Shape analysis of 3D nanoscale reconstructions of brain cell nuclear envelopes by implicit and explicit parametric representations
تجزیه و تحلیل 3D بازسازی شکل در مقیاس نانو سلول های مغز پاکت های هسته ای توسط نمایندگی پارامتری ضمنی و صریح-2019
Shape analysis of cell nuclei is becoming increasingly important in biology and medicine. Recent results have identified that large variability in shape and size of nuclei has an important impact on many biological processes. Current analysis techniques involve automatic methods for detection and segmentation of histology and microscopy images, but are mostly performed in 2D. Methods for 3D shape analysis, made possible by emerging acquisition methods capable to provide nanometric-scale 3D reconstructions, are still at an early stage, and often assume a simple spherical shape. We introduce here a framework for analyzing 3D nanoscale reconstructions of nuclei of brain cells (mostly neurons), obtained by semiautomatic segmentation of electron micrographs. Our method considers two parametric representations: the first one customizes the implicit hyperquadrics formulation and it is particularly suited for convex shapes, while the latter considers a spherical harmonics decomposition of the explicit radial representation. Point clouds of nuclear envelopes, extracted from image data, are fitted to the parameterized models which are then used for performing statistical analysis and shape comparisons. We report on the analysis of a collection of 121 nuclei of brain cells obtained from the somatosensory cortex of a juvenile rat.
Keywords: Shape analysis | Nanoscale cell reconstruction | Nuclear envelopes | Cell classification
مشتقات ثابت دو بعدی تفکیک پذیر صریح برای تشخیص جسم
سال انتشار: 2019 - تعداد صفحات فایل pdf انگلیسی: 9 - تعداد صفحات فایل doc فارسی: 19
مشتقات ثابت تصویر به طور گسترده ای در زمینه های تشخیص الگو و دید رایانه مورد استفاده قرار گرفته اند، زیرا آنها قادر به ارائه الگوی ویژگی های مستقل تبدیل هندسی هستند. در حال حاضر، ثابت های تفکیک پذیر و مشتقات آنها به دلیل توانایی در ترکیب ویژگی های اساسی ثابت های متعامد مختلف، بیشتر مورد توجه قرار گرفته است. با این حال، بسیاری از مشتق های ثابت تفکیک پذیر موجود، به طور غیرمستقیم از مشتق های هندسی و بر اساس رابطه چندجمله ای متعامد و هندسی، به دست می آیند. بنابراین، در این مقاله، رویکرد مستقیمی برای ساخت مجموعه ای از مشتق های ثابت تفکیک پذیر گسسته Chebichef-Krawtchouk پیشنهاد شد که در آن به طور همزمان مشتق برای چرخش، مقیاس پذیری و تبدیل انتقال فراهم می شود و مبتنی بر فرم صریح چند جمله ای Tchebichef و Krawtchouk است. در نتیجه، نتایج تجربی و نظری اثربخشی روش پیشنهادی اثبات شد و ارجحیت آنها در طبقه بندی تصویر و شناخت الگو در مقایسه با روش های موجود نشان داده شد.
کليدواژه: مشتقات غیرمستقیم | روش صریح | ثابت تفکیک پذیر | چندجمله ای Krawtchouk | چندجمله ای Tchebichef | تشخیص الگو
|مقاله ترجمه شده|
Anticipating bank distress in the Eurozone: An Extreme Gradient Boosting approach
پیش بینی بحران مالی بانک ها در منطقه یورو: یک رویکرد تقویت گرادیان شدید-2019
The banking sector plays a special role in the economy and has critical functions which are essential for economic stability. Hence, systemic banking crises disrupt financial markets and hinder global economic growth. In this study, Extreme Gradient Boosting, a state of the art machine learning method, is applied to identify a set of key leading indicators that may help predict and prevent bank failure in the Eurozone banking sector. The crosssectional data used in this study consists of 25 annual financial ratio series for commercial banks in the Eurozone. The sample includes Eurozone listed failed and non-failed banks for the period 2006–2016. A number of early warning systems and leading indicator models have been developed to prevent bank failure. Yet the breadth and depth of the recent financial crisis indicates that these methods must improve if they are to serve as a useful tool for regulators and managers of financial institutions. Our goal is to build a classification model to determine which variables should be monitored to anticipate bank financial distress. A set of key variables are identified to anticipate bank defaults. Identifying leading indicators of bank failure is necessary so that regulators and financial institutions management can take preventive and corrective measures before it is too late.
