درخت حوزه‌های تخصصی

Most real-time speech signals are frequently disrupted by noise such as traffic, babbling, and background noises, among other things. The goal of speech denoising is to extract the clean speech signal from as many distorted components as possible. For speech denoising, many researchers worked on sparse representation and dictionary learning algorithms. These algorithms, however, have many disadvantages, including being overcomplete, computationally expensive, and susceptible to orthogonality restrictions, as well as a lack of arithmetic precision due to the usage of double-precision. We propose a greedy technique for dictionary learning with sparse representation to overcome these concerns. In this technique, the input signal's singular value decomposition is used to exploit orthogonality, and here the ℓ1-ℓ2 norm is employed to obtain sparsity to learn the dictionary. It improves dictionary learning by overcoming the orthogonality constraint, the three-sigma rule-based number of iterations, and the overcomplete nature. And this technique has resulted in improved performance as well as reduced computing complexity. With a bit-precision of Q7 fixed-point arithmetic, this approach is also used in resource-constrained embedded systems, and the performance is considerably better than other algorithms. The greedy approach outperforms the other two in terms of SNR, Short-Time Objective Intelligibility, and computing time.

The main aim of this thesis is to investigate the factors that could affect the students to adopt e-learning system in Libyan universities. This study is quantitative approach, a questionnaire was adopted from previous studies and distributed among the students to collect the data. The sample of the study consists 365 students from Libya. AMOS software was used to analysis the data. The results indicated that Performance Expectancy, Efforts Expectancy, Facilitating Conditions, Habit and Trust have significant impact on behavioural intention. Moreover, the relationship between Behavioural intention and use behaviour is also significantly positive. However, the relationship of social influence and behavioural intention was not found significant. Finally, the moderation effect was significant and supported between social influence, trust, and Habit with behavioural intention.

On a global scale, one of the prevalent causes of dementia is Alzheimer’s disease (AD). It will cause a steady deterioration in the individual from the mild stage to the severe stage, and thus impair their capacity to finish any tasks with no aid. The diagnosis is done with the utilization of existing methods which include medical history; neuropsychological testing as well as MRI (Magnetic Resonance Imaging), a lack of sensitivity as well as precision does affect the consistency of efficient procedures. With the deep learning network’s utilization, it is possible to create a framework for detecting specific AD characteristics from the MRI images. While automatic diagnosis is done with the application of diverse machine learning techniques, the existing ones do suffer from certain constraints with regards to accuracy. Thus, this work’s key goal is to increase the classification’s accuracy through the inclusion of a pre-processing approach prior to the deep learning model. The Alzheimer's disease Neuroimaging Initiative (ADNI) database of AD patients was used to develop a deep learning approach for AD identification. In addition, this study will present ideas for Haralick features, feature extraction from Local Binary Pattern (LBP), Artificial Neural Network (ANN), and Visual Geometry Group (VGG)-19 network techniques. The results of the experiments show that the deep learners offered are more effective than other systems already in use.

Managers should pay more attention to flexible production systems in order to cope with the challenges posed by factors such as global competition, changing customer demands, increasing market penetration, and rapid technological growth. On the other hand, the development of information and communication technology (ICT) provides significant opportunities for a more effective supply chain management including mobile supply chains. This research is aimed at identifying and prioritizing the factors affecting the diffusion of mobile supply chain management systems in dairy industries. To do this, the effective factors and key performance variables were identified through the reviewing associated literature followed by utilizing the Interpretative Ranking Process (IRP). The Prioritization of the factors was conducted with respect to the performance variables. Applying this method provides the ability to prioritize indicators with respect to variables that are very influential in business based on experts' opinions. The results of this study indicate that having appropriate knowledge, compatibility with existing infrastructure, Privacy of data stored and company revenue have the highest rank in this prioritization.

Flash floods are considered to be one the worst kind of hazard. They are characterized by their suddenness, rarity, small scale, heavy rain and peak discharge, unpredictable, fast and violent movement. It has severe effects on human society in the form life losses, damages to property, roads, communication and on natural settings. Advances in hydrology, meteorology, engineering, using of GIS and remote sensing still not able to increase real time forecast. Researchers from developed countries have stressed to more focus to improve very short time an effective early warning system with collaboration of local communities for flash flood risk supervision. The data were combined with the Geographical Information System to analyze the temporal and spatial distribution of flood events in Salah Al-Din Governorate and Ramadan Valley. The analysis of the spatial distribution of the floods proves that most of the occurrences are recorded in the southern part of the study area. Most of the flooded areas in the study area are mainly pre-classified areas within the areas threatened by the flood due to the low level of its surface and its proximity to the course of the main valley (Wadi Jarnav), which flows into the Tigris River. The proposed method estimates the localization of sites prone to flood, and it may be used for flood hazard assessment mapping and for flood risk management. It was therefore, suggested that government agencies and policy makers should adopt this powerful technique for reliable and well synthesized information which is a vital component of flood risk assessment and planning.

This paper is aimed at evaluating critical success factors in Business Intelligence (BI) implementation in an Enterprise Resource Planning (ERP) environment. The data analysis method used in this paper is the Decision Making Trial and Evaluation Laboratory Model (DEMATEL). The study has been conducted on a cement manufacturing strategic holding company that has implemented ERP since 2010. This research is done through literature review and interviews with the head of the BI development team as the expert for this research, before distributing questionnaires to Information and Communication Technologies (ICT) Team and BI stakeholders. The questionnaire has been addressed to 18 respondents consisting of the BI development team and stakeholders, which include the Strategic Planning Division, Business Development Division, Transformation Management Division, and Accounting Division. There are 13 factors evaluated, consisting of 4 factors related to the organization, four factors related to the development process, three factors related to the technology, and two factors associated with the external environment. The most critical factor for organizational criteria is Top management support. The most important factor for process criteria is Effective project management. The most important factor for technology criteria is System reliability, flexibility, and scalability. The most important factor for environment criteria is the selection of a vendor.