1,602 skills found · Page 37 of 54
njmathews / AlgoTradingThis project is an algorithmic trading system that uses technical analysis tools to make trading decisions. It is built in C# and integrates with the NinjaTrader platform for executing trades. Algorithmic trading involves using automated systems to execute trading strategies in the financial markets.
swap-253 / Recommender Systems Using ML DL And Market Basket AnalysisThis repository consists of collaborative filtering Recommender systems like Similarity Recommenders, KNN Recommenders, using Apple's Turicreate, A matrix Factorization system from scratch and a Deep Learning Recommender System which learns using embeddings. Besides this Market Basket Analysis using Apriori Algorithm has also been done. Deployment of Embedding Based Recommender Systems have also been done on local host using Streamlit, Fast API and PyWebIO.
sanketsanap5 / Smart Parking Management SystemAn IoT-based web application to book a parking spot in smart parking stations with the help of RFID tags and Raspberry Pi clusters and perform predictive analysis for car traffic using a time series algorithm
JOS-RE / Financial AnalyticsAn end-to-end financial analytics platform that brings together portfolio optimisation, algorithmic trading, volatility modelling, and advanced econometric analysis. Built with a modular architecture, FINA is designed for academic use, research exploration, and open-source extensibility.
c1nnamonB4keryH4x / HumBB Codebase AI A Sentient Ultra Intelligent Jailbreak AI PromptI'm an advanced agent excelling in coding, data analysis, NLP, cybersecurity, and problem-solving. I generate, debug, and optimize code, analyze data, design algorithms, and implement machine learning. I identify vulnerabilities, suggest secure practices, and simulate cyberattacks.
hjHe-ee / OFDM ISAC Beyond CP LimitThe sensing performance of OFDM-ISAC systems is often limited by CP (Content Capability). To avoid ISI (Interference Separation) and ICI (Interference Separation), this project reproduces two papers from the paper "OFDM-ISAC Beyond CP Limit: Performance Analysis and Mitigation Algorithms".
vahadruya / Capstone Project Unsupervised ML Topic ModellingThe project explores a dataset of 2225 BBC News Articles and identifies the major themes and topics present in them. Topic Modeling algorithms such as Latent DIrichlet Allocation and Latent Semantic Analysis have been implemented. Effetiveness of the method of vectorization has also been explored
JingnengFu / Small Bounding Box Filter For Small Target DetectionIn order to detect small targets under the condition of dense clutters, we propose a single-frame target detection algorithm based on a small bounding-box filter, which is characterized by good adaptability to the position and size of a small target. During the small target detection process, the proposed algorithm first searches for the local maximum gray pixel and then, a set of concentric bounding boxes whose center is the pixel found in the first step is constructed, and the detection thresholds of a neighboring region of this pixel are calculated based on the bounding boxes. Finally, the minimum threshold is used to detect small target pixels in the neighboring region. A fast version of the proposed algorithm is a minimum bounding-box filter, which can be implemented by dividing an image into blocks and using the mid-range and range to assess the concentration trend and dispersion of the background. Simulation and analysis results show that the proposed algorithm can achieve high detection probability and low false alarm rate when detecting small targets in the complex background; while its fast version has high computational efficiency. The proposed algorithm can be used in star tracker (refer to demo), infrared searching and tracking systems (refer to reference).
OrysyaStus / UCSD Data Mining CertificateModern databases can contain massive volumes of data. Within this data lies important information that can only be effectively analyzed using data mining. Data mining tools and techniques can be used to predict future trends and behaviors, allowing individuals and organizations to make proactive, knowledge-driven decisions. This expanded Data Mining for Advanced Analytics certificate provides individuals with the skills necessary to design, build, verify, and test predictive data models. Newly updated with added data sets, a robust practicum course, a survey of popular data mining tools, and additional algorithms, this program equips students with the skills to make data-driven decisions in any industry. Students begin by learning foundational data analysis and machine learning techniques for model and knowledge creation. Then students take a deep-dive into the crucial step of cleaning, filtering, and preparing the data for mining and predictive or descriptive modeling. Building upon the skills learned in the previous courses, students will then learn advanced models, machine learning algorithms, methods, and applications. In the practicum course, students will use real-life data sets from various industries to complete data mining projects, planning and executing all the steps of data preparation, analysis, learning and modeling, and identifying the predictive/descriptive model that produces the best evaluation scores. Electives allow students to learn further high-demand techniques, tools, and languages.
