2022

Permanent URI for this collection

https://escholar.umt.edu.pk/handle/123456789/15511

Browse

Now showing 1 - 20 of 33

A blockchain-based framework to make sugarcane crop in agricultural supply chain transparent and reliable
(UMT Lahore, 2022) Muhammad Asad Khan
Sugarcane crop is used for making several ecofriendly and food products making it one of most importantbcrop in world. Sugarcane crop contributes in 60% sugar production of world. The malpractice in supply chain effects farmers’ motivation with low profits even after putting a lot of efforts in cultivation and governments bear economic losses by paying extra money to import sugar from other countries. Sugarcane supply chain processes are not transparent due to which it is difficult for authorities to keep track of malpractices and illegal exports. This paper proposed a blockchain-based framework for sugarcane supply chain traceability and reliability. A new token Sugar Coin (SC) has been introduced to keep track of transactions between supply chain entities. Furthermore, our proposed framework also covers crypto wallets, economic model and Initial Coin Offering (ICO) of SugarCoin. Additionally, a complete transaction processing system have been proposed using smart contracts for traceability of sugarcane trading and conversion of SC to fiat and vice versa. The Inter Planetary File System (IPFS) have been introduced for storing encrypted private data of farmers, companies and retailers to enhance availability, security and transparency. Finally, experiment results depict that proposed framework approximately performs better than already existing supply chain projects in terms of new blocks latency, transaction per minute, transactions average gas fee and times for transaction verifications.
A detailed and comprehensive performance analysis on the largest covid-19 chest x-ray image dataset using a custom cnn model and state-of-the-art deep learning models
(UMT Lahore, 2022) ALI TARIQ NAGI
The modern Scientific World has ever been endeavoring towards battling and devising solutions for the newly arising pandemics. One such pandemic which has disarrayed the world’s accustomed routine upside down is COVID-19 and has devastated the world’s economy consuming around 45 million lives around the globe. The governments and scientists have taken front lines striving towards the diagnosis and engineering of the vaccination for the said virus. The COVID-19 can be diagnosed using Artificial Intelligence with an accuracy higher than the traditional methods using chest X-Rays. The subject research work involves an evaluation of the performance of Deep Learning models for COVID-19 diagnosis using chest X-Ray images on a dataset containing the largest number of COVID-19 images ever used in the literature research work according to the best of the authors’ knowledge. Further, a CNN model was developed, named Custom-Model in this study for an evaluation and comparison with the state-of-the-art deep learning models. The intention was not to develop a new highperforming deep learning model rather evaluate the performance of deep learning models on a larger COVID-19 chest X-Ray images’ dataset. Moreover, Xception and MobilNetV2 based models have also been used for evaluation purposes. The criteria for evaluation have been based on Accuracy, Precision, Recall, F1-Score, ROC curves, AUC, Confusion matrix, and Macro and Weighted averages. Among the deployed models, Xception turns out to be a top performer in terms of precision and accuracy while MobileNetV2 based model could detect slightly more COVID-19 cases than Xception and slightly fewer False Negatives while giving far more False Positives than the remaining models. Also, the custom CNN model exceeds MobileNetV2 model in terms of precision. The best Accuracy, Precision, Recall, and F1-Score out of these three models turn out to be 94.2%, 99%, 95%, and 97% as shown by the Xception model. Finally, It was found that the overall accuracy in the current evaluation was curtailed by approximately 2.2% as compared to the average accuracy of previous works on multi-class vii classification while a very high precision value has been observed which is of high scientific value.
