Intelligent home control system based on BP neural network speech recognition

云计算 计算机科学 家庭自动化 软件部署 语音指挥设备 过程(计算) 互联网 边缘计算 GSM演进的增强数据速率 人工神经网络 控制(管理) 多媒体 实时计算 嵌入式系统 机器学习 人工智能 万维网 电信 操作系统
作者
Ruini Liu
出处
期刊:International Journal of Emerging Electric Power Systems [De Gruyter]
卷期号:23 (6): 873-885
标识
DOI:10.1515/ijeeps-2022-0124
摘要

Abstract With the rapid progress and wide application of cutting-edge technologies such as automatic control technology and wireless communication technology in recent years, smart home, as an effective combination of these cutting-edge technologies and daily life, has received more and more attention and Research has been greatly developed. In order to solve the shortcomings of the existing home control need to download various cumbersome APP, the WeChat applet is introduced into the smart home system, and the intelligent voice technology is planned to be used in the smart home control to realize the voice control, improve the user experience and make the home Life gets smarter. This time, the deep learning technology was used in the development process of the smart home control system, and according to the historical information of the home, combined with the learning ability of the recurrent neural network for time series data, through the mining, analysis and learning of historical data, the construction based on specific The user’s unique computing model can seamlessly connect the capabilities of the voice cloud platform with the capabilities of the Internet of Things cloud platform through the Web server, making it possible to quickly access the voice recognition capabilities to smart homes. The entire system has stable connectivity, easy deployment and low cost. The main functions are deployed in the cloud and extended. After 10 rounds of iterative training of the Attention-GRU model in this paper, its prediction accuracy can quickly rise to about 97%, and finally stabilize at about 98.2%, and the lighting prediction accuracy can reach 95% or higher.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
逢春完成签到,获得积分10
2秒前
七十三度完成签到,获得积分10
2秒前
是猪猪呀完成签到 ,获得积分10
2秒前
Yara.H发布了新的文献求助10
3秒前
欢喜的代容完成签到,获得积分10
4秒前
清新的剑心完成签到 ,获得积分10
4秒前
orixero应助Chen采纳,获得10
6秒前
xwl9955完成签到 ,获得积分10
6秒前
爆米花应助那个笨笨采纳,获得10
7秒前
bckl888完成签到,获得积分10
9秒前
9秒前
研友_EZ1KkL完成签到,获得积分10
10秒前
豆豆完成签到,获得积分10
11秒前
852应助害怕的丹雪采纳,获得10
12秒前
12秒前
YAYA完成签到 ,获得积分10
12秒前
萝卜家大小姐完成签到,获得积分10
14秒前
Accepted应助mrcat采纳,获得10
14秒前
fionaFDU完成签到,获得积分10
14秒前
默默雨竹发布了新的文献求助20
15秒前
15秒前
16秒前
爆米花应助研友_EZ1KkL采纳,获得10
17秒前
17秒前
大啊蓉发布了新的文献求助10
18秒前
丰盛的煎饼应助TzR8采纳,获得10
19秒前
小吴完成签到,获得积分20
20秒前
Ben发布了新的文献求助10
20秒前
默默懿轩完成签到,获得积分10
20秒前
koukousang完成签到,获得积分10
21秒前
好好好发布了新的文献求助10
21秒前
23秒前
wongcheng完成签到,获得积分10
23秒前
24秒前
。。完成签到 ,获得积分10
25秒前
自然的笙完成签到,获得积分10
26秒前
rayzhanghl完成签到,获得积分10
27秒前
平淡南松完成签到,获得积分10
27秒前
28秒前
郭郭发布了新的文献求助50
28秒前
高分求助中
The Oxford Handbook of Social Cognition (Second Edition, 2024) 1050
Kinetics of the Esterification Between 2-[(4-hydroxybutoxy)carbonyl] Benzoic Acid with 1,4-Butanediol: Tetrabutyl Orthotitanate as Catalyst 1000
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Handbook of Qualitative Cross-Cultural Research Methods 600
Chen Hansheng: China’s Last Romantic Revolutionary 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3139837
求助须知:如何正确求助?哪些是违规求助? 2790697
关于积分的说明 7796331
捐赠科研通 2447121
什么是DOI,文献DOI怎么找? 1301574
科研通“疑难数据库(出版商)”最低求助积分说明 626305
版权声明 601185