Models, code, and papers for "Ahmed A":

Assistive System in Conversational Agent for Health Coaching: The CoachAI Approach

Apr 25, 2019
Ahmed Fadhil

With increasing physicians' workload and patients' needs for care, there is a need for technology that facilitates physicians work and performs continues follow-up with patients. Existing approaches focus merely on improving patient's condition, and none have considered managing physician's workload. This paper presents an initial evaluation of a conversational agent assisted coaching platform intended to manage physicians' fatigue and provide continuous follow-up to patients. We highlight the approach adapted to build the chatbot dialogue and the coaching platform. We will particularly discuss the activity recommender algorithms used to suggest insights about patients' condition and activities based on previously collected data. The paper makes three contributions: (1) present the conversational agent as an assistive virtual coach, (2) decrease physicians workload and continuous follow up with patients, all by handling some repetitive physician tasks and performing initial follow up with the patient, (3) present the activity recommender that tracks previous activities and patient information and provides useful insights about possible activity and patient match to the coach. Future work focuses on integrating the recommender model with the CoachAI platform and test the prototype with patient's in collaboration with an ambulatory clinic.

  Access Model/Code and Paper
Controller Design and Implementation of a New Quadrotor Manipulation System

Apr 11, 2019
Ahmed Khalifa

The previously introduced aerial manipulation systems suffer from either limited end-effector DOF or small payload capacity. In this dissertation, a quadrotor with a 2-DOF manipulator is investigated that has a unique topology to enable the end-effector to track 6-DOF trajectory with the minimum possible number of actuators/links and hence, maximize the payload and/or mission time. The proposed system is designed, modeled, and constructed. An identification process is carried out to find the system parameters. An experimental setup is proposed with a 6-DOF state measurement and estimation scheme. The system feasibility is validated via numerical and experimental results. The inverse kinematics require a solution of complicated algebraic-differential equations. Therefore, an algorithm is developed to get an approximate solution of these equations. Furthermore, the motion control of this quadrotor manipulation system is quite challenging. The system has strong nonlinearities, fast dynamics and unstable dynamics that are very susceptible to parameters variations and external disturbances. Thus, a linear Disturbance Observer (DOb)-based robust controller is utilized to address these issues. A modified DOb loop is proposed and designed to use the direct measurements. A Model Predictive Control (MPC) is used in the external loop of the DOb to save power consumption that increases the mission time and to consider of the actuators constraints. The manipulation tasks require estimating (applying) certain force at the end-effector. However, the current developed techniques have limitations because they are model-based methods, based on ignoring some dynamics, or requiring an indicator of the environment contact. Hence, a robust sensorless force estimation and impedance control scheme is proposed to overcome these limitations.

* Ph.D. Thesis. Supervisors: Prof. Mohamed Fanni (EJUST), Prof. Toru Namerikawa (Keio University) 

  Access Model/Code and Paper
Novel Quadrotor Manipulation System

Apr 10, 2019
Ahmed Khalifa

This thesis introduces a novel quadrotor manipulation system that consists of 2-link manipulator attached to the bottom of a quadrotor. This new system presents a solution for the drawbacks found in the current quadrotor manipulation system which uses a gripper fixed to a quadrotor. Unlike the current system, the proposed system has a 6-DOF, and it provides enough distance between the quadrotor and the object. System kinematics and dynamics are derived. To study the feasibility of the proposed system, a quadrotor with high enough payload to add the 2-link manipulator is constructed. Its parameters are identified to be used in the simulation and controller design. A CAD model is developed to calculate the mass and moments of inertia in an accurate way. Direct relationships between Pulse Width Modulation and each of the angular speeds, thrust forces, and drag moments of the rotors are identified. A Direction Cosine Matrix complementary filter is used to estimate the attitude of the quadrotor using the IMU measurements. Attitude stabilization controller is designed based on feedback linearization technique to test the identified parameters and the attitude estimation. The results of the experiments show satisfactory accuracy of the identified structure parameters, the identified rotor assembly parameters, and the attitude estimation algorithm. A controller for the proposed system is designed based on three control techniques: feedback linearization based PID control, direct fuzzy logic control, and fuzzy model reference learning control. These controllers are tested to provide system stability and trajectory tracking under the effect of picking and placing a payload and the effect of changing the operating region. Simulation results show that the fuzzy model reference learning control technique has superior performance. The results indicate the feasibility of the proposed system.

