49 skills found · Page 1 of 2
scrapinghub / AduanaFrontera backend to guide a crawl using PageRank, HITS or other ranking algorithms based on the link structure of the web graph, even when making big crawls (one billion pages).
jinhongjung / Tutorial On Link AnalysisHands-on tutorial about link analysis techniques
fzakaria / Space SavingSpace Saving algorithm implementation (StreamSummary) in Java, used to solve heavy hitters / topk items.
utkarsh1148 / Golf TrailThis project focuses on predicting the final golf ball location after the ball is hit by the golfer with only one camera using Machine Learning Algorithms and Open CV.
Aghoreshwar / Awesome Customer AnalyticsCustomer analytics has been one of hottest buzzwords for years. Few years back it was only marketing department’s monopoly carried out with limited volumes of customer data, which was stored in relational databases like Oracle or appliances like Teradata and Netezza. SAS & SPSS were the leaders in providing customer analytics but it was restricted to conducting segmentation of customers who are likely to buy your products or services. In the 90’s came web analytics, it was more popular for page hits, time on sessions, use of cookies for visitors and then using that for customer analytics. By the late 2000s, Facebook, Twitter and all the other socialchannels changed the way people interacted with brands and each other. Businesses needed to have a presence on the major social sites to stay relevant. With the digital age things have changed drastically. Customer issuperman now. Their mobile interactions have increased substantially and they leave digital footprint everywhere they go. They are more informed, more connected, always on and looking for exceptionally simple and easy experience. This tsunami of data has changed the customer analytics forever. Today customer analytics is not only restricted to marketing forchurn and retention but more focus is going on how to improve thecustomer experience and is done by every department of the organization. A lot of companies had problems integrating large bulk of customer data between various databases and warehouse systems. They are not completely sure of which key metrics to use for profiling customers. Hence creating customer 360 degree view became the foundation for customer analytics. It can capture all customer interactions which can be used for further analytics. From the technology perspective, the biggest change is the introduction of big data platforms which can do the analytics very fast on all the data organization has, instead of sampling and segmentation. Then came Cloud based platforms, which can scale up and down as per the need of analysis, so companies didn’t have to invest upfront on infrastructure. Predictive models of customer churn, Retention, Cross-Sell do exist today as well, but they run against more data than ever before. Even analytics has further evolved from descriptive to predictive to prescriptive. Only showing what will happen next is not helping anymore but what actions you need to take is becoming more critical. There are various ways customer analytics is carried out: Acquiring all the customer data Understanding the customer journey Applying big data concepts to customer relationships Finding high propensity prospects Upselling by identifying related products and interests Generating customer loyalty by discovering response patterns Predicting customer lifetime value (CLV) Identifying dissatisfied customers & churn patterns Applying predictive analytics Implementing continuous improvement Hyper-personalization is the center stage now which gives your customer the right message, on the right platform, using the right channel, at the right time. Now via Cognitive computing and Artificial Intelligence using IBM Watson, Microsoft and Google cognitive services, customer analytics will become sharper as their deep learning neural network algorithms provide a game changing aspect. Tomorrow there may not be just plain simple customer sentiment analytics based on feedback or surveys or social media, but with help of cognitive it may be what customer’s facial expressions show in real time. There’s no doubt that customer analytics is absolutely essential for brand survival.
vibhaa / HashpipeHeavy hitter detection algorithm that is entirely in the dataplane
chihsuan / Link AnalysisImplementing three algorithms : HITS, PageRank and SimRank.
