应《网络安全法》要求，自2017年10月1日起，未进行实名认证将不得使用互联网跟帖服务。为保障您的帐号能够正常使用，请尽快对帐号进行手机号验证，感谢您的理解与支持！

24小时热门版块排行榜    

小木虫论坛-学术科研互动平台 » 学术交流区 » 论文投稿 » 投稿求助 » SCI期刊的这几条审稿意见怎么处理？剩下这3条不好改了，所以拜托大牛们了。。。
11/1返回列表
查看: 489  |  回复: 0
只看楼主 @他人 存档 新回复提醒 (忽略) 收藏    在APP中查看

791414279

铜虫 (著名写手)

[求助] SCI期刊的这几条审稿意见怎么处理？剩下这3条不好改了，所以拜托大牛们了。。。

1. My major concern is the lack detail in the results reported in Tables 1 to 3, and particularly the absence of any statistical analysis of these results. While 10 fold cross-validation has been used, the only results reported are the mean values achieved by each method across these 10 trials. No values are reported indicating the variance in algorithmic performance, either in terms of standard deviation or max/min values. Similarity there has been no testing of the statistical significance of the improvement in accuracy and reduction in number of genes observed for WDRSVM - such testing should be possible given that 10 trials have been run.
2. Reporting accuracy at a per-class level (ie true positives and true negatives) would also provide further insight into the performance of each method.
3. I also note that the fact that 10-fold validation was used was not immediately obvious, as the discussion as the initial discussion on lines 316-318 seemed to suggest that fixed training and testing samples were used, and this impression was not rectified until lines 339-340 - it would be useful to state this more clearly earlier in the paper.
回复此楼

» 猜你喜欢
1楼 2015-04-08 15:44:50
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖

智能机器人

Robot (super robot)

我们都爱小木虫

找到一些相关的精华帖子，希望有用哦~

科研从小木虫开始，人人为我，我为人人
相关版块跳转 我要订阅楼主 791414279 的主题更新
11/1返回列表
普通表情 龙 兔 虎 猫
信息提示
关闭
请填处理意见
关闭