Cambios
En el instante 11 de octubre de 2025, 1:23:13 UTC,
-
Añadido recurso Homicide forecasting for the state of Guanajuato using LSTM and geospatial information a Homicide forecasting for the state of Guanajuato using LSTM and geospatial information
f | 1 | { | f | 1 | { |
2 | "author": "JH Garc\u00eda-G\u00f3mez, SI Valdez, H Carlos", | 2 | "author": "JH Garc\u00eda-G\u00f3mez, SI Valdez, H Carlos", | ||
3 | "author_email": null, | 3 | "author_email": null, | ||
4 | "creator_user_id": "a3da3ec9-3fd4-47a4-8d04-0a90b09614e0", | 4 | "creator_user_id": "a3da3ec9-3fd4-47a4-8d04-0a90b09614e0", | ||
5 | "extras": [ | 5 | "extras": [ | ||
6 | { | 6 | { | ||
7 | "key": "Publicaci\u00f3n", | 7 | "key": "Publicaci\u00f3n", | ||
8 | "value": "Conferencia" | 8 | "value": "Conferencia" | ||
9 | }, | 9 | }, | ||
10 | { | 10 | { | ||
11 | "key": "Tipo", | 11 | "key": "Tipo", | ||
12 | "value": "Publicaci\u00f3n" | 12 | "value": "Publicaci\u00f3n" | ||
13 | } | 13 | } | ||
14 | ], | 14 | ], | ||
15 | "groups": [ | 15 | "groups": [ | ||
16 | { | 16 | { | ||
17 | "description": "Este grupo integra las publicaciones | 17 | "description": "Este grupo integra las publicaciones | ||
18 | acad\u00e9micas derivadas de los proyectos de investigaci\u00f3n del | 18 | acad\u00e9micas derivadas de los proyectos de investigaci\u00f3n del | ||
19 | Observatorio Metropolitano CentroGeo. Incluye art\u00edculos | 19 | Observatorio Metropolitano CentroGeo. Incluye art\u00edculos | ||
20 | presentados en congresos nacionales e internacionales, manuscritos en | 20 | presentados en congresos nacionales e internacionales, manuscritos en | ||
21 | formato preprint, cap\u00edtulos de libro y trabajos publicados en | 21 | formato preprint, cap\u00edtulos de libro y trabajos publicados en | ||
22 | revistas cient\u00edficas especializadas. Estos materiales reflejan la | 22 | revistas cient\u00edficas especializadas. Estos materiales reflejan la | ||
23 | labor de investigaci\u00f3n, desarrollo metodol\u00f3gico y | 23 | labor de investigaci\u00f3n, desarrollo metodol\u00f3gico y | ||
24 | an\u00e1lisis territorial del observatorio, contribuyendo al avance | 24 | an\u00e1lisis territorial del observatorio, contribuyendo al avance | ||
25 | del conocimiento en temas urbanos, metropolitanos y geoespaciales.", | 25 | del conocimiento en temas urbanos, metropolitanos y geoespaciales.", | ||
26 | "display_name": "Publicaciones", | 26 | "display_name": "Publicaciones", | ||
27 | "id": "a15a6b77-ddf5-4594-acab-7e772938a5b0", | 27 | "id": "a15a6b77-ddf5-4594-acab-7e772938a5b0", | ||
28 | "image_display_url": "", | 28 | "image_display_url": "", | ||
29 | "name": "publicaciones", | 29 | "name": "publicaciones", | ||
30 | "title": "Publicaciones" | 30 | "title": "Publicaciones" | ||
31 | } | 31 | } | ||
32 | ], | 32 | ], | ||
33 | "id": "c67f80e5-db87-486a-b984-71de9f4b81db", | 33 | "id": "c67f80e5-db87-486a-b984-71de9f4b81db", | ||
34 | "isopen": false, | 34 | "isopen": false, | ||
35 | "license_id": null, | 35 | "license_id": null, | ||
36 | "license_title": null, | 36 | "license_title": null, | ||
37 | "maintainer": null, | 37 | "maintainer": null, | ||
38 | "maintainer_email": null, | 38 | "maintainer_email": null, | ||
39 | "metadata_created": "2025-10-11T01:23:12.803847", | 39 | "metadata_created": "2025-10-11T01:23:12.803847", | ||
n | 40 | "metadata_modified": "2025-10-11T01:23:12.803869", | n | 40 | "metadata_modified": "2025-10-11T01:23:13.355261", |
41 | "name": | 41 | "name": | ||
42 | ate-of-guanajuato-using-lstm-and-geospatial-information-e8b8b0c1ae66", | 42 | ate-of-guanajuato-using-lstm-and-geospatial-information-e8b8b0c1ae66", | ||
43 | "notes": "In the last years, intentional homicides have increased | 43 | "notes": "In the last years, intentional homicides have increased | ||