raj1603chdry / CSE3020 Web Mining LabsRepository containing all the codes created for the lab sessions of CSE3020 Web Mining at VIT University Chennai Campus
Nishant-Wadhwani / Intelligent Infotainment System For Automobiles# Intellifotainment assist” – Smart HMI for passenger cars To run the program, download all files and save them in the same directory. After that, simply run 'Master.py' in the terminal. At the moment, the program will only run in linux based systems. # The Idea Infotainment systems have come a long way since the first set of dashboards installed in cars. Through our idea, we aim to create a Human Machine interaction model that takes infotainment systems to a new level. The driver tends to get distracted from the road while performing secondary tasks such as changing the music track, locking/unlocking the door while driving etc. Our system shall enable the driver to focus only on driving. Controlling the secondary tasks will be much easier. Our product primarily comprises of 5 modules: 1) Attention and drowsiness detection: - A camera shall be present on the dashboard, in front of the driver, behind the steering wheel. Through digital image processing techniques , using hough circle algorithm and haarcascade of an eye, we shall keep track of the driver’s sight. If he or she is looking away from the road while driving for more than a specified amount of time, we shall alert the driver to focus. We shall map the head orientation and iris position to accurately identify the driver’s attention. 2) Infotainment control features using blink combination: Through a combination of blinks, the driver can turn on or of the headlights, tail lights as well as indicators. Blinking of the eyes shall be detected using ‘dlib’ features in python. This shall give extremely accurate results. 3) Voice commands to control wipers, car lock, music system and windows A simple, yet extremely useful idea that would make the life of the driver a whole lot easy. Enabling the driver to speak to his car infotainment system would allow him to control and navigate these functionalities with great ease. The car will be enabled with a virtual assistant. 4) Automatic rear view mirror adjustment scheme: Using the camera placed in front of the driver, the system shall detect the position of the driver’s head. This shall also be done using image processing techniques and we shall identify the coordinates of the driver head in 3D space. There will be a mapping between the head position and mirror adjustment scheme. The mirrors will adjust their position using servo motors and shall do so automatically by identifying the head position. 5) A revolutionary reverse-assistance algorithm for smart parking and general reversing: Probably the highlight of our model, this feature shall make driving the car in and out of a parking spot, or rather, even reversing a car in general, far easier and safer than what it already is. Like most other modern cars, our model shall also have a camera installed at the back and the corresponding image displayed at the infotainment screen for parking assistance. Upon activating the reverse gear, the screen shall trace the line of motion of the car corresponding to the current position of the steering wheel. Because of this feature, the driver gets an idea of whether or not he’ll hit an obstacle while reversing if the steering wheel is kept at that position. Taking this feature to another level, the rear camera, after capturing the live video feed from the back of the car, shall perform image processing and machine learning algorithms to find a safe, obstacle-free path for reversing and indicate the driver to move the steering wheel accordingly. So instead of relying solely on the drivers judgement, our system shall actually find the path to be taken while reversing, such that other cars and other obstacles will be avoided, and accordingly recommend the driver to steer the wheel in that direction. This feature shall be extremely useful for new drivers/ learners. During the initial phase, to prevent errors from creeping in, we will always have a manual override button. After a good amount of testing, further modifications and refinements can be made. Our systems adds new dimensions to both precautionary safety measures, as well as convenience. If implemented properly, we are confident that our project will reach new heights of HMI and driver assistance technology. It will give drivers several less reasons to worry about.
fish2000 / LibsiftfastMy fork of zerofrog's fast SIFT C++ reimplementation of Bill Lowe's original smash-hit image-analysis algorithm.
khooi8913 / P4 HashpipeUnofficial P4_16 implementation of the HashPipe heavy hitter detection algorithm proposed in the paper, "Heavy-Hitter Detection Entirely in the Data Plane" @ SOSR'17
Naeemeh146 / Cec Benchmark 2013 Pythonfor testing metaheuristic algorithm which is specific for continuous search spaces like Particle Swarm optimizations, Differential evolutions, etc, one can be sure about the performances of algorithm bt testing them in this benchmark. benchmark has been defined by IEEE World Congress on Computational Intelligence in C++. then developers implemented them in MATLAB and R. Now I have implemented them in Python as these language getting hit between data scientists a lot. I hope you find it useful.
