Intuitive Communication

Several  forms  of  communication  are  directly  or  indirectly  within  our  knowledge, including internal, external, transverse, ascending, descending, sign, image ... etc. That which  is  well  omitted  in  typologies  is,  by  designation,  intuitive  communication, otherwise  called the  exchange of  ideas  between  two  subjects by  way of  intuition. Obviously, she expresses herself through the deeds missed by physical gesture and gaze. The interest of highlighting this communication is to be able to show how much man escapes from his own psychic self-control. The verification on the truthfulness of the remarks held by a person takes place by diagnosing it by the visual sensation and the facts recited. In the case of contradictions, intuitive communication testifies and goes into action. It is important to note beyond this simple observation, that stress does not play any role in this slip. On the other hand, it makes it possible to ensure the relationship between  two  species  of  different  nature  and  communication.  The  discovery  of  a cohabitation between a predator and its prey is not the result of chance but the work of this communication. It is actually more universal than the most spoken language on Earth, whether it is specific to humans; invertebrates or even for animals. Still, it is for Man a way to unveil a domain of his unconscious, which remains unexploited. Often, visible by defense of interest especially the example of the common food consumption, certain behavior escapes us to the detriment of the other. Seeming mischievous and destabilizes the normal state of a person. Precisely, it is enough to express an idea with a silent look so that it is decrypted by your interlocutor without any verbal or other communication. The recipient overwhelms the discomfort that it receives a decryption whose origin of the message is out of the ordinary.  It is new to no one, but to explain is still an advantage to go so far in understanding oneself. Several characteristics highlight it, among others, it can take place at any exchange between two subjects whatever the age or the kind. By its principles, it does not require interpretation and is easily grasped by the target people. It is a way of expressing oneself with its undesirable side. The eventual encounter between a non-terrestrial creature and a human, just like an animal and its master, the intuitive communicative will bear fruit for the pooling of ideas. In general, this communication reflects the exchanges not between organic species, but between immaterial and inorganic spirits, which does not try to understand this body which encloses it through another body. Hence the existence of a relationship between 

society, which is not on the agenda. Indeed, provided with  an astonishing truth  and unknown to the eyes of the world. 

Abdi-Basid ADAN, 2019

 © 2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.

 

 

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

Contact : Abdi-Basid ADAN [abdi-basid@outlook.com]

 © 2017-2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved

Intra-Annual NDVI Time-Series Reconstruction by Combining EEMD and Breakpoint Analysis – Application to Godoria Mangrove Ecosystem

 

 

 

Pixel 1 vs Pixel 2 : Time series without Missing NDVI value

1. Inter annual NDVI variation from Landsat 5/7/8/9 (30 m) over the period 1984-2023. (b) mean monthly NDVI variation.

  

 

1. Seasonally Decomposed Missing Value Imputation [Pixel 1] 

• (R. B. Cleveland, W. S. Cleveland, J.E. McRae, and I. Terpenning (1990) STL: A Seasonal-Trend Decomposition Procedure Based on Loess. Journal of Official Statistics, 6, 3–73.)

 

 

1. Reconstructing NDVI Time-Series Based on EEMD and BreakPoint on C internnual component.

 

 

   2.5 %        breakpoints      97.5 %

1   1992(9)    1992(12)          1993(2)

2   1998(10)   1998(12)         2001(6)

3   2006(10)   2006(11)         2007(2)

4 2013(8)       2013(9)          2015(5)

 

 

 © 2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.

LinkedIn group page: https://www.linkedin.com/groups/ 

 

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

Contact : Abdi-Basid ADAN [abdi-basid@outlook.com]

Click below to view the full Course Catalogue :

       *The Abdi-Basid Courses Institute*

 © 2017-2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved

Comparative Evaluation of Time Series Forecasting Models for Monthly Industrial Production in Electric and Gas Utilities: From Classical SARIMAX to Deep Learning Approaches

Website: https://sites.google.com/view/theabdibasidcoursesinstitut/accueil

Description of the Code Objectives: This code conducts a comprehensive analysis and empirical comparison of univariate forecasting methods applied to a historical monthly time series: the Industrial Production Index for U.S. electric and gas utilities (FRED series IPG2211A2N, spanning 1939 to approximately 2019–2020).

The main objectives are as follows: Exploratory Analysis and Preprocessing: Examine stationarity, identify trend and strong seasonality (annual cycles related to energy consumption), and prepare the series for modeling through differencing and decomposition. Comparison of Forecasting Paradigms: Assess the performance of classical statistical models (SARIMAX), tree-based methods (Random Forest with recursive reduction), interpretable neural models (N-BEATS), attention-based architectures (Temporal Fusion Transformer), and probabilistic deep learning models (DeepAR) over a 12-month forecast horizon. Objective Evaluation: Compute MSE/RMSE on a held-out test period to determine which approach—traditional, machine learning, or deep learning—best captures the trend, seasonal, and nonlinear patterns of this critical economic series. Practical Implications: In the energy sector, accurate forecasting of electricity and gas production supports capacity planning, management of seasonal and climate-related risks, and anticipation of industrial demand—particularly important in the context of the energy transition and fluctuating consumption patterns.

Figures:

🎯 The detailed methodology and results can be accessed through this link:

👉click here now! :  https://github.com/abdibasidadan-byte

 © 2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.