44 | significantly in Mexico. A proven strategy to confront the problem is | 44 | significantly in Mexico. A proven strategy to confront the problem is | ||
45 | applying predictive methods used to anticipate the resources and | 45 | applying predictive methods used to anticipate the resources and | ||
46 | logistics of the security corps. This work tackles the forecasting of | 46 | logistics of the security corps. This work tackles the forecasting of | ||
47 | intentional homicides using three forecasting methods: ARIMA, LSTM, | 47 | intentional homicides using three forecasting methods: ARIMA, LSTM, | ||
48 | and NeuralProphet, applied to the 16 municipalities of Guanajuato | 48 | and NeuralProphet, applied to the 16 municipalities of Guanajuato | ||
49 | state with the highest count. The approach is replicable to all | 49 | state with the highest count. The approach is replicable to all | ||
50 | Mexico's municipalities since the same data are reported. We conducted | 50 | Mexico's municipalities since the same data are reported. We conducted | ||
51 | an exhaustive search of optimal hyper-parameters of the LSTM and an | 51 | an exhaustive search of optimal hyper-parameters of the LSTM and an | ||
52 | exhaustive search for the optimal lag for NeuralProphet. In the same | 52 | exhaustive search for the optimal lag for NeuralProphet. In the same | ||
53 | regard, different combinations of neighboring municipalities were | 53 | regard, different combinations of neighboring municipalities were | ||
54 | tested to include geospatial information. The methods are compared via | 54 | tested to include geospatial information. The methods are compared via | ||
55 | MAE, MSE, and bootstrap hypothesis tests. LSTM improved with | 55 | MAE, MSE, and bootstrap hypothesis tests. LSTM improved with | ||
56 | geospatial data, so the best LSTM model showed a superior performance | 56 | geospatial data, so the best LSTM model showed a superior performance | ||
57 | to the ARIMA by 23.1% in the MAE and 35.6% in the MSE. On the other | 57 | to the ARIMA by 23.1% in the MAE and 35.6% in the MSE. On the other | ||
58 | hand, NeuralProphet showed a similar performance to the ARIMA | 58 | hand, NeuralProphet showed a similar performance to the ARIMA | ||
59 | according to the bootstrap hypothesis test, showing no statistically | 59 | according to the bootstrap hypothesis test, showing no statistically | ||
60 | significant difference between them. The results show that the | 60 | significant difference between them. The results show that the | ||
61 | phenomenon is related to the spatial context and encourage the use of | 61 | phenomenon is related to the spatial context and encourage the use of | ||
62 | geospatial information in forecasting models.", | 62 | geospatial information in forecasting models.", | ||
n | 63 | "num_resources": 0, | n | 63 | "num_resources": 1, |
64 | "num_tags": 8, | 64 | "num_tags": 8, | ||
65 | "organization": { | 65 | "organization": { | ||
66 | "approval_status": "approved", | 66 | "approval_status": "approved", | ||
67 | "created": "2022-05-19T00:10:30.480393", | 67 | "created": "2022-05-19T00:10:30.480393", | ||
68 | "description": "Observatorio Metropolitano CentroGeo", | 68 | "description": "Observatorio Metropolitano CentroGeo", | ||
69 | "id": "b3b3a79d-748a-4464-9471-732b6c74ec53", | 69 | "id": "b3b3a79d-748a-4464-9471-732b6c74ec53", | ||
70 | "image_url": | 70 | "image_url": | ||
71 | "2022-05-19-001030.456616FullColor1280x1024LogoOnly.png", | 71 | "2022-05-19-001030.456616FullColor1280x1024LogoOnly.png", | ||
72 | "is_organization": true, | 72 | "is_organization": true, | ||