A framework to make wheat crop supply chain transparent and reliable using blockchain technology
(UMT Lahore, 2022) Zain Khalid Ansari
The wheat crop is the world’s second-largest cultivated crop. This crop fulfills almost 35% of human food demand and is used in making many by-products such as bread, flour, flakes, and other baked products. The World Health Organization (WHO) has been reported many issues related to food safety. The farmers have been putting a lot of effort into the production of wheat crop and their motivation is harmed by getting low revenues during crop harvesting season and the government suffers economic losses by spending additional money to import wheat from other countries in the off-season. These issues happened due to lack of transparency, security, reliability and traceability in the agriculture supply chain. Many systems have been developed for the agriculture supply chain safety, traceability, transparency and reliability however, all these systems have not been successful due to monopolistic centralized control. It has eventually gained consumer’s trust in branded products and rejects other products due to lack of traceable supply chain information. In this article, we have proposed a blockchain-based framework for supply chain traceability system that provides trustable, transparent, secure, and reliable services for the wheat crop. A crypto token called Wheat Coin (WC) has been introduced to keep track of transactions among the stakeholders of wheat supply chain. Moreover, we have introduced an Initial coin offering (ICO) of WC, crypto wallets and an economic model. Furthermore, a smart contract-based transaction system has been proposed for the transparency of wheat crop transactions and conversion of WC to fiat and vice versa. We have developed the Interplanetary File System (IPFS) to improve data availability, security, and transparency which stores encrypted private data of farmers, businesses, and merchants. Lastly, the results of the experiments show that the proposed framework improves as compared to previous crop supply chain solutions in terms of latency to add-blocks, per minute transactions, average gas charge for transaction, and transaction verification time
A moel for the prediction of ozone layer weakness using fuzzy logic
(UMT Lahore, 2022) SIDRA IKRAM
Since the evolution of mankind, man has always been curious about why and how things happen. Why is something the way it is, the question still arises. More, humans have been trying to invent and discover new things one better than the other in every domain. With time this human behavior had been increasing as more and more is being invented and discovered day by day but the quest is continued. The proposed method is developed in a way that it uses the ozone layer weakness prediction data from a specific population related to the factors that are economy, pollution, and social setup as input and then it analyzes the data and gives an output in the form of OLWPSF (Ozone layer weakness Prediction System Using Fuzzy Logic). This system is developed to find out the expected burden on the ozone layer due to the above-mentioned factors by finding out their effect on the weakness of the layer of a certain region or country. The output results thus will be available for the use of government officials, policymakers, and authorized personnel in that region so that they would be able to make decisions based on those results.
A systematic process to develop machine readable pakistan sign language corpus
(UMT Lahore, 2022) FATIMA MUBARAKA
A person's thoughts and emotions can be expressed in sign language (SL) in the most natural and intuitive way in the deaf community. PSL is a form of sign language which provides information through the use of hands and other body parts. It is estimated that there are ten million deaf people in Pakistan, but only 5% of them go to school. People who are hearing impaired lack a basic understanding of language and literacy due to the lack of educational resources in Pakistan. An automated system that can overcome this problem is needed to improve communication skills among the deaf community. A PSL dictionary creation system based on Hamnonsys is presented in this thesis. PSL dictionary contains the sign gloss of a given word and Hamnonsys. A virtual keyboard is used for entering Hamnonsys for given signs. A method is also being developed to add nonmanual components to the proposed system, for instance, there is a gaze, mouth gestures, facial expressions, and body posture to consider. When the user retrieves the sign and Hamnonsys from the dictionary, they can be converted to SiGML for input to a signed avatar that will animate the sign. It is possible to retrieve the sign and Hamnonsys from the dictionary. The proposed system could be used to animate signs and for creating Pakistan sign language dictionaries.
An investigation on the role of iot in the advancement of healthcare services
(UMT Lahore, 2022) GOHAR SARWAR HAMEED
Smart objects are the final foundations in the evolution of technologically intelligent frameworks thanks to the Internet of Things. The Internet of Things has a wide range of application areas, such as health care. The Internet of Things revolution is profoundly changing advanced health care, with encouraging technological, financial, and communal outcomes. This paper examines the latest network frameworks, software solutions, and market trends in Internet of Things healthcare solutions, as well as improvements in electronic health. Furthermore, from a healthcare perspective, this paper examines various IoT data security and privacy protection features, such as safety protocols, threat prevention models, and attack categorizations. Furthermore, this paper offers a smart cooperative security framework to reduce potential threats; addresses how various innovations, including data warehousing, embedded systems, and wearable electronics, can be utilized in a health care context; discusses emerging Internet of Things and electronic health rules and regulations around the globe to find how they can enhance economic growth in terms of durable development; and indicates several future research directions for Internet of Thingsbased health care, consisting of a set of problems and concerns. A host of health challenges confront the world today, all of which necessitate personal action. The most significant health challenges now are chronic conditions found in youngsters and the elderly. Children in orphanages and older residents in healthcare facilities suffer from various ailments, and basic health checks are not undertaken regularly or until immediate medical treatment is required. Their medical screening could be done more often on a daily or monthly basis if they used an IoT gadget with sensing devices. The records from the device will be sent to the doctor, who will analyze them. If a severe problem is discovered, the patient will receive the best possible care. It will also produce a medical report. This research examines the role of the Internet of vii Things in attaining this vision of the healthcare platform vision. Healthcare is one of the most valuable and important domains in which automated systems are being established and enhanced.