* M.Sc. Thesis. Supervisors: Prof. Mohamed Fanni, Dr. Ahmed Ramadan, Prof. Ahmed Abo-Ismail 

  Access Model/Code and Paper
Data-Free/Data-Sparse Softmax Parameter Estimation with Structured Class Geometries

Jul 22, 2018
Nisar Ahmed

This note considers softmax parameter estimation when little/no labeled training data is available, but a priori information about the relative geometry of class label log-odds boundaries is available. It is shown that `data-free' softmax model synthesis corresponds to solving a linear system of parameter equations, wherein desired dominant class log-odds boundaries are encoded via convex polytopes that decompose the input feature space. When solvable, the linear equations yield closed-form softmax parameter solution families using class boundary polytope specifications only. This allows softmax parameter learning to be implemented without expensive brute force data sampling and numerical optimization. The linear equations can also be adapted to constrained maximum likelihood estimation in data-sparse settings. Since solutions may also fail to exist for the linear parameter equations derived from certain polytope specifications, it is thus also shown that there exist probabilistic classification problems over m convexly separable classes for which the log-odds boundaries cannot be learned using an m-class softmax model.

* Final version accepted to IEEE Signal Processing Letters (double column), submitted July 21, 2018 

  Access Model/Code and Paper
Beyond Patient Monitoring: Conversational Agents Role in Telemedicine & Healthcare Support For Home-Living Elderly Individuals

Mar 03, 2018
Ahmed Fadhil

There is a need for systems to dynamically interact with ageing populations to gather information, monitor health condition and provide support, especially after hospital discharge or at-home settings. Several smart devices have been delivered by digital health, bundled with telemedicine systems, smartphone and other digital services. While such solutions offer personalised data and suggestions, the real disruptive step comes from the interaction of new digital ecosystem, represented by chatbots. Chatbots will play a leading role by embodying the function of a virtual assistant and bridging the gap between patients and clinicians. Powered by AI and machine learning algorithms, chatbots are forecasted to save healthcare costs when used in place of a human or assist them as a preliminary step of helping to assess a condition and providing self-care recommendations. This paper describes integrating chatbots into telemedicine systems intended for elderly patient after their hospital discharge. The paper discusses possible ways to utilise chatbots to assist healthcare providers and support patients with their condition.

* 7 pages 

  Access Model/Code and Paper
Towards Automatic & Personalised Mobile Health Interventions: An Interactive Machine Learning Perspective

Mar 03, 2018
Ahmed Fadhil

Machine learning (ML) is the fastest growing field in computer science and healthcare, providing future benefits in improved medical diagnoses, disease analyses and prevention. In this paper, we introduce an application of interactive machine learning (iML) in a telemedicine system, to enable automatic and personalised interventions for lifestyle promotion. We first present the high level architecture of the system and the components forming the overall architecture. We then illustrate the interactive machine learning process design. Prediction models are expected to be trained through the participants' profiles, activity performance, and feedback from the caregiver. Finally, we show some preliminary results during the system implementation and discuss future directions. We envisage the proposed system to be digitally implemented, and behaviourally designed to promote healthy lifestyle and activities, and hence prevent users from the risk of chronic diseases.

* 9 pages 

  Access Model/Code and Paper
A Conversational Interface to Improve Medication Adherence: Towards AI Support in Patient's Treatment

Mar 03, 2018
Ahmed Fadhil

Medication adherence is of utmost importance for many chronic conditions, regardless of the disease type. Engaging patients in self-tracking their medication is a big challenge. One way to potentially reduce this burden is to use reminders to promote wellness throughout all stages of life and improve medication adherence. Chatbots have proven effectiveness in triggering users to engage in certain activity, such as medication adherence. In this paper, we discuss "Roborto", a chatbot to create an engaging interactive and intelligent environment for patients and assist in positive lifestyle modification. We introduce a way for healthcare providers to track patients adherence and intervene whenever necessary. We describe the health, technical and behavioural approaches to the problem of medication non-adherence and propose a diagnostic and decision support tool. The proposed study will be implemented and validated through a pilot experiment with users to measure the efficacy of the proposed approach.

