Cem Haligur Email & Phone Number

Zurich, Switzerland

Switzerland

Zurich, Switzerland

📊 Overall description 📊I am integral to a forward-thinking team dedicated to enhancing our Leak Detection Algorithm with the newest and most innovative methods available in artificial intelligence and computational technology. Our objective is ambitious yet clear : to transform our current systems with state-of-the-art AI techniques that offer unparalleled accuracy and efficiency in leak detection.

Zurich, Switzerland

👉 Implementation and production of an algorithm using object detection technology to qualify the quality of a lens. (𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 / 𝑴𝒆𝒕𝒉𝒐𝒅𝒔 𝒖𝒔𝒆𝒅 : 𝑶𝒑𝒆𝒏𝑪𝑽, 𝑷𝒚𝑻𝒐𝒓𝒄𝒉, 𝑳𝒊𝒏𝒆𝒂𝒓 𝑨𝒍𝒈𝒆𝒃𝒓𝒂, 𝑮𝒆𝒐𝒎𝒆𝒕𝒓𝒊𝒄 𝑻𝒓𝒂𝒏𝒔𝒇𝒐𝒓𝒎𝒂𝒕𝒊𝒐𝒏𝒔, 𝑫𝒂𝒓𝒌𝒏𝒆𝒕)👉 Root cause analysis with an internal system for checking the correct operation of an ultrasound camera(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 / 𝑴𝒆𝒕𝒉𝒐𝒅𝒔 𝒖𝒔𝒆𝒅 : 𝑷𝒂𝒏𝒅𝒂𝒔, 𝑵𝒖𝒎𝒑𝒚, 𝑺𝒄𝒊𝒌𝒊𝒕-𝒍𝒆𝒂𝒓𝒏, 𝑺𝒄𝒊𝒑𝒚, 𝑴𝒂𝒕𝒑𝒍𝒐𝒕𝒍𝒊𝒃 / 𝑺𝒆𝒂𝒃𝒐𝒓𝒏, 𝑮𝒓𝒂𝒑𝒉 𝑻𝒉𝒆𝒐𝒓𝒚, 𝑴𝒂𝒄𝒉𝒊𝒏𝒆 𝑳𝒆𝒂𝒓𝒏𝒊𝒏𝒈)👉Development and deployment of a sophisticated internal verification algorithm designed to capture and analyze data from a specialized device, ensuring comprehensive quality assessment and validation(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 / 𝑴𝒆𝒕𝒉𝒐𝒅𝒔 𝒖𝒔𝒆𝒅 : 𝑹𝒆𝒒𝒖𝒆𝒔𝒕𝒔, 𝑷𝒂𝒏𝒅𝒂𝒔 / 𝑵𝒖𝒎𝒑𝒚, 𝑺𝑸𝑳𝑨𝒍𝒄𝒉𝒆𝒎𝒚 / 𝑷𝒐𝒔𝒕𝒈𝒓𝒆𝑺𝑸𝑳)👉 Ongoing dissemination of sophisticated data analyses conducted by myself during meetings, focusing on persistent errors and critical issues to monitor, aimed at enhancing overall comprehension and awareness.(𝑺𝒑𝒆𝒂𝒌𝒊𝒏𝒈 𝒔𝒌𝒊𝒍𝒍𝒔, 𝑶𝒓𝒂𝒍 𝒇𝒍𝒖𝒆𝒏𝒄𝒚)

Paris Et Périphérie

📊 𝙏𝙝𝙚 𝙛𝙪𝙣𝙘𝙩𝙞𝙤𝙣𝙖𝙡 𝙨𝙘𝙤𝙥𝙚 𝙤𝙛 𝙩𝙝𝙚 𝙢𝙞𝙨𝙨𝙞𝙤𝙣 𝙞𝙨 𝙙𝙚𝙛𝙞𝙣𝙚𝙙 𝙖𝙣𝙙 𝙜𝙪𝙞𝙙𝙚𝙙 𝙗𝙮 𝙖 𝙏𝙚𝙘𝙝 𝙡𝙚𝙖𝙙𝐓𝐡𝐞 𝐦𝐢𝐬𝐬𝐢𝐨𝐧 𝐢𝐬 𝐭𝐨 𝐩𝐫𝐞𝐝𝐢𝐜𝐭 𝐭𝐡𝐞 𝐌𝐕𝐏 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐟𝐮𝐭𝐮𝐫 𝐍𝐁𝐀 𝐬𝐞𝐚𝐬𝐨𝐧. 👇👉 Scrapping the statistics since 1980 of each player(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝐒𝐞𝐥𝐞𝐧𝐢𝐮𝐦, 𝐁𝐞𝐚𝐮𝐭𝐢𝐟𝐮𝐥𝐒𝐨𝐮𝐩, 𝐒𝐐𝐋𝐢𝐭𝐞𝟑) 👉 Cleaning and transformation of data from the previously created SQL database.(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝐩𝐚𝐧𝐝𝐚𝐬, 𝐧𝐮𝐦𝐩𝐲, 𝐒𝐐𝐋𝐢𝐭𝐞𝟑, 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐓𝐨𝐨𝐥𝐬)Successfully predicted, season 2022-2023 : Joel Embiid