Keywords: Bank failure prediction | Bank failure prevention | Bank financial distress | Machine learning | Extreme Gradient Boosting |XGBoost
A flow-based approach for Trickbot banking trojan detection
یک رویکرد مبتنی بر جریان برای شناسایی تروجان بانکی Trickbot-2019
Nowadays, online banking is an attractive way of carrying out financial operations such as ecommerce, e-banking, and e-payments without much effort or the need of any physi- cal presence. This increasing popularity in online banking services and payment systems has created motivation for financial attackers to steal customer‘s credentials and money. Banking trojans have been a way of committing attacks on these financial institutions for more than a decade, and they have become one of the primary drivers of botnet traffic. How- ever, the stealthy nature of financial botnets requires new techniques and novel systems for detection and analysis in order to prevent losses and to ultimately take the botnets down. TrickBot, which specifically threatens businesses in the financial sector and their customers, has been behind man-in-the-browser attacks since 2016. Its main goal is to steal online banking information from victims when they visit their banking websites. In this study, we utilize machine learning techniques to detect TrickBot malware infections and to identify TrickBot related traffic flows without having to analyze network packet payloads, the IP addresses, port numbers and protocol information. Since command and control server IPs are updated almost daily, identification of TrickBot related traffic flows without looking at specific IP addresses is significant. We adopt behavior-based classification that uses artifacts created by the malware during the dynamic analysis of TrickBot malware samples. We compare the performance results of four different state-of-the-art machine learning algorithms, Random Forest, Sequential Minimal Optimization, Multilayer Perceptron, and Logistic Model to identify TrickBot related flows and detect a TrickBot infection. Then, we optimize the proposed classifier via exploring the best hyperparameter and feature set selection. Looking at network packet identifiers such as packet length, packet and flag counts, and inter-arrival times, the Random Forest classifier identifies TrickBot related flows with 99.9534% accuracy, 91.7% true positive rate.
Keywords:Trickbot | Banking trojan | Machine learning | Anomaly traffic detection | Dynamic analysis | Random Fores
Language models and fusion for authorship attribution
مدل های زبان و همجوشی برای انتساب نویسندگی-2019
We deal with the task of authorship attribution, i.e. identifying the author of an unknown document, proposing the use of Part Of Speech (POS) tags as features for language modeling. The experimentation is carried out on corpora untypical for the task, i.e., with documents edited by non-professional writers, such as movie reviews or tweets. The former corpus is homogeneous with respect to the topic making the task more challenging, The latter corpus, puts language models into a framework of a continuously and fast evolving language, unique and noisy writing style, and limited length of social media messages. While we find that language models based on POS tags are competitive in only one of the corpora (movie reviews), they generally provide efficiency benefits and robustness against data sparsity. Furthermore, we experiment with model fusion, where language models based on different modalities are combined. By linearly combining three language models, based on characters, words, and POS trigrams, respectively, we achieve the best generalization accuracy of 96% on movie reviews, while the combination of language models based on characters and POS trigrams provides 54% accuracy on the Twitter corpus. In fusion, POS language models are proven essential effective components.
Keywords: Authorship attribution | Language models | Computational linguistics | Text classification | Machine learning
Unsupervised by any other name: Hidden layers of knowledge production in artificial intelligence on social media
بدون نظارت با هر نام دیگری: لایه های پنهان تولید دانش در هوش مصنوعی در رسانه های اجتماعی-2019
Artificial Intelligence (AI) in the form of different machine learning models is applied to Big Data as a way to turn data into valuable knowledge. The rhetoric is that ensuing predictions work well—with a high degree of autonomy and automation. We argue that we need to analyze the process of applying machine learning in depth and highlight at what point human knowledge production takes place in seemingly autonomous work. This article reintroduces classification theory as an important framework for understanding such seemingly invisible knowledge production in the machine learning development and design processes. We suggest a framework for studying such classification closely tied to different steps in the work process and exemplify the framework on two experiments with machine learning applied to Facebook data from one of our labs. By doing so we demonstrate ways in which classification and potential discrimination take place in even seemingly unsupervised and autonomous models. Moving away from concepts of non-supervision and autonomy enable us to understand the underlying classificatory dispositifs in the work process and that this form of analysis constitutes a first step towards governance of artificial intelligence.