* 7 pages 

  Access Model/Code and Paper
Can a Chatbot Determine My Diet?: Addressing Challenges of Chatbot Application for Meal Recommendation

Feb 25, 2018
Ahmed Fadhil

Poor nutrition can lead to reduced immunity, increased susceptibility to disease, impaired physical and mental development, and reduced productivity. A conversational agent can support people as a virtual coach, however building such systems still have its associated challenges and limitations. This paper describes the background and motivation for chatbot systems in the context of healthy nutrition recommendation. We discuss current challenges associated with chatbot application, we tackled technical, theoretical, behavioural, and social aspects of the challenges. We then propose a pipeline to be used as guidelines by developers to implement theoretically and technically robust chatbot systems.

* 6 pages 

  Access Model/Code and Paper
Lexical Normalisation of Twitter Data

Sep 20, 2015
Bilal Ahmed

Twitter with over 500 million users globally, generates over 100,000 tweets per minute . The 140 character limit per tweet, perhaps unintentionally, encourages users to use shorthand notations and to strip spellings to their bare minimum "syllables" or elisions e.g. "srsly". The analysis of twitter messages which typically contain misspellings, elisions, and grammatical errors, poses a challenge to established Natural Language Processing (NLP) tools which are generally designed with the assumption that the data conforms to the basic grammatical structure commonly used in English language. In order to make sense of Twitter messages it is necessary to first transform them into a canonical form, consistent with the dictionary or grammar. This process, performed at the level of individual tokens ("words"), is called lexical normalisation. This paper investigates various techniques for lexical normalisation of Twitter data and presents the findings as the techniques are applied to process raw data from Twitter.

* Removed typos 

  Access Model/Code and Paper
Predictive Capacity of Meteorological Data - Will it rain tomorrow

Sep 16, 2014
Bilal Ahmed

With the availability of high precision digital sensors and cheap storage medium, it is not uncommon to find large amounts of data collected on almost all measurable attributes, both in nature and man-made habitats. Weather in particular has been an area of keen interest for researchers to develop more accurate and reliable prediction models. This paper presents a set of experiments which involve the use of prevalent machine learning techniques to build models to predict the day of the week given the weather data for that particular day i.e. temperature, wind, rain etc., and test their reliability across four cities in Australia {Brisbane, Adelaide, Perth, Hobart}. The results provide a comparison of accuracy of these machine learning techniques and their reliability to predict the day of the week by analysing the weather data. We then apply the models to predict weather conditions based on the available data.

* 7 pages, 2 Result Sets 

  Access Model/Code and Paper
Proposing LT based Search in PDM Systems for Better Information Retrieval

Feb 09, 2011
Zeeshan Ahmed

PDM Systems contain and manage heavy amount of data but the search mechanism of most of the systems is not intelligent which can process user"s natural language based queries to extract desired information. Currently available search mechanisms in almost all of the PDM systems are not very efficient and based on old ways of searching information by entering the relevant information to the respective fields of search forms to find out some specific information from attached repositories. Targeting this issue, a thorough research was conducted in fields of PDM Systems and Language Technology. Concerning the PDM System, conducted research provides the information about PDM and PDM Systems in detail. Concerning the field of Language Technology, helps in implementing a search mechanism for PDM Systems to search user"s needed information by analyzing user"s natural language based requests. The accomplished goal of this research was to support the field of PDM with a new proposition of a conceptual model for the implementation of natural language based search. The proposed conceptual model is successfully designed and partially implementation in the form of a prototype. Describing the proposition in detail the main concept, implementation designs and developed prototype of proposed approach is discussed in this paper. Implemented prototype is compared with respective functions of existing PDM systems .i.e., Windchill and CIM to evaluate its effectiveness against targeted challenges.

* International Journal of Computer Science & Emerging Technologies (E-ISSN: 2044-6004), Volume 1, Issue 4, P86-100, December 2010 
* 15 pages, 31 figures 

  Access Model/Code and Paper
AI 3D Cybug Gaming

Sep 10, 2010
Zeeshan Ahmed

In this short paper I briefly discuss 3D war Game based on artificial intelligence concepts called AI WAR. Going in to the details, I present the importance of CAICL language and how this language is used in AI WAR. Moreover I also present a designed and implemented 3D War Cybug for AI WAR using CAICL and discus the implemented strategy to defeat its enemies during the game life.

