Computer Science
Loading...
ISSN 1508-2806
e-ISSN: 2300-7036
Issue Date
2022
Volume
Vol. 23
Number
No. 3
Description
Journal Volume
Computer Science
Vol. 23 (2022)
Projects
Pages
Articles
A DHCR_SmartNet: a smart Devanagari handwritten character recognition using level-wised CNN architecture
(Wydawnictwa AGH, 2022) Deore, Shalaka Prasad
Handwritten script recognition is a vital application of the machine-learning domain. Applications like automatic license plate detection, pin-code detection, and historical document management increases attention toward handwritten script recognition. English is the most widely spoken language in India, hence, there has been a lot of research into identifying a script using a machine. Devanagari is a popular script that is used by a large number of people on the Indian subcontinent. In this paper, a level-wised efficient transfer-learning approach is presented on the VGG16 model of a convolutional neural network (CNN) for identifying isolated Devanagari handwritten characters. In this work, a new dataset of Devanagari characters is presented and made accessible to the public. This newly created dataset is comprised of 5800 samples for 12 vowels, 36 consonants, and 10 digits. Initially, a simple CNN is implemented and trained on this new small dataset. During the next stage, a transfer-learning approach is implemented on the VGG16 model, and during the last stage, the efficient fine-tuned VGG16 model is implemented. The obtained accuracy of the fine-tuned model’s training and testing came to 98.16% and 96.47%, respectively.
Plant disease detection using ensembled CNN framework
(Wydawnictwa AGH, 2022) Mondal, Subhash; Banerjee, Suharta; Mukherjee, Subinoy; Sengupta, Diganta
Agriculture exhibits the prime driving force for the growth of agro-based economies globally. In agriculture, detecting and preventing crops from the attacks of pests is a primary concern in today’s world. The early detection of plant disease becomes necessary in order to avoid the degradation of the yield of crop production. In this paper, we propose an ensemble-based convolutional neural network (CNN) architecture that detects plant disease from the images of a plant’s leaves. The proposed architecture considers CNN architectures like VGG-19, ResNet-50, and InceptionV3 as its base models, and the prediction from these models is used as an input for our meta-model (Inception-ResNetV2). This approach helped us build a generalized model for disease detection with an accuracy of 97.9% under test conditions.
Comparative analysis of different trust metrics of user-user trust-based recommendation system
(Wydawnictwa AGH, 2022) Roy, Falguni; Hasan, Mahamudul
Information overload is the biggest challenge nowadays for any website – especially e-commerce websites. However, this challenge has arisen due to the fast growth of information on the web (WWW) along with easier access to the internet. A collaborative filtering-based recommender system is the most useful application for solving the information overload problem by filtering relevant information for users according to their interests. However, the current system faces some significant limitations such as data sparsity, low accuracy, cold-start, and malicious attacks. To alleviate the above-mentioned issues, the relationship of trust incorporates in the system where it can be among users or items, such a system is known as a trust-based recommender system (TBRS). From the user perspective, the motive of a TBRS is to utilize the reliability among users to generate more-accurate and trusted recommendations. However, the study aims to present a comparative analysis of different trust metrics in the context of the type of trust definition of TBRS. Also, the study accomplishes 24 trust metrics in terms of the methodology, trust properties & measurements, validation approaches, and the experimented data set.
Impact of n-stage latent Dirichlet allocation on analysis of headline classification
(Wydawnictwa AGH, 2022) Güven, Zekeriya Anil; Diri, Banu; Çakaloğlu, Tolgahan
Data analysis becomes difficult when the amount of the data increases. More specifically, extracting meaningful insights from this vast amount of data and grouping it based on its shared features without human intervention requires advanced methodologies. There are topic-modeling methods that help overcome this problem in text analyses for downstream tasks (such as sentiment analysis, spam detection, and news classification). In this research, we benchmark several classifiers (namely, random forest, AdaBoost, naive Bayes, and logistic regression) using the classical latent Dirichlet allocation (LDA) and n-stage LDA topic-modeling methods for feature extraction in headline classification. We ran our experiments on three and five classes of publicly available Turkish and English datasets. We have demonstrated that, as a feature extractor, $n$-stage LDA obtains state-of-the-art performance for any downstream classifier. It should also be noted that random forest was the most successful algorithm for both datasets.
Performance measurement with high-performance computer using HW-GA anomaly-detection algorithms for streaming data
(Wydawnictwa AGH, 2022) Fondaj, Jakup; Hasani, Zirije; Krrabaj, Samedin
Anomaly detection for streaming real-time data is very important, more significant is the performance of an algorithm in order to meet real-time requirements. Anomaly detection is very crucial in every sector because, by knowing what is going wrong with data/digital systems, we can make decisions to help in every sector. Dealing with real-time data requires speed, for this reason, the aim of this paper is to measure the performance of our proposed Holt–Winters genetic algorithm (HW-GA) as compared to other anomaly-detection algorithms with a large amount of data as well as to measure how other factors such as visualization and the performance of the testing environment affect the algorithm’s performance. The experiments will be done in R with different data sets such as the as real COVID-19 and IoT sensor data that we collected from Smart Agriculture Libelium sensors and e-dnevnik as well as three benchmarks from the Numenta data sets. The real data has no known anomalies, but the anomalies are known in the benchmark data, this was done in order to evaluate how the algorithm works in both situations. The novelty of this paper is that the performance will be tested on three different computers (in which one is a high-performance computer), also, a large amount of data will be used for our testing, as will how the visualization phase affects the algorithm’s performance.