An optimized approach for detecting ddos attacks in iot using application networks
(UMT Lahore, 2022) Muhammad Ayaz Zafar
The Internet of Things (IoT) brings new applications (such as smart homes, smart cities, smart health, and smart grid) that help traditional infrastructure to communicate with smart devices. Things are linked to the Internet, and a slew of new IoT gadgets are being developed at breakneck speed. Because these smart things are connected and capable of communicating with one another in unprotected contexts, the entire communication ecology need security solutions at various levels. With billions of such gadgets already on the market with severe vulnerabilities, there is a dangerous risk to Internet networks and even individual cyberphysical systems that are also connected to the Internet. Unlike traditional networks, IoT technology has distinct features such as varying resource limits and varied network protocol needs. The attacker uses a variety of security flaws in an IoT infrastructure to launch a Distributed Denial of Service (DDoS) attack. The rise in DDoS assaults has made it critical to handle the implications in the IoT business. This study presents an effective, SoftwareDefined Internet of Things (SD-IoT)-based architecture for providing IoT network security services. We developed a novel framework for DDoS attack Recognition in SD-IoT networks leverag- ing SD-IoT. The proposed framework is based onCountdown of Recognition of DDoS Attack (C-RDA), The framework is a dynamic and programmable solution and is deeply tested with different network parameters. The algorithms demonstrate good performance with better results through Software-Defined Networking (SDN).The C-RDA approach have 97% accuracy. Moreover, the proposed framework recognizes the attack efficiently in a minimum amount of time and with lesser CPU and memory resources consumption
Analysis of covid 19 clinical data through machine learning techniques
(UMT Lahore, 2022) Analysis of covid 19 clinical data through machine learning techniques
Analysis of COVID-19 related data has been a hot topic of research. Many researchers have been working hard to play their part to take the research forward. In this research we have used different machine learning techniques to perform analysis on the Covid clinical data repository taken from carbon health team. The objective of this research was to train a model which can diagnose and predict result with best accuracy. This research helps to study what Covid is at early stage. The dataset used in this study corresponds to front lines ground realities. This Research helps in-patients and out-patients to know their vitals through symptoms along with Covid Test results. The data we used here required pre-processing. In the first phase we pre-processed the data and brought it in such a shape which could be used to perform different analytical operations. We selected the most important features by evaluating their scores. In the second phase we used multiple classification methods including decision tree classifier, random forest classifier, SVM, etc. for data classification. We experimented with different validation techniques like train test split, K fold cross validation, etc. Performance of the classifiers have been reported using confusion matrices. We also report other evaluation measures including accuracy, precision, and recall, etc. Finally, we are able to successfully train a classification model that has high accuracy, ROC AUC curve and Matthew correlation coefficient values. Hence the proposed method can find its application in the real-world scenarios of COVID-19 to diagnose the disease with better accuracy.
Applications of augmented reality for treatment and rehabilitation of neurological disorders
(UMT Lahore, 2022) Zirva Zahid
Neurology is one of the most challenging fields in medical science due to the complexity of the nervous system in the human body. The infusion of technology in medical science has immensely improved patients’ and healthcare workers’ experiences, especially in neurology. Augmented Reality (AR) is more hardware independent as compared to other technologies that use 3D modeling and can be executed on relatively cheaper and easily accessible hardware. As per our knowledge, there is no specific review that emphasizes the usage of augmented reality for the treatment and therapy of patients suffering from neurological disorders. This research presents the usage of AR for the rehabilitation and treatment of Neurological Disorders. A total of 135 papers have been analyzed out of which 50 papers were selected based on inclusion criteria focusing on AR and neurology. We have proposed a taxonomy of usage of AR applications in the field of neurology with different branches including diagnosis, prognosis, rehab, and medical training during patients’ life cycle. We have identified specific challenges where patients suffering from neurological disorders experience difficulty using AR applications. Based on the challenges identified we have proposed a framework for application designers and developers to overcome the identified challenges and develop an application that performs better to treat and assist patients. We have also designed an AR architecture especially for designing the AR systems for Neuropatients with degenerative or movement neuro-disorders. Lastly, we detailed some directions for future work in terms of AR usage in neuroscience.
