Tài liệu miễn phí Kỹ thuật lập trình
Download Tài liệu học tập miễn phí Kỹ thuật lập trình
Applying empirical thresholding algorithm for a keystroke dynamics based authentication system
The proposed methodology yields very low equal error rate of 0.5% and the authentication accuracy of 99.5%, which are considered suitable and efficient for real-time implementation. The proposed method can be a useful resource for identifying illegal invasion and is valuable in securing the system as a correlative or substitute form of client validation.
4/3/2023 8:47:25 PM +00:00
A deep autoencoder based representation for arabic text categorization
To overcome these shortcomings, we proposed a deep Autoencoder based representation for Arabic text categorization. It consisted of three stages: (1) Extracting from Arabic WordNet the most relevant concepts based on feature selection processes (2) Features learning via an unsupervised algorithm for text representation (3) Categorizing text using deep Autoencoder.
4/3/2023 8:47:16 PM +00:00
A discourse - based information retrieval for tamil literary texts
This paper proposes a novel information retrieval framework that uses discourse processing techniques in aiding semantic analysis and representation of Tamil literary texts. The proposed framework was tested using two ancient literary works, the Thirukkural and Naladiyar, which were written in 300 Before the Common Era (BCE).
4/3/2023 8:47:04 PM +00:00
A hybrid least squares support vector machine with bat and CUCKOO search algorithms for time series forecasting
Following the success, this study has integrated the two algorithms to better optimize the LSSVM. The newly proposed forecasting algorithm, termed as CUCKOO-BAT-LSSVM, produces better forecasting in terms of MAPE, accuracy and RMSPE. Such an outcome provides an alternative model to be used in facilitating decision-making in forecasting.
4/3/2023 8:46:55 PM +00:00
Summarizing indonesian news articles using graph convolutional network
This study used three different representation types for the sentence relationship graph. The sentence selection component then generates a summary with two different techniques: by greedily choosing sentences with the highest scores and by using the Maximum Marginal Relevance (MMR) technique.
4/3/2023 8:46:45 PM +00:00
A syntactic based sentence validation technique for malay text summarizer
This paper used the Malay dataset of 100 new articles covering the natural disaster and events domain to find the optimal compression rate and its effect on the summary content.
4/3/2023 8:46:35 PM +00:00
Preliminary analysis of wireless collaborative network on mobile devices
The findings, it was concluded that the biggest challenge of setting up WCN was the ability of mobile devices to provide bridging functionality.This paper also discussed the expected architecture of WCN and suggests simulation tools with relevant metrics to be considered in this research area.
4/3/2023 8:46:23 PM +00:00
A practical model from multidimensional layering: Personal finance information framework using mobile software interface operations
This research applied aspect orientation and informative multidimensional layering to present a better features model for mobile personal finance application. In addressing the gap, this research proposes a clearer operation of three-dimensional models, functional data, and aspect elements that cut across through informative multidimensional layering.
4/3/2023 8:46:15 PM +00:00
Adaptive variable extractions with lda for classification of mixed variables, and applications to medical data
Accordingly, the models proposed in this paper, including the strategy that was adapted, were successful in presenting good results over the full LDA model. Regarding the indicators that were used to extract and to retain the variables in the model, cumulative variance explained (CVE).
4/3/2023 8:46:07 PM +00:00
A hybrid ant colony optimization algorithm for solving a highly constrained nurse rostering problem
The results showed that with a larger value of pheromone, the chances of obtaining a good solution was found with only small penalty values. This study has proven that the hybrid ACO is able to solve NRPs with good potential solutions that satisfied all four important criteria: coverage, quality, flexibility, and cost.
4/3/2023 8:45:56 PM +00:00
Hybrid cryptographic approach for internet of things applications: A review
In addition, AES and ECC have been found to be the most popular methods used in the hybrid approach due to its computing speed and security resistance among other schemes.
