STL Linear Combination Forecast Graph. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

LOSS curves for BWO-BiLSTM model training. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Analysis of STL-PCA prediction results. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Accumulated contribution rate of PCA. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Figure of ablation experiment. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Flowchart of the STL-PCA-BWO-BiLSTM model. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Parameter optimization results of BiLSTM. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Descriptive statistical analysis of data. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

The MAE value of the model under raw data. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Three error values under raw data. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Decomposition of time scries plot. by Xiangjuan Liu (618000)

“…First, seven benchmark models including Prophet, ARIMA, and LSTM were applied to raw price series, where results demonstrated that deep learning models significantly outperformed traditional methods. Subsequently, STL decomposition decoupled the series into trend, seasonal, and residual components for component-specific modeling, achieving a 22.6% reduction in average MAE compared to raw data modeling. …”

Achieving Improved Ion Swarm Shaping Based on Ion Leakage Control in Ion Mobility Spectrometry by Jiyao Wang (2121157)

“…In Ion Mobility Spectrometry (IMS), ion gates are essential for controlling ion flow, significantly impacting detection sensitivity and resolution. …”

AO/EtBr Staining of Cancer cell lines: <i>To check whether vitamin D3 promoted cell death in cancer cells, a dual staining protocol was implemented as detailed in the methods secti... by Vidya G. Bettada (22208808)

Dynamics and functional role of TOR signaling during cell cycle re-entry in Vasa2+/Piwi1+ cells after refeeding. by Eudald Pascual-Carreras (12115380)

Gating strategy of experiment using 30 min EdU pulses experiments in mOr2-Piwi1 juvenile polyps. by Eudald Pascual-Carreras (12115380)

Supplementary file 1_Influence of attentional state on EEG-based motor imagery of lower limb.docx by Penghai Li (19823646)

“…Cluster-based permutation testing confirmed that this α-band ERD difference was significant (corrected p < 0.05). Moreover, the TBR index proved to be an effective real-time metric, decreasing significantly under focused attention. …”

Image 1_EEG-based characterization of auditory attention and meditation: an ERP and machine learning approach.png by Eyad Talal Attar (22124251)

“…</p>Result<p>Examination of eventrelated potentials (ERPs) demonstrated that P300 amplitude showed significant growth when responding to oddball stimuli, which indicates increased attention allocation (p < 0.05). …”

Image 8_EEG-based characterization of auditory attention and meditation: an ERP and machine learning approach.png by Eyad Talal Attar (22124251)

“…</p>Result<p>Examination of eventrelated potentials (ERPs) demonstrated that P300 amplitude showed significant growth when responding to oddball stimuli, which indicates increased attention allocation (p < 0.05). …”

Image 6_EEG-based characterization of auditory attention and meditation: an ERP and machine learning approach.png by Eyad Talal Attar (22124251)

“…</p>Result<p>Examination of eventrelated potentials (ERPs) demonstrated that P300 amplitude showed significant growth when responding to oddball stimuli, which indicates increased attention allocation (p < 0.05). …”

Image 2_EEG-based characterization of auditory attention and meditation: an ERP and machine learning approach.png by Eyad Talal Attar (22124251)

“…</p>Result<p>Examination of eventrelated potentials (ERPs) demonstrated that P300 amplitude showed significant growth when responding to oddball stimuli, which indicates increased attention allocation (p < 0.05). …”