Volume 12 | Issue 12

 Abstract

The goal of this paper is to identify flower varieties in conjunction with Kaggle Flowers dataset employing Convolutional Neural Networks (CNNs). The dataset contains images of five classes of flowers being, daisy, dandelion, rose, sunflower, and tulip. A classifier based on CNN was developed based on 4323 images and was able to attain a classification accuracy rate of 99.09%. The framework displays an efficient interface where users can upload images of flowers with hopes of obtaining an accurate classification. The model performance was improved by implementing data augmentation and multi-level design of CNN enabling the model to accommodate images variability. This application is useful in areas such as botany, gardening and retail sector because it helps people to use images in identifying and selecting their opportunities faster and more accurately. The project demonstrates the efficiency of CNN networks as applied in image classification and their future use into practice.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Flower,CNN

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Drowsy driving is one of the major causes of road accident and fatalities. This paper proposes a low-cost, a real-time, driver drowsiness detection system through webcam based behavioral analysis and technologically modified software. Facial features are defined to evaluate anthropometric measures such as eye aspect ratio (EAR) and Mouth Creating Ratio (MAR). Adaptive thresholding is used to identify prolonged eye closure or yawning where drowsiness is likely to set in. It deploys a learning of classification Support Vector Machines (SVM) that detects and recognizes images for later use offline achieving 95.58% sensitivity and 100% specificity. Such a system is non-obtrusive and cost effective thereby reducing the risk of drowsy driving. Future work should involve embedding into car systems and evaluation based on the actual driving experience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

MAR, Drowsy, SVM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Children are increasingly becoming vulnerable to cyber harassment and predatory behavior on social media. Hence, this project aims to enhance the online safety of children by building a system which uses machine learning algorithms to detect and combat online harassment. The developed system integrates various supervised learning algorithms namely, support vector machine, random forest, naive bayes, k nearest neighbors and decision tree. Upon analyzing user content, the algorithm seeks possible abuse potential regarding posts and messages. Numerous harassing and non-harassing texts are included in the dataset which is used to create algorithms for prediction of such actions in real time. The system will first send alerts to a designated authority within the cyber cell every time, austere patterns are observed. This way, no time is wasted in the intervention. The system further enables providing a quicker and reasonable approach to tackle the issues that come up with young people by ensuring their safety as much as possible.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

K-Nearest Neighbors, SVM, Decision Tree

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The goal of this paper is to boost the resolution of images using Convolutional Neural Networks (CNN) along with the auto-encoder layers. This method trains the CNN model with pairs of low-resolution and high-resolution images so that it can learn to improve the pixel values of low-quality images. The pixel values of low-intensity pixels are replaced with high-intensity pixels and a high-resolution image is generated. The intention of the system is to provide effective enhanced images that can be used in a variety of fields including medicine, satellite, and surveillance images. We propose our own dataset and code to emphasize the focus on the novelty while ensuring the efficacy. Having conducted a number of tests, the project brings forth enhancement in the quality of the reconstructed image which depicts the superiority of auto-encoders and CNNs as promising tools for further developments in super-resolution imaging technology.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN, Auto-encoder

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The focus of this work relates to the identification and tampering detection of forensic scanners through deep neural production techniques. Tools built on convolution neural networks (CNNs) and the CASIA dataset are employed to determine which type of scanner was used to create an image and locate portions that were edited. Among others, processes involve transforming the photographs into error level analysis (ELA) images in order to accentuate the inconsistencies and training a CNN in a procedure where the CNN architecture is optimized. The system achieves promising levels of performance and is thus appropriate for distinguishing between images that are or are not altered. As demonstrated by the series of experiments, the model was able to withstand different circumstances and enabled accuracy of over 82% during validation. This work has a considerable contribution to automated media forensics since it solves the problem of scanner identification and digital manipulation detection in an effective and scalable manner.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN, ELA, SCANNER

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents the design of a multiscale convolutional neural network (MCNN) for the task of human behavior recognition, with the aim of increasing accuracy and reducing complexity of the model. Previous models such as CNN2D and LSTM time series modeling relied on a mean global average but neglected other spatial and depth features resulting in inaccuracies. The MCNN model is based on the concept of space-time interaction and depth-separable convolution modules inserted into a CNN3D model in which both the spatial and temporal information are enhanced. The system was trained and evaluated on the UCI HAR dataset which has six activity labels that were recorded using smartphone's sensors. The evaluation showed that the new model offered a 94% accuracy rate while improving learning complexity. An extended hybrid model comprising of a combination of convolutional neural networks, Gated recurrent units, and bidirectional algorithms produced an accuracy of 96% while using less parameters thus showing tremendous effectiveness and capability for real world tasks.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