Levallois-Perret, Île-De-France, France

📊 𝙏𝙝𝙚 𝙛𝙪𝙣𝙘𝙩𝙞𝙤𝙣𝙖𝙡 𝙨𝙘𝙤𝙥𝙚 𝙤𝙛 𝙩𝙝𝙚 𝙢𝙞𝙨𝙨𝙞𝙤𝙣 𝙞𝙨 𝙙𝙚𝙛𝙞𝙣𝙚𝙙 𝙗𝙮 𝙖 𝙋𝙧𝙤𝙙𝙪𝙘𝙩 𝙊𝙬𝙣𝙚𝙧 𝙖𝙣𝙙 𝙜𝙪𝙞𝙙𝙚𝙙 𝙗𝙮 𝙖 𝙏𝙚𝙘𝙝 𝙡𝙚𝙖𝙙𝐓𝐡𝐞 𝐦𝐢𝐬𝐬𝐢𝐨𝐧 𝐢𝐬 𝐭𝐨 𝐟𝐚𝐜𝐢𝐥𝐢𝐭𝐚𝐭𝐞 𝐭𝐡𝐞 𝐫𝐞𝐚𝐝𝐢𝐧𝐠 𝐨𝐟 𝐜𝐚𝐥𝐥𝐬 𝐟𝐨𝐫 𝐭𝐞𝐧𝐝𝐞𝐫 𝐛𝐲 𝐀𝐂𝐓𝐈𝐕𝐔𝐒 👇 👉 Consolidation of a large number of emails reported over several years (as a tender) in order to intelligently leverage them to make it readable by employees(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝑴𝒊𝒄𝒓𝒐𝒔𝒐𝒇𝒕 𝑷𝒐𝒘𝒆𝒓 𝑨𝒖𝒕𝒐𝒎𝒂𝒕𝒆, 𝑺𝑸𝑳𝒊𝒕𝒆) 👉 Development of an application with an AI focus that allows for prediction of needs as well as suggestion according to the tender (Classification of the most suitable profiles according to the needs).(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝑶𝒑𝒆𝒏𝑪𝑽, 𝑵𝒖𝒎𝒑𝒚, 𝑷𝒂𝒏𝒅𝒂𝒔) 👉 Hosting the application on a Datacenter to make the tool usable for each 𝐀𝐂𝐓𝐈𝐕𝐔𝐒 employee.(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝑮𝒊𝒕) ⏳ 𝐃𝐮𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐡𝐞 𝐢𝐦𝐩𝐥𝐞𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐡𝐞 𝐚𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧: 𝟏𝟔 𝐰𝐞𝐞𝐤𝐬

