CNN feature and classifier fusion on novel transformed image dataset for dysgraphia diagnosis in children by Jayakanth, Kunhoth

“…Transfer learning is applied using a pre-trained DenseNet201 network to develop four distinct CNN models separately trained on word, pseudoword, difficult word, and sentence images. …”
Get full text
Get full text
Get full text

A novel hybrid methodology for fault diagnosis of wind energy conversion systems by Khaled Dhibi (16891524)

“…Therefore, a hybrid feature selection based diagnosis technique, that can preserve the advantages of wrapper and filter algorithms as well as RF model, is proposed. In the first phase, the neighborhood component analysis (NCA) filter algorithm is used to reduce and select only the pertinent features from the original raw data. …”

Corona power loss computation in bundled bipolar conductors by Al-Hamouz, Z.M.

“…The effectiveness of the present method is demonstrated using HVDC full scale and laboratory model transmission lines. …”
Get full text
Get full text

Investigation of Forming a Framework to shortlist contractors in the tendering phase by DABASH, MOHANNAD SALAH

“…After obtaining the weights of the decision factors, a model using Machine Learning algorithm on Google Colab was written using the Python language. …”
Get full text

Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring by Muhammad E.H. Chowdhury (17151154)

“…Twenty-seven t-domain, f-domain, and Mel frequency cepstral coefficients (MFCC) features were used to train a public database to identify the best-performing algorithm for classifying abnormal and normal heart sound (HS). …”

CNN feature and classifier fusion on novel transformed image dataset for dysgraphia diagnosis in children by Jayakanth Kunhoth (14158908)

“…Transfer learning is applied using a pre-trained DenseNet201 network to develop four distinct CNN models separately trained on word, pseudoword, difficult word, and sentence images. …”

DASSI: differential architecture search for splice identification from DNA sequences by Shabir Moosa (14153316)

“…</p> <h2>Results</h2> <p>Our experimental evaluation demonstrated that the discovered architecture outperformed baseline models and fixed architectures and showed competitive results against state-of-the-art models used in classification of splice sites. …”

A survey and comparison of wormhole routing techniques in a meshnetworks by Al-Tawil, K.M.

“…These multiprocessing systems consist of processing elements or nodes which are connected together by interconnection networks in various topologies. …”
Get full text
Get full text

Data mining approach to predict student's selection of program majors by SIDDARTHA, SHARMILA

“…The approach includes a methodology to manage data mining projects, sampling techniques to handle imbalanced data and multiclass data, a set of classification algorithms to predict and measures to evaluate performance of models. …”
Get full text

A conjugate self-organizing migration (CSOM) and reconciliate multi-agent Markov learning (RMML) based cyborg intelligence mechanism for smart city security by S. Shitharth (12017480)

“…Moreover, the Reconciliate Multi-Agent Markov Learning (RMML) based classification algorithm is used to predict the intrusion with its appropriate classes. …”

Enhancement of power system dynamic performance through an on-line self-tuning adaptive SVC controller by Rahim, A.H.M.A.

“…Use of a self-tuning adaptive control algorithm as a supplementary controller for the SVC is presented in this article. …”
Get full text

Autonomous 3D Deployment of Aerial Base Stations in Wireless Networks with User Mobility by Islambouli, Rania

“…We present performance results for the algorithm as a function of various system parameters assuming a random walk mobility model. …”
Get full text
Get full text
Get full text
Get full text

Swarm intelligence-based hyper-heuristic for the vehicle routing problem with prioritized customers by Tarhini, Abbas

“…Various studies have been conducted regarding this topic; nevertheless, up to now, few studies used the Cuckoo Search-based hyper-heuristic. This paper modifies a classical mathematical model that represents the VRPC, implements and tests an evolutionary Cuckoo Search-based hyper-heuristic, and then compares the results with those of our proposed modified version of the Clarke Wright (CW) algorithm. …”
Get full text
Get full text
Get full text
Get full text

Automatic and Intelligent Stressor Identification Based on Photoplethysmography Analysis by Sami Elzeiny (16891521)

“…This work leverages the output of wearable technology to provide automatic stress and stressor identification model. In particular, this study proposes a novel algorithm that first detects instances of stress and then classifies the stressor type using photoplethysmography (PPG) data from wearable smartwatches. …”

Online Control and Optimization of Directional Drilling by unknown

“…In this thesis, dynamic modeling of two different DSS were developed and optimized using different control and optimization techniques. …”
Get full text

Artificial Intelligence–Driven Serious Games in Health Care: Scoping Review by Alaa Abd-alrazaq (17058018)

“…The most common algorithm used in the included studies was support vector machine. …”

Optimal shunt compensators at nonsinusoidal busbars by El-Amin, I.M.

“…The Direct Search Polytope algorithm is used. The solution of this model yields an optimal shunt LC compensator for the nonlinear load. …”
Get full text
Get full text

Developing an online hate classifier for multiple social media platforms by Joni Salminen (7434770)

“…Although researchers have found that hate is a problem across multiple platforms, there is a lack of models for online hate detection using multi-platform data. …”

Computation of conformal invariants by Mohamed M.S., Nasser

“…In particular, we provide an algorithm for computing the conformal capacity of a condenser. …”
Get full text
Get full text
Get full text

Artificial intelligence-based methods for fusion of electronic health records and imaging data by Farida Mohsen (16994682)

“…From an AI perspective, conventional ML models were the most used (19 studies), followed by DL models (16 studies). …”