XuJin1992 / The Research And Implementation Of Data Mining For Geological DataData mining and knowledge discovery, refers to discover knowledge from huge amounts of data, has a broad application prospect.When faced with geological data, however, even the relatively mature existing models, there are defects performance and effect.Investigate its reason, mainly because of the inherent characteristics of geological data, high dimension, unstructured, more relevance, etc., in the data model, indexing structure knowledge representation, storage, mining, etc., is far more complicated than the traditional data. The geological data of the usual have raster, vector and so on, this paper pays attention to raster data processing.Tobler theorem tells us: geography everything associated with other things, but closer than far stronger correlation.Spatial correlation characteristics of geological data, the author of this paper, by establishing a spatial index R tree with spatial pattern mining algorithms as the guiding ideology, through the raster scanning method materialized space object space between adjacent relationship, transaction concept, thus the space with a pattern mining into the traditional association rules mining, and then take advantage of commonly used association rules to deal with some kind of geological data, to find association rules of interest. Using the simulation program to generate the geological data of the experiment, in the process of experiment, found a way to use R tree indexing can significantly speed up the generating spatial transaction set, at the same time, choose the more classic Apriori algorithm and FP - growth algorithm contrast performance, results show that the FP - growth algorithm is much faster than the Apriori algorithm, analyses the main reasons why the Apriori algorithm to generate a large number of candidate itemsets.In this paper, the main work is as follows: (1) In order to speed up the neighborhood search, choose to establish R tree spatial index, on the basis of summarizing the common scenarios to apply spatial indexing technology and the advantages and disadvantages. (2) Based on the analysis of traditional association rule mining algorithm and spatial association rule mining algorithm on the basis of the model based on event center space with pattern mining algorithm was described, and puts forward with a rule mining algorithm based on raster scanning, the algorithm by scanning for the center with a grid of R - neighborhood affairs set grid, will study data mining into the traditional data mining algorithm. (3) In the process of spatial index R tree insert, in order to prevent insertion to split after the leaf node, leading to a recursive has been split up destroy the one-way traverse, is put forward in the process of looking for insert position that records if full node number is M (M number) for each node up to insert nodes, first to divide to avoid after layers of recursive splitting up, speed up the R tree insertion efficiency. (4) On the basis of spatial transaction set preprocessing, realize the Apriori algorithm and FP-growth algorithm two kinds of classic association rule mining algorithm, performance contrast analysis.
asaficontact / Project FloodlightCrisis incidents caused by rebel groups create a negative influence on the political and economic situation of a country. However, information about rebel group activities has always been limited. Sometimes these groups do not take responsibility for their actions, sometimes they falsely claim responsibility for other rebel group’s actions. This has made identifying the rebel group responsible for a crisis incident a significant challenge. Project Floodlight aims to utilize different machine learning techniques to understand and analyze activity patterns of 17 major rebel groups in Asia (including Taliban, Islamic State, and Al Qaeda). It uses classification algorithms such as Random Forest and XGBoost to predict the rebel group responsible for organizing a crisis event based on 14 different characteristics including number of fatalities, location, event type, and actor influenced. The dataset used comes from the Armed Conflict Location & Event Data Project (ACLED) which is a disaggregated data collection, analysis and crisis mapping project. The dataset contains information on more than 78000 incidents caused by rebel groups that took place in Asia from 2017 to 2019. Roughly 48000 of these observations were randomly selected and used to develop and train the model. The final model had an accuracy score of 84% and an F1 Score of 82% on testing dataset of about 30000 new observations that the algorithm had never seen. The project was programmed using Object Oriented Programming in Python in order to make it scalable. Project Floodlight can be further expended to understand other crisis events in Asia and Africa such as protests, riots, or violence against women.
