5324 research outputs found
Sort by
A domain-based feature generation and convolution neural network approach for extracting adverse drug reactions from social media posts
Get PDFThe recent popularity of the social media networks including forums, blogs, and
micro-blogging networks changed the way patients share their health experiences and
treatment options. Such forums offer valuable, unsolicited, uncensored information on
drug safety and side effects directly from patients. However, it is very challenging to
extract useful information from such forums due to several factors such as grammatical
and spelling errors, colloquial language, and post length limitation. Furthermore,
due to the sensitivity of the domain for adverse drug reactions (ADR) detection, it is
more critical to identify correct ADRs (i.e., achieve higher classification precision) than
identifying non-precise ones.
The aims of this thesis are: (i) to develop a new approach for ADR classification in
twitter posts called Semantic Vector(SemVec); (ii) to explore natural language processing
(NLP) approaches for generating domain features from text, and utilizing them for
ADRs detection; and (iii) to improve convolution neural network (CNN) ADR classifi-
cation precision by incorporating domain features.
This thesis proposes a dynamic and pluggable model, named SemVec, for representing
words as a vector of both domain and morphological features. Based on the problem
domain, domain features can be added or removed to generate an enriched word representation
with domain knowledge. SemVec represents each post as a matrix of word
vectors, which is fed into CNN. SemVec is scalable, can be applied to other domains
by employing relevant natural language processing methods and domain lexicons. The
proposed method was evaluated on Twitter (ADR) dataset. Results show that SemVec
improves the precision of ADR detection by 13.43% over other state-of-the-art deep
learning methods with a comparable recall score
Feature selection using binary particle swarm optimization with time varying inertia weight strategies
Get PDFIn this paper, a feature selection approach that based on Binary Particle Swarm Optimization (PSO) with time varying inertia weight strategies is proposed. Feature Selection is an important preprocessing technique that aims to enhance the learning algorithm (e.g., classification) by improving its performance or reducing the processing time or both of them. Searching for the best feature set is a challenging problem in feature selection process, metaheuristics algorithms have proved a good performance in finding the (near) optimal solution for this problem. PSO algorithm is considered a primary Swarm Intelligence technique that showed a good performance in solving different optimization problems. A key component that highly affect the performance of PSO is the updating strategy of the inertia weight that controls the balance between exploration and exploitation. This paper studies the effect of different time varying inertia weight updating strategies on the performance of BPSO in tackling feature selection problem. To assess the performance of the proposed approach, 18 standard UCI datasets were used. The proposed approach is compared with well regarded metaheuristics based feature selection approaches, and the results proved the superiority of the proposed approach
Episiotomy practice in six Palestinian hospitals : a population-based cohort study among singleton vaginal births
Get PDFObjective To explore the rates, characteristics and indications for episiotomy among women delivering vaginally for the first time, as well as parous women. Study design A prospective, population-based birth
cohort study. Setting Obstetric departments in six Palestinian government hospitals. Participants All women with singleton vaginal births (n=29 165) from 1 March 2015 until 1 March 2016.
Methods All women were divided into two groups: first vaginal birth group (n=9108), including primiparous women and women with their first vaginal birth after one caesarean section, and the parous group (n=20 057). Each group was analysed separately. Data were presented as numbers and percentages or range. Differences in rates were assessed by the p values of χ2 test, or Fisher’s exact
test if there are cell counts less than 5. Main outcome measures Episiotomy rates and indications among women of singleton births. Results The overall episiotomy rate was 28.7%: 78.8%
for women with first vaginal birth (range 56.6%–86.0%) and 5.9% for parous women (range 1.0% 9.5%). The most common indications for episiotomy were ‘primiparity’ in the first vaginal birth group (69.9%) and ‘protecting the perineum’ in the parous group (59.5%). The least common indications were prolonged second stage (1.5%) and fetal distress (6.9%), respectively.
Conclusion In Palestine, the majority of women who delivered vaginally for the first time had an episiotomy. Education of birth attendants, clinical audits, educational interventions and adherence to the updated guidelines may help to decrease the routine overuse of episiotomyNorwegian Research Counci
Automatic generation of Android SQLite database components
No full textMobile applications (apps) are becoming ubiquitous and at the same time getting more complex to develop. Specific development tools and techniques are always essential to facilitate the development of reliable and cost effective mobile apps. However, a large fraction of Android app developers are known to be novice and come from non-computing background. To assist developers, this paper addresses the problem of automatic generation of Android database components, and presents a technique for creating SQLite database and APIs. The technique is based on a tool named Android SQLite Creator (ASQLC) that can automatically generate Android SQLite database as well as the API classes that perform read/write operation on that database. To evaluate the tool, a preliminary experiment was conducted by junior computer science students in building a small size Android database. This preliminary evaluation shows that our tool can be usable and promising particularly for novice developers
Land, property rights, and colonial procrastination : between the Balfour Declaration and the Nakba
No full textنشر في مجلة أسطور، العدد 8، ص. 193تناقش هذه المقالة التغيير في ملكية الأراضي الذي قامت به بريطانيا والذي أدخل في فلسطين كاختصاص حكومي حاول فيه البريطانيون إدارة علاقات اصحاب الأرض و المستوطنين ، وكأرض سياسية للحشد من أجل الوصول كما للأرض كما للسيادة
This article discusses the British land reform introduced in Palestine as a governmental field in which the British attempted to manage native/settler relations, and as a political ground for mobilization for access to land as well as for sovereignty
خلافة أبي بكر الصديق 11-13هـ / 632-634 م بين التطبيق و النظرية
No full textيطلق على النظام السياسي في الإسلام مصطلح الخلافة، وقد ظهر هذا المصطلح بعد وفاة الرسول (ص)، ولذلك لم يكن له قواعد محددة، خاصة أن القرآن والحديث لم ينطرقا لذلك، ولذلك أصبحت تجارب الخلفاء خاصة تجربة أبي بكر الأساس لبناء النظرية السياسية للحكم فيما بعد، حيث جسدت عدداً كبيراً من المبادئ والقيم السياسية، مثل الانتخاب والشورى، ووحدة الخلافة، والعدل، وسيادة الشرع، والقرشية، والسابقة في الإسلام. وكما لوحظ كذلك دور المفاهيم القبلية في تقرير مبادئ وطبيعة، هذا النظام على حساب القيم الدينية بحيث أصبح السن، والتجربة ، والحكمة ، ورفض التوريث كما في حالة شيوخ القبائل ذات تأثير واضح في اختيار الخليف
قصص من التراث : مجموعة من القصص للأطفال من جزر آران تسمى جوث نا مارا، صوت البحر
No full textترجمة لمجموعة قصص للأطفال من الإيرلندية الى العربيةقصص للأطفال
من أيرلندا
الكتاب الأول
"قصص من التراث"
مجموعة من القصص للأطفال من جزر آران
تسمى (جوث نا مارا) صوت البحرتم إصدار هذه القصص بدعم كريم من لجنة البحث العلمي في جامعة بيرزيت
Supported by research team at Birzeit Universit