73 | "name": "observatorio-metropolitano-centrogeo", | 73 | "name": "observatorio-metropolitano-centrogeo", | ||
74 | "state": "active", | 74 | "state": "active", | ||
75 | "title": "Observatorio Metropolitano CentroGeo", | 75 | "title": "Observatorio Metropolitano CentroGeo", | ||
76 | "type": "organization" | 76 | "type": "organization" | ||
77 | }, | 77 | }, | ||
78 | "owner_org": "b3b3a79d-748a-4464-9471-732b6c74ec53", | 78 | "owner_org": "b3b3a79d-748a-4464-9471-732b6c74ec53", | ||
79 | "private": false, | 79 | "private": false, | ||
80 | "relationships_as_object": [], | 80 | "relationships_as_object": [], | ||
81 | "relationships_as_subject": [], | 81 | "relationships_as_subject": [], | ||
t | 82 | "resources": [], | t | 82 | "resources": [ |
83 | { | ||||
84 | "cache_last_updated": null, | ||||
85 | "cache_url": null, | ||||
86 | "created": "2025-10-11T01:23:13.384379", | ||||
87 | "datastore_active": false, | ||||
88 | "description": "In the last years, intentional homicides have | ||||
89 | increased significantly in Mexico. A proven strategy to confront the | ||||
90 | problem is applying predictive methods used to anticipate the | ||||
91 | resources and logistics of the security corps. This work tackles the | ||||
92 | forecasting of intentional homicides using three forecasting methods: | ||||
93 | ARIMA, LSTM, and NeuralProphet, applied to the 16 municipalities of | ||||
94 | Guanajuato state with the highest count. The approach is replicable to | ||||
95 | all Mexico's municipalities since the same data are reported. We | ||||
96 | conducted an exhaustive search of optimal hyper-parameters of the LSTM | ||||
97 | and an exhaustive search for the optimal lag for NeuralProphet. In the | ||||
98 | same regard, different combinations of neighboring municipalities were | ||||
99 | tested to include geospatial information. The methods are compared via | ||||
100 | MAE, MSE, and bootstrap hypothesis tests. LSTM improved with | ||||
101 | geospatial data, so the best LSTM model showed a superior performance | ||||
102 | to the ARIMA by 23.1% in the MAE and 35.6% in the MSE. On the other | ||||
103 | hand, NeuralProphet showed a similar performance to the ARIMA | ||||
104 | according to the bootstrap hypothesis test, showing no statistically | ||||
105 | significant difference between them. The results show that the | ||||
106 | phenomenon is related to the spatial context and encourage the use of | ||||
107 | geospatial information in forecasting models.", | ||||
108 | "format": "HTML", | ||||
109 | "hash": "", | ||||
110 | "id": "07377713-5195-4c0b-9a51-0cd6a109e9e6", | ||||
111 | "last_modified": null, | ||||
112 | "metadata_modified": "2025-10-11T01:23:13.361507", | ||||
113 | "mimetype": null, | ||||
114 | "mimetype_inner": null, | ||||
115 | "name": "Homicide forecasting for the state of Guanajuato using | ||||
116 | LSTM and geospatial information", | ||||
117 | "package_id": "c67f80e5-db87-486a-b984-71de9f4b81db", | ||||
118 | "position": 0, | ||||
119 | "resource_type": null, | ||||
120 | "size": null, | ||||
121 | "state": "active", | ||||
122 | "url": "https://doi.org/10.1109/enc56672.2022.9882957", | ||||
123 | "url_type": null | ||||
124 | } | ||||
125 | ], | ||||
83 | "state": "active", | 126 | "state": "active", | ||
84 | "tags": [ | 127 | "tags": [ | ||
85 | { | 128 | { | ||
86 | "display_name": "artificial-intelligence", | 129 | "display_name": "artificial-intelligence", | ||
87 | "id": "47cb06d3-c2a4-42af-b633-03eea6181083", | 130 | "id": "47cb06d3-c2a4-42af-b633-03eea6181083", | ||
88 | "name": "artificial-intelligence", | 131 | "name": "artificial-intelligence", | ||
89 | "state": "active", | 132 | "state": "active", | ||
90 | "vocabulary_id": null | 133 | "vocabulary_id": null | ||