* In the proceedings of 9th National Research Conference on Management and Computer Sciences, SZABIST Institute of Science and Technology, Pakistan 

  Access Model/Code and Paper
Decentralized Gaussian Mixture Fusion through Unified Quotient Approximations

Jul 09, 2019
Nisar R. Ahmed

This work examines the problem of using finite Gaussian mixtures (GM) probability density functions in recursive Bayesian peer-to-peer decentralized data fusion (DDF). It is shown that algorithms for both exact and approximate GM DDF lead to the same problem of finding a suitable GM approximation to a posterior fusion pdf resulting from the division of a `naive Bayes' fusion GM (representing direct combination of possibly dependent information sources) by another non-Gaussian pdf (representing removal of either the actual or estimated `common information' between the information sources). The resulting quotient pdf for general GM fusion is naturally a mixture pdf, although the fused mixands are non-Gaussian and are not analytically tractable for recursive Bayesian updates. Parallelizable importance sampling algorithms for both direct local approximation and indirect global approximation of the quotient mixture are developed to find tractable GM approximations to the non-Gaussian `sum of quotients' mixtures. Practical application examples for multi-platform static target search and maneuverable range-based target tracking demonstrate the higher fidelity of the resulting approximations compared to existing GM DDF techniques, as well as their favorable computational features.

* submitted for journal review to Information Fusion; conference version published in IEEE MFI 2015 conference: N. Ahmed, "What's One Mixture Divided by Another? A unified approach to high-fidelity distributed data fusion with mixture models" 

  Access Model/Code and Paper
L0 Regularization Based Neural Network Design and Compression

May 31, 2019
S. Asim Ahmed

We consider complexity of Deep Neural Networks (DNNs) and their associated massive over-parameterization. Such over-parametrization may entail susceptibility to adversarial attacks, loss of interpretability and adverse Size, Weight and Power - Cost (SWaP-C) considerations. We ask if there are methodical ways (regularization) to reduce complexity and how can we interpret trade-off between desired metric and complexity of DNN. Reducing complexity is directly applicable to scaling of AI applications to real world problems (especially for off-the-cloud applications). We show that presence and evaluation of the knee of the tradeoff curve. We apply a form of L0 regularization to MNIST data and signal modulation classifications. We show that such regularization captures saliency in the input space as well.

* 4 pages 11 figures 

  Access Model/Code and Paper
Unsupervised Method to Localize Masses in Mammograms

Apr 12, 2019
Bilal Ahmed Lodhi

Breast cancer is one of the most common and prevalent type of cancer that mainly affects the women population. chances of effective treatment increases with early diagnosis. Mammography is considered one of the effective and proven techniques for early diagnosis of breast cancer. Tissues around masses look identical in mammogram, which makes automatic detection process a very challenging task. They are indistinguishable from the surrounding parenchyma. In this paper, we present an efficient and automated approach to segment masses in mammograms. The proposed method uses hierarchical clustering to isolate the salient area, and then features are extracted to reject false detection. We applied our method on two popular publicly available datasets (mini-MIAS and DDSM). A total of 56 images from mini-mias database, and 76 images from DDSM were randomly selected. Results are explained in-terms of ROC (Receiver Operating Characteristics) curves and compared with the other techniques. Experimental results demonstrate the efficiency and advantages of the proposed system in automatic mass identification in mammograms.

  Access Model/Code and Paper
Sequence to sequence learning for unconstrained scene text recognition

Jul 20, 2016
Ahmed Mamdouh A. Hassanien

In this work we present a state-of-the-art approach for unconstrained natural scene text recognition. We propose a cascade approach that incorporates a convolutional neural network (CNN) architecture followed by a long short term memory model (LSTM). The CNN learns visual features for the characters and uses them with a softmax layer to detect sequence of characters. While the CNN gives very good recognition results, it does not model relation between characters, hence gives rise to false positive and false negative cases (confusing characters due to visual similarities like "g" and "9", or confusing background patches with characters; either removing existing characters or adding non-existing ones) To alleviate these problems we leverage recent developments in LSTM architectures to encode contextual information. We show that the LSTM can dramatically reduce such errors and achieve state-of-the-art accuracy in the task of unconstrained natural scene text recognition. Moreover we manually remove all occurrences of the words that exist in the test set from our training set to test whether our approach will generalize to unseen data. We use the ICDAR 13 test set for evaluation and compare the results with the state of the art approaches [11, 18]. We finally present an application of the work in the domain of for traffic monitoring.