Keywords: Artificial intelligence | machine learning | classification | social media| Facebook | discrimination | bias
Police staffing and workload assignment in law enforcement using multi-server queueing models
کارکنان پلیس و تخصیص بار کاری در اجرای قانون با استفاده از مدل های صف بندی چند سروری-2019
Criminal activities have been posing threat to human societies. In many countries, police officers have been serving as one major solution in addressing crime. However, some countries suffer from a scarcity of police officers and the unbalanced distribution of police forces. In this research, we study the law enforcement problem to address the aforementioned situation by dividing it into two sub-problems, i.e., the police staffing problem and the workload assignment problem. To improve staffing efficiency and service quality, we propose a double-resource queueing model (DRQM) with referral and a single-resource queueing model (SRQM) with inner classification. We solve the problems of police staffing and workload assignment by optimizing the referral threshold in the DRQM and the inner classification criterion in the SRQM. Results show that the SRQM with inner classification can always achieve higher staffing efficiency than the DRQM with referral. On service quality, dependent on the optimal referral threshold in DRQM or the optimal inner classification criterion in SRQM, either DRQM or SRQM is preferred.
Keywords: Decision support systems | Law enforcement | Police staffing | Workload assignment | Queueing model
The Regulations–Risk Taking Nexus under Competitive Pressure: What about the Islamic Banking System?
مقررات - ریسک پذیری Nexus تحت فشار رقابتی: سیستم بانکی اسلامی چیست؟-2019
Does market power condition the effect of bank regulations and supervision on bank risk taking? We focus on three regulatory tools: capital requirements, the restriction of activities, and official supervisory powers. Employing 10 years of unbalanced panel data on 123 Islamic and conventional banks operating in the Middle East and Asia, we arrive at the following conclusions. First, banking market power strengthens the negative impact of capital regulation on bank risk taking. Second, our empirical results suggest that the negative effect of activity restrictions on stability is diminished when banks have greater market power. Finally, we do not find strong evidence that the negative effect of supervisory power on banks’ risk taking is conditioned by their competitive behavior. In further analysis, we differentiate between Islamic and conventional banks regarding their competition, as well as their risk behavior. The results differ according to the banking business model. These findings could be useful for bank regulators in light of the accomplishment of Islamic banks’ regulatory framework. Indeed, the adoption of Basel III represents a significant regulatory challenge, given that it does not take into account the specificities of Islamic bank
Keywords: Market power | Z-score | nonperforming loans | banking regulations | Islamic banks | JEL Classification: G21 | G32
Friction, snake oil, and weird countries: Cybersecurity systems could deepen global inequality through regional blocking
اصطکاک، روغن مار، و کشورهای عجیب و غریب: سیستم های امنیت سایبری می تواند نابرابری جهانی را از طریق مسدود سازی منطقه ای تقویت کند-2019
In this moment of rising nationalism worldwide, governments, civil society groups, transnational companies, and web users all complain of increasing regional fragmentation online. While prior work in this area has primarily focused on issues of government censorship and regulatory compliance, we use an inductive and qualitative approach to examine targeted blocking by corporate entities of entire regions motivated by concerns about fraud, abuse, and theft. Through participant-observation at relevant events and intensive interviews with experts, we document the quest by professionals tasked with preserving online security to use new machine-learning based techniques to develop a ‘‘fairer’’ system to determine patterns of ‘‘good’’ and ‘‘bad’’ usage. However, we argue that without understanding the systematic social and political conditions that produce differential behaviors online, these systems may continue to embed unequal treatments, and troublingly may further disguise such discrimination behind more complex and less transparent automated assessment. In order to support this claim, we analyze how current forms of regional blocking incentivize users in blocked regions to behave in ways that are commonly flagged as problematic by dominant security and identification systems. To realize truly global, non-Eurocentric cybersecurity techniques would mean incorporating the ecosystems of service utilization developed by marginalized users rather than reasserting norms of an imagined (Western) user that casts aberrations as suspect.
Keywords: Regional blocking | machine learning | classification | inequality | discrimination | security
Direct marketing campaigns in retail banking with the use of deep learning and random forests
کمپین های بازاریابی مستقیم در بانکداری خرده فروشی با استفاده از یادگیری عمیق و جنگل های تصادفی-2019
Credit products are a crucial part of business of banks and other financial institutions. A novel approach based on time series of customer’s data representation for predicting willingness to take a personal loan is shown. Proposed testing procedure based on moving window allows detection of complex, sequen- tial, time based dependencies between particular transactions. Moreover, this approach reduces noise by eliminating irrelevant dependencies that would occur due to the lack of time dimension analysis. The system for identifying customers interested in credit products, based on classification with random forests and deep neural networks is proposed. The promising results of empirical studies prove that the system is able to extract significant patterns from customers historical transfer and transactional data and predict credit purchase likelihood. Our approach, including the testing method, is not limited to banking sector and can be easily transferred and implemented as a general purpose direct marketing campaign system.
Keywords: Consumer credit | Retail banking | Direct marketing | Marketing campaigns | Database marketing | Random forest | Deep learning | Deep belief networks | Data mining | Time series | Feature selection | Boruta algorith