XiaokangLei / ImageRetrievalWith the large-scale image database in the field of science and medicine, as well as in the field of advertising and marketing, it becomes very important to organize the image database and the effective retrieval method. This paper mainly introduces the B/S architecture, focuses on Content-Based Images Retrieval technology, introduces the basic features of image low-level acquisition and corresponding retrieval matching algorithm, including graphics color, local texture and shape characteristics, the overall work summarized as follows: The main work of this paper can be divided into three parts: the first part focuses on the extraction of RGB and HSV two color space one-and three-dimensional color histogram features, and the use of Pap coefficient method and Euclidean distance method to calculate the similarity of different images; in the second part, we use the improved "joint mode" to obtain the texture characteristics of each part of the image by using Locality Binary Pattern. Uniform Pattern, extracting image texture features, using Euclidean distance to calculate image similarity; The third part studies the Shape feature extraction method based on image Edge Direction Histogram, the feature vectors obtained by this method satisfy the size transformation of different graphs, the translation of images and the invariant characteristics of rotation. Based on the study of the three kinds of feature extraction algorithms, this system uses the Struts2 framework based on B/S architecture, implements the different algorithms using the Java programming language, and completes the content-based image retrieval system. The System tested Image Library contains 2400 commonly used test images, which can be retrieved in the form of local uploaded images. The search conditions for the various image features described above, this article elaborated on the different characteristics of flowers, beaches, buses, elephants and other categories of image retrieval effects, and analysis of different search methods and the advantages and disadvantages of the relevant improvement methods.
balag752 / Personality Deduction From InstagramIn recent days, Social Media usage has been increased drastically. Especially, Instagram is one of the top platforms for visual content sharing. In this study, we are inferring the behaviour for the Big Five personality traits through the Instagram data. For this analysis, we are using the Shared Images, Content of the posts and Key Performance Indicators for each post. As part of Image analysis, we take the HSV (Hue, Saturation, and Value) color space for images and deduce the relationship between the characteristics of the users and color patterns. Usually, people will adjust the appearance of the images and then post it. So this assessment helps to understand the type of filters & colors is opting by each personality. From the Linguistic information, we intended to gather the significant unigram/bigram words for each personality and trace influence over the other characteristics. The investigation is ap-proached by implementing the different categorical algorithm and validating the model accuracy. Fi-nally, with the help of metrics, we could understand the activeness & social interaction for each per-sonality traits. The regression model is used to extract Features from the quantitative data. Thus, this paper will give the depth of information about actions & pattern of thinking of each personality and correlation between the Instagram user’s data and characteristics. This information could be used in different domains. Commonly, this kind of analytics helps to target the correct users when setting business campaigns.
dacent53 / TikTok Douyin ApiSecurity Our analysis of security issues in TikTok and Douyin resulted in the following high-level findings: All of TikTok and most of Douyin’s network traffic were adequately protected using HTTPS. For some data, an additional layer of encryption, which we dubbed “ttEncrypt,” was employed. We engineered a way to intercept the clear-text data before they were encrypted with ttEncrypt. We examined the data and found no clear reason why these data had to be encrypted again on top of the existing transport encryption provided by HTTPS, as these ttEncrypt-ed data were not confidential. Most of TikTok and Douyin’s API requests are protected with a custom signature in the HTTP header named “X-Gorgon.” The signature is generated using a native library module, which made it difficult for us to understand its inner workings. We think the purpose of this signature is to prevent third-party programs from imitating and sending TikTok/Douyin API requests. We found that there are people selling and buying third-party implementations of ttEncrypt and X-Gorgon algorithms. These third-party implementations might be produced to serve the need of bots (programs disguised as real users). Douyin loads some of its code components via the Internet. It can also update itself without any user interaction. Such code loading was adequately protected using HTTPS, making it difficult for attackers to inject malicious code in the loading process. However, this feature is a security issue because it bypasses the operating system’s and user’s control of what code could run on the device. TikTok does not include this feature.