smutneja03 / PageRank PysparkContains the code and notes for the the algorithms namely Page Rank, Topic Sensitive Page Rank and HITS in Python using Spark Framework(PySpark)
BlockchainLabs / KryptonEthereum has brought us tools like Smart Contract, Dapp and DAO creation, deployment, and management. We can easily pay someone without ever hitting the send button, access decentralized applications that cannot be censored or shut down and we can be part of Decentralized Autonomous Organizations. Mistakes were made, bugs were found, and recently, millions were lost. Some are calling The DAO hack the most expensive bug bounty ever held, but whoever said this certainly didn’t have his Ether invested in The DAO, as the situation regarding the seizure of the stolen funds doesn’t seem to be improving. The DAO happened, it failed, all we can do now is move on and learn from our mistakes. The problem is that if we keep learning from $50m errors, we’ll be the wisest and poorest people on the planet. That’s why it’s good to have training wheels sometimes. Ethereum is the perfect playground for skilled developers, but with its 700% value increase since creation, it has made Solidity, one of the programming languages in Ethereum, a very expensive toy. That’s why Krypton has launched an open invitation to all developers to poke around the Krypton blockchain and see what it has to offer. Krypton (KR) is an Ethereum-based cryptocurrency that allows users all the same features and perks (Smart Contracts, Dapps, DAOs, DACs) but for a lower “price.” Ethereum transaction fees, which are known as “Gas” are spent according to computational costs, which means that the higher the price of Ether, the higher those costs will be. covertress, the Krypton founder, and project manager said: We’ve contacted several faculties at major universities and invited them to use the KR chain for this purpose. All of this means that developers have a testbed for smart contracts and Dapps, which are less expensive to deploy in the KR blockchain, before moving on to a more mainstream environment like Ethereum. Krypton can now be considered as a “gateway” into Ethereum. The team isn’t planning to stay humble forever but will, however, take their time before deploying anything and becoming a direct competitor to Ethereum, allowing them to tighten up security and functionality before moving on to providing smart contracts and Dapp solutions for companies. If you liked this article follow us on Twitter @themerklenews and make sure to subscribe to our newsletter to receive the latest bitcoin and altcoin price analysis and the latest cryptocurrency news. Krypton – Smart Contracts and DAPPs Development for Business Systems & IoT Ticker: KR Algorithm: Dagger-Hashimoto Block Reward: 0.25 KR Block Target: 15 Seconds Listen Port: 17171 RPC Port: 8888 Total KR: ~2.669 Million Real-Time Total KR Ethereum-Based: Utilizes Smart Contracts, DAOs, DACs and DAPPs Block Explorer: http://explorer.krypton.rocks After years in the tech sector, for engineering, entertainment, travel & finance companies, I’ve turned my focus to blockchain and building a startup, Krypton, to help companies realize their distributed applications. $KR is my vision for an ultra-fast blockchain that can realize all of the features of Ethereum with fewer initial coins, faster speed and lower inflation. Krypton can do the same things as Ethereum. However, with Ethereum’s codebase being updated to safely deploy DAOs, DACs, and DAPPs, there will be an explosion of practical-use cases, especially in the Internet of Things field. Companies will be actively seeking experienced developers. KR is an alternative platform on which to deploy these new technologies and Krypton developers are ready to build these systems. Join me in connecting Ðapps devs with real-life applications. Let’s code the future. — covertress, Founder & Project Manager Krypton is now hiring Smart Contracts and Ðapps developers with experience in Solidity, JS, and node.js. Please join Krypton’s Slack to apply: http://slack.krypton.rocks
martech-engineer / WebKnoGraphWebKnoGraph is an open research project that uses data processing, vector embeddings, and graph algorithms to optimize internal linking at scale. Built for both academic and industry use, it offers THE FIRST FULLY transparent, AI-driven framework for improving SEO and site navigation through reproducible methods.
fontclos / HitandrunHit-and-run algorithm in python 3.6
leejch / Apex Sparrow Dart CalcApex Legends琉雀追踪器飞镖射击角度计算器，集θ→g拟合与分段线性算法于一体，精准命中侦查信标。A Sparrow Tracker Dart trajectory calculator for Apex Legends, integrating θ→g fitting and piecewise linear algorithms for precise beacon hits.
mortzdk / Heavy HittersThis repository contains implementations of the Count-Min and Count-Median sketches. Furthermore it contains 6 different implementations of approximate heavy hitters algorithms.
nikhil-iyer-97 / HITS Algorithm ImplementationImplementation of HITS algorithm for finding hub and authority scores for twitter users
osvamsi / TurtleBot PathPlanningImplementing BFS, UCS, GBFS, and A* using ROS/Gazebo platform and Evaluating the performance of these algorithms for the robot navigation problem where the Turtlebot 3 robot needs to hit the target object (and only the target object).