4/3/2023 8:45:49 PM +00:00
Mitigating slow hypertext transfer protocol distributed denial of service attacks in software defined networks
This study contributes towards the ongoing research in detecting and mitigating slow HTTP DDoS attacks with emphasis on the use of machine learning classification and meta-heuristic algorithms.
4/3/2023 8:45:40 PM +00:00
An exploratory study for investigating the issues and current practices of service oriented architecture adoption
The study also portrayed five best practices related to technology, framework, platform, standards, and tools. In addition, results from the study showed five IT and business benefits, consecutively.
4/3/2023 8:45:31 PM +00:00
Gender classification on skeletal remains: Efficiency of metaheuristic algorithm method and optimized back propagation neural network
This study used 1,538 data samples from Goldman Osteometric Dataset which consisted of femur, humerus and tibia parts. Based on the feature selection results, the Optimized BPNN outperformed other methods for all datasets.
4/3/2023 8:45:19 PM +00:00
Hyper-heuristic evolutionary approach for constructing decision tree classifiers
In this paper, a hyper-heuristic approach was presented for tuning the hyper parameters of recursive and partition trees (Rpart), which is a typical implementation of CART in statistical and data analytics package R. The study employed an evolutionary algorithm as hyper-heuristic for tuning the hyper parameters of the decision tree classifier.
4/3/2023 8:45:03 PM +00:00
Self adaptive model based on goal oriented requirements engineering for handling service variability
The purpose of this research is to realize service flexibility through variability modeling, which is an extension of previous work to enrich the adaptability view. It also meets the expected level (level-5: adapting) of the adaptive capability maturity model as a standard for assessment of a service system adaptation.
4/3/2023 8:44:54 PM +00:00
An improved grey wolf optimization based learning of artificial neural network for medical data classification
The performance measures were described in terms of mean squared errors, classification accuracies, sensitivities, specificities, the area under the curve, and receiver operating characteristic curve. It was found that IMGWO outperformed three popular metaheuristic approaches including GWO, genetic algorithm, and particle swarm optimization. Results confirmed the potency of IMGWO as a viable learning technique for an ANN
4/3/2023 8:44:40 PM +00:00
Motion learning using spatio temporal neural network
In this study, learning is implemented on a reward basis without the need for learning targets. The algorithm has shown good potential in learning motion trajectory particularly in noisy and dynamic settings.
4/3/2023 8:44:33 PM +00:00
A computational model of temporal dynamics for anxiety in interviewee mental state
The results conform to established facts in the literature. Consequently, this model can serve as a basis to build an integrated interviewee mental state model embedded with self-efficacy and motivation constructs as a holistic approach to support interviewees in coaching environments during simulated training.
4/3/2023 8:44:26 PM +00:00
Review of multi-objective swarm intelligence optimization algorithms
In this paper, the status of MOO research and state-of-the-art MOSI algorithms, namely multi-objective particle swarm, artificial bee colony, firefly algorithm, bat algorithm, gravitational search algorithm, grey wolf optimizer, bacterial foraging, and moth-flame optimization algorithms, were reviewed.
4/3/2023 8:44:13 PM +00:00
Human activity detection and action recognition in videos using convolutional neural networks
The main aim of this work is to detect and track human activity, and classify actions for two publicly available video databases. In this work, a novel approach of feature extraction from video sequence by combining Scale Invariant Feature Transform and optical flow computation are used where shape, gradient and orientation features are also incorporated for robust feature formulation.
4/3/2023 8:44:03 PM +00:00
Information and communication technology, Automation of quranic readings gathering process
In this paper, this process was algorithmically formulated and a developed software system was presented to automate this process. This system took Quranic verse texts as input and generated a text file containing the detailed gathering of the readings of this verse as done by a specialised reciter.
4/3/2023 8:43:52 PM +00:00
A collision aware priority level medium access control protocol for underwater acoustic sensor networks
The simulation results showed that the proposed CAPL-MAC protocol achieved the earlier stated performance rather than by existing protocols such as Competitive Transmission-MAC and Channel Aware Aloha.