Automated method for detection and recognition of seven-segment digits from electric meters using machine learning
(UMT Lahore, 2022) HAMZA HASEEB
Technology is growing rapidly and everything should be automated to save time, cost, and effort. This research aims to accurately detect and recognize seven-segment digits from captured images of digital electric meters in Pakistan. Detecting and recognizing seven-segment digits from collected data samples may be helpful to improve the infrastructures of our metering systems. In this research, Dataset is collected from the power development authority officials, containing 23,000 sample images of electric meters. These samples are taken under multiple daylight conditions. Some samples are blurred, having shadows, poor contrast, and tilted which makes it more challenging to accurately recognize digits. First, we used Edge detection to find our region of interest (ROI), an LCD of a meter. After extracting ROI, Computer vision (CV) techniques such as gray scaling, Gaussian blur, adaptive thresholding, and some morphological operations are applied. After all of this preprocessing, digits are then segmented based on the features and pixel values. Finally, these segmented images (DIGITS) are then given to our pre-trained Convolutional Neural Network (CNN) model. This CNN model is trained on 24,475-digit samples which are capable of giving 92% accuracy. Data augmentation is also applied while training the model. Multiple machine learning algorithms are used like k-nearest neighbors (KNN), decision tree (DT), random forest (RF), and Support Vector Machine (SVM) in this research. Results show that using a Support Vector Machine (SVM) gives better results than using other models.
Automated psoriasis detection using deep learning
(UMT Lahore, 2022) Nagina Amin
Psoriasis is a chronic, non contagious skin condition that cannot be cured but its early detection can help prevent serious life threatening complications. The high visual similarity between normal skin and psoriasis has made the detection of psoriasis a very complex task. Moreover, it can be confused with different skin abnormalities like eczema, tinea corporis, lichen planus, pityriasis, dandruff, seborrheic dermatitis. Image processing using deep learning has proven better than other approaches in this context because of its automatic feature extractions with intelligent decisions and less chances of distorted features. In this paper, automated detection of psoriasis using deep learning has been proposed. To obtain good results for a small dataset transfer learning mechanism is used in which pre- trained deep learning models are applied on a dataset to obtain the required results. Firstly, different transfer learning models are applied on our data to work on the best obtained accuracy. Among them, ResNeXt gave the best output for an appropriate accuracy to detect psoriasis from healthy skin as well as other skin diseases. Secondly, we have worked on facilitating the development of an automated system which classifies psoriasis, lichen planus, eczema, seborrheic dermatitis, pityriasis, normal skin and tinea corporis diseases by applying and improving the final layers of pre-trained model. We have obtained an accuracy of 94% on test images with 2 classifiers and an output to show if the input image is classified as psoriasis or not. Finally, we have also applied the classifier on 3 classes; normal skin, psoriasis and other skin diseases, and obtained good results.
Blockchain-based iot devices in supply chain management
(UMT Lahore, 2022) Waheed Javed
Recent progress in shape of modern supply chain have evolved to complex networks. It remembers information for deals, arrangements, and distribution controls. But the previous supply chain management system faces a variety of challenges, including: lack of visibility of the upstream party (Provider) to the downstream party (Client), lack of flexibility in the face of sudden variations in demand and control of operating costs, lack of reliance on safety stakeholders, ineffective management of supply chain risks, etc. Blockchain (BC) uses in the supply chain to overcome the challenges because the growing demands of items have been increased. Internet of things (IoT) is a profoundly encouraging innovation that can help companies to observe, track, and monitor products, activities, and processes within their respective value chain networks. Research establishments and logical gatherings are ceaselessly attempting to convey answers for IoT gadgets in supply chain management. This paper speaks to an orderly writing audit by directing a review of Blockchain-based IoT advances and their present usage themes in gracefully chain the board framework. We discuss the smart devices used in this system and which device is the most appropriate in SCM. It also examines the future examination themes in blockchain-based IoT alluded to as the executive's framework production network. The essential deliberate writing audit has been consolidated by surveying research articles circulated in highly reputable—scenes someplace in the scope of 2016 and 2021. Lastly, open issues and challenges have been presented to provide the researchers with promising future directions in the domain of the IoT supply chain management system.
Classifiction of antibiotic resistance genes using position relative statistical moments through machine learning techniques
(UMT Lahore, 2022) USAMA SIDDIQUE
Antibiotics bacterial resistant genes can be produced through microorganisms and feature the ability to inhibit the boom of different microorganisms that extra often cause illness. Such resistant genes are very challenging in today era because it creates a barrier to modern antibiotics; therefore it reduces the ability of treatment from bacterial infections. They may cause dangerous effects by transferring between human, bacteria and surrounding environment. Classification of resistant gene is very important and crucial task. Previously several methods are proposed to predict antibiotic resistant bacterial gene However, they were an expensive and time-consuming process. As a result, proposed a classifier that predicts ARG’s by calculating different features and position relative statistical moments. Our classifier computes statistical instants and position based on structures of the resistant genes by using Chou’s 5-step rules, XGBoost is there used as a classifier for the accurateness of this model to identify the best results. The process was authenticated by using the Self-consistency, independence, K-Fold test and Jackknife test giving 99.15%, 99.75%, 99.15%, and 99.5% precise outcomes respectively. These outcomes describe that the recommended classifier can play a vital part in the estimate of antibiotic resistance genes
Computational predictors for lysine post-translational modification sitesto prevent sars-cov-2 and iav infection.
(UMT Lahore, 2022) AGHA WAFA ABBAS
Lysine post-translational modifications (PTMs) are indispensable in manipulating protein activities as well as biological mechanisms. Notwithstanding, due to the brobdingnagian amounts of sequencing data elicited by genome-sequencing endeavors, rigorous unearthing of distinct kinds of lysine PTM substrates and PTM sites across the whole proteome poses a substantial obstacle. We utterly flabbergast to probe that a plethora of computational approaches in determining lysine PTMs have been contrived throughout current times. Ergo, here is an imperative necessity to scrutinize such approaches and amalgamate their methodologies in order to ameliorate and subsequently burgeon computational strategies for accurately recognizing lysine PTMs utilizing gargantuan volumes of sequence data. In this research, I utilize a maximum of 240 research articles.
Cte-ml
(UMT Lahore, 2022) Anam Sana
Transposable Elements (TEs) are the repeated DNA sequences that are mostly found in eukaryotic genomes. TEs can change their location within the genome and produce multiple copies of themselves throughout the genome. These sequences can produce both positive and negative effects on organisms. Many diseases are produced by TEs translocation as it cause to increase the rate of mutation, insertions, and deletions in the genome and may cause manyn cancer-related diseases. Meanwhile, the productive outcome of TEs translocation is the genetic variability and progression of genomes. For understanding their roles in genomic evolution and stability, accurate classification of TEs is needed. TEs can be classified into orders, classes, subclasses and superfamilies. Many conventional bioinformatics tools has been used for the classification of TEs but no one has achieved reliable results. In our study, we present a method for the classification of transposable elements to their orders and superfamilies level. For this, we have collected and used benchmark dataset in this study. For feature vectors, we have calculated statistical moments along with position and composition relative features. Later on, we have trained four machine learning models to classify TEs. We have conducted nine experiments to classify TEs into a deeper level of orders and superfamilies by using validation techniques, i.e. self-consistency testing, independent set testing and cross-validation testing technique. These validation techniques are applied to models to check the effectiveness and to measure performance metrics, i.e. specificity, sensitivity, accuracy and Mathew’s correlation coefficient (MCC). For self-consistency testing, CTE-DT has achieve higher results for experiments 1, 2 and 3. For experiment 1, 99.53% Acc, 99.96% Sn, 99.53% Sp and 0.99 MCC is observed. For experiment 2, 100% Acc, 100% Sn, 100% Sp and 1.0 MCC is observed. For experiment 3, 100% Acc, 100% Sn, 99.99% Sp and 0.99 MCC is observed. For independent set testing, CTE-RF has achieved higher results for experiments 4, 5 and 6. For experiment 4, 92.74% Acc, 92.08% Sn, 93.39% Sp and 0.85 MCC is observed. For experiment 5, 95.27% Acc, 98.45% Sn, 99.49% Sp and 0.93 MCC is observed. For experiment 6, 96.09% Acc, 93.01% Sn, 89.86% Sp and 0.95 MCC is observed. For cross-validation testing, CTE-RF has achieved higher results for experiments 7, 8 and 9. For experiment 7, 90.68% Acc, 89.07% Sn, 92.28% Sp and 0.81 MCC is observed. For experiment 8, 95.08% Acc, 97.25% Sn, 99.49% Sp and 0.93 MCC is observed. For experiment 9, 95.08% Acc, 97.25% Sn, 99.49% Sp and 0.93 MCC is observed. Based on validation and comparison of models, the proposed model can help in the classification of transposable elements in an efficient and accurate way
Deep convolution neural network (pooling functions for object detection and segmentation)
(UMT Lahore, 2022) MUHAMMAD DANISH
Deep Convolutional Neural Networks (DCNN) delivers state-of-the-art performance in Object Detection, Classification, and Segmentation and are utilized for a range of Computer Vision applications. Pooling is an important component of many DCNN architectures. Pooling layers decrease the input's spatial size to lower the architecture's resource consumption. Commonly used pooling functions in DCNN are static and do not adapt to the feature maps that are being pooled. Investigating the impact of adaptive pooling functions in a DCNN for detection and segmentation is the goal of this work. This paper explains the theoretical foundations of DCNN, typical modifications, and prominent architectural designs. The flexible pooling algorithms Gated and Tree Pooling are then implemented as Keras layers. Gated Pooling achieves this by learning a combination of Max and Average Pooling and Tree Pooling learns pooling functions and how to combine them. Additionally, it is explained how to develop the MaskX R-CNN architecture by extending an existing Mask R-CNN implementation. This entails constructing a weight transfer function from the bounding box head to the mask head and combining mask predictions that are both class-specific and class agnostic. Following this approach, several MaskX R-CNN configurations are trained on all 80 categories of the Microsoft COCO dataset using these pooling methods. This thesis demonstrates that, when trained and tested on CIFAR-10 and CIFAR-100, utilizing these flexible pooling functions in tiny CNN results in better performance than Max Pooling. Analysis of the Mask and MaskX R-CNN models reveals that the performance of the basic Mask R-CNN implementation produces somewhat superior results. The performance of a MaskX R-CNN architecture trained and evaluated utilizing Tree Pooling within the ResNet backbone is marginally worse than the MaskX R-CNN baseline. The MaskX R-network CNN's heads that used Gated Pooling had the worst performance of all the trained models. However, the performance of the MaskX R-CNN implementations may be explained by the fact that they have around 4.5 times as many parameters as the Mask R-CNN baseline while adhering to the same training regimen. Because the MaskX R-CNN architecture is more complex, it is expected that: (1) using a prolonged iv training schedule will improve the performance of the baseline and the implementation using Tree Pooling; and (2) Tree Pooling with further training will eventually achieve a better performance than the baselines, as seen on the performance increase on CIFAR-10 and CIFAR-100.
Detection of cancerlectin proteins using deep learning
(UMT Lahore, 2022) FATIMA KAMRAN
Bio informatics has made significant advancements in recent years, particularly in the study of cancer lectins. Neural Networks may be able to fill the inherent gaps and limitations in machine learning techniques. In proteomics and genomics, deep learning (DL) and neural networks have gained appeal due to their capacity to unearth complex correlations that are concealed in vast amounts of biological data. This study began by examining state-of-the-art statistical techniques for finding cancer lectins. According to studies, machine learning techniques and a range of feature extraction techniques are used in the majority of the work done to predict the cancer lectin sites. There are various issues and restrictions with these machine learning-based forecasts that required to be resolved. A possible method to improve the reliability of cancer lectin predictions is deep learning. Chou’s five-step rule is used in this paper to include a deep learning-based method for better prediction of cancer lectins. the deep learning methodology uses the gated recurrent unit, long short-term memory unit, and convolutional neural network. the results show a dataset improvement with the highest accuracy at 86% using the CNN model.
Detection of thermophilic proteins using deep learning
(UMT Lahore, 2022) MUHAMMAD SHAHRAIZ DURRAN
Bio informatics has made significant advancements in recent years, particularly in the study of thermophiles. Neural Networks may be able to fill the inherent gaps and limitations in machine learning techniques. In proteomics and genomics, deep learning (DL) and neural networks have gained appeal due to their capacity to unearth complex correlations that are concealed in vast amounts of biological data. This study began by examining state-of-the-art statistical techniques for finding thermophiles. According to studies, machine learning techniques and a range of feature extraction techniques are used in the majority of the work done to predict the thermophiles sites. There are various issues and restrictions with these machine learning-based forecasts that required to be resolved. A possible method to improve the reliability of thermophilic protein predictions is deep learning. Chou’s five-step rule is used in this paper to include a deep learning-based method for better prediction of thermophilic proteins. the deep learning methodology uses the gated recurrent unit, long short-term memory unit, and convolutional neural network. the results show a dataset improvement with the highest accuracy at 86% using the FCN model
Empirical analysis of voice over internet protocol (voip) for 4g in pakistan
(UMT Lahore, 2022) ALI SHAN AKRAM
Voice over Internet Protocol techniques is used to make local, long-distance, and international voice phone calls via the Internet. We can make phone calls over the Internet with VoIP, which includes signaling, managing, and transport techniques. All telecom companies use a 4G network, and an enhanced variant of 4G that can achieve a bit rate marketed as 4G. Telephony companies came to notice the pros of sending data through IP in the twenty-first century, with increased speed, lower costs, and higher quality of calls. In this study, we provide a complete performance evaluation of VoIP traffic via experimental trials in a real 4G environment. Two stages make up the campaign. First, we define VoIP based on a dataset of over 123,152 packets of data-voice calls between fixed and mobile terminals. We empirically analyze the performance of different VoIP codecs. The network and terminals offer a variety of compensating mechanisms for dealing with jitter and packet loss. This study explores experiments that include two scenarios on 4G Networks. Node (x, y) experiment is several voice flow available that take into account a range of audio codecs and experiment is based on statistical analysis and involved the two most important parameters (jitter, RTT) respectively. We looked upon VoIP flows across several codecs in terms of quality and bandwidth usage in the second phase. The use of the maximum likelihood requirement to estimate parameters indicates both behaviors for jitter and RTT. Our study outclasses all the existing state-of-theart codecs and researchers in the telecom Industry. Aim to achieve the best codecs for VoIP communication and provide a suitable method to improve the quality of services in VoIP.
Forecasting covid-19 vaccination trends using time series analysis based on hybrid harvest model
(UMT Lahore, 2022) AMNA KHALIL
There are numerous valuable worldwide works to develop and distribute vaccination. Vaccination is a huge region of the world’s populace, which is critical to controlling pestilence, presently faces another arrangement of boundaries, worldwide rivalry due to congestion, and antibodies. COVID-19 vaccination data using time series analysis techniques. A time series analysis conducted a COVID-19 vaccination dataset to forecast future trends. Four models were used, including ARIMA, Prophet, LSTM, and the proposed Hybrid Harvest model. Proposed Hybrid Harvest model, a combination of ARIMA and Prophet, was found to be the most accurate in terms of prediction accuracy with a RMSE of 0.0305 and an MSE of 0.1323. The LSTM model was not suitable for this type of data with a high RMSE and MSE. This study highlights the potential of combining models in time series analysis and the importance of considering multiple models in forecasting future trends. This Work provide new insights into the temporal patterns of COVID-19 vaccination data and can contribute to the development of more effective vaccination strategies. The results are limited to the specific dataset used and further research is needed in this area.

Browse

Browsing 2022 by Title

Results Per Page

Sort Options