MERAL Myanmar Education Research and Learning Portal
Item
{"_buckets": {"deposit": "666f6fbb-2458-4d6f-a133-9ebf4e4b50a2"}, "_deposit": {"created_by": 45, "id": "5865", "owner": "45", "owners": [45], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "recid", "value": "5865"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/5865", "sets": ["1596102427017", "user-uit"]}, "communities": ["uit"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC)", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Human physical activity recognition process using mobile phones\nis very complicated with many extracted features in which some\nfeatures are irrelevant or redundant. Removing irrelevant or\nredundant features is not only reducing the dataset size but also\nsaving the time consuming task. Hence, a reason to pick out the\neffective and useful features is our main study. We propose a noble\nfeature selection technique using Linearly Dependent Concept\n(LDC). Our proposed work attempts a new feature selection method\non UCI-HAR dataset. For classification, we use the feed forward\nneural network and compare the performance result with the\noriginal dataset. The goal of our study is not only to find an\neffective and useful features set from the original dataset but also\nto be better performance than original dataset. Finally, the\nexperimental result of proposed method gives 2.7% more accuracy\nand reduces the relative error up to 2.67% of the original dataset."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Neural Network"}, {"interim": "Linearly Dependent"}, {"interim": "Feature Selection"}, {"interim": "Mobile Phone"}, {"interim": "Sensor"}, {"interim": "Human Activity Recognition"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2020-10-26"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC).pdf", "filesize": [{"value": "481 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "© 2018 Association for Computing Machinery.", "licensetype": "license_free", "mimetype": "application/pdf", "size": 481000.0, "url": {"url": "https://meral.edu.mm/record/5865/files/A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC).pdf"}, "version_id": "1375ae57-918d-42a7-9c79-d0dbb390941b"}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "ICSCA", "subitem_c_date": "February, 2018", "subitem_conference_title": "7th International Journal on Software and Computer Applications", "subitem_place": "Kuantan, Malaysia"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Win Win Myo"}, {"subitem_authors_fullname": "Wiphada Wettayaprasit"}, {"subitem_authors_fullname": "Pattara Aiyarak"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Conference paper"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2018-02-01"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "10.1145/3185089.3185131"}, "item_title": "A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC)", "item_type_id": "21", "owner": "45", "path": ["1596102427017"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000005865", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-10-26"}, "publish_date": "2020-10-26", "publish_status": "0", "recid": "5865", "relation": {}, "relation_version_is_last": true, "title": ["A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC)"], "weko_shared_id": -1}
A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC)
http://hdl.handle.net/20.500.12678/0000005865
http://hdl.handle.net/20.500.12678/00000058653ba3f36f-b32c-4953-a526-adb218e87d3d
666f6fbb-2458-4d6f-a133-9ebf4e4b50a2
Name / File | License | Actions |
---|---|---|
A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC).pdf (481 Kb)
|
© 2018 Association for Computing Machinery.
|
Publication type | ||||||
---|---|---|---|---|---|---|
Conference paper | ||||||
Upload type | ||||||
Publication | ||||||
Title | ||||||
Title | A Noble Feature Selection Method for Human Activity Recognition using Linearly Dependent Concept (LDC) | |||||
Language | en | |||||
Publication date | 2018-02-01 | |||||
Authors | ||||||
Win Win Myo | ||||||
Wiphada Wettayaprasit | ||||||
Pattara Aiyarak | ||||||
Description | ||||||
Human physical activity recognition process using mobile phones is very complicated with many extracted features in which some features are irrelevant or redundant. Removing irrelevant or redundant features is not only reducing the dataset size but also saving the time consuming task. Hence, a reason to pick out the effective and useful features is our main study. We propose a noble feature selection technique using Linearly Dependent Concept (LDC). Our proposed work attempts a new feature selection method on UCI-HAR dataset. For classification, we use the feed forward neural network and compare the performance result with the original dataset. The goal of our study is not only to find an effective and useful features set from the original dataset but also to be better performance than original dataset. Finally, the experimental result of proposed method gives 2.7% more accuracy and reduces the relative error up to 2.67% of the original dataset. |
||||||
Keywords | ||||||
Neural Network, Linearly Dependent, Feature Selection, Mobile Phone, Sensor, Human Activity Recognition | ||||||
Identifier | 10.1145/3185089.3185131 | |||||
Conference papers | ||||||
ICSCA | ||||||
February, 2018 | ||||||
7th International Journal on Software and Computer Applications | ||||||
Kuantan, Malaysia |