Paris Et Périphérie

𝐓𝐡𝐢𝐬 𝐩𝐫𝐨𝐣𝐞𝐜𝐭 𝐰𝐚𝐬 𝐚 𝐡𝐚𝐫𝐦𝐨𝐧𝐢𝐨𝐮𝐬 𝐜𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐢𝐨𝐧 𝐛𝐞𝐭𝐰𝐞𝐞𝐧 𝐂𝐲𝐓𝐞𝐜𝐡, 𝐭𝐡𝐞 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 𝐨𝐟 𝐁𝐨𝐫𝐝𝐞𝐚𝐮𝐱, 𝐚𝐧𝐝 𝐂𝐍𝐑𝐒, 𝐲𝐢𝐞𝐥𝐝𝐢𝐧𝐠 𝐫𝐞𝐦𝐚𝐫𝐤𝐚𝐛𝐥𝐞 𝐨𝐮𝐭𝐜𝐨𝐦𝐞𝐬.📊 𝙏𝙝𝙚 𝙛𝙪𝙣𝙘𝙩𝙞𝙤𝙣𝙖𝙡 𝙨𝙘𝙤𝙥𝙚 𝙤𝙛 𝙩𝙝𝙚 𝙢𝙞𝙨𝙨𝙞𝙤𝙣 𝙞𝙨 𝙙𝙚𝙛𝙞𝙣𝙚𝙙 𝙗𝙮 𝙨𝙚𝙫𝙚𝙧𝙖𝙡 𝙧𝙚𝙨𝙚𝙖𝙧𝙘𝙝𝙚𝙧𝙨 𝙞𝙣 𝙖𝙧𝙩𝙞𝙛𝙞𝙘𝙞𝙖𝙡 𝙞𝙣𝙩𝙚𝙡𝙡𝙞𝙜𝙚𝙣𝙘𝙚𝐌𝐲 𝐫𝐨𝐥𝐞 𝐰𝐚𝐬 𝐭𝐨 𝐬𝐮𝐩𝐩𝐨𝐫𝐭 𝐫𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐞𝐫𝐬 𝐢𝐧 𝐮𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝𝐢𝐧𝐠 𝐭𝐡𝐞 𝐢𝐧𝐝𝐮𝐬𝐭𝐫𝐢𝐚𝐥 𝐝𝐲𝐧𝐚𝐦𝐢𝐜𝐬 𝐨𝐟 𝐭𝐡𝐞 𝐀𝐈 𝐬𝐞𝐜𝐭𝐨𝐫 𝐚𝐧𝐝 𝐢𝐭𝐬 𝐜𝐨𝐧𝐬𝐞𝐪𝐮𝐞𝐧𝐜𝐞𝐬 𝐨𝐧 𝐭𝐡𝐞 𝐞𝐦𝐩𝐥𝐨𝐲𝐦𝐞𝐧𝐭 𝐚𝐧𝐝 𝐢𝐧𝐧𝐨𝐯𝐚𝐭𝐢𝐨𝐧 𝐦𝐚𝐫𝐤𝐞𝐭. 👇 👉 Setting up and labeling a database built by WebScrapping(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝑩𝒆𝒂𝒖𝒕𝒊𝒇𝒖𝒍𝑺𝒐𝒖𝒑) 👉 Automatic classification of professional experiences #NLP (𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝙉𝙇𝙏𝙆, 𝙎𝙆𝙇𝙚𝙖𝙧𝙣, 𝙆𝙚𝙧𝙖𝙨) ⏳ 𝐃𝐮𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐡𝐞 𝐢𝐦𝐩𝐥𝐞𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐡𝐞 𝐚𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧: 𝟔 𝐦𝐨𝐧𝐭𝐡

Ville De Paris, Île-De-France, France

📊 𝐓𝐡𝐢𝐬 𝐢𝐧𝐭𝐞𝐫𝐧𝐬𝐡𝐢𝐩 𝐠𝐚𝐭𝐡𝐞𝐫𝐬 𝟑 𝐬𝐦𝐚𝐥𝐥 𝐩𝐫𝐨𝐣𝐞𝐜𝐭𝐬 𝐰𝐡𝐢𝐜𝐡 𝐚𝐥𝐥𝐨𝐰 𝐭𝐡𝐞 𝐞𝐦𝐩𝐥𝐨𝐲𝐞𝐞𝐬 𝐭𝐨 𝐚𝐮𝐭𝐨𝐦𝐚𝐭𝐞 𝐬𝐨𝐦𝐞 𝐨𝐟 𝐭𝐡𝐞𝐢𝐫 𝐭𝐚𝐬𝐤𝐬 👇 👉 Conception of an AI managing image recognition to extract key data from an invoice(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝙊𝙥𝙚𝙣𝘾𝙑, 𝘿𝙚𝙩𝙚𝙘𝙩𝙞𝙣𝙜 𝙩𝙚𝙭𝙩 𝙛𝙧𝙤𝙢 𝘼𝙒𝙎, 𝙋𝙤𝙬𝙚𝙧 𝘼𝙪𝙩𝙤𝙢𝙖𝙩𝙚) 👉 Creation of a software on an interactive terminal with dynamic display that allows a user to receive smart advice on which mode of transportation to use according to their needs (Human - AI)(𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝒏𝒐𝒅𝒆.𝒋𝒔, 𝒍𝒂𝒎𝒃𝒅𝒂𝒔 𝒇𝒖𝒏𝒄𝒕𝒊𝒐𝒏𝒔 𝒃𝒚 𝑨𝑾𝑺) 👉 Data analysis to enable exploitation of company's data for better understanding (𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒊𝒆𝒔 𝒖𝒔𝒆𝒅 : 𝑻𝒆𝒏𝒔𝒐𝒓𝒇𝒍𝒐𝒘, 𝑵𝒖𝒎𝒑𝒚, 𝑺𝒄𝒊𝒑𝒚, 𝑷𝒂𝒏𝒅𝒂𝒔, 𝑺𝒄𝒊𝒌𝒊𝒕-𝑳𝒆𝒂𝒓𝒏) ⏳ 𝐃𝐮𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐡𝐞 𝐢𝐦𝐩𝐥𝐞𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐡𝐞 𝐚𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧: 𝟏𝟐 𝐰𝐞𝐞𝐤𝐬