MCNN, GRU,CNN2D

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Protection of data in digital communication is important to avoid any tampering especially for information of sensitive nature like financial or personal details. The branch of mathematics known as cryptography is concerned with the processes of encryption and decryption which allows secure communication across open and untrustworthy channels. In this project, auto-associative neural networks based on Hebb's rule are proposed to advance cryptographic processes. The system issues keys for encryption, teaches neural networks to encode-decode data streams, and measures the effectiveness of the system in terms of accuracy and time factors. To prevent data from the growing range of threats, the frameworks formulates protection with neural network flexibility. The system also provides the user with a graphical display so that recording and playback is performed automatically. Such method indicates the prospect of use of neural networks for the improvement of ordinary codes and ciphers, and focuses a number of challenges emerging from the contemporary information security.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cryptography, encryption, decryption

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

All traditional economic control has been nullified due to the existence of counterfeit currency, everywhere across the globe. Counterfeit detection using Decision Tree, Random Forest, SVM, Naives Bayes, and other approaches have been used by researchers in the recent past to test fake banknotes. A survey of UCI repository showed that some features were missing and a certain amount of data was pre-processed before model training. A number of splits in the training and testing samples were created and the algorithms were assessed and trained on parameters such as accuracy, precision, recall and F1 score. The outcomes have shown the strength of specific models such as Random Forest that almost achieved satisfactory classification accuracy and can be used in real-life applications within banking kiosks and ATMs. The research further highlights with facts, the need for automated systems which can curb financial fraud and the methodologies required to put in place an effective counterfeit detection machine learning system.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Security concerns have arisen in today's society as a result of using facial recognition systems that use deep learning model due to some feature being artificially manipulated. This paper revisits the question of how image manipulation in the form of social media filters for a facial feature or a facial expression impacts the recognition performance of models such as ResNet, MobileNet and InceptionV3. It was found that the recognition accuracy drops from 75% on unaltered images to 50% on altered images, thereby validating the observed weakness across the three architectures. Furthermore, a more advanced version VGG16 demonstrated to be more effective with 85% accuracy on altered images. This paper investigated these problems and proposed GRADCAM for heatmap analysis demonstrating why certain images with known resistive properties cannot be used to repulse such attacks, while also discussing possible countermeasures for protecting biometric systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

VGG16, MobileNet, biometric

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Biomedical imaging forgeries pose a challenge to social networks and forensics. It is becoming harder to tell these images apart from the real ones. This project employs a set of machine learning approaches, that CNN uses to solve the problem. A network called LBPNET is built with local binary patterns (LBP) for texture feature extraction. The parameters extracted through the LBP are used to train the CNN which learns the difference between real and fake face images. Advanced image preprocessing and training are integrated into the model in order to ensure high performance in a situation whereby real-time decision making has to occur. This work averts the threat that image forgeries bring to different sectors.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN, LBP, images

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Driven by exhaustion is one of the leading causes of road accidents across the world which result in many reported deaths each year. This project attempts to mitigate the challenge using machine learning and deep learning techniques for easier and precise detection of fatigue. EEG signals and video images from the DROZY dataset are utilized to train ML and DL models, respectively. SVM, Random Forest, and KNN are some of the machine learning algorithms utilized for the analysis of EEG signals while the images are analyzed through CNN, ConvLSTM, and also a multi-model approach CNN+ConvLSTM. Further accuracy is enhanced by employing ensemble techniques such as Bagging Classifier. PV and PCA methods were applied to obtain superior model performance resulting in all 100% accuracy for all CNN-based approaches. Thus, this system provides strong approaches toward supporting real time driver fatigue assessment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

ConvLSTM, EEG, KNN

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The emergence of exotic diseases points out a pressing void for swift medical aid. In this project, the authors focus on the recommendation of drugs utilizing a combination of patient reviews, disease description and machine learning aided sentiment analysis. The methodology incorporates TF-IDF, Bag of Words, and Word2Vec for feature extraction along with Logistic Regression and Multilayer Perceptron (MLP) as algorithms. For training and testing of the models the authors utilized the DRUGREVIEW dataset publicly available in UCI, reviews and drugs with ratings are used to anticipate drug outcomes. It was determined that for predicting drug outcomes MLP shows greater efficiency than the rest, hence it was chosen as the core algorithm in the developed system. Additionally doctors' prescribed medications are supplemented with suggested sentiments so that the chances of self medicine withdrawal are decreased and patients make better choices with regard to the medications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