* It is my master thesis. The thesis was done at Sony Technology Center Stuttgart and presented to Nile University. The thesis supervisors are Mark Blaxall, Fabien Cardinaux, and Motaz Abdelwahab 

  Access Model/Code and Paper
A Novice Guide towards Human Motion Analysis and Understanding

Sep 03, 2015
Ahmed Nabil Mohamed

Human motion analysis and understanding has been, and is still, the focus of attention of many disciplines which is considered an obvious indicator of the wide and massive importance of the subject. The purpose of this article is to shed some light on this very important subject, so it can be a good insight for a novice computer vision researcher in this field by providing him/her with a wealth of knowledge about the subject covering many directions. There are two main contributions of this article. The first one investigates various aspects of some disciplines (e.g., arts, philosophy, psychology, and neuroscience) that are interested in the subject and review some of their contributions stressing on those that can be useful for computer vision researchers. Moreover, many examples are illustrated to indicate the benefits of integrating concepts and results among different disciplines. The second contribution is concerned with the subject from the computer vision aspect where we discuss the following issues. First, we explore many demanding and promising applications to reveal the wide and massive importance of the field. Second, we list various types of sensors that may be used for acquiring various data. Third, we review different taxonomies used for classifying motions. Fourth, we review various processes involved in motion analysis. Fifth, we exhibit how different surveys are structured. Sixth, we examine many of the most cited and recent reviews in the field that have been published during the past two decades to reveal various approaches used for implementing different stages of the problem and refer to various algorithms and their suitability for different situations. Moreover, we provide a long list of public datasets and discuss briefly some examples of these datasets. Finally, we provide a general discussion of the subject from the aspect of computer vision.

* 35 Pages 

  Access Model/Code and Paper
Cross-Language Personal Name Mapping

May 24, 2014
Ahmed H. Yousef

Name matching between multiple natural languages is an important step in cross-enterprise integration applications and data mining. It is difficult to decide whether or not two syntactic values (names) from two heterogeneous data sources are alternative designation of the same semantic entity (person), this process becomes more difficult with Arabic language due to several factors including spelling and pronunciation variation, dialects and special vowel and consonant distinction and other linguistic characteristics. This paper proposes a new framework for name matching between the Arabic language and other languages. The framework uses a dictionary based on a new proposed version of the Soundex algorithm to encapsulate the recognition of special features of Arabic names. The framework proposes a new proximity matching algorithm to suit the high importance of order sensitivity in Arabic name matching. New performance evaluation metrics are proposed as well. The framework is implemented and verified empirically in several case studies demonstrating substantial improvements compared to other well-known techniques found in literature.

* International Journal of Computational Linguistics Research, vol 4, issue 4, December 2013 

  Access Model/Code and Paper
Perception Lie Paradox: Mathematically Proved Uncertainty about Humans Perception Similarity

Feb 19, 2012
Ahmed M. Mahran

Agents' judgment depends on perception and previous knowledge. Assuming that previous knowledge depends on perception, we can say that judgment depends on perception. So, if judgment depends on perception, can agents judge that they have the same perception? In few words, this is the addressed paradox through this document. While illustrating on the paradox, it's found that to reach agreement in communication, it's not necessary for parties to have the same perception however the necessity is to have perception correspondence. The attempted solution to this paradox reveals a potential uncertainty in judging the matter thus supporting the skeptical view of the problem. Moreover, relating perception to intelligence, the same uncertainty is inherited by judging the level of intelligence of an agent compared to others not necessarily from the same kind (e.g. machine intelligence compared to human intelligence). Using a proposed simple mathematical model for perception and action, a tool is developed to construct scenarios, and the problem is addressed mathematically such that conclusions are drawn systematically based on mathematically defined properties. When it comes to formalization, philosophical arguments and views become more visible and explicit.

* 5 pages, 5 figures 

  Access Model/Code and Paper
Designing a Miniature Wheel Arrangement for Mobile Robot Platforms

Apr 02, 2011
Saheeb Ahmed Kayani

In this research report details of design of a miniature wheel arrangement are presented. This miniature wheel arrangement is essentially a direction control mechanism intended for use on a mobile robot platform or base. The design is a specific one employing a stepper motor as actuator and as described can only be used on a certain type of wheeled robots. However, as a basic steering control element, more than one of these miniature wheel arrangements can be grouped together to implement more elaborate and intelligent direction control schemes on varying configurations of wheeled mobile robot platforms.

* Final published version, hardcopy available from technical library of NUST College of E&ME, Rawalpindi, Pakistan on request 

  Access Model/Code and Paper