1,720,982 research outputs found
SeniorSentry: Safeguarding AgeTech Devices and Sensors Using Contextual Anomaly Detection and Supervised Machine Learning
Full text linkWith the ever-growing reliance on IoT-enabled sensors to age in place, a need arises to protect them from malicious activities by detecting attacks or other anomalies. In this work, we first confirm the presence of correlations between co-located sensors by statistically analyzing two public smart-home datasets and a dataset we collected from our lab. Then, we leverage the sliding window approach and supervised machine learning to develop a novel contextual-anomaly-detection model that reaches a true positive rate of 89.47% and a false positive rate of 0%.
Furthermore, as homes become smarter with these IoT sensors, the underlying communication technology they employ becomes a target for attackers. Typically, these sensors are paired with a micro-controller that has an inbuilt communication module (e.g., Bluetooth/WiFi), to form an edge device that facilitates communication. Monitoring vitals, climate control, illumination control, fall detection, incontinence detection, pill dispensing, and several other functions are successfully addressed by these devices. The family of vulnerabilities recently found in the the Link Manager Protocol (LMP) and baseband layers of the Bluetooth Classic (BT Classic) stack called BrakTooth, poses a genuine threat to the availability of such devices. In response, our research introduces a cost-effective experimental active sniffer that captures traffic at both these layers of the BT Classic stack and utilizes supervised machine learning to detect Braktooth-based attacks.Graduat
Assessing IP Weight Metrics for Cloud Intrusion Detection using Machine Learning Techniques
Full text linkDespite the growing popularity of cloud computing, security is still an important concern of cloud customers and potential adopters. Cloud computing is prone to the same attack vectors as traditional networks, in addition to new attack vectors that are specific to cloud platforms. Intrusion Detection Systems (IDS) deployed in the cloud must take into account the specificity of the underlying threat landscape as well as the architectural and operational constraints of cloud platforms. In this project, an IDS that utilizes IP weight metrics for feature selection is implemented. Additionally, this system is tested with different supervised classification models and evaluated on a cloud intrusion dataset. In comparison with the results under conventional network environment, we conclude that the performance of IDS against cloud intrusions is promising, however, other developments such as unsupervised intrusion detection techniques and extra data preprocessing stages should be researched for the best practice of the system.Graduat
Detecting opinion spam and fake news using n-gram analysis and semantic similarity
No full textIn recent years, deceptive contents such as fake news and fake reviews, also known as opinion spams, have increasingly become a dangerous prospect, for online users. Fake reviews affect consumers and stores a like. Furthermore, the problem of fake news has gained attention in 2016, especially in the aftermath of the last US presidential election. Fake reviews and fake news are a closely related phenomenon as both consist of writing and spreading false information or beliefs. The opinion spam problem was formulated for the first time a few years ago, but it has quickly become a growing research area due to the abundance of user-generated content. It is now easy for anyone to either write fake reviews or write fake news on the web. The biggest challenge is the lack of an efficient way to tell the difference between a real review or a fake one; even humans are often unable to tell the difference. In this thesis, we have developed an n-gram model to detect automatically fake contents with a focus on fake reviews and fake news. We studied and compared two different features extraction techniques and six machine learning classification techniques. Furthermore, we investigated the impact of keystroke features on the accuracy of the n-gram model. We also applied semantic similarity metrics to detect near-duplicated content. Experimental evaluation of the proposed using existing public datasets and a newly introduced fake news dataset introduced indicate improved performances compared to state of the art.Graduat
Machine learning techniques for the preservation of data privacy
Full text linkMachine learning has been successfully applied in various domains in recent years. Still, its use is limited since training or testing data may contain sensitive information which cannot be shared with model owners due to privacy concerns. For example, healthcare providers may be bound by patient privacy laws. Without large publicly available datasets, useful models become impossible to train. Therefore, ML methods that preserve the privacy of private training data are required. One solution is to use homomorphic encryption to carry out mathematical operations on encrypted data without compromising the privacy of said data. However, sometimes a large dataset that is difficult for a single institution to obtain is needed for complex learning tasks. In such a case, federated learning can be used to learn from private data distributed across multiple owners without compromising the privacy of each owner’s data.
However, federated learning carries its own risks. For example, exchanging even the minimum information needed for training can compromise privacy, and rogue participants in a federated learning network may attempt to sabotage model performance. Further, data that is not independently and identically distributed hampers the convergence of federated learning techniques. Additionally, once training is complete, regardless of the means, extra steps must be taken to ensure model privacy during the inference phase. Such steps are needed to ensure the model owner(s) can retain sole proprietorship of the global model. Further, if a model’s parameters are leaked, then an adversary may be able to reverse engineer them to compromise the privacy of the training data. Keeping a model private eliminates this risk.
