately, numerous studies are based on the web-based corpus and measure the performance in VLE. The main focus of this study is to analyze the student's behavior in VLE by using original data or collecting original reviews of students. Our total corpus consists of 2031 reviews. After some applying pre-processing technique final corpus consists of 1934 reviews. We applied seven machine learning algorithms to evaluate the student's behavior. To evaluate the performance of the students in VLE standard evaluation measures are used. After extensive experimentation, evaluation results show that stylometry word-based features produced the highest results of the first experiment NB Kernel (Accuray = 86.61, F1-measure = 89.91), and in the second experiment highest accuracy was achieved by DT (Accuray = 87.45, F1-measure = 92.13) on proposed corpus on reviews total 1934-Corpus.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116859836","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":"A Survey of the Algorithms Used for Traffic Light Scheduling Systems","authors":"A. Farooq, Tahir Iqbal, Ehtashamul Haq, A. Ghaffar","doi":"10.32350/air.0102.05","DOIUrl":"https://doi.org/10.32350/air.0102.05","url":null,"abstract":"Traffic congestion are among the most important issue that a country needs to confront due to increasing volume of vehicles around the world, particularly in the large urban areas. As a result, the requirement begins for modeling and improving traffic management procedures to improve the growing need. In order to address traffic problems in urban areas a smart traffic management method is the need of time. The solution in this paper is found through the dimensions of traffic mass on the roads. The core objective of this paper is to highlight latest techniques algorithm which has been used for scheduling traffic lights and a comparison based on achieved accuracy.","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116440913","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":"Big Data Analytics in Smart Power Systems: A Survey Paper","authors":"Farhan Ahmad","doi":"10.32350/air.0102.02","DOIUrl":"https://doi.org/10.32350/air.0102.02","url":null,"abstract":"In recent years, technology has brought us many advancements. One of them is integrating big data with smart grid/smart power. In this study, a scientific approach used to help the power system is studied. Additionally, with the help of previously published literature, different survey papers are reviewed to investigate the key challenges of integrating Big Data Analytics (BDA) with smart grid. Subsequently, BDA characteristics are also studied. Next, data analysis techniques and BDA applications in the domain of smart grids are studied. It is followed by a section discussing techniques such as Hadoop and Spark. Their framework is also briefly examined in order to know about their working. The last section provides a conclusion and future directions. \u0000KEYWORDS: advanced metering infrastructure (AMI), applications of big data, big data analytics (BDA), data architectures, data mining, data privacy, data security, data uncertainty, data volume,  hadoop, spark, Vz of the data,  smart grid, smart power system big \u0000 ","PeriodicalId":198719,"journal":{"name":"UMT Artificial Intelligence Review","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123881438","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}