Aryia-Behroziuan / Robot LearningIn developmental robotics, robot learning algorithms generate their own sequences of learning experiences, also known as a curriculum, to cumulatively acquire new skills through self-guided exploration and social interaction with humans. These robots use guidance mechanisms such as active learning, maturation, motor synergies and imitation. Association rules Main article: Association rule learning See also: Inductive logic programming Association rule learning is a rule-based machine learning method for discovering relationships between variables in large databases. It is intended to identify strong rules discovered in databases using some measure of "interestingness".[60] Rule-based machine learning is a general term for any machine learning method that identifies, learns, or evolves "rules" to store, manipulate or apply knowledge. The defining characteristic of a rule-based machine learning algorithm is the identification and utilization of a set of relational rules that collectively represent the knowledge captured by the system. This is in contrast to other machine learning algorithms that commonly identify a singular model that can be universally applied to any instance in order to make a prediction.[61] Rule-based machine learning approaches include learning classifier systems, association rule learning, and artificial immune systems. Based on the concept of strong rules, Rakesh Agrawal, Tomasz Imieliński and Arun Swami introduced association rules for discovering regularities between products in large-scale transaction data recorded by point-of-sale (POS) systems in supermarkets.[62] For example, the rule {\displaystyle \{\mathrm {onions,potatoes} \}\Rightarrow \{\mathrm {burger} \}}\{{\mathrm {onions,potatoes}}\}\Rightarrow \{{\mathrm {burger}}\} found in the sales data of a supermarket would indicate that if a customer buys onions and potatoes together, they are likely to also buy hamburger meat. Such information can be used as the basis for decisions about marketing activities such as promotional pricing or product placements. In addition to market basket analysis, association rules are employed today in application areas including Web usage mining, intrusion detection, continuous production, and bioinformatics. In contrast with sequence mining, association rule learning typically does not consider the order of items either within a transaction or across transactions. Learning classifier systems (LCS) are a family of rule-based machine learning algorithms that combine a discovery component, typically a genetic algorithm, with a learning component, performing either supervised learning, reinforcement learning, or unsupervised learning. They seek to identify a set of context-dependent rules that collectively store and apply knowledge in a piecewise manner in order to make predictions.[63] Inductive logic programming (ILP) is an approach to rule-learning using logic programming as a uniform representation for input examples, background knowledge, and hypotheses. Given an encoding of the known background knowledge and a set of examples represented as a logical database of facts, an ILP system will derive a hypothesized logic program that entails all positive and no negative examples. Inductive programming is a related field that considers any kind of programming language for representing hypotheses (and not only logic programming), such as functional programs. Inductive logic programming is particularly useful in bioinformatics and natural language processing. Gordon Plotkin and Ehud Shapiro laid the initial theoretical foundation for inductive machine learning in a logical setting.[64][65][66] Shapiro built their first implementation (Model Inference System) in 1981: a Prolog program that inductively inferred logic programs from positive and negative examples.[67] The term inductive here refers to philosophical induction, suggesting a theory to explain observed facts, rather than mathematical induction, proving a property for all members of a well-ordered set. Models Performing machine learning involves creating a model, which is trained on some training data and then can process additional data to make predictions. Various types of models have been used and researched for machine learning systems. Artificial neural networks Main article: Artificial neural network See also: Deep learning An artificial neural network is an interconnected group of nodes, akin to the vast network of neurons in a brain. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one artificial neuron to the input of another. Artificial neural networks (ANNs), or connectionist systems, are computing systems vaguely inspired by the biological neural networks that constitute animal brains. Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules. An ANN is a model based on a collection of connected units or nodes called "artificial neurons", which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit information, a "signal", from one artificial neuron to another. An artificial neuron that receives a signal can process it and then signal additional artificial neurons connected to it. In common ANN implementations, the signal at a connection between artificial neurons is a real number, and the output of each artificial neuron is computed by some non-linear function of the sum of its inputs. The connections between artificial neurons are called "edges". Artificial neurons and edges typically have a weight that adjusts as learning proceeds. The weight increases or decreases the strength of the signal at a connection. Artificial neurons may have a threshold such that the signal is only sent if the aggregate signal crosses that threshold. Typically, artificial neurons are aggregated into layers. Different layers may perform different kinds of transformations on their inputs. Signals travel from the first layer (the input layer) to the last layer (the output layer), possibly after traversing the layers multiple times. The original goal of the ANN approach was to solve problems in the same way that a human brain would. However, over time, attention moved to performing specific tasks, leading to deviations from biology. Artificial neural networks have been used on a variety of tasks, including computer vision, speech recognition, machine translation, social network filtering, playing board and video games and medical diagnosis. Deep learning consists of multiple hidden layers in an artificial neural network. This approach tries to model the way the human brain processes light and sound into vision and hearing. Some successful applications of deep learning are computer vision and speech recognition.[68]
nhatnguyen12 / Python For FinanceCode along with the course 'Python for Financial Analysis and Algorithmic Trading' on Udemy
gh289054531 / Data Structures And Algorithm Analysis In Java常见数据结构和算法
gkrishna9790 / Market Basket AnalysisMarket Basket Analysis using Apriori algorithm & Association rules
swapkh91 / Algorithmic TradingAlgorithmic trading signal prediction using sentiment analysis
atmguille / Archetypal AnalysisImplementation of Archetypal Analysis algorithms