In this dissertation, we provide an in-depth background to the problems of machine learning with encryption and federated learning. We propose novel techniques for private inference that maintain the privacy of both the model and the data the model performs inferences on. We propose a federated learning framework which, in addition to maintaining the privacy of the data used during training, is, to the best of our knowledge, the only approach that enables just a single participant to obtain the jointly trained model. We also present a secure method for distributed dimensionality reduction, which can be used as a preprocessing step to enhance the performance of the proposed federated learning framework. Finally, we combine these approaches and propose an end-to-end federated learning and private inference framework which maintains data privacy during the federated learning and private inference phase, as well as ensures the privacy of the trained model’s parameters during each phase.Graduate2025-07-3
Solving Combinatorial Optimization Problems using Statistical Learning
Full text linkThis thesis examines the use of geometric deep neural networks to provide
competent solutions (in terms of runtime versus duality gap), not necessarily
incumbent, to the capacitated vehicle routing problem and the bin packing
problem—which have non-deterministic polynomial computational complexity.
The core idea is based on learning to approximate the decisions made by
the branch and bound algorithm using the computationally expensive strong
branching strategy. The classifiers - graph convolutional neural network, Graph-
SAGE, and graph attention network - are trained on six topologically different
(to investigate the geographical dispersion effect on optimality) instances and
evaluated on eight additional instances. The experiments we conducted show that the proposed approach is able to match the performance of the branch and bound algorithm and improve upon it on two different branching strategies, while requiring significantly less computation time and explored branching nodes.Graduat
Analyse du rejet des films radiologiques dans le centre médical CELY de Bamako avant la mise en oeuvre de la numérisation de la radiologie conventionnelle
No full textIl s'agissait d'une étude rétrospective et analytique qui s'est déroulée pendant une période d'étude de six mois allant de septembre 2008 à mars 2009 dans le centre médical CELY I et CELY II de Bamako sur 646 clichés mis au rebut. L'objectif général était d'évaluer le taux de mise au rebut des films radiographiques pendant une période d'étude de six mois. Au terme de notre étude il ressort que les causes de rebut de clichés radiographiques étaient dominées par les erreurs dans le choix des constantes avec 58,82 p.100, les erreurs de centrage avec 20,43 p.100 et les erreurs dans le développement du film avec 20,43 p.100 . Le taux de rejet de film est estimé à 5,52 p.100 . Les rebuts de clichés radiographiques étaient responsables de pertes économiques considérables estimées à 376100 F CFA en six mois avec un taux de rejet estimé à 5,52 p.100 pour une période d'étude rétrospective de six mois. Les incidences fréquemment retrouvées étaient celles du rachis de face et de profil avec 35,60 p.100, du thorax de face et profil avec 23,22 p.100 et des membres avec 20,59 p.100 . Les formats correspondant étaient respectivement 35x43 avec 34,98 p.100,24x30 avec 27,55 p.100,et 35x35 avec 17,03 p.100 . La solution préconisée est l'installation d'appareil de numérisation de l'image en radiologie conventionnelle pour permettre non seulement la réduction des pertes économiques en films et en bain (révélateur et fixateur) et en même temps permettre le traitement, la visualisation, l'archivage et le transfert à distance des images numérisées. Elle serait ainsi l'objet d'une nouvelle étude
La problématique du Numérus Clausus à la FMOS/FAPH de l'USTTB au Mali
No full textIntrodiction : Le numérus clausus veut dire en latin « nombre fermé ». Cela veut dire donc en médecine qu'il n'y aura qu'un nombre restreint de personnes qui auront accès à la deuxième année de médecine ou deuxième année d' odontostomatologie ou deuxième année de pharmacie. Généralité : Au Mali, le quota est fixé en fonction du nombre de professeurs ou enseignants de rang A et du nombre de lits dans les hôpitaux. Selon l'arrêté ministériel de2003, le quota est de cinq (5) étudiants par enseignant de rang A en médecine, en pharmacie et 15 en odontostomatologie et le Mali est le seul pays en Afrique à appliquer le Numerus Claususau bout d'une année universitaire de concours (2). Résultat : Le ratio étudiant par enseignant de rang A est de 49 pour la FMOS et de 52 pour la FAPH, l'UNESCO qui préconise 30 étudiants par enseignantL'effectif des étudiants de la FMOS de 2017 est plus élevé que celle de 2003 avec un écart de 455 étudiants.L'effectif des étudiants de la FAPH de 2017 est plus élevé que celle de 2003 avec un écart de 710 étudiants.Le budget lié à la santé de 2017 est le doublet de 2003, qui est de 14,8 p.100 contre 7 p.100 .Sur472 étudiants ayant participé à notre étude,81,1 p.100 sont desrecalés, 29 p.100 sont d'accord que le numerus est pertinent,95,1 p.100 sont des étudiants de nationalité malienne,85,8 p.100 n'ont pas fait une autre étude parallèlement à la FMOS/FAPH de l'USTTB, 74,4 p.100 ont un soutien financier des parents,59,5 p.100 des ont une bourse entière,35 p.100 des étudiants avaient obtenu leur baccalauréat à 18 ans,dans 39,9 p.100 des recalés ne faisaient rien. Conclusion :Au terme de notre étude et au vue du changement de formation des médecins et des pharmaciens au Mali par l'instauration des facultés de médecine et de pharmacie privées, la pertinence et l'efficacité du Numérus Clausus à la FMOS/FAPH de l'USTTB au Mali sont questionnables
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