4/3/2023 8:43:44 PM +00:00
An iterated two- step sinusoidal pitch contour formulation for expressive speech synthesisan iterated two step sinusoidal pitch contour formulation for expressive speech synthesis
This paper formulated an improved pitch contour algorithm to develop a modified pitch contour resembling the natural pitch contour. In this work, the syllable pitch contours of nine storytellers were extracted from their storytelling speeches to create an expressive speech syllable dataset called STORY_DATA.
4/3/2023 8:40:40 PM +00:00
Sarcasm detection in persian
In this study, the deep polarity feature was proposed by conducting a sentiment analysis using deep neural network architecture. In addition, to extract the sentiment feature, a Persian sentiment dictionary was developed, which consisted of four sentiment categories.
4/3/2023 8:40:29 PM +00:00
Đánh giá chất lượng một số thuật toán giải mã mới cho mã NB-LDPC
Bài viết này đánh giá chất lượng sửa lỗi của một số thuật toán giải mã mới cho mã NB-LDPC trên các trường khác nhau với các mã có độ dài từ mã khác nhau. Kết quả cho thấy độ lớn của trường hữu hạn và độ dài từ mã sẽ quyết định đến phẩm chất của bộ giải mã.
4/3/2023 3:40:02 PM +00:00
Nghiên cứu và đánh giá hiệu năng Retinaface với một số phương pháp nhận diện hiện đại
Bài viết thực hiện nghiên cứu đặc trưng cơ bản của Retinaface với ứng dụng dò tìm trên video và đối sánh kết quả thực nghiệm. Từ đó so sánh tham số hiệu năng với các giải pháp khác để rút ra các kết luận hữu ích.
4/3/2023 3:39:48 PM +00:00
Một phương pháp phân luồng người khám bệnh dựa trên học sâu và xử lý ngôn ngữ tự nhiên
Bài viết này đề xuất phương pháp dùng các giải thuật học sâu cho việc chẩn đoán ban đầu trong thử nghiệm nhận định một số bệnh. Phương pháp mà bài viết đề xuất ứng dụng các kỹ thuật xử lý ngôn ngữ tự nhiên đối với tiếng Việt trong việc xây dựng kho dữ liệu huấn luyện hệ thống học sâu từ các bệnh án cũng như dựa trên sự tư vấn của bác sĩ chuyên môn.
4/3/2023 3:39:33 PM +00:00
Nghiên cứu bộ tiền mã hóa và giải mã cho hệ thống MIMO trải trễ dựa trên tiêu chí cân bằng lỗi
Hiện tượng trải trễ gây ra nhiễu giữa các symbol (ISI: Inter-Symbol Interference), dẫn đến tỷ lệ lỗi symbol tăng đáng kể. Bài viết đề xuất sử dụng bộ tiền mã hóa và giải mã tuyến tính cho hệ thống đa đầu vào - đa đầu ra (MIMO: Multiple-Input Multiple-Output) đơn sóng mang có kênh truyền trải trễ để nâng cao chất lượng hệ thống.
4/3/2023 3:35:48 PM +00:00
Nhận dạng các loại quả ứng dụng cho robot tự động thu hoạch bằng thuật toán Single Shot Multibox Detector
Bài viết trình bày về phương pháp nhận dạng các loại hoa quả thân gỗ có độ phức tạp hơn trong bài toán nhận dạng và thu hoạch như táo, cam, xoài,... sử dụng thuật toán SSD. Thuật toán được triển khai thử nghiệm trên phần cứng nhúng Rasberry Pi 3+ cho kết quả nhận dạng các loại quả theo thời gian thực với kết quả độ chính xác khá cao, có thể ứng dụng cho robot tự động thu hoạch.
4/3/2023 3:33:07 PM +00:00