LinkedIn group page: https://www.linkedin.com/groups/ 

 

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

Contact : Abdi-Basid ADAN [abdi-basid@outlook.com]

 © 2017-2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved

Evaluation of Zero-Shot Transformer Models for Real-Time Churn Intent Classification

Main Objective: 

To implement a non-linear NLP (Natural Language Processing) pipeline capable of categorizing unstructured customer feedback without prior task-specific training.

Model Output :

Text: "I think the subscription has become too expensive for what it is." Prediction: Churn Risk (Confidence: 0.58).

Text: "I love my plan, the network is great everywhere!" Prediction: Support Request (Confidence: 0.36).

Text: "My contract is expiring soon and I'm looking at the competition." Prediction: Support Request (Confidence: 0.52).

Key Takeaways :

For the first result (0.58): > "The model identified a pricing pain point. In natural language processing, 'expensive' is a strong predictor for customer attrition, hence the 'Churn Risk' label.

For the second result (0.36): > "This is a false positive due to a low confidence score. Because the model didn't have a 'Positive' or 'Satisfied' category to choose from, it defaulted to 'Support Request' with very low certainty. We call this a forced choice.

For the third result (0.52): > "The model correctly sensed an intent to switch. Mentioning 'competition' and 'contract expiration' triggers a high probability for a retention-related support ticket."

🎯 The detailed methodology and results can be accessed through this link:

👉click here now! :  https://www.geeksforgeeks.org/

The Abdi-Basid Courses Institute (tABCi)

LinkedIn group page: https://www.linkedin.com/groups/ 

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

@ (c)2025 Abdi-Basid ADAN [abdi-basid@outlook.com]

Industrial Reliability Study: Predicting APS System Failures in Scania Trucks

Description 

The APS (Air Processing System) is critical for the operation of Scania trucks. APS failures can lead to significant industrial costs and production downtime. Historical sensor data enables the analysis of system behavior and early detection of anomalies before they escalate into critical failures.

In this study, a Random Forest model was trained to detect APS system failures, with special attention given to the highly imbalanced nature of the dataset by applying class weighting to the rare positive instances. Model performance was evaluated using standard metrics including precision, recall, F1-score, and confusion matrices, while the associated industrial cost was calculated based on the impact of false positives and false negatives. To further optimize failure detection and reduce total costs, XGBoost was optionally employed. Additionally, feature importance analysis was conducted to identify the most critical sensors influencing APS failure predictions, with the top features visualized through horizontal bar charts to provide interpretable insights for industrial decision-making.

Figure 1 illustrates the confusion matrix of the Random Forest model applied to APS failure detection under a highly imbalanced class distribution. The model correctly classifies the majority of non-failure cases, as reflected by the large number of true negatives and the very low number of false positives. This indicates a strong capability to avoid unnecessary maintenance actions. However, a non-negligible number of APS failures are misclassified as normal operations (false negatives), which represent critical cases from an industrial perspective due to their high associated cost. This result emphasizes the importance of cost-sensitive learning and motivates the use of alternative models, such as XGBoost, to further reduce false negatives and optimize industrial cost. In the confusion matrix, the value 15,607 corresponds to true negatives, that is, trucks that do not have an APS system failure and are correctly identified as such by the model, demonstrating its ability to avoid unnecessary maintenance interventions.

Figure 2 presents the top 15 most influential sensor variables used by the Random Forest model to predict APS failures. The results indicate that the prediction is driven by a limited subset of sensors, with aa_000 being the most dominant feature, followed by ci_000, ck_000, and dn_000. This suggests that APS failures are strongly associated with specific operational measurements rather  than uniformly across all sensors. The concentration of importance among these variables highlights their potential relevance for targeted monitoring and preventive maintenance strategies, as focusing on key sensors could improve fault detection efficiency while reducing system complexity.

Conclusion

The experimental results confirm that the proposed machine learning approach is effective for detecting failures of the Air Pressure System (APS) in heavy-duty trucks. The Random Forest model achieved a high overall accuracy (≈99%) and a strong precision for the negative class, indicating reliable identification of non-failure cases. However, the recall for APS failures remained moderate (≈58–61%), highlighting the intrinsic difficulty of detecting rare failure events in highly imbalanced industrial datasets.

The integration of class weighting significantly reduced the number of false negatives, which are associated with the highest industrial cost. Using the defined cost function, the Random Forest model resulted in a total industrial cost of approximately 74,000–78,000 units, demonstrating a meaningful improvement over non–cost-aware baselines. Furthermore, the XGBoost model substantially outperformed Random Forest in cost optimization, reducing the total industrial cost to approximately 29,850 units, primarily by further decreasing missed APS failures.

Feature importance analysis revealed that a limited set of sensor variables (e.g., aa_000, ci_000, ck_000, dn_000) consistently contributed most to the predictive performance. This suggests that APS degradation can be detected through specific operational patterns captured by onboard sensors. Overall, these results validate the relevance of cost-sensitive learning for industrial reliability studies and demonstrate the practical value of data-driven predictive maintenance in intelligent transportation systems.

🎯 The detailed methodology and results can be accessed through this link:

👉click here now! :  https://github.com/

  

The Abdi-Basid Courses Institute (tABCi)

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

@ (c)2025 Abdi-Basid ADAN [abdi-basid@outlook.com]