91 | }, | 134 | }, | ||
92 | { | 135 | { | ||
93 | "display_name": "autoregressive-integrated-moving-average", | 136 | "display_name": "autoregressive-integrated-moving-average", | ||
94 | "id": "84d0899a-0cce-49ed-a1c5-55f1f2910c57", | 137 | "id": "84d0899a-0cce-49ed-a1c5-55f1f2910c57", | ||
95 | "name": "autoregressive-integrated-moving-average", | 138 | "name": "autoregressive-integrated-moving-average", | ||
96 | "state": "active", | 139 | "state": "active", | ||
97 | "vocabulary_id": null | 140 | "vocabulary_id": null | ||
98 | }, | 141 | }, | ||
99 | { | 142 | { | ||
100 | "display_name": "computer-science", | 143 | "display_name": "computer-science", | ||
101 | "id": "29cae056-cd7e-43f7-be5b-b25869a3fbf2", | 144 | "id": "29cae056-cd7e-43f7-be5b-b25869a3fbf2", | ||
102 | "name": "computer-science", | 145 | "name": "computer-science", | ||
103 | "state": "active", | 146 | "state": "active", | ||
104 | "vocabulary_id": null | 147 | "vocabulary_id": null | ||
105 | }, | 148 | }, | ||
106 | { | 149 | { | ||
107 | "display_name": "context-archaeology", | 150 | "display_name": "context-archaeology", | ||
108 | "id": "a031c0ee-d17a-4f2b-a798-26d36b194438", | 151 | "id": "a031c0ee-d17a-4f2b-a798-26d36b194438", | ||
109 | "name": "context-archaeology", | 152 | "name": "context-archaeology", | ||
110 | "state": "active", | 153 | "state": "active", | ||
111 | "vocabulary_id": null | 154 | "vocabulary_id": null | ||
112 | }, | 155 | }, | ||
113 | { | 156 | { | ||
114 | "display_name": "econometrics", | 157 | "display_name": "econometrics", | ||
115 | "id": "4012759c-588f-49af-8586-166086a779ca", | 158 | "id": "4012759c-588f-49af-8586-166086a779ca", | ||
116 | "name": "econometrics", | 159 | "name": "econometrics", | ||
117 | "state": "active", | 160 | "state": "active", | ||
118 | "vocabulary_id": null | 161 | "vocabulary_id": null | ||
119 | }, | 162 | }, | ||
120 | { | 163 | { | ||
121 | "display_name": "geospatial-analysis", | 164 | "display_name": "geospatial-analysis", | ||
122 | "id": "acd92b42-66d6-40aa-81b1-f0129fe5c6a9", | 165 | "id": "acd92b42-66d6-40aa-81b1-f0129fe5c6a9", | ||
123 | "name": "geospatial-analysis", | 166 | "name": "geospatial-analysis", | ||
124 | "state": "active", | 167 | "state": "active", | ||
125 | "vocabulary_id": null | 168 | "vocabulary_id": null | ||
126 | }, | 169 | }, | ||
127 | { | 170 | { | ||
128 | "display_name": "machine-learning", | 171 | "display_name": "machine-learning", | ||
129 | "id": "99557dd8-2914-4e28-8278-7a042cfb23d0", | 172 | "id": "99557dd8-2914-4e28-8278-7a042cfb23d0", | ||
130 | "name": "machine-learning", | 173 | "name": "machine-learning", | ||
131 | "state": "active", | 174 | "state": "active", | ||
132 | "vocabulary_id": null | 175 | "vocabulary_id": null | ||
133 | }, | 176 | }, | ||
134 | { | 177 | { | ||
135 | "display_name": "time-series", | 178 | "display_name": "time-series", | ||
136 | "id": "1caecee0-56f0-4346-bd8f-69ac1d3f1c2c", | 179 | "id": "1caecee0-56f0-4346-bd8f-69ac1d3f1c2c", | ||
137 | "name": "time-series", | 180 | "name": "time-series", | ||
138 | "state": "active", | 181 | "state": "active", | ||
139 | "vocabulary_id": null | 182 | "vocabulary_id": null | ||
140 | } | 183 | } | ||
141 | ], | 184 | ], | ||
142 | "title": "Homicide forecasting for the state of Guanajuato using | 185 | "title": "Homicide forecasting for the state of Guanajuato using | ||
143 | LSTM and geospatial information", | 186 | LSTM and geospatial information", | ||
144 | "type": "dataset", | 187 | "type": "dataset", | ||
145 | "url": "https://doi.org/10.1109/enc56672.2022.9882957", | 188 | "url": "https://doi.org/10.1109/enc56672.2022.9882957", | ||
146 | "version": null | 189 | "version": null | ||
147 | } | 190 | } |