MLP, TF-IDF, Logistic Regression

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Diagnosing heart disease is a medical problem that is both critical and has a time factor which has to be taken into consideration in order to be treated. This project looks into the performance analysis of four machine learning models which are SVM, KNN, Logistic Regression and XGBoost, with and without parameter tuning via GridSearchCV. The analysis set up is based on Hungarians Cleveland data set which has attributes for predicting whether the patient is likely to have heart problems. XGBoost computes higher accuracy among the algorithms but had prolonged computation time. The study therefore extends with Random Forest in that regard which parallels the accuracy of XGboost but decreased computation time. This project underlines the importance of parameter tuning in the improvement of model performance and identifies Random Forest as a low cost method which will result in faster and more accurate predictions for heart diseases.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

XGBoost, KNN, SVM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper describes a professional system designed to detect cases of ransomware assaults based on data related to processor usage and disk usage. System processes and the activities dealing with files are some of the classical methods used, but at times power effectiveness is compromised and the methods are not very reliable. In order to compensate for these, VMware environment is used in this work in order to obtain HPC as well as I/O events without degrading performance. The machine learning algorithms that were employed in the evaluation of the model included SVM, Random Forest, and XGBoost, where Random Forest and XGBoost achieved 98% accuracy. In addition, other DNN and LSTM deep learning models were applied, and an extension with CNN2D was reported with most accuracy of 98.83%. This self-learning system of detection has changed the way ransomware detection is done without compromising the performance of the system in a big way and is an effective means of dealing with cyber threats.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN2D, DNN, LSTM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN, ANN, SVM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Today almost every person uses a credit card, but fraudulent activities are a great concern to both the customers and the financial institutions. This project compares the performance of several machine learning algorithms such as Decision Tree, KNN, Logistic Regression, SVM, Random Forest, and also XGBOOST, as well as a combined approach, which introduces the use of deep learning CNN. The main issue tackled is the problem on dataset which is fairly skewed, and hence, the normal transactions are a majority, while the fraudulent transactions are few. PCA for feature selection and SMOTE for data balancing techniques are applied for this purpose. A combination of the two, wherein CNN is combined with Decision Tree, increases all detection accuracy to 100%. This project offers valuable contributions as it highlights sample solutions to the problem of credit card fraud by using the Canadian Credit Card Dataset in a fast and accurate way.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN, XGBOOST, SVM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The accurate prediction of crop is crucial for effective agricultural planning and resource mobilization. This project constructs and enhances the system of predicting crop yield harnessing the features of the agriculture environment. The important environmental features to be focused on includes among other soil type, rainfall and temperature by implementing various feature selection methods including BORUTA and Recursive Feature Elimination (RFE). These features are fed to the ensemble of machine learning algorithms such as Random Forest, SVM and KNN to improve the prediction accuracy. The system also provides fertilizer application and yield prediction. Testing in databases yields promising results in the improvement of precision and decision making. The proposed model proves to be reliable and cost efficient and assists farmers with actionable information to enhance crop productivity and sustainable farming techniques.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

BORUTA, SVM, KNN

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In this work, we propose an ANN-based AI cyber security framework for detecting cyber attacks. By converting security incidents into single entities, the architecture takes advantage of advanced learning models including CNN and LSTM to improve the detection rate of the system. The AI-SIEM system decreases the occurrence of false alarms, thus enabling more efficient and faster response to changing cyber attacks. Experiments carried out on benchmark datasets, such as NSLKDD, CISIDS2017, results high values when compared to other machine learning techniques like SVM, k-NN and Decision Trees. The technique in question has been designed with an emphasis on practical scenarios, where issues such as data annotation and overfitting are expected. The results confirm that the elaborated framework is competent enough for intrusion detection, working with large volumes of information and responding to a changing threat landscape, thus providing strong defense in various spheres of cybersecurity.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

LSTM, k-NN, SVM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project applies deep transfer learning to understand facial features and ascertain certain diseases including beta-thalassemia, hyperthyroidism, Down syndrome and leprosy. System incorporates VGG16, ALEXNET and Kernel SVM as advanced models and the Disease Specific Face dataset for training and testing performance evaluations. DLIB along with GABOR is used for the preprocessing to extract features and for facial alignment respectively. Of all the models, VGG16 and LSTM had performed best with accuracy of about 99%. The system also uses other performance metrics including accuracy, precision, recall and F-score to confirm the importance of working systems within the provided scope. It can be concluded based on the results of the project that the combination of transfer learning and feature extraction improves the medical diagnosis process and provides an effective overall scheme of facial recognition-based disease detection system.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

DLIB, GABOR, VGG16

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

NLP, SVM, SQP

  License

Creative Commons Attribution 4.